Faculty Profiles - YAMAZAKI Tatsuya

Papers - YAMAZAKI Tatsuya

Division display >> ／ All the affair displays 1 - 103 of about 103

CT Image Diagnostic Support System for Predicting EGFR Gene Mutations in Lung Cancer.

Cher Yen Tan, Ryotaro Akagawa, Tatsuya Yamazaki, Motohiko Yamazaki

Journal of Information Processing 32 ( MBL-108 ) 533 - 542 2024

Publishing type：Research paper (scientific journal)

Lung cancer is the most common type of cancer and is the leading cause of cancer-related deaths in Japan. Regarding lung cancer diagnosis, a pivotal aspect in lung cancer treatment is tumor detection and selection of appropriate cancer treatment. Computer Tomography (CT) images are usually used to detect tumors. After tumor detection, identifying mutations in the Epidermal Growth Factor Receptor (EGFR) gene is essential for cancer treatment selection. The EGFR gene is a key factor associated with cancer cell proliferation its mutation appears both inside and around the tumors. This paper proposes a lung cancer diagnostic system designed to streamline the process from tumor detection to EGFR gene mutation identification. The proposed system consists of three modules: an input interface module, an automated lung tumor segmentation module, and an EGFR mutation prediction module. The system is characterized in that all modules are consistently based on image processing. Consequently, the proposed system enables users to acquire the diagnosis results of tumor detection as well as EGFR gene mutation prediction by just providing the input CT image data and the patients’ clinical features. Our experimental results confirm that the system achieves performance levels comparable to existing research, both in terms of lung tumor segmentation accuracy and the precision of EGFR mutation predictions.

DOI： 10.2197/ipsjjip.32.533

Machine learning algorithms mimicking specialists decision making on initial treatment for people with type 2 diabetes mellitus in Japan diabetes data management study (JDDM76). International journal

Jenny Elizabeth Price, Kazuya Fujihara, Satoru Kodama, Katsuya Yamazaki, Hiroshi Maegawa, Tatsuya Yamazaki, Hirohito Sone

Diabetes & metabolic syndrome 18 ( 11-12 ) 103168 - 103168 2024

Language：English Publishing type：Research paper (scientific journal)

OBJECTIVE: To evaluate whether typical machine learning models that mimic specialists' care can successfully reproduce information, not only on whether to prescribe medications but also which hypoglycemic agents to prescribe as initial treatment for type 2 diabetes. RESEARCH DESIGN AND METHODS: A medical records database containing prescriptions for medications for 16,005 patients who visited a diabetologist's office for the first time was utilized to train five typical machine learning models as well-as a model used for logistic analysis. Prescribed were no medications (diet and exercise therapy), insulin, biguanides (BG), sulfonylureas (SU), dipeptidyl peptidase-4 inhibitors (DPP-4I), alpha-glucosidase inhibitors (α-GI) or glinides. Models were compared based on the F1 score and ROC/AUC scores. RESULTS: XGBoost, which splits decision-making into three sections, was the top performing model (42 % accuracy) among five models and conventional logistic regression (35 % accuracy). The second highest scoring model was Support Vector Machines, which had an accuracy of 40 %. When using XGBoost to compare decisions on no medication needed vs. needing medication the AUC was 0.96. Insulin vs. oral medications had an AUC of 0.78. With all remaining oral medications removed, the AUC was 0.76. CONCLUSIONS: Among the five models investigated, XGBoost outperformed the other machine learning models examined as well as the traditional logistic model, suggesting that its accuracy had the potential to assist non-specialists in decision-making regarding treatment of patients with type 2 diabetes in the future.

DOI： 10.1016/j.dsx.2024.103168

Development of Automatic Visual Anomaly Detection System for Data Centers

Misheel Enkhbaatar, Tatsuya Yamazaki

Sensors and Materials 36 ( 6 ) 2539 - 2556 2024

Publishing type：Research paper (scientific journal)

In this paper, we present a practical automated visual monitoring system designed to enhance the efficiency of visual inspection in data centers. Visual inspection is a manual process of detecting failures in electronic devices based on light-emitting diode (LED) lighting. The objective of data center monitoring is to implement real-time failure detection to prevent any service disruptions or loss of user data. To improve the reliability of data centers, we propose a monitoring system that automatically detects anomalies in electronic devices. The system integrates a digital camera and a novel algorithm that is tailored to distinguish normal LED lighting patterns from abnormal patterns. Experimental data were collected in an actual data center room and the system was evaluated with experiments involving LED region segmentation and anomaly detection. For the LED segmentation task, we propose a K-means-based method that outperformed a previous method based on background subtraction by 8%. For anomaly detection, recorded videos covering continuous monitoring of approximately 17 h were used. The proposed method successfully detected all five true anomalies in the video data. The results of another experiment for anomaly detection demonstrate that prolonged video recording for collecting patterns of LED lighting can positively contribute to a better understanding of normal patterns and can effectively be used to ensure the detection of device anomalies.

DOI： 10.18494/SAM5012

Fundamental Sentiment Analysis by Natural Language Processing and Machine Learning for Email Classification.

Adewale Adesoji Emmanuel, Tatsuya Yamazaki

Proceedings of the 2023 5th Asia Pacific Information Technology Conference(APIT) 2023 103 - 105 2023

Publisher：ACM

Due to its ease of use, speed, adaptability, and ability to keep a complete record of correspondence, email is a commonly used and trusted communication medium. The vulnerability of these emails to cyberattacks has increased. This study utilized the hybrid-based sentiment analysis approach for email fraud detection. The lexicon-based using the Word2Vec feature and Machine Learning (ML) classification approach using both the Bag of Words and TF-IDF feature extraction techniques are adopted to optimize accuracy. The ML classifiers adopted are Random Forest, k-nearest neighbors (k-NN), Support Vector Machine, and Logistic Regression. The predictive and classification comparison of the ML models suggests that Random Forest slightly outperformed the other models with 87% accuracy and 78% F1-score and k-NN performed worst.

DOI： 10.1145/3588155.3588171

Other Link： https://dblp.uni-trier.de/db/conf/apit/apit2023.html#AdewaleY23

An Anomaly Detection Method for Data Center Devices

Misheel Enkhbaatar, Tatsuya Yamazaki

2023 6th World Symposium on Communication Engineering, WSCE 2023 28 - 33 2023

Publishing type：Research paper (international conference proceedings)

Data center demand is growing significantly due to the widespread use of remote working by businesses and cloud-based services. As a demand grows, the number of infrastructure devices, such as servers and storage, increase. An interruption or the failure of a device is costly for the data centers. To prevent thousands of electric devices from unpredictable failures, the data center must implement a speedy and accurate monitoring method. A visual monitoring method is considered reliable for detecting failures in the electric devices, but the method is very slow to monitor numerous devices due to fully manual work and a pattern of failures is not explicitly defined. Therefore, automation of the visual monitoring method is required for the data centers. This paper discusses an anomaly detection method from the video recording of the devices and development of a monitoring system. In an experimental environment of Niigata University, the proposed method performed 100% (anomaly: 4/4, regular: 225/225) accuracy for detecting anomalies from the video frames.

DOI： 10.1109/WSCE59557.2023.10365893

Information Security in Social Media Sites: Sentiment Analysis of Email.

Adewale Adesoji Emmanuel, Tatsuya Yamazaki

18th IEEE International Conference on Computer Science and Information Technologies(CSIT) 1 - 5 2023

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

In today's digital era, email stands as a fundamental tool for communication due to its convenience, rapidity, flexibility, and comprehensive archival capabilities. However, the escalating risk of cyber threats targeting emails has introduced new challenges. This research introduces an innovative approach to identify fraudulent emails through a hybrid-based approach using sentiment analysis. The proposed method unites the lexicon-based technique using Word2Vec features with a Machine Learning (ML) classification approach. Two prominent feature extraction methods, Bag of Words and TF-IDF, are integrated to enhance the precision of the analysis. The study employed well-established ML classifiers including Random Forest, KNN, Decision Tree, SVM, Multilayer Perception, and logistic model to analyze the emails. The result of the analysis was impressive across the selected models, with Support Vector Machine and Multilayer Perception slightly surpassing others with an impressive 99% accuracy, F1-score, and Recall rate respectively. This emphasizes the effectiveness of this model in recognizing fraudulent emails.

DOI： 10.1109/CSIT61576.2023.10324038

Other Link： https://dblp.uni-trier.de/db/conf/csit/csit2023.html#EmmanuelY23

Traveler Data Collection and Analysis to Extract Travel Behavior

Tatsuya Yamazaki

International Conference on Electrical, Computer and Energy Technologies, ICECET 2023 2023

Publishing type：Research paper (international conference proceedings)

To enhance the Value of Travel Time (VTT) is important for the tourism-related or transport infrastructure industries. Evaluation of VTT needs a simple way to collect vast and diverse traveler log data. In this paper, an experiment collecting such huge traveler data set by using QR codes and smartphones. Moreover, the static and dynamic data analyzing methods of the traveler log data are introduced. Finally, a typical traveler behavior is extracted from the data.

DOI： 10.1109/ICECET58911.2023.10389556

Quality Evaluation of Kohaku Koi (Cyprinus rubrofuscus) Using Image Analysis

Mikhail A. Domasevich, Hideo Hasegawa, Tatsuya Yamazaki

Fishes 7 ( 4 ) 2022.8

Publishing type：Research paper (scientific journal)

Quality evaluation of koi (Cyprinus rubrofuscus) is essential to the koi industry. However, the community has a lack of knowledge about the quality evaluation of koi and about features of koi which are valuable. During the “All Japan Nishikigoi Show” competition, a quality evaluation of koi was conducted by authoritative experts. In the present study, photos of participants of this competition were used for analysis to discover features affecting the quality of the Kohaku variety of koi. The HSVA color model was used to define and extract from image red and pale red coverage rates in Kohaku body coloration. Body aspect ratio, body proportions, red coverage rate, and pale red coverage rate were extracted using tools written in Python programming language. Analyses of the extracted data revealed the significant impact body aspect ratio (p < 0.001) and pale red coverage rate (p < 0.001) on Kohaku quality. A low body aspect ratio has a positive impact on Kohaku quality, while a high pale red coverage rate has a very strong negative impact on Kohaku quality. This study and its results can be an important foundation for further research about koi quality.

DOI： 10.3390/fishes7040158

Performance Evaluation of Device LED Extraction for Data Center Infrastructure Monitoring.

Misheel Enkhbaatar, Tatsuya Yamazaki

11th IEEE Global Conference on Consumer Electronics(GCCE) 613 - 614 2022

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Availability is the core metric of a data center operation. To be available at any time, data centers must use a real-time and precise failure detection method. However, current methods are not enough to bring data centers to their goal. One of the practical device failure detection methods is visual monitoring. Human inspectors detect failures by checking LEDs of infrastructure devices. This manual method requires a lot of effort as well as it is not suitable for real-time monitoring for big scale data centers. The goal of this study is to achieve real-time and high accuracy failure monitoring for the data center. This paper presents performance evaluation of an automatic LED extraction system which is a part of work to achieve an automatic data center monitoring. The system performed the LED detection with an accuracy of 83.7%.

DOI： 10.1109/GCCE56475.2022.10014401

Other Link： https://dblp.uni-trier.de/db/conf/gcce/gcce2022.html#EnkhbaatarY22

XGBoost: Interpretable Machine Learning Approach in Medicine

Jenny Price, Tatsuya Yamazaki, Kazuya Fujihara, Hirohito Sone

WSCE 2022 - 2022 5th World Symposium on Communication Engineering 109 - 113 2022

Publishing type：Research paper (international conference proceedings)

This research tries to establish a communication bridge between the decision making of a practicing physician and a machine learning model. Machine learning has long been used to assist in diagnosing patients through deep learning and medical image analysis. However, in medical science, it is possible to have multiple right answers when treating patients. This leaves the practitioners room to exercise their judgement on what would be best for the patient. The machine learning model can be a communication tool to assist the practitioners in reach the final decision. In this paper, the machine learning model used for this experiment is XGBoost, a gradient boosted decision tree. Through the experiment with the real patient data, we show how decision tree constructions are easily readable for medical determination.

DOI： 10.1109/WSCE56210.2022.9916029

A Vision-Based Auricular Diagnosis Assistance System with Deep Learning.

Meng-Lin Chiang, Ling Hou, Chiung-Yao Fang, Tatsuya Yamazaki

4th IEEE Global Conference on Life Sciences and Technologies(LifeTech) 475 - 479 2022

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

In the area of auricular medicine research, researchers believe that human diseases are reflected in corresponding locations on the external ears, known as the positive reactions of auricular points. If some auricular points on a person's external ear exhibit abnormal positive reactions, then the person is being attacked by a corresponding disease. This paper proposes a vision-based auricular diagnosis assistance system to help doctors detect diseases by discovering the visual positive reactions of auricular points on patients' external ears. The proposed vision-based auricular diagnosis assistance system includes visual positive reaction detection and disease identification. First, external ear images are input into the system to detect the visual positive reactions of the auricular points on the external ear using an improved version of the U-Net model. Improvements of the U-Net model include batch standardization, atrous convolution, convolution stage reduction, and multi-expansion-rate integration. Second, the detection results of visually positive reactions are then used to identify the diseases. This study identified nine types of diseases through their corresponding positive reactions, including hepatitis, mastitis, cervicitis, prostatitis, frontal headache, migraine, occipital headache, vertex headache, and headache. The dataset used in this study was collected by the authors and called the CVIU 108 EAR Dataset. The experimental results show that the disease diagnosis accuracy rate of the proposed system is 99.60%.

DOI： 10.1109/LifeTech53646.2022.9754793

Other Link： https://dblp.uni-trier.de/db/conf/lifetech/lifetech2022.html#ChiangHFY22

Automatic Visual Monitoring System for Data Center Device Management

Misheel Enkhbaatar, Tatsuya Yamazaki

WSCE 2022 - 2022 5th World Symposium on Communication Engineering 22 - 25 2022

Publishing type：Research paper (international conference proceedings)

One of the core responsibilities of a data center is to provide stability and availability for online services. But the data center frequently faces infrastructure failures and unpredicted irregularities. In order to minimize hardware related failures, data centers must monitor the housing devices for 24 hours and 365 days. Due to various physical and software related failure causes, monitoring has always been a challenging task. A visual inspection by human operators is a reliable method which is widely used for checking device's status. However, growth of number of devices in data centers causes exponential cost growth for visual checks and it is almost impossible to detect anomaly occurrences in real time. Therefore, we have proposed an automatic visual monitoring system for data centers to substitute human visual monitoring. In this paper, we present the overview of the proposed system and show experimental results to evaluate LED detection performance of the system.

DOI： 10.1109/WSCE56210.2022.9916030

Impact on Sleep Quality of Electronic Device Usage.

Tatsuya Yamazaki

17th IEEE International Conference on Computer Sciences and Information Technologies(CSIT) 2022-November 203 - 205 2022

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

A recent research result reports that the use of electronic devices is one of the factors affecting sleep. Polysomnography, in which EEG (Electroencephalogram), heart rates, and so on are measured, is often used to measure the state of sleep. Polysomnography burdens subjects because electrodes need to be attached to their heads and chests all night long. On the other hand, wearable devices have recently become popular as small and lightweight measurement devices worn on the body due to electronic circuit downsizing. A typical example is a wrist-watch type device, which can measure heart rates and sleep status just by being worn on the wrist. This study aims to clarify the effect of using electronic devices before bedtime on the quality of sleep through experiments. The sleep state of the subjects was measured by using a wearable device in the experiments. The measured results are compared based on the three kinds of tasks to the subject in pre-sleep time: regular books, electronic books (e-books), and electronic games (e-games). The results of statistical analysis for the measured data have shown that e-books and e-games increased the time to fall asleep and decreased sleep efficiency compared to reading regular books.

DOI： 10.1109/CSIT56902.2022.10000506

Other Link： https://dblp.uni-trier.de/db/conf/csit/csit2022.html#Yamazaki22

Dependency of Audio and Video for Two Types of Online Dialogue Conference Services Reviewed International journal

Tatsuya Yamazaki, Shunta Sasaki, Takumi Miyoshi

International Conference on Emerging Technologies for Communications (ICETC2021) ( P4-18 ) 2021.12

Language：English Publishing type：Research paper (international conference proceedings) Publisher：The Institute of Electronics, Information and Communication Engineers

Usually both video and audio media are used for online conferences. Although previous works, in general, support existence of video media because of smooth communication, some research results in no significant differences between video and audio (V-A) conferences and audio-only (A-O) conferences. This work conducts a comparative experiment between V-A and A-O conferences. In the experiment, two tasks are devised: the association dialogue task and the alternative play script reading task. The former is categorized as a contemplation dialogue and needs more discussion and thoughts for the subjects, while the latter is categorized as a light dialogue. From the 14 subject experiment results, video media could contribute to easiness of task achievement. But the contribution was smaller for the play script reading task, because this task uses more superficial communication than the association dialogue task.

DOI： 10.34385/proc.68.P4-18

Quality of Experience (QoE) Studies: Present State and Future Prospect.

Tatsuya Yamazaki

IEICE Transactions on Communications 104-B ( 7 ) 716 - 724 2021.7

Publishing type：Research paper (scientific journal)

With the spread of the broadband Internet and high-performance devices, various services have become available anytime, anywhere. As a result, attention is focused on the service quality and Quality of Experience (QoE) is emphasized as an evaluation index from the user's viewpoint. Since QoE is a subjective evaluation metric and deeply involved with user perception and expectation, quantitative and comparative research was difficult because the QoE study is still in its infancy. At present, after tremendous devoted efforts have contributed to this research area, a shape of the QoE management architecture has become clear. Moreover, not only for research but also for business, video streaming services are expected as a promising Internet service incorporating QoE. This paper reviews the present state of QoE studies with the above background and describes the future prospect of QoE. Firstly, the historical aspects of QoE is reviewed starting with QoS (Quality of Service). Secondly, a QoE management architecture is proposed in this paper, which consists of QoE measurement, QoE assessment, QoS-QoE mapping, QoE modeling, and QoE adaptation. Thirdly, QoE studies related with video streaming services are introduced, and finally individual QoE and physiology-based QoE measurement methodologies are explained as future prospect in the field of QoE studies.

DOI： 10.1587/transcom.2020cqi0003

Machine Learning Approach to Decision Making for Insulin Initiation in Japanese Patients With Type 2 Diabetes (JDDM 58): Model Development and Validation Study. International journal

Kazuya Fujihara, Yasuhiro Matsubayashi, Mayuko Harada Yamada, Masahiko Yamamoto, Toshihiro Iizuka, Kosuke Miyamura, Yoshinori Hasegawa, Hiroshi Maegawa, Satoru Kodama, Tatsuya Yamazaki, Hirohito Sone

JMIR medical informatics 9 ( 1 ) e22148 2021.1

Language：English Publishing type：Research paper (scientific journal)

BACKGROUND: Applications of machine learning for the early detection of diseases for which a clear-cut diagnostic gold standard exists have been evaluated. However, little is known about the usefulness of machine learning approaches in the decision-making process for decisions such as insulin initiation by diabetes specialists for which no absolute standards exist in clinical settings. OBJECTIVE: The objectives of this study were to examine the ability of machine learning models to predict insulin initiation by specialists and whether the machine learning approach could support decision making by general physicians for insulin initiation in patients with type 2 diabetes. METHODS: Data from patients prescribed hypoglycemic agents from December 2009 to March 2015 were extracted from diabetes specialists' registries, resulting in a sample size of 4860 patients who had received initial monotherapy with either insulin (n=293) or noninsulin (n=4567). Neural network output was insulin initiation ranging from 0 to 1 with a cutoff of >0.5 for the dichotomous classification. Accuracy, recall, and area under the receiver operating characteristic curve (AUC) were calculated to compare the ability of machine learning models to make decisions regarding insulin initiation to the decision-making ability of logistic regression and general physicians. By comparing the decision-making ability of machine learning and logistic regression to that of general physicians, 7 cases were chosen based on patient information as the gold standard based on the agreement of 8 of the 9 specialists. RESULTS: The AUCs, accuracy, and recall of logistic regression were higher than those of machine learning (AUCs of 0.89-0.90 for logistic regression versus 0.67-0.74 for machine learning). When the examination was limited to cases receiving insulin, discrimination by machine learning was similar to that of logistic regression analysis (recall of 0.05-0.68 for logistic regression versus 0.11-0.52 for machine learning). Accuracies of logistic regression, a machine learning model (downsampling ratio of 1:8), and general physicians were 0.80, 0.70, and 0.66, respectively, for 43 randomly selected cases. For the 7 gold standard cases, the accuracies of logistic regression and the machine learning model were 1.00 and 0.86, respectively, with a downsampling ratio of 1:8, which were higher than the accuracy of general physicians (ie, 0.43). CONCLUSIONS: Although we found no superior performance of machine learning over logistic regression, machine learning had higher accuracy in prediction of insulin initiation than general physicians, defined by diabetes specialists' choice of the gold standard. Further study is needed before the use of machine learning-based decision support systems for insulin initiation can be incorporated into clinical practice.

DOI： 10.2196/22148

Continuous Experiments for Elderly Person's Exercise Sensing and Evaluation.

Tatsuya Yamazaki

3rd IEEE Global Conference on Life Sciences and Technologies(LifeTech) 341 - 343 2021

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

To motivate elderly people to continue exercises and support busy staffs in care facilities, a sensing and evaluating system is developed for the elderly people exercises. The system consists of a Kinect sensor and a personal computer and detects joint movements of the elderly persons. 5 days continuous experiments have been conducted to evaluate the developed system with the cooperation of a care facility. A male in his 70’s and a female in her 90’s were the experimental subjects. In the experiments, the weather condition data such as temperature and humidity were collected to evaluate the relationship between the weather condition and the joint movement. Analysis of the experimental results reveals tendency of each person’s exercise. Moreover, it is found that atmospheric pressure may affect joint movements.

DOI： 10.1109/LifeTech52111.2021.9391851

Other Link： https://dblp.uni-trier.de/db/conf/lifetech/lifetech2021.html#Yamazaki21

Development of an Automatic Visual Monitoring System for Data Center Devices.

Misheel Enkhbaatar, Tatsuya Yamazaki

IEEE 16th International Conference on Computer Sciences and Information Technologies 2 194 - 197 2021

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

The main responsibility of a data center is sustaining stability and availability for online services. Even so, any data center frequently faces infrastructure failures and unpredicted irregularities. Most of the data centers hosts hundreds or thousands of physical devices. In order to minimize hardware related failures, data centers must monitor the housing devices for 24 hours and 365 days. Due to physical and software related numerous failure causes, monitoring has never been an easy task. A visual inspection by human operators is a reliable method which is widely used for checking device's health. However, growth of number of devices in data centers could cause exponential cost growth for data center management as it requires human work on each LED's inspection, and it is almost impossible to detect anomaly occurrences in real time. Therefore, we propose an efficient and low-cost method for data centers to substitute human visual monitoring. In this paper, we discuss designing and development of automatic visual monitoring system for data centers. Therefore, usability of the automatic monitoring system is experimented in real data center environment.

DOI： 10.1109/CSIT52700.2021.9648588

Other Link： https://dblp.uni-trier.de/db/conf/csit/csit2021-2.html#EnkhbaatarY21

Brain activity sensing to verify effects of facial image reconstruction puzzle—Verification by young students

Shu Iwata, Tatsuya Yamazaki

Sensors and Materials 32 ( 11 ) 3567 - 3580 2020.11

Publishing type：Research paper (scientific journal)

We have developed an application for cognitive function training in order to cope with the increased number of dementia patients and the shortage of care workers in an aging society. This application generates an image in which a person’s facial image is transformed into a puzzle where the aim is to reconstruct the face. The puzzle is presented as a problem of person estimation to activate brain functions. In this study, we conduct two brain activity sensing experiments using electroencephalograms to evaluate the effect of the facial image reconstruction puzzle on cognitive function. The experiments suggest that the image reconstruction puzzle may affect the frontal lobe.

DOI： 10.18494/SAM.2020.2883

A cognitive system of elderly exercise evaluation with sensors and robots

Tatsuya Yamazaki

Cognitive Informatics, Computer Modelling, and Cognitive Science: Volume 2: Application to Neural Engineering, Robotics, and STEM 49 - 63 2020.1

Publishing type：Part of collection (book)

As the aged society is approaching soon, importance of physical practice is increasing for elderly people more to keep their joint flexibility and cognition ability. Although such physical practice is conducted at care facilities in many cases, necessary care is not always available because the elderly population growth is quite rapid. Therefore it is important to introduce ICT (information and communications technology) into the elderly care support at the care facilities to supplement the care shortage. As the first step of introduction of ICT, we propose a cognitive system to watch elderly persons during exercising and to evaluate their exercise. The system consists of three processes. In the first process, body joint data of an elderly person are collected by a depth sensor. Then we extract features to evaluate the elderly person’s exercise from the measured data in the second process. Finally, in the third process, the evaluation is feedbacked to the elderly person by using an intimate robot interface. The cognition system can be extended by using multiple depth sensors to mitigate occlusion. When multiple depth sensors are used, there appear two problems: frame synchronization and calibration. We also approach these two problems.

DOI： 10.1016/B978-0-12-819445-4.00003-5

Study on Automatic LED Monitoring System for Data Center Devices.

Misheel Enkhbaatar, Tatsuya Yamazaki

IEEE 15th International Conference on Computer Sciences and Information Technologies 1 340 - 343 2020

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Monitoring is an essential process of data center operation. There are some common methods to detect data center device corruption or any type of intrusions in the operation. The best practices of monitoring data center are ensuring physical features of data center environment such as room temperature, humidity, and usage of the central processing unit (CPU) and storage of the machines which is used for hosting user services. Due to exceeding varieties of physical feature combination in data center environment, data center managing organizations cannot fully monitor it and experience unexpected conditions from time to time. Many organizations who manage data center also apply visual monitoring of Light Emission Diode (LED) indicators of devices with human interaction which takes large amount of cost and labor to reduce service interruption occurrences. In this paper, we present the concept and experimental results of an automatic monitoring system for data center devices. The concept of the automatic monitoring system is based on monitoring frequency of flickering LEDs of the device method. To evaluate performance of the automatic monitoring, we applied it to video recording of flickering LED of server device. During the implementation stage, we successfully located LED position from frame images and visualized series duration time of flickering LEDs. The experimental results present evaluation of the proposed method.

DOI： 10.1109/CSIT49958.2020.9322008

Other Link： https://dblp.uni-trier.de/db/conf/csit/csit2020-1.html#EnkhbaatarY20

First impression factor analysis through facial video evaluation experiments

Tatsuya Yamazaki

Facial Expressions: Recognition Technologies and Analysis 169 - 184 2019.5

Publishing type：Part of collection (book)

To construct a good interpersonal relationship, people generally try to make a favorable first impression on other persons. In the process of first impression construction, faces relatively rule impression formation. Since what causes the favorable first impression is still unclear, some persons are good at constructing or improving their impression and others are not. We study to find out the cause of impression improvement by conducting subjective evaluation experiments using facial video images. Two different kinds of videos are used: one is that of uttering the fixed words in a natural way (the natural video) and the other is that of reading the fixed story in such a way as to give a good impression to someone (the impressed video). A person appearing in the video is called a subject and the person who evaluates the subject is called an evaluator. For evaluation, the evaluators score the impressed videos by Semantic Differential method. Using Principal Component Analysis (PCA), two main factors on impression are extracted as "steadiness" and "forcefulness." Moreover, using two kinds of videos, the impression improvement is evaluated by the Double Stimulus Continuous Quality Scale method and the subjects are divided into two groups, that is the high and low improvement groups. By the two-way analysis of variance for the PCA factors, it is found that evaluation of "steadiness" lowers for the high improvement group. In addition, it is revealed that both genders (male and female) equally evaluate impression improvement because there is no significant difference.

Preface

Tatsuya Yamazaki

ACM International Conference Proceeding Series V 2019.1

Water management based on precision agriculture for pears

Tatsuya Yamazaki, Kazuya Miyakawa

Pears: Cultivars, Production and Harvesting 205 - 223 2019.1

Publishing type：Part of collection (book)

Water management is one of the key practices in fruit production worldwide. It is not so straightforward when to and how to control water in agriculture fields. Farmers rely on their experience and intuition and visit their farm day after day to check whether the products need to be irrigated or not. Recently, Precision Agriculture including sensing technologies is prevailed to support their decision in water management. In this paper, targeting at pears, effects of Precision Agriculture are verified for water management, which consists of irrigation and humidity measurement. For irrigation, a machine learning scheme is introduced to support farmers’ decision on irrigation. A learning mechanism is proposed where soil moisture sensing data are used. For humidity, a small sensor is used to carry out the measurement of temperature and humidity in fruit bags for pears. As the result, although there is little difference of the temperature change regardless fruit bag types, difference of the humidity change is observed for each fruit bag. Finally, pear fruit outlook quality is evaluated manually and it is related with the inner-bag factors by a statistical model.

Case studies on biometric application for quality-of-experience evaluation in communication

Tatsuya Yamazaki

Advances in Biometrics: Modern Methods and Implementation Strategies 227 - 247 2019.1

Publishing type：Part of collection (book)

With the popularization of portable terminals, the frequency of application use in the mobile environment increases, and the demand for QoS (Quality of Service) is also increasing. In the mobile environment, the communication fluctuation is large, and the quality requirement for an application that frequently transmits user’s operation to the server side, e.g., a game, becomes severe. QoE (Quality of Experience) has become one of the important topics as a mobile communication ultimate metrics in the academic field as well as in the business field. In this study, we focus on Internet service quality evaluation by biometrics. We aim to analyze the relationship between the quality of the communication service and the biometric signal in a mobile role-playing game situation as a case study. Therefore, we originally build an experimental environment to control delay as a QoS parameter, collect EEG (electroencephalography) and subjective QoE assessment data during game operation, and analyze correlation between the QoE evaluation and the EEG data of gaming. We verify the relationship between the biological signal and QoE in this study.

DOI： 10.1007/978-3-030-30436-2_11

A Narrow-Area Specific Messaging System for Tsunami Evacuation.

Naoki Kobayashi, Tatsuya Yamazaki

IEEE 8th Global Conference on Consumer Electronics(GCCE) 1032 - 1033 2019

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

For Tsunami evacuation, specific evacuation information needs to be transmitted to each evacuee, for example, the nearest evacuation facility. At present, such an information transmitting system for narrow specific areas has not been organized well. In this paper, we propose a narrow-area specific messaging system where taxis play a role of information transmitters. Since taxis have a mobility property, their allocation pattern can be changed within the target area. Effectiveness of information transmission according to the taxi allocation pattern is evaluated through Multi-Agent System computer simulation. As the experimental results, it is found that decentralized and unbiased taxi allocation can accelerate evacuation completion.

DOI： 10.1109/GCCE46687.2019.9015452

Other Link： https://dblp.uni-trier.de/db/conf/gcce/gcce2019.html#KobayashiY19

Load Profile-Based Coordination of Appliances in a Smart Home.

Rui Teng, Tatsuya Yamazaki

IEEE Trans. Consumer Electron. 65 ( 1 ) 38 - 46 2019

Publishing type：Research paper (scientific journal)

Fine-scale load profile monitoring in smart home systems provides large sources of data for the energy consumption patterns of various home appliances. New opportunities for home energy management with high-level granularity can rise due to the increasing availability of load profile data. Such energy management is especially important for hybrid energy sources, which have limited power capacity for renewable energy. This paper introduces a home energy system that collects load profiles and supports event reservation with the proactive coordination of appliances. We address the problem of profile-based coordination among home appliances, which may operate concurrently. The coordination efficiency is measured by the total energy cost, which is a function of energy prices and the energy consumption at each energy source. We propose a profile-matched time-shift approach in order to minimize the total energy cost. The proposed approach identifies a set of start times of multiple home appliances according to the power consumption prices, delay tolerances, and energy sources capacities. The proposed method is evaluated by a comparison with other methods, such as random shifting. The results show that the profile-matched shifting of home appliances yields the lowest cost compared the costs of with other approaches.

DOI： 10.1109/TCE.2018.2885874

Information Design of Evaluation Application and Process for Japanese Sake.

Yuki Hashimoto, Tatsuya Yamazaki

14th IEEE International Conference on Computer Sciences and Information Technologies 2 1 - 4 2019

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

With the progress of sensor technologies, quantitative numerical data are available for food and beverage producers. On the other hand, in most cases, consumers evaluate the food and the beverage intuitively and subjectively. It is necessary to clarify how the numerical data correlate with the mass consumer subjective evaluation. Focusing on Japanese Sake, we develop an application to collect the consumer evaluation as numerical data. Also, we propose an evaluation process with the developed application to carry out a tasting experiment. A Japanese Sake tasting experiment has been conducted by the developed application and the proposed process with 22 subjects. The questionnaire opinions from the subjects reveals that VAS (Visual Analog Scales) is appropriate for the input interface of evaluation data in the application, because evaluation of VAS is 3.6 out of 5. Also, it is found that detailed description on the evaluation items of VAS is needed for some items with ambiguous definition.

DOI： 10.1109/STC-CSIT.2019.8929764

Other Link： https://dblp.uni-trier.de/db/conf/csit/csit2019-2.html#HashimotoY19

Alert Application to Texting While Walking of the Improving Momentary User Experience and Increasing the user's intention to use the proposed that. Reviewed

Eguchi Masato, Miyoshi Takumi, Niitsu Yoshihiro, Yamazaki Tatsuya, Ohno Takehiko

The Transactions of Human Interface Society 20 ( 2 ) 243 - 254 2018

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：ヒューマンインタフェース学会

Walking-while-texting on mobile phones has become a large social problem because conflict accidents with other people frequently occur in the traffic areas such as the station yards. Applications to prevent the walking-while-texting have already been launched, but they do not seem to be used commonly. In this paper, we have considered two new view points, an internal factor of screen watching and an external factor of environmental risk conditions in referring to the knowledge obtained by the group interview. We have developed a new system to timely alert to the walking-while-texting user by using a smartphone application and environmental measurement sensors. As a result of comparison of the proposed system to the application officially provided by NTT docomo, we successfully achieved the application efficiency, the effect of prevention of walking-while-texting, improving momentary user experience and raising intention to use.

Study of relationship between physiological index and quality of experience for video streaming service Reviewed

Yamazaki Tatsuya, Yamamoto Ryohei, Iijima Atsuhiko

IEICE COMMUNICATIONS EXPRESS 7 ( 6 ) 218 - 223 2018

Introduction of Following Behavior and Proposal of Reductive Models for Delay Risk in Urban Evacuation Simulation Reviewed

Tamai Hiroyuki, Yamazaki Tatsuya, Owada Yasunori, Sato Goshi, Karasawa Naoyuki

Transaction of the Japan Society for Simulation Technology 10 ( 1 ) 17 - 24 2018

Language：Japanese Publishing type：Research paper (scientific journal) Publisher：日本シミュレーション学会

&emsp;Multi-agent systems are often used in evacuation simulation. The agent needs to be modeled to include psychological factors of evacuees. The following behavior, which is one of the major psychological factors, is defined as the behavior to follow other persons when he/she does not know where to evacuate. While the following behavior is known as the risk of inducing wrongly directed evacuation, it may expedite the evacuation by chaining a group of people to a right direction. The effects of following behavior are, however, almost unknown at the city level.<br> &emsp;In this paper, the agent model with the following behavior is introduced and evaluated its property at the city level. Also, two models of &ldquo;path memory&rdquo; and &ldquo;follow-up promotion behavior&rdquo; are proposed as countermeasures against the property of evacuation delaying caused by the following behavior.<br> &emsp;Through the evacuation simulation experiments assuming the tsunami disaster, it is shown that evacuation speed depends on the ratio of the agents who know an evacuation spot. Also, we show that &ldquo;path memory&rdquo; accelerates the evacuation behavior when few surrounding agents have knowledge on the evacuation spots as well as &ldquo;follow-up promotion behavior&rdquo; shows the same tendency when several surrounding agents have the same knowledge.<br>

Agent Walking Model Construction in Urban Disaster Simulation.

Tatsuya Yamazaki, Naoki Kobayashi, Yasunori Owada, Goshi Sato

IEEE 7th Global Conference on Consumer Electronics(GCCE) 355 - 356 2018

Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Computer simulation is useful to study movement of a crowd of evacuees in a large-scale urban disaster case. Multi-Agent System is often used in the simulation and agent behaviors must reflect the psychological and physical properties of human behaviors as much as possible. In this paper, we propose an evacuating agent walking model. The walking speed depends on each person and the elderly person's walking speed can be modeled based on pseudo-elderly walk experiments. Also, based on the real evacuation data at the time of the Great East Japan Earthquake, the distribution of the evacuation start time is estimated.

DOI： 10.1109/GCCE.2018.8574780

Other Link： https://dblp.uni-trier.de/db/conf/gcce/gcce2018.html#YamazakiKOS18

Urban disaster simulation incorporating human psychological models in evacuation behaviors Reviewed

Tatsuya Yamazaki, Hiroyuki Tamai, Yasunori Owada, Kiyohiko Hattori, Shin’ichi Taira, Kiyoshi Hamaguchi

IFIP Advances in Information and Communication Technology 501 20 - 30 2017

Language：English Publishing type：Research paper (international conference proceedings) Publisher：Springer New York LLC

Building evacuation simulation provides us with various knowledge and suggestion before a real disaster happens. To date, however, evacuees were often modeled as homogeneous without individual motivation in a large-scale urban simulation model, which is rather different from real human behavior. In this paper, an evacuation simulation model with human psychological models is developed for urban disaster situation. Three psychological models are actually incorporated: normalcy bias, emotional contagion bias, and sympathy behavior bias. Normalcy bias is the initial evacuation delay caused by a belief that abnormal events rarely happen. Emotional contagion is the effect of one person’s emotional state on the emotional state of people around him/her both explicitly and implicitly. Simulated experimental results show that the proposed model provides accurate evacuation behaviors than the normal behavior model without psychological consideration.

DOI： 10.1007/978-3-319-68486-4_3

Soil Moisture Sensing Experiments for Water Management in Pear Fields.

Tatsuya Yamazaki, Kazuya Miyakawa

Proceedings of the 6th International Conference on Informatics, Environment, Energy and Applications(IEEA) Part F128273 56 - 59 2017

Publishing type：Research paper (international conference proceedings) Publisher：ACM

Water management is one of the most important tasks in agriculture. However, the farmers rely on their intuition and experience to determine when and how much water should be provided. Sensing technologies have been highly developed and several test works were conducted. There are two types of sensors to measure soil moisture: soil moisture content and soil moisture tension sensors. The usage of these sensors can be different from each agricultural product and there is no validation test for pear cultivation. In this paper, we describe the validation experiment of these two types of sensors which are conducted in pear fields. After measuring the soil moisture during one-season pear cultivation, we have clarified the difference of two types of sensors . The soil moisture tension sensor can quantify the waterretaining power of soil, while the soil moisture content sensor can detect detailed fluctuation of the water content ratio in soil.

DOI： 10.1145/3070617.3070633

Other Link： https://dblp.uni-trier.de/db/conf/ieea/ieea2017.html#YamazakiM17

Matching of Energy Provisions in Multihop Wireless Infra-Structures Reviewed

Rui Teng, Huan-Bang Li, Ryu Miura, Tatsuya Yamazaki, Peter Davis

ENERGIES 9 ( 1 ) 2016.1

Language：English Publishing type：Research paper (scientific journal) Publisher：MDPI AG

Recently there have been large advances in energy technologies for battery-operated systems, including green energy resources and high capacity batteries. The effective use of battery energy resources in wireless infrastructure networks to improve the versatility and reliability of wireless communications is an important issue. Emerging applications of smart cities, Internet of Things (IoT), and emergency responses highly rely on the basic communication network infrastructures that enable ubiquitous network connections. However, energy consumption by nodes in a wireless infrastructure network depends on the transmissions of other nodes in the network. Considering this inter-dependence is necessary to achieve efficient provision of energy in wireless networks. This paper studies the issue of energy provision for wireless relay nodes in Wireless Multihop Infrastructures (WMI) assuming constraints on the total energy provision. We introduce a scheme of Energy Provision Matching (Matching-EP) for WMI which optimizes energy provision based on matching of energy provision with estimates of differentiated position-dependent energy consumption by wireless nodes distributed in the network. The evaluation results show that Matching-EP with 4%-34% improvement in energy matching degree enables 10%-40% improvement of the network lifetime, and 5%-40% improvement of packet delivery compared with conventional WMI networks.

DOI： 10.3390/en9010045

Congestion Field Detection for Service Quality Improvement Using Kernel Density Estimation Reviewed

Yuki Shitara, Tatsuya Yamazaki, Takumi Miyoshi, Kyoko Yamori

2016 18TH ASIA-PACIFIC NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM (APNOMS) 1 - 4 2016

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Owing to proliferation of smart phones, communication services such as a video streaming service are common in a mobile situation. For these services, quality evaluation and communication control based on Quality of Experience (QoE), which is the degree of a user's subjective satisfaction, is very important because the final goal of delivering high-quality service is improving user's satisfaction. QoE tends to be affected by several factors including Quality of Service (QoS). Therefore, collecting QoS data from the users who use the mobile application has become one of promising schemes to meet the QoE, which is called the crowd sourcing data. The crowd sourcing data are, however, apt to be affected by sensing errors and low accuracy. In this study, we propose to estimate some densities just from the records of application use and its location information to remove the sensing errors and low accuracy. The Kernel density estimator is used to derive a continuous density function from discrete distributed sample data such as the collected QoS data. From the viewpoint of QoS, it is important to extract high-density fields of the application use to find out QoS degradation. After estimating the Kernel density estimator, we determine the borderline between the high-density field and the other field by using the reference value that can be determined from the observed data. Simulated experiments verify effectiveness of the proposed method.

DOI： 10.1109/APNOMS.2016.7737246

Interactive Facial Expression Reader and Extension to First Impression Improver Reviewed

Tatsuya Yamazaki, Ken'ichi Maehara, Koichiro Enomoto

PERCEPTION AND MACHINE INTELLIGENCE, 2015 26-27-February-2015 183 - 188 2015

Language：English Publishing type：Research paper (international conference proceedings) Publisher：ASSOC COMPUTING MACHINERY

Facial expression plays an important role as non-verbal information in dialogue communication. People complement verbal information with non-verbal information to hold a smooth conversation. To date, collaboration between information engineering and psychology has enabled development of human facial expression recognition technology. Most of the related studies, however, have ended up with a laboratory-based demonstration. In this paper, focusing on the facial expression database, we overview the facial expression recognition technology. Then we present a simple application using the current status of the facial expression recognition technology. Finally we show prospect of the technology with a more realistic application.

DOI： 10.1145/2708463.2709059

Other Link： http://dblp.uni-trier.de/db/conf/permin/permin2015.html#conf/permin/YamazakiME15

Verification of View-based Self-localization of Autonomous Outdoor Mobile Robots Reviewed

Tatsuya Yamazaki, Shinichi Yuta, Tadahiro Hasegawa

2015 54TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE) 1140 - 1143 2015

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

We reported on the self-localization of autonomous outdoor mobile robots based on detecting the edge of pavement in camera images. The detecting technique of utilizing the difference in color between the edge and pavement was proposed and verified, to realize edge detection that is not affected by the sunshine condition of pavement in the captured image. The experimental results showed that the self-localization based on the edge of pavement in camera images is useful for outdoor mobile robots.

DOI： 10.1109/SICE.2015.7285572

Temperature and Humidity Measurement inside Pear (Pyrus Communis) Bags during Preharvest Bagging Reviewed

Tatsuya Yamazaki, Tomohiko Sugiyama

2015 54TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE) 1199 - 1202 2015

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

In order to protect fruits, preharvest bagging is usually used for fruit growth including apples, peaches, grapes and pears. Characteristic and performance of the fruit bag used for the preharvest bagging have an important role to improve quality of the fruits. Effects of preharvest bagging have been studied by surveying postharvested fruits. However, studies on the inner-bag environment including temperature and humidity have been hardly studied during fruit growing so far. In this paper, it is proposed to measure temperature and humidity inside different fruit bags to clarify difference of the bags. Targeting at pears 'Le Lectier', a small sensing logger is used to carry out the measurement for three different types of bags. Based on 130 days continuous measurement, the difference of the bags are gured and visualized.

DOI： 10.1109/SICE.2015.7285426

Resource Allocation Method Based on QoE for Multiple User Types Reviewed

Tatsuya Yamazaki, Takumi Miyoshi

7th International Conference on Communication Theory, Reliability, and Quality of Service (CTRQ2014) 13 - 18 2014.2

Language：English Publishing type：Research paper (international conference proceedings)

Both of Quality of Service (QoS) and Quality of Experience (QoE) are defined to specify the degree of service quality. In some sense, QoE includes subjective evaluation from the users as an extension of QoS. Therefore feedback from QoE to QoS control might realize user-oriented resource allocation in network services. Utility functions are sometimes used to assign a bridging role between QoS and QoE. Although the user characteristic has variety, a single utility function was used in previous studies in most cases. Moreover the QoS control, i.e. the resource allocation, by making use of the utility functions are hardly studied yet. In this paper, multiple user types which have respective utility functions are considered. Respective utility functions are acquired from real experiments. Then a resource allocation method is proposed to reflect each user type satisfaction based on the utility functions. The simple case is studied and the resource allocation method is derived analytically.

Quality of Experience Modeling with Psychological Effect for Interactive Web Services Reviewed

Tatsuya Yamazaki, Masato Eguchi, Takumi Miyoshi, Kyoko Yamori

2014 IEEE NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM (NOMS) 1 - 4 2014

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Notion of the user-centered design (UCD) is requisite to improve user satisfaction. Matching the concept of UCD, Quality of Experience (QoE) is expected to become a paradigm shift from the existing operator-initiative network services. There are, however, several difficulties to realize practical communication services based on QoE. One difficulty is how to bridge QoE and Quality of Service (QoS) parameters relevant to system performance. Moreover, since QoE is based on the end-user subjective evaluation, flexible modeling corresponding to the end-user psychological status is needed. In this paper, an interactive Web service is considered and a QoE model with end-user psychological effect is derived by use of the Weber-Fechner law. Data of QoE and QoS parameter are collected through experiments and the mapping functions between QoE and QoS are estimated from the data.

DOI： 10.1109/NOMS.2014.6838398

QoE-driven Bandwidth Allocation Method Based on User Characteristics Reviewed

Huong Pham-Thi, Hiep Hoang-Van, Takumi Miyoshi, Tatsuya Yamazaki

2014 16th Asia-Pacific Network Operations and Management Symposium (APNOMS) 1 - 6 2014

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Network providers are nowadays facing with a big question in allocating network resources due to the constantly increasing of Internet services. While the network resource is not unlimited, users always desire the best quality of experience (QoE) with the huge information exchange. Therefore, finding a justice of network resource allocation based on the user experience is mandatory. In previous studies, network resources were allocated to all users by using a specific utility function without considering the user characteristics. In fact, the network resource consumptions are very different among individual users and directly depend on users' behavior. For instance, the network demands of relax users are usually lower than those of busy users. Thus, allocating the same amount of resources to all users might not meet their expectations. In this paper, we propose two bandwidth allocation methods by classifying users into different groups based on their characteristics such as relax, short-time busy, and long-time busy users. To allocate the bandwidth in each group, specific utility functions are applied. By using these methods, the obtained results show that users get the different allocated bandwidth while they still experience the same level of QoE. On the other hand, the allocation considers users' behavior to allocate suitable bandwidth based on the real resource consumption of users. As a result from these analyses, our proposal tends toward a fair allocation as well as an efficient management of the network resources.

DOI： 10.1109/APNOMS.2014.6996518

Assistive technologies in smart homes

Tatsuya Yamazaki

Assistive Technologies: Concepts, Methodologies, Tools, and Applications 663 - 678 2013.8

Publishing type：Part of collection (book)

This book chapter provides a review of the assistive technologies deployed in smart spaces with a variety of smart home or house examples. In the first place, home networking technologies and sensing technologies are surveyed as fundamental technologies to support smart environment. After reviewing representative smart home projects from across the world, concrete assistive services related with the fundamental technologies in smart environment are deployed not only for the elderly and handicapped but for people in ordinary families as well. Adaptability is one of the key essences in the assistive technologies in smart environment and, for this purpose, human-ware studies including man-machine interfaces, ergonomics and gerontology are needed to be linked with the hardware specific fundamental technologies.

DOI： 10.4018/978-1-4666-4422-9.ch032

Special Section on Quality of Communication Services Improving Quality of Life FOREWORD Reviewed

Tatsuya Yamazaki

IEICE TRANSACTIONS ON COMMUNICATIONS E96B ( 2 ) 391 - 391 2013.2

Foreword. Reviewed

Tatsuya Yamazaki

IEICE Transactions 96-B ( 2 ) 391 2013

Tatsuya Yamazaki

IEICE Trans. Commun. 96-B ( 2 ) 391 - 391 2013

A service quality coordination model bridging QoS and QoE Reviewed

Tatsuya Yamazaki, Takumi Miyoshi, Masato Eguchi, Kyoko Yamori

IEEE International Workshop on Quality of Service, IWQoS 1 - 4 2012

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Both of Quality of Service (QoS) and Quality of Experience (QoE) are defined to specify the degree of service quality. Although they are dealt with in different layers in multi-layered models, collaboration of these is necessary to improve the user satisfaction for telecommunication services. In this paper, after sorting out the concepts and specification of QoS and QoE, a service quality coordination model combining these is proposed. The model is applied to a video-sharing service and its coordination model is derived based on subjective experiments. The structural equation modeling is used to compute the user satisfaction from QoS and QoE. © 2012 IEEE.

DOI： 10.1109/IWQoS.2012.6245977

Communicative Robot Interface for the Ageing Society Reviewed

Tatsuya Yamazaki

2012 12TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS & VISION (ICARCV) 668 - 671 2012

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Supporting the elder people's independent life is needed for the imminent ageing societies. Assistance should be provided from both physical and cognitive aspects. The houses enhanced by use of ICT (Information and Communication Technology) are called smart homes and they proved to be useful for physical assistance for the elder persons. Communication is important to improve elderly people's moods and interactive robots are another promising ICT to provide mental or cognitive support for the elder people. In this paper, effects of the interactive robots are evaluated based on a real-life experiment with a couple of husband and wife in their sixties. The impression of the interactive robots is analyzed based on the score of SD (Semantic Differential) method.

DOI： 10.1109/ICARCV.2012.6485237

A POWER CONSUMPTION ACTIVITY BASED HETEROGENEOUS SOA FRAMEWORK FOR CONTEXT-AWARE HOME SERVICES Reviewed

Hyun Sang Cho, Takekazu Kato, Tatsuya Yamazaki, Minsoo Hahn

JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS 20 ( 7 ) 1211 - 1230 2011.11

Language：English Publishing type：Research paper (scientific journal) Publisher：WORLD SCIENTIFIC PUBL CO PTE LTD

The home network is one of the emerging areas from the last century. However, the growth of the home network market is stationary at present. This paper describes the limitations of the home network system and the requirements for overcoming the current limitations. Also described is a new home network service system known as COWS and its easy installation and scalable operation. COWS consists of power consumption monitor and control devices along with a service server that is a complementary combination of Open Service Gateway initiative (OSGi) and web services. A home network system has a dynamic, heterogeneous, distributed, and scalable topology. Service Oriented Architecture (SOA) has been proposed as a solution that satisfies the requirement of a home network, and OSGi and web services are two successful SOA-based frameworks. An included service server has a flexible architecture that consists of a core and extendable service packages. A power consumption monitor and control function provides useful context information for activity-based context-aware services and optimizes the power consumption. The system can be installed easily into existing and new houses to solve the current barrier of the popularization of home network services.

DOI： 10.1142/S0218126611007840

Bandwidth-efficient media access protocol for wireless feedback control in home energy networks Reviewed

Rui Teng, Tatsuya Yamazaki, Kiyoshi Hamaguchi

IEEE International Conference on Communications 2011

Language：English Publishing type：Research paper (international conference proceedings)

Home energy networks require the integration of networked sensing with networked control for energy monitoring and management. Shared communication media for sensing and control is easy to be configured but introduces the delay and packet loss. This paper studies the Media Access Control (MAC) layer support of reliable wireless feedback control and flexible sensing in home networks. We discuss the problem of large bandwidth requirement of reliable feedback control in the limited bandwidth of the shared network media. We propose a dynamic bandwidth assignment approach that fits the reliability requirement of feedback control and enables a high bandwidth utilization to solve the problem. The simulation results reveal that FCMA can achieve high bandwidth efficiency with low packet losses. © 2011 IEEE.

DOI： 10.1109/iccw.2011.5963576

Implementation of Daily Activity Management Service System with Smart Grid Reviewed

Hyun Sang Cho, Tatsuya Yamazaki, Sung Eun Kim, Minsoo Hahn

AGING FRIENDLY TECHNOLOGY FOR HEALTH AND INDEPENDENCE 6159 230 - + 2010

Language：English Publishing type：Research paper (international conference proceedings) Publisher：SPRINGER-VERLAG BERLIN

Health management is fundamental to enabling elderly people to 'age in place' in their homes, and health care services can help elderly people to manage their health. The number of elderly people who require such care services is increasing rapidly, causing a parallel rise in the need for expert care providers. One of the solutions to this demand for expert care is an automatic health care system that may be integrated into a residence, but installing and operating such systems can be prohibitively expensive. To solve this issue, a cost-effective activity monitoring based health care system is proposed in this study. The system uses the infrastructure of a smart grid and a home network system in order to reduce the costs of installation and operation.

DOI： 10.1007/978-3-642-13778-5_30

QoS Supported MAC for Arbitrary Networked Control in Home Networks Reviewed

Rui Teng, Tatsuya Yamazaki, Kiyoshi Hamaguchi

2ND IEEE INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER CONTROL (ICACC 2010), VOL. 1 1 460 - 464 2010

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Home appliances can be connected in a ubiquitous manner by communication networks. In addition to the operation sensing of home appliances, appliance management via sending control messages will be needed. The control operations include power adjustment of home appliances and sampling rate change of a sensing device. It should be noted that control messages differ from sensing data and the former generally require more reliability. In this paper, we study the delay performance of control messages at MAC (Media Access Control) layer in the network with shared communication media. The proposed approach can confine the delay uncertainty of the control messages within a specified tolerant time for respective appliance.

DOI： 10.1109/ICACC.2010.5487149

SNMP-based Computer Resource Usage Monitoring System for Energy Conservation in Office Environment Reviewed

Seungwon Oh, Minsoo Hahn, Tatsuya Yamazaki

2010 INTERNATIONAL COLLOQUIUM ON COMPUTING, COMMUNICATION, CONTROL, AND MANAGEMENT (CCCM2010), VOL III 280 - 282 2010

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

We propose a SNMP-based Computer Resource Usage Monitoring System (CRUMS) to reduce computer power consumption in office environment. This system suggests the efficient method for the power management service included in operating system without complex operation processes or additional devices. To achieve this, the proposed system monitors the information of computer hardware resource usage from each computer connected by office network using SNMP. By considering the resource usage data, the system can minimize not only computer power consumption but inconvenience to users. The result of our experiment shows the value of the system and proves the effectiveness in conserving energy in office environment.

Bit-Watt Home System with Hybrid Power Supply Reviewed

Rui Teng, Tatsuya Yamazaki

2010 2ND INTERNATIONAL CONFERENCE ON COMPUTER AND AUTOMATION ENGINEERING (ICCAE 2010), VOL 5 5 59 - 63 2010

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

This paper introduces a basic architecture of BitWatt home system, one target of which is to optimize the energy consumption of home appliances. The Bit-Watt system consists of intelligent home appliances, a home energy server, and hybrid power supplies. We introduce an energy cost model and propose a proactive energy management approach for the home system. The proposed approach applies time-shift operation to home appliances according to the cost of power supplies. We evaluate the performance of energy management by computer simulation. The simulation result reveals that the proposed approach enables the optimization of energy cost in the home system with hybrid power supplies.

DOI： 10.1109/ICCAE.2010.5451519

Simple and Robust Method for Detecting the Electrical Appliances Using Markers and Programmable Logic Devices Reviewed

Hyun Sang Cho, Minsoo Hahn, Takekazu Kato, Tatsuya Yamazaki

ISCE: 2009 IEEE 13TH INTERNATIONAL SYMPOSIUM ON CONSUMER ELECTRONICS, VOLS 1 AND 2 407 - + 2009

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

The detection of appliances and their location is important for the efficient management and automatic operation of appliances and their power consumption. In this paper, we describe a simple and robust method of detecting appliances based on their location by using programmable logic devices (PLDs). The results of simulation and implementation are also included.

Life with a Robot Companion: Video Analysis of 16-Days of Interaction with a Home Robot in a "Ubiquitous Home" Environment Reviewed

Naoko Matsumoto, Hirotada Ueda, Tatsuya Yamazaki, Hajime Murai

HUMAN-COMPUTER INTERACTION, PT II 5611 ( PART 2 ) 341 - + 2009

Language：English Publishing type：Research paper (international conference proceedings) Publisher：SPRINGER-VERLAG BERLIN

This paper examines human-robot interaction within a home environment over the Course of a 16 day-long experiment. Its purpose is to describe the human cognitive activities involving a symbiotic robot with dialogue interface within domestic settings. The participants were a couple in their 60's. Analysis of video data indicates that (a) the participants continuously used the robot's dialogue interlace, and persevered within this despite the performance of the voice recognition system (b) the participants checked out the robot's function as a tool and gradually came to regard the robot as a companion, (c) fixed instruction expressions increased the use of the dialogue interface for the light controls, while the participants employed both the dialogue interface and the remote controller for the TV and light controls.

DOI： 10.1007/978-3-642-02577-8_37

Simple and robust method for detecting the electrical appliances using markers and programmable logic devices Reviewed

Sang Cho Hyun, Hahn Minsoo, Takekazu Kato, Tatsuya Yamazaki

Digest of Technical Papers - IEEE International Conference on Consumer Electronics 334 - 338 2009

Language：English Publishing type：Research paper (international conference proceedings)

The detection of appliances and their location is important for the efficient management and automatic operation of appliances and their power consumption. In this paper, we describe a simple and robust method of detecting appliances based on their location by using programmable logic devices (PLDs). The results of simulation and implementation are also included. ©2009 IEEE.

DOI： 10.1109/ISCE.2009.5156906

Activity-based computing Reviewed

Nigel Davies, Daniel P. Siewiorek, Rahul Sukthankar

IEEE PERVASIVE COMPUTING 7 ( 2 ) 20 - 21 2008.4

A home sensor network that controls power consumption Reviewed

Jaewook Jung, Youngiae Kim, Minsoo Hahn, Tatsuya Yamazaki, Tetsuo Toyomura, Takashi Matsuyama

IEEE PERVASIVE COMPUTING 7 ( 2 ) 60 - 60 2008.4

Sense Cup: A Design of a New Interactive Holistic Sense Convergence Device for Digital Storytelling Reviewed

Hyun Sang Cho, Soohyun Lim, Tatsuya Yamazaki, Minsoo Hahn

ENTERTAINMENT COMPUTING - ICEC 2008 5309 173 - + 2008

Language：English Publishing type：Research paper (international conference proceedings) Publisher：SPRINGER-VERLAG BERLIN

In this paper, we propose "Sense cup" as a new design concept of a device for enhancing the digital storytelling by serving interactive five senses convergence experience. We designed the cup for providing holistic sense experiences with beverage that synchronized with digital contents such as movies and music and catch the user reaction to generate interaction between users and contents provider.

DOI： 10.1007/978-3-540-89222-9-20

A Study on Improving Image Quality of Highly Compressed Moving Pictures Reviewed

Tomio Goto, Tatsuya Yamazaki, Masaru Sakurai

2008 INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY AND ITS APPLICATIONS, VOLS 1-3 1428 - 1433 2008

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

Recently, the opportunity to treat images has increased. Most of the images are large, so they are usually compressed with JPEG and MPEG, which is a major compression standard. JPEG and MPEG use DCT (Discrete Cosine Transform) for transform. The DCT causes more and more blocky noise as the compression rate is set higher and higher. The images taken in the past axe usually strongly compressed. We propose a method of improving image quality using inverse wavelet transform. The proposed method transforms DCT coefficients into wavelet coefficients, decodes the coefficients by using inverse wavelet transform that selects the basis filters. The edge is protected by setting the threshold and controlling process, and improving image quality is aimed at.

Integration of Sensor Network and Energy Management System in Home and Regional Community Environments Reviewed

Tatsuya Yamazaki, Jaewook Jung, Youngjae Kim, Minsoo Hahn, Rui Teng, Yasuo Tan, Takashi Matsuyama

WMSCI 2008: 12TH WORLD MULTI-CONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL II, PROCEEDINGS 2 276 - 279 2008

Language：English Publishing type：Research paper (international conference proceedings) Publisher：INT INST INFORMATICS & SYSTEMICS

Decreasing greenhouse gas emissions is one of the urgent issues that mankind is facing to. So far energy management systems (EMS) have been installed into a factory environment and good results have been obtained. In this paper, we propose to integrate sensor network systems and EMS to adapt to a heterogeneous home environment and to expand EMS enhanced by information and communication technologies to the level of regional community. Our proposal consists of four phases. A prototype development of the sensor network-based power monitoring and controlling system is presented to prove the effects of the first and second phases. Also two study cases are presented to support the third and forth phases of the proposed system.

Structuring Information on People and Environment for Supporting Robotic Services Reviewed

S. Nishio, N. Hagita, T. Miyashita, T. Kanda, N. Mitsunaga, M. Shiomi, T. Yamazaki

2008 IEEE/RSJ INTERNATIONAL CONFERENCE ON ROBOTS AND INTELLIGENT SYSTEMS, VOLS 1-3, CONFERENCE PROCEEDINGS 2637 - + 2008

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

This paper proposes a new server platform for supporting various robotic services that interact with people. Every robot serving people in public spaces need to know: where the person is, what the person is doing, and what is happening at the place. The proposed platform is the first integrated system that can robustly measure, recognize and provide information on human activities and spatial nature in the environment, in a standard way. In the shopping mall experiment, the system is able to track and capture activities of more than 20 people simultaneously in real time. We also describe the result of robotic service experiment utilizing the power of this platform.

DOI： 10.1109/IROS.2008.4651198

Sharing of real-life experimental data in smart home and data analysis tool development Reviewed

Tatsuya Yamazaki, Tetsuo Toyomura

SMART HOMES AND HEALTH TELEMATICS 5120 161 - 168 2008

Language：English Publishing type：Research paper (international conference proceedings) Publisher：SPRINGER-VERLAG BERLIN

Collecting smart environment experimental data in a real situation and sharing the data are necessary to make the technologies used in the smart environment more practical. We have developed a data analysis tool for the real-life experiment data collected in a smart home environment. The subjects of the 16-day experimental data were a couple of husband and wife in their sixties. The data analysis tool as well as the collected data with the consent of the subjects are open for the purpose of research and development. In this paper, we introduce how the data were collected and the outline of the data analysis tool to promote interdisciplinary research and standardization activities in the field of smart environments.

DOI： 10.1007/978-3-540-69916-3_19

Game interface design guidelines to solve the dysfunction of an online game

Jaewook Jung, Minsoo Hahn, Tatsuya Yamazaki

21st International Symposium on Human Factors in Telecommunication, HFT 2008 359 - 366 2008

Publishing type：Research paper (international conference proceedings)

An online game is one of the most popular entertainments to the youth, but it affects physical, mental and social dysfunction to the youth as well as their family. The reason is that, even though, most of online games are not proper as a family entertainment, many young peoples like to play an online game. This paper suggests three guidelines for designing an online game interface to solve the dysfunction by changing an online game into a proper family entertainment. According to the suggested guidelines, the four directional waist movement based game interface was implemented and has been applied to the commercialized online game without the modification of the game software. The suggested interface has been verified at two times exhibitions. ©2008 HFT2008.

IMIS 2008 message from the workshop organizers MUE 2008

Seong Moo Yoo, Bonam Kim, Hui Huang Hsu, Ilsun You, Jong Hyuk Park, Minyi Guo, Ching Hsien Hsu, David Simplot-Ryl, Edwin H.M. Sha, Hai Jin, Javier Lopez, Shu Ching Chen, Tatsuya Yamazaki, Junmo Yang, Wen Tzeng Huang, Akiyo Nadamoto, Chengcui Zhang, Ching Sheng Wang, Chunming Rong, Frode Eika Sandnes, Geyong Min, Howard Leung, Hyobeom Ahn, Hyunju Kim, Indrakshi Ray, Isabelle Simplot-Ryl, Ismail Khalil Ibrahim, Javier García-Villalba, Jemal H. Abawajy, Jinhua Guo, Jon Youn, Kouichi Sakurai, Kuei Ping Shih, Lawrence Y. Deng, Mei Ling Shyu, Mohammad Al-Shurman, Oh Heum Kwon, Pedro M. Ruiz, Pilar Herrero, Q. Shi, Qun Jin, Seungjin Park, Sang Hyuk Son, Whai En Chen, Witold Pedrycz, Xiaofeng Chen, Yin Fu Huang

Proceedings - 2008 International Conference on Multimedia and Ubiquitous Engineering, MUE 2008 2008

Distributed and cooperative service platforms for home network services

Tatsuya Yamazaki, Atsushi Sawada, Toshikazu Nishimura, Masanori Takaoka, Yosuke Tajika, Michihiko Minoh

Journal of the National Institute of Information and Communications Technology 54 ( 3 ) 155 - 164 2007.9

Publishing type：Research paper (scientific journal)

In the UKARI (Universal Knowledgeable Architecture for Real-life appliances) project, we studied and developed distributed and cooperative service platforms for home network services, which provide services by cooperating functions from networked appliances (NAs). The NAs include consumer appliances as well as sensors, robots, and so on. Main research results were "UKARI-Core" and "UKARI-Kernel", which constitute the platforms. UKARI-Core is a middleware with must and core modules of distributed function cooperation. UKARI-Kernel is, moreover, another middleware as an extension of UKARI-Core with additional functions for flexible user adaptation. We implemented the middleware into various kinds of real appliances and constructed home network services in a real environment to evaluate the efficiency of the proposed service platforms.

Detection of people and tracking test bed using multiple sensors Reviewed

Tatsuya Yamazaki, Kentaro Kayama, Seiji Igi

MUE: 2007 International Conference on Multimedia and Ubiquitous Engineering, Proceedings 135 - 140 2007

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE COMPUTER SOC

In mobile and ubiquitous computing environments, acquisition of contextual information about a user situation is necessary to provide useful services. Although the definition of user context may change according to the situation or the service used, contextual information about who, where, and when are considered to be essential. We have built a test bed with multiple sensors: floor pressure sensors, RFID (radio frequency identification) tag systems, and cameras, to carry out experiments to detect the positions of users and track their movement. The test bed is described and experimental results are presented. By using the background subtraction method, which is conventional and effective, we found moving objects can be extracted under limited conditions in real time.

DOI： 10.1109/MUE.2007.119

Pervasive Computing for Quality of Life Enhancement, 5th International Conference On Smart Homes and Health Telematics, ICOST 2007, Nara, Japan, June 21-23, 2007, Proceedings Reviewed

ICOST 2007 4541 2007

An intelligent artifact as a cohabitant: An analysis of a home robot's conversation log

Naoko Matsumoto, Tatsuya Yamazaki, Akifumi Tokosumi, Hirotada Ueda

Second International Conference on Innovative Computing, Information and Control, ICICIC 2007 2007

Publishing type：Research paper (international conference proceedings)

This paper examines an unprecedented phenomenon in communication between human and intelligent artifacts within the home environment over the course of a 16 day-long experiment. We applied protocol analysis to analyze user utterances recognized by a voice recognition system on the home robot from the cognitive viewpoint. In this paper, two types of analysis have been conducted: (i) time-series analysis and (ii) analysis of differences in each room. The results indicate that (a) users get accustomed over time to the intelligent artifact and attachment emotions are elicited gradually with the passage of time, (b) users have gradually mixed cognition for the intelligent artifacts, which come to be recognized both as a cohabitant and as a tool, (c) users' complains have been counterbalanced with attachment emotions, and (d) users' cognition is different in each room and their cognition involving the intelligent artifacts would be also different. © 2007 IEEE.

DOI： 10.1109/ICICIC.2007.158

Special section on human communication II

Shinya Miyazaki, Tatsuya Yamazaki, Yoshimitsu Aoki, Kazunori Fujimoto, Atsushi Fukayama, Kiyoshi Hoshino, Masayuki Ihara, Kyoko Ito, Miyuki Kamachi, Yoshinari Kameda, Hirokazu Kato, Shinichi Kita, Mitsunori Matsushita, Akira Okamoto, Hiroko Shoji, Yugo Takeuchi, Tetsuya Watanabe, Yasuyuki Yanagida, Michihiko Minoh

IEICE Transactions on Information and Systems E89-D ( 6 ) 1767 - 1767 2006.6

Human action detection and context-aware service implementation in a real-life living space test bed Reviewed

Tatsuya Yamazaki

2006 2ND INTERNATIONAL CONFERENCE ON TESTBEDS AND RESEARCH INFRASTRUCTURES FOR THE DEVELOPMENT OF NETWORKS & COMMUNITIES 2006 274 - 279 2006

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

After completion of a real-life living space test bed, the Ubiquitous Home, new sensors have been implemented. In this paper, new functions of the Ubiquitous Home and actual sensed data are presented. Since one of the purposes for the Ubiquitous Home is to evaluate the context-aware services in a real-life situation, a case of context-aware service implementation is also presented. For the service implementation, we have developed a network middleware for consumer appliances and sensors named "UKARI-Core". The outline of the UKARI-Core is described briefly.

DOI： 10.1109/TRIDNT.2006.1649162

Beyond the smart home Reviewed

Tatsuya Yamazaki

2006 International Conference on Hybrid Information Technology, Vol 2, Proceedings 2 350 - 355 2006

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE COMPUTER SOC

Due to progress in wired and wireless home networking, sensor networks, networked appliances, mechanical and control engineering, and computers, we can build smart homes, and many smart home projects are currently proceeding throughout the world. However, we have to be careful not to repeat the same mistake that was made with home automation technologies that were booming in the 1970s. That is, [total?] automation should not be a goal of smart home technologies. I believe the following points are important in construction of smart homes from users' viewpoints: development of interface technologies between humans and systems for detection of human intensions, feelings, and situations; improvement of system knowledge; and extension of human activity support outside homes to the scopes of communities, towns, and cities.

DOI： 10.1109/ICHIT.2006.253633

Elderly People Supporting Experiment in a Real-Life Environment Reviewed

Tatsuya Yamazaki

SMART HOMES AND BEYOND 19 149 - 156 2006

Language：English Publishing type：Research paper (international conference proceedings) Publisher：I O S PRESS

The National Institute of Information and Communications Technology of Japan completed a real-life test bed, called the "Ubiquitous Home," for home context-aware service experiments in 2004. Various kinds of sensors are installed in this test bed to collect residents' behavior data and comprehend their situation. Phyno, a dialogue-based interface robot, intermediates between the the Ubiquitous Home and the residents. Three kinds of context-aware services were implemented: TV program recommendation service, cooking recipe showing service and forgotten-property check service. We have conducted a real-life living experiment with a couple of husband and wife in their sixties to evaluate the context-aware services and Phyno's ability. In this paper, we introduce the Ubiquitous Home and Phyno briefly. After explanation of the implemented context-aware services, the experimental results are presented.

Emulator implementation of service scenario description framework for home networked appliances Reviewed

T Yamazaki, D Kwon, A Sawada, M Minoh

2005 JOINT INTERNATIONAL CONFERENCE ON AUTONOMIC AND AUTONOMOUS SYSTEMS AND INTERNATIONAL CONFERENCE ON NETWORKING AND SERVICES (ICAS/ICNS) 2005 23 - 28 2005

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

A home network service middleware called "UKARl-Kernel" has been proposed for distributed and collaborative networked appliances and networked sensors. A home network service can be established by the middleware using distributed function elements on the networked appliances. The middleware uses a service scenario description framework on the basis of BPEL, an XML language to define business processes, to set up the service according to the present situation. In this paper, we describe the overview and of the home network service middleware and its service scenario description. Then implementation of an emulator for the set-vice scenario description framework is reported. It is noted that the proposed description framework can be constructed easily by using the existing toolkits.

DOI： 10.1109/ICAS-ICNS.2005.48

Networked Appliances Collaboration on the Ubiquitous Home Reviewed

Tatsuya Yamazaki, Hirotada Ueda, Atsushi Sawada, Yosuke Tajika, Michihiko Minoh

FROM SMART HOMES TO SMART CARE 15 135 - 142 2005

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IOS PRESS

The National Institute of Information and Communications Technology of Japan completed a real-life test bed, called the "Ubiquitous Home," for home context-aware service experiments in 2004. Various kinds of sensors are installed in this test bed to collect residents' behavior data and comprehend their situation. At the Ubiquitous Home, experimenters can collect real-life data as if living in their own house, not in a laboratory. Variety of actuators and networked appliances are connected to the Ubiquitous Home. "UKARI-Core," a service platform for distributed and cooperative networked appliances, has also been developed to construct home network services using function elements of the networked appliances. The UKARI-Core has its own role-based functional description and function elements are categorized into defined types. One feature of the UKARI-Core is that it can find necessary function elements from plural different networked appliances via network to create a residential service dynamically and in ad hoc way. This paper introduces an overview of the Ubiquitous Home and the UKARI-Core and presents service examples realized at the Ubiquitous Home using the UKARI-Core.

Collaborative system construction with networked appliances and networked sensors

Tatsuya Yamazaki, Masaki Yamauchi, Yosuke Tajika

Second IEEE Workshop on Embedded Networked Sensors, EmNetS-II 2005 153 - 155 2005

Publishing type：Research paper (international conference proceedings)

A collaborative system with networked appliances and networked sensors has been developed at a real-life testbed. The networked appliances are connected by the middleware that establishes a service using distributed function elements on the networked appliances. The networked sensors are connected by IEEE802.15.4 and collaboratively work with the networked appliances. We will show a prototype implementation of the collaborative system. © 2005 IEEE.

DOI： 10.1109/EMNETS.2005.1469111

Ubiquitous home: real-life testbed for home context-aware service Reviewed

T Yamazaki

FIRST INTERNATIONAL CONFERENCE ON TESTBEDS AND RESEARCH INFRASTRUCTURES FOR THE DEVELOPMENT OF NETWORKS AND COMMUNITIES, PROCEEDINGS 2005 54 - 59 2004

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE COMPUTER SOC

The National Institute of Information and Communications Technology of Japan completed a real-life testbed, called the "ubiquitous home," for home context-aware service experiments in 2004. From the viewpoint of sensor ubiquity, the Ubiquitous Home is superior to other similar testbeds. At the Ubiquitous Home, experimenters can collect real-life data as if living in their own house, not in a laboratory. This paper introduces an overview and detailed sensor arrangement of the Ubiquitous Home. Two cases from several progressing experiments are also presented. The first case is on connecting networked appliances; the second concerns the combination of wearable devices and the Ubiquitous Home sensors to record user behavior

DOI： 10.1109/TRIDNT.2005.37

A study of QoS-based multimedia data retrieval systems

T. Yamazaki

IEEE International Symposium on Industrial Electronics I 485 - 489 2003

Publishing type：Research paper (international conference proceedings)

Multimedia applications that treat various types of data like videos, audios, and images are becoming popular amongst the Internet users. Assuming best-effort networks as the infrastructure, we are developing a multimedia data retrieval system based on QoS (quality of service) concept that searches and retrieves various types of multimedia data from plural multimedia data archives. As one of QoS parameters, we select the user's response time. Since the response time is related with network throughputs, throughput measurement becomes an important technology in the system. So far, we have developed a mechanism to decide a retrieval order of multimedia data that match with the user's searching request. The mechanism is called QoS scenario and it balances the user's searching request (keyword matching) and the QoS factor related with the user's response time that can be determined by the throughput measurement. The QoS scenario was used in the first version of our multimedia data retrieval system. In this paper, we study the active and passive throughput measurement technologies. Also, a multimedia data structure is introduced on the basis of the Dublin Core that has been standardized. Owing to the multimedia data structure, the system is able to hold interoperability and wide-area-network search and retrieval can be realized.

DOI： 10.1109/ISIE.2003.1267298

A multiagent reinforcement learning method based on the model inference of the other agents Reviewed

Yoichiro Matsuno, Tatsuya Yamazaki, Jun Matsuda, Shin Ishii

Systems and Computers in Japan 33 ( 12 ) 67 - 76 2002.11

Language：English Publishing type：Research paper (scientific journal)

This paper proposes a reinforcement learning method based on an actor-critic architecture, which can be applied to multiagent competitive games. As an example, we deal with the card game "Hearts." We introduce a method combining an actor-critic learning and model inference of the other agents. A single Hearts game is divided into three stages, and three actors are prepared so that one of them determines actions separately in each stage. In the middle stage, in particular, actions are determined based on expected temporal-difference error. Computer simulation results suggest the importance of the model inference of the other agents.

DOI： 10.1002/scj.10110

A multimedia service composition scheme for ubiquitous networks Reviewed

M Kosuga, N Kirimoto, T Yamazaki, T Nakanishi, M Masuzaki, K Hasuike

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS 25 ( 4 ) 279 - 293 2002.10

Language：English Publishing type：Research paper (scientific journal) Publisher：ACADEMIC PRESS LTD ELSEVIER SCIENCE LTD

It is a challenging task to develop a high quality and secure multimedia service for mobile terminals used in the ubiquitous computing environment. One of the issues is the resource limitation of mobile terminals. In this paper, we presented a multimedia service composition scheme for sharing computer and communication resources by using plural terminals to compensate for this resource limitation. The proposed scheme is based on user authentication, service access control, and the multi-agent-based adaptive Quality-of-Service (QoS) control framework that we developed. We also proposed a novel access mode control based on the trustworthiness of users and extension of the multi-agent-based adaptive QoS control framework to plural users. Focusing on the home network as a typical ubiquitous network, we implemented a prototype testbed system and showed experimental results for the multimedia service composition. (C) 2002 Elsevier Science Ltd. All rights reserved.

DOI： 10.1006/jnca.2002.0140

A Study of Multimedia Communication Coordination with Content Processing

YAMAZAKI Tatsuya, HASUIKE Kazuo, MASE Kenichi, SENGOKU Masakazu

ITE Technical Report 26 ( 13 ) 25 - 30 2002.2

Language：Japanese Publisher：The Institute of Image Information and Television Engineers

Distributing multimedia data to edge servers prevents concentration of access, so that end-users are provided high-quality multimedia services. The CCS (Communication Coordination Server) that we propose is a kind of edge server and provides QoS (Quality of Service) transform by a transcoding technique. We propose a new communication service coordination scheme for the CCS by content processing according to user's requirement or purpose.

DOI： 10.11485/itetr.26.13.0_25

Proactive information supply for activating conversational interaction in virtual communities Reviewed

N. Kurabayashi, T. Yamazaki, T. Yuasa, K. Hasuike

Proceedings - IEEE Workshop on Knowledge Media Networking, KMN 2002 167 - 170 2002

Language：English Publishing type：Research paper (international conference proceedings) Publisher：Institute of Electrical and Electronics Engineers Inc.

This paper describes a method for activating conversational interaction in virtual communities. Our method supplies information proactively to promote utterances of participants. The notion of subjective usefulness of information is introduced to guide conversation effectively so that the participants can obtain or exchange useful information. We implemented an agent that employs our method and conducted the experiments to verify validity of our method. As a result, we found that our method was able to activate conversational interaction and assist participants in obtaining or exchanging useful information.

DOI： 10.1109/KMN.2002.1115180

A multiagent-based adaptive QoS management scheme Reviewed

M Kosuga, T Yamazaki, N Ogino, J Matsuda

ELECTRONICS AND COMMUNICATIONS IN JAPAN PART I-COMMUNICATIONS 85 ( 10 ) 96 - 105 2002

Language：English Publishing type：Research paper (scientific journal) Publisher：SCRIPTA TECHNICA-JOHN WILEY & SONS

With the improvement of speed in personal computers and workstations for communication networks and communication terminals, various applications have been emerging in recent years based on multimedia communications, including stream-type media. In these communication applications, there must be a framework by which the QoS of its stream is determined and adjusted to meet its own purposes according to the user's request and the situation of the terminal and the network. When such an adaptive QoS control mechanism is built in an individual communi cation application, however, the communication application will become complicated. It is thus desirable that the adaptive QoS control mechanism should be realized as a common basis for various communication applications. This paper proposes a framework to realize an adaptive QoS control mechanism that can serve as the common basis for various communication applications, based on direct or indirect collaboration by multiple agents. The proposed framework is implemented and its operation is verified. (C) 2002 Wiley Periodicals, Inc.

DOI： 10.1002/ecja.1135

Composing a multimedia service by plural terminals in ubiquitous networks Reviewed

N Kirimoto, M Kosuga, T Yamazaki, T Nakanishi, M Masuzaki, K Hasuike

IEEE WORKSHOP ON KNOWLEDGE MEDIA NETWORKING, PROCEEDINGS 57 - 62 2002

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE COMPUTER SOC

It is a challenging task to develop a high quality and secure multimedia service for mobile terminals used in the ubiquitous computing environment. One of the issues is the resource limitation of mobile terminals. In this paper, we presented a multimedia service composition scheme for sharing computer and communication resources by using plural terminals to compensate for this resource limitation. The proposed scheme is based on user authentication, service access control, and the multiagent-based adaptive QoS control framework that we developed We also proposed a novel access mode control based on the trustworthiness of users and extension of the multi-agent-based adaptive QoS control framework to plural users. Focusing on the home network as a typical ubiquitous network, we implemented a prototype testbed system and showed experimental results for the multimedia service composition.

DOI： 10.1109/KMN.2002.1115163

QoS adjustment scheme for video transmission to a heterogeneous receivers group Reviewed

T Yamazaki

PROCEEDINGS OF THE 6TH JOINT CONFERENCE ON INFORMATION SCIENCES 6 996 - 1000 2002

Language：English Publishing type：Research paper (international conference proceedings) Publisher：ASSOC INTELLIGENT MACHINERY

In this paper, a QoS adjustment scheme is proposed for real-time video transmission applications which deal with heterogeneous receivers. The heterogeneity of the receivers includes the performance difference of user terminals and networks as well as the difference of the user requirements for multimedia services. The proposed scheme considers the user's respective communication environments and calculates a feasible QoS for each user to utilize the system resources like CPU powers or network bandwidths efficiently. The proposed scheme is implemented in a proxy server, which intermediates between a video server and a group of receivers.

Spline-based QoS Mapping Mechanisms for Hierarchical Multilevel QoS Models.

Tatsuya Yamazaki

IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 85-A ( 6 ) 1349 - 1351 2002

Publishing type：Research paper (scientific journal)

A generic multilevel quality-of-service (QoS) model for distributed multimedia applications is presented. QoS mapping mechanisms are required to translate the QoS parameters among the hierarchical levels. One QoS mapping mechanism based on the spline functions is proposed, hence two splines are compared. One is natural splines and the other is B-splines. QoS measurement experiments were conducted, and it is found that the B-splines give more accurate mapping results than the natural splines once the knots for the splines are selected appropriately.

Other Link： https://dblp.uni-trier.de/db/journals/ieiceta/ieiceta85.html#Yamazaki02

A scalable resource allocation scheme over DiffServ towards end-to-end QoS assurance Reviewed

A Alexelis, T Yamazaki, K Hasuike

IEICE TRANSACTIONS ON COMMUNICATIONS E84B ( 12 ) 3113 - 3123 2001.12

Language：English Publishing type：Research paper (scientific journal) Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG

In recent years, the concept of Quality of Service (QoS) has gained attention in thc network research community and its extension towards delivering QoS level assurance to sensitive applications has generally been agreed to be crucial for the longevity and usability of the Internet On the Internet, the Differentiated Services (DiffServ) architecture is a general framework for the differentiated treatment of traffic aggregates in the core network. However, DiffServ does not extend to end-to-end QoS assurance, In this paper, we propose a simple. resource-brokering scheme, operating over a hierarchically connected internetwork of administratively-independent DiffServ-capable domains that is a simplified model of the Internet. The proposed asynchronous, multi-agent resource-brokering scheme operates locally but avoids conflicts globally. In this way, the traffic control reflects the underlying structure of the internetwork, introduces only a localized complexity thus scaling up well, and permits independent policies between the interconnected domains.

Subjective video Quality Measurement Experiments for Adaptive QoS Control

YAMAZAKI Tatsuya, SATO Noriyuki, FUKUNAGA Shigeru

ITE Technical Report 25 ( 17 ) 23 - 29 2001.2

Language：Japanese Publisher：The Institute of Image Information and Television Engineers

A real-time MPEG-4 video transmission system is used to conduct subjective video quality measurements. In the measurements, three video QoS(Quality of Service)parameters, that is, the frame size, frame rate, and quantization scale change, then the double stimulus continuous quality scale method is used to obtain the subjective test scores from the testees. This report provides the experimental results and discusses on the correlation between the QoS parameters and the user assessment, which might be useful for user-adaptive QoS control in video streaming service.

DOI： 10.11485/itetr.25.17.0_23

Subjective video quality assessment for adaptive quality-of-service control Reviewed

Tatsuya Yamazaki

Proceedings - IEEE International Conference on Multimedia and Expo 397 - 398 2001

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE Computer Society

A real-time MPEG-4 video transmission system is used to conduct subjective video quality measurements. In the measurements, three video QoS (Quality of Service) parameters, that is, the frame size, frame rate, and quantization scale change, then the double stimulus continuous quality scale method is used to obtain the subjective test scores from the subjects. This report provides the experimental results and discusses on the correlation between the QoS parameters and the user assessment, which might be useful for user-adaptive QoS control in video streaming service.

DOI： 10.1109/ICME.2001.1237740

Zinger: Conversation support based on interest similarity Reviewed

Noriyuki Kurabayashi, Tatsuya Yamazaki, Kazuo Hasuke, Taiichi Yuasa

Proceedings - IEEE International Conference on Multimedia and Expo 435 - 438 2001

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE Computer Society

In this paper, we introduce a conversation support agent called Zinger. Zinger acquires the current interest of a participant, identifies a partner who has a similar interest, and recommends several topics related to the interest. This recommendation is expected to help the participant establish common ground in conversing with the partner. The participant can get valuable information with a successful conversation. Experimental results show that Zinger could promote utterances of 35% subjects. In addition, factors affecting the participant's utterances are examined by multiple regression analysis. The results suggest that providing helpful information and appropriate presentations can contribute to better utterances.

DOI： 10.1109/ICME.2001.1237750

A multi-agent reinforcement learning method for a partially-observable competitive game. Reviewed

Yoichiro Matsuno, Tatsuya Yamazaki, Shin Ishii

Proceedings of the Fifth International Conference on Autonomous Agents, AGENTS 2001, Montreal, Canada, May 28 - June 1, 2001 39 - 40 2001

Publishing type：Research paper (international conference proceedings) Publisher：ACM

This article proposes a reinforcement learning (RL) method based on an actor-critic architecture, which can be applied to partially-observable multi-agent competitive games. As an example, we deal with a card game "Hearts". In our method, the actor plays so as to enlarge the expected temporal-difference error, which is obtained based on the estimation of the state transition. The state transition is estimated by taking the inferred card distribution and the other player's action models into account.

DOI： 10.1145/375735.375856

Other Link： http://dblp.uni-trier.de/db/conf/agents/agents2001.html#conf/agents/MatsunoYIM01

A Study of Color Image Segmentation Based on a Multi-dimensional Histogram

YAMAZAKI Tatsuya

ITE Technical Report 24 ( 50 ) 9 - 14 2000.9

Language：Japanese Publisher：The Institute of Image Information and Television Engineers

A deta-driven segmentation algorithm based on a multi-dimensional histogram is proposed for color images. An image is observed as a mixture of multi-variate data, but the number of clusters in the mixture is generally unknown. The proposed algorithm determines the width of a histogram to use and then obtains the number of clusters according to the observed multivariate data. Next, the statistics for each cluster are computed, since this is a requisite for clustering all of the other elements. The proposed clustering method can be applied to various kinds of images, because it is not restricted by an image model used in model-based approaches. The effectiveness of the algorithm is evaluated by computer simulation, and the algorithm is applied to real color image clustering.

DOI： 10.11485/itetr.24.50.0_9

Adaptive QoS management for multimedia applications in heterogeneous environments Reviewed

T Yamazaki, M Kosuga, N Ogino, J Matsuda

PROCEEDINGS OF THE FIFTH JOINT CONFERENCE ON INFORMATION SCIENCES, VOLS 1 AND 2 5 ( 2 ) A564 - A567 2000

Language：English Publishing type：Research paper (international conference proceedings) Publisher：ASSOC INTELLIGENT MACHINERY

In heterogeneous communication environments of wired and wireless networks, gaps in network and terminal performance bring about QoS (Quality of Service) differences. In addition, individual user's QoS requirement changes according to his/her communication situation. We have developed an agent-based adaptive QoS management framework called MARM (Multi-Agent Resource Management) to satisfy the user's requirement in consideration of usable network and terminal resources. In this paper we present a proxy server called CCS (Communication Coordination Server) to intermediate among sender/receiver terminals and to compensate the QoS differences. The CCS is equipped with QoS transformation and error resilience control functions. The CCS is useful to mitigate the complex QoS negotiation in the MARM framework, and facilitates multicasting of media streams in heterogeneous environments.

Adaptive QoS Management Using Layered Multi-Agent System for Distributed Multimedia Applications. Reviewed

Masakatsu Kosuga, Tatsuya Yamazaki, Nagao Ogino, Jun Matsuda

Proceedings of the International Conference on Parallel Processing 1999, ICPP 1999, Wakamatsu, Japan, September 21-24, 1999 388 - 394 1999

A model of adaptive QoS management platform based on cooperation of layered multi-agents Reviewed

N Ogino, M Kosuga, T Yamazaki, J Matsuda

GLOBECOM'99: SEAMLESS INTERCONNECTION FOR UNIVERSAL SERVICES, VOL 1-5 1 406 - 413 1999

Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE

It is important for distributed multimedia applications to assure end-to-end QoS of media streams. Moreover, the end-to-end QoS needs to be managed adaptively according to fluctuation of system states and variation of user requests. In this paper, a model of adaptive QoS management platform for distributed multimedia applications is proposed. In this model, the adaptive QoS management is achieved by direct and indirect cooperation of layered multi-agents. By using the layered multi-agents system, the proposed QoS management platform can flexibly adapt to user's QoS requirements and large variation of system states, and can quickly adapt to small fluctuation of system states, simultaneously.

An agent-based adaptive QoS management framework and its applications Reviewed

M Kosuga, T Yamazaki, N Ogino, J Matsuda

INTERACTIVE DISTRIBUTED MULTIMEDIA SYSTEMS AND TELECOMMUNICATION SERVICES 1718 371 - 376 1999

Language：English Publishing type：Research paper (scientific journal) Publisher：SPRINGER-VERLAG BERLIN

For distributed multimedia applications, adaptive QoS management mechanisms need to be developed to guarantee various end-to-end QoS requirements. In this paper, we propose an adaptive QoS management framework based on multi-agent systems. Adaptation to system resource changes and various user requirements is achieved by the direct or indirect collaboration of agents in the respective phases. In the flow establishment and re-negotiation phase, application agents determine the optimal resource allocation through QoS negotiations to maximize the total users' utility. In the media-transfer phase, stream agents collaborate to adjust each stream QoS reactively. In addition, personal agents help novice users specify stream QoS without any a priori knowledge on QoS. Some multimedia applications have been designed based on the proposed framework.

DOI： 10.1007/3-540-48109-5_30

Remote sensing image classification for forestry using MRF models and VQ method

Tatsuya Yamazaki, Denis Gingras

IEEE International Symposium on Industrial Electronics 3 753 - 756 1997

Publishing type：Research paper (international conference proceedings)

Conventional pixelwise classification techniques have two drawbacks. The first is that they tend to occur isolated misclassifications because they classify each site independently using spectral information only. The second is that sample data which represent each class are indispensable to estimate model parameters or to train classification Neural Networks. In this manuscript a new unsupervised contextual method is proposed for multispectral remote sensing image classification. Markov Random Field (MRF) models are used for modeling the observed and classified images in the proposed method. Both spectral and spatial information can be exploited by the MRF models so as to dissolve contextual inconsistency caused by the first drawback. In addition the Vector Quantization (VQ) method is introduced to dissolve the second drawback. The VQ method classifies the observed data into several clusters without using any sample data. The image classified by the VQ method is so coarse that it includes misclassification and unknown-class sites, however it can be used as an initial classified image for the following MRF-based classification algorithm. The proposed method was applied to LANDSAT Thematic Mapper data to discriminate deciduous trees from ever-green trees. The accuracy of classification was 64.4% by the VQ method and it was improved up to 88.8% by the MRF-based method.

Contextual classification system for remote sensing using a multivariate Gaussian MRF model

Tatsuya Yamazaki, Denis Gingras

Proceedings - IEEE International Symposium on Circuits and Systems 2 648 - 651 1996

Publishing type：Research paper (international conference proceedings)

We propose a spatial contextual classification system for remote sensing images. In the system the observed multi-spectral images are modeled with a multivariate Gaussian Markov Random Field (GMRF) model and the hidden classified image is modeled with another type of MRF model. The classification is carried out from the viewpoint of Maximum a Posteriori (MAP) estimation. One of the well-known problems of MAP estimation is its high computational complexity involved. One way to avoid this problem is a pixelwise classification that is successfully implemented on a computer with a clique-type block matrix notation of a multivariate GMRF local conditional density function (LCDF). The proposed system is applied to real remote sensing data.

Data-driven segmentation of degraded images based on Markov random field models

Tatsuya Yamazaki, Mehdi N. Shirazi, Hideki Noda

Journal of the Communications Research Laboratory 41 ( 1 ) 19 - 36 1994.3

Publishing type：Research paper (scientific journal)

A data-driven segmentation algorithm is developed for images consisting of a known number of distinct regions corrupted by region-dependent white-Gaussian noises with unknown parameters. A recursive algorithm based on the Expectation and Maximization (EM) method is developed to estimate the parameters of the regional noises. Using these estimates, the initially segmented image is estimated by the conventional Maximum Likelihood (ML) method. The region process (true image) is modeled by a Markov Random Field (MRF); then the estimation of the parameters of the model and the segmentation of the true image are alternated using the Maximum Pseudo-Likelihood (MPL) and Iterated Conditional Modes (ICM) methods, respectively. The performance of the algorithm is shown through typical simulation results.

Data-driven segmentation of noisy images modeled with Markov random fields

Tatsuya Yamazaki, Mehdi N. Shirazi, Hideki Noda

Systems and Computers in Japan 24 ( 10 ) 62 - 72 1993

Publishing type：Research paper (scientific journal)

A data-driven texture-based image segmentation plays an important role in a broad field of application. This paper considers a special case where textures can be modeled by white Gaussian noises. A data-driven segmentation algorithm is developed for images consisting of distinct regions which are corrupted (covered) with region-dependent white Gaussian noise. It is assumed that the number of distinct regions is known whereas the noise parameters are unknown. A recursive algorithm based on the expectation and maximization (EM) method is developed to estimate the parameters of the regional noises. The true scene is considered as a realization of a region process modeled by a Markov random field (MRF) which is observed indirectly. Using the observation image and a provisional estimate of the region process, the region process (MRF's) parameters are estimated by applying the maximum pseudo-likelihood (MPL) method. Then using the estimates of the MRF's parameters, the provisional estimate of the region process is updated by applying the iterated conditional modes (ICM) method. This cycle of parameter estimation and region extraction is continued until it converges. The performance of the proposed algorithm is studied through computer simulation.

Multi-spectral Image Classification Using Spectral and Spatial Information

Yamazaki Tatsuya, Denis Gingras

ITE Technical Report 17 ( 58 ) 7 - 12 1993

Language：Japanese Publisher：The Institute of Image Information and Television Engineers

A new criterion using spectral and spatial information is proposed to classify multi-spectral remote sensing images or textured images. The images are modeled with a hierarchical Markov Random Field(MRF) model, which consists of the observed intensity process and the hidden class label process. The class labels are estimated according to the maximum a posteriori(MAP) criterion, however, some reasonable approximations are done to reduce the computational expenses. Finally a stepwise classification algorithm is derived and simulation and experimental results are shown to verify the validity of this algorithm.

DOI： 10.11485/tvtr.17.58_7

Data-driven restoration of degraded binary MRF images using em method

T. Yamazaki, M. N. Shirazi, H. Noda

IEEE Region 10 Annual International Conference, Proceedings/TENCON 799 - 803 1992

Publishing type：Research paper (international conference proceedings)

A data-driven restoration algorithm is developed for binary images degraded nonadditively with flip noises. The true image is assumed to be a realization of a Markov random field (MRF), and the nonadditive flip noises are assumed to be statistically independent and asymmetric. The parameter estimations of the noise and the true image are carried out iteratively in the context of an expectation and maximization (EM) procedure by approximating Baum's auxiliary function of the EM procedure. To approximate Baum's auxiliary function, the estimate of the true image at each EM iteration is used. Simulation examples show the effectiveness of the data-driven restoration algorithm and the parameter estimation procedures.

DOI： 10.1109/TENCON.1992.271860

　 PREV - NEXT 　

1