論文 - 松田　憲幸

Sketch Drawing Support Environment based on Recognition Skill Analysis

Masato Soga, Noriyuki Matsuda, Hirokazu Taki

Proceedings of the 1st International Symposium on Skill Science 2007 (ISSS'07)     61 - 67   2007年09月  [査読有り]

Sketch Learning Environment Based on Drawing Skill Analysis.

Masato Soga, Noriyuki Matsuda, Saeko Takagi, Hirokazu Taki, Fujiichi Yoshimoto

KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS: KES 2007 - WIRN 2007, PT III, PROCEEDINGS ( SPRINGER-VERLAG BERLIN )  4694   1073 - 1080   2007年  [査読有り]

　概要を見る

Skill knowledge is important human knowledge as well as symbolic knowledge. Definition of skill knowledge is knowledge on high level technique that human acquire through repeated training. Skill knowledge is needed for arts, sports and crafts. It concerns human body structure, muscles, and joints. Also, skill knowledge concerns process of human interaction with objects, namely, recognition and action. There are many researches on learning support system for describable knowledge, such as mathematics, physics, grammar, etc. However, there is few pieces of research on learning support system for skill such as arts and sports. This paper analyses skills and generalize skill features. Then we describe problems to diagnose skill errors. After that, we introduce a learning support system for sketch as an example of a skill learning support environment.

DOI

Indoor Localization for Mobile Node Based on RSSI.

Hirokazu Miura, Kazuhiko Hirano, Noriyuki Matsuda, Hirokazu Taki, Norihiro Abe, Satoshi Hori

KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS: KES 2007 - WIRN 2007, PT III, PROCEEDINGS ( SPRINGER-VERLAG BERLIN )  4694   1065 - 1072   2007年  [査読有り]

　概要を見る

Context-aware computing that recognizes the context in which a user performs a task is one of the most important techniques for supporting user activity in ubiquitous computing. To realize context-aware computing, a computer needs to recognize the user's location. This paper describes a technique for location detection inside a room using radio waves from a user's computer. The proposed technique has to be sufficiently robust to cater for dynamic environments and should require only ordinary network devices, such as radio signal emitters, without the need for special equipment. We propose performing localization by relative values of RSSI (Received Signal Strength Indicator) among wireless nodes, and also our system support the node mobility. We evaluate the performance of our system in the environment where the node is movable.

DOI

Authoring System of Digital Educational Content Based on Student Model Concerning Development Stage of Autistic Person.

Hisashi Ogawa, Noriyuki Matsuda, Hirokazu Miura, Hirokazu Taki

SUPPORTING LEARNING FLOW THROUGH INTEGRATIVE TECHNOLOGIES ( IOS PRESS )  162   105 - 108   2007年  [査読有り]

　概要を見る

This paper describes the production of digital educational content which is reflected development stage of each autistic person. There are issues to model learner's developmental stage and to reflect it to the digital educational content. Therefore, we propose student model which consists of three acknowledgement skills (Language, Figure, and Matching) and correspondence rules which describes the relation between the student model and the digital educational content. Then, we developed the authoring system which consists of the student model and the correspondence rules. Instructors evaluated this system. Effectiveness of the system is turned out by the evaluation.

An Interpretation Method for Classification Trees in Bio-data Mining.

Shigeki Kozakura, Hisashi Ogawa, Hirokazu Miura, Noriyuki Matsuda, Hirokazu Taki, Satoshi Hori, Norihiro Abe

KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 2, PROCEEDINGS ( SPRINGER-VERLAG BERLIN )  4252   620 - 627   2006年  [査読有り]

　概要を見る

This research describes the analysis of a decision tree to interactively make rules from data that includes noise. A decision tree is often used in data mining technology because classification rules generated by the decision tree form new knowledge for the domain. However, it is difficult for a non-specialist user of data analysis to discover knowledge even if the decision tree is presented to the user. Moreover, the target data for raining may have both discrete values and continuous values, and these may include a lot of noise and exceptions. To understand the rules, the user needs the intermediate results of mining. Our system has interactive functions to realize interactive mining, and in this research, we propose a data mining technique with an interpretation function so that the user can understand analyzed data from which a required rule is derived.

DOI

Adequate RSSI Determination Method by Making Use of SVM for Indoor Localization.

Hirokazu Miura, Junichi Sakamoto, Noriyuki Matsuda, Hirokazu Taki, Noriyuki Abe, Satoshi Hori

KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 2, PROCEEDINGS ( SPRINGER-VERLAG BERLIN )  4252   628 - 636   2006年  [査読有り]

　概要を見る

Context-aware computing that recognizes the context in which a user performs a task is one of the most important techniques for supporting user activity in ubiquitous computing. To realize context-aware computing, a computer needs to recognize the user's location. This paper describes a technique for location detection inside a room using radio waves from a user's computer. The proposed technique has to be sufficiently robust to cater for dynamic environments and should require only ordinary network devices, such as radio signal emitters, without the need for special equipment. We propose performing localization by relative values of RSSI (Received Signal Strength Indicator) among wireless nodes. Furthermore, we use SVM (Support Vector Machine) to find the criteria for classification (whether a node is inside or outside a given area), in the case where absolute RSSI values are used for localization.

DOI

Improvement of relief algorithm to prevent inpatient's downfall accident with nightvision CCD camera

Noriyuki Matsuda, Takeshi Yamamoto, Shinobu On, Kumiko Mori, Yoshiko Kounose, tsuko Maeda, Hirokazu Miura, Hirokazu Taki, Satoshi Hori, Noriyuki Abe (担当区分： 筆頭著者 )

Proc. SPIE 6051, Optomechatronic Machine Vision, 605118     2005年12月  [査読有り]

　概要を見る

"ROSAI" hospital, Wakayama City in Japan, reported that inpatient's bed-downfall is one of the most serious accidents in hospital at night. Many inpatients have been having serious damages from downfall accidents from a bed. To prevent accidents, the hospital tested several sensors in a sickroom to send warning-signal of inpatient's downfall accidents to a nurse. However, it sent too much inadequate wrong warning about inpatients' sleeping situation. To send a nurse useful information, precise automatic detection for an inpatient's sleeping situation is necessary. In this paper, we focus on a clustering-algorithm which evaluates inpatient's situation from multiple angles by several kinds of sensor including night-vision CCD camera. This paper indicates new relief algorithm to improve the weakness about exceptional cases.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

DOI

A Sketch Learning Support System with Automatic Diagnosis and Advice

Tomohiro IWAKI, Tatsuya TSUJI, Hirotaka MAENO, Masato SOGA, Noriyuki MATSUDA, Saeko TAKAGI, Hirokazu TAKI, Fujiichi YOSHIMOTO

The 13th International Conference on Computers in Education (ICCE2005)     977 - 979   2005年11月  [査読有り]

Tutoring System for Basic Sketching

Saeko Takagi, Noriyuki Matsuda, Masato Soga, Hirokazu Taki, Fujiichi Yoshimoto

The 3rd nternational Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia (GRAPHITE2005)     Poster Session No. 19   2005年11月  [査読有り]

Support System for Basic Sketch Skill Learning

Saeko Takagi, Noriyuki Matsuda, Masato Soga, Hirokazu Taki, Fujiichi Yoshimoto

Proc. of NICOGRAPH International 2005     61 - 66   2005年06月  [査読有り]

Constructive Induction-Based Clustering Method for Ubiquitous Computing Environments.

Takeshi Yamamoto, Hirokazu Taki, Noriyuki Matsuda, Hirokazu Miura, Satoshi Hori, Noriyuki Abe

In: Khosla R., Howlett R.J., Jain L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science ( Springer, Berlin, Heidelberg )  3684   136 - 142   2005年  [査読有り]

　概要を見る

This paper describes a classification criteria-structuring method for handling exception cases. Clustering technology is utilized to classify large amounts of data effectively. In current clustering technology, however, it is impossible for a system to classify all data completely, due to exceptions in the data. In an ubiquitous computing environment, exceptions arise due to changes in the environment. We propose an architecture in which the system changes classification criteria and rules using constructive induction.

DOI

Indoor Location Determination Using a Topological Model.

Junichi Sakamoto, Hirokazu Miura, Noriyuki Matsuda, Hirokazu Taki, Noriyuki Abe, Satoshi Hori

KES'05: Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part IV ( Springer )    143 - 149   2005年  [査読有り]

　概要を見る

Context-aware computing that recognizes the context in which a user performs a task is one of the most important techniques for supporting user activity in ubiquitous computing. To realize context-aware computing, a computer needs to recognize the user's location. This paper describes a technique for location detection inside a room using radio waves from a user's computer. The proposed technique has to be sufficiently robust to cater for dynamic environments and should require only ordinary network devices, such as radio signal emitters, without the need for special equipment. We propose a topological model representing the structure of rooms in a building, and describe a room-detection method using this model.

DOI

Real Time Advice System for Sketch Learning.

Hirotaka Maeno, Tomohiro Iwaki, Masato Soga, Noriyuki Matsuda, Saeko Takagi, Hirokazu Taki, Fujiichi Yoshimoto

TOWARDS SUSTAINABLE AND SCALABLE EDUCATIONAL INNOVATIONS INFORMED BY LEARNING SCIENCES ( IOS PRESS )  133   795 - 798   2005年  [査読有り]

　概要を見る

We are developing a sketch learning support system that advises the way of modification to learners on their way in drawing a sketch. It is important to draw motif as it is when we draw a sketch. It is difficult for novice learners to grasp the form of motif or relation of position because they don't know the features they should focus on or take notice. Therefore, novice learners need some advice for sketch learning. We are developing sketch learning support system that advises the way of modification to learners on their way in drawing sketch. The advice system consists of area-dependent advice system and hand & arm motion advice system. Area-dependent advice system offers advice according to the way of drawing a figure when learners begin to draw the figure. Hand & arm motion advice system offers advice according to the way of moving hand & arms and modification method on their way in drawing sketch. We expect high learning effect with these real time advice systems.

Design of an Authoring System Based on a Student Model for Digital Educational Content for Autistic People

Hisashi Ogawa, Noriyuki Matsuda, Hirokazu Miura, Hirokazu Taki, Norihiro Abe, Satoshi Hori

Proceeding of International Conference on Computers in Education 2004     1697 - 1706   2004年12月  [査読有り]

　概要を見る

特殊教育では,学習者ごとの学習能力や生活環境が大きく異なるため,個々の学習者に応じて教材が製作されている.デジタル教育コンテンツは,反復学習に向いている,メディアを使った質の高い教材を製作できる点を活かし,実際に利用されている.しかしながら,製作には,コンピュータの専門技術を要するため,手軽に製作する環境とはなっていない.本論文は,学習者の実態,教え方,学習対象のモデルを元に,教材のカスタマイズを行う技術を提案する.

Design of Semantic Web Application based on Physical State Model of Products

Noriyuki Matsuda, Michiyasu Hiramatsu, Hirokazu Taki, Satoshi Hori, Norihiro Abe (担当区分： 筆頭著者 )

3rd International Semantic Web Conference (ISWC2004) Poster abstracts     37 - 38   2004年11月  [査読有り]

　概要を見る

ネットワークは,文字,映像,画像の転送を行えるが,動きを転送することができない.本稿では,アクチュエータの汎用的な動きを転送し,各ローカル環境における異なるアクチュエータでできるだけ同じ動きを再現するシステムを提案する.対象にコーヒーメーカーを取り上げ,物理状態の記述言語を作成し,工業用ロボットハンドと自動販売機(エミュレーター)において共通の振る舞いを実現できた.

Design and Evaluation of Automated Integration System for a Programming Class

Noriyuki Matsuda, Katsuyuki Harada, Hirokazu Taki (担当区分： 筆頭著者 )

Proceeding of International Conference on Computers in Education     2111 - 2113   2004年11月  [査読有り]

Design of an Automated Record Integration System for a Programming Exercise Class

松田 憲幸 (担当区分： 筆頭著者 )

The 4th IEEE International Conference on Advanced Learning Technologies ( IEEE Computer Society )    862 - 863   2004年09月  [査読有り]

　概要を見る

To reuse an electronic educational material, a teacher has to understand its availability and methodology. This paper proposed the technique of integrating electronic class text, such as HTML/XML, into automated records of activities in a class. Our hypothesis is that an activity has influence on both the automated records and the class text. Currently, we have held evaluation experiment. We designed structured record expression and event rules. Our system integrates a class text into automated records by forward deductive inference.

DOI

Automated Record Integration System For a Class

Noriyuki Matsuda, Hirokazu Taki (担当区分： 筆頭著者 )

Proceedings of the IADIS International Conference (e-Society 2004)     403 - 408   2004年07月  [査読有り]

　概要を見る

教員の指導技術の向上を目的とした授業研修では,授業の活動をビデオ映像に記録し,映像を再生しなら議論を通して指導技術の向上を図る.しかしながら,映像から,個々の学生の具体的な活動を再生することは難しい.本稿では,プログラミング講義を行う教室内の教員,学生の個々の教育・学習活動を記録する手段を述べる.

Advice Recording Method for a Lesson with Computers.

Katsuyuki Harada, Noriyuki Matsuda, Hirokazu Miura, Hirokazu Taki, Satoshi Hori, Norihiro Abe

In: Negoita M.G., Howlett R.J., Jain L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2004. Lecture Notes in Computer Science ( Springer, Berlin, Heidelberg )  3214   181 - 187   2004年  [査読有り]

　概要を見る

In a lesson, a teacher requires to understand immediately the student their errors and give them adequate advice. As teaching training, teachers often visit an expert teacher’s class to observe the teaching and record the lesson by a video camera to analyze teaching skills. Although it is satisfactory to analyze the whole lesson, it takes much time to analyze and to search good advices in the long tape. Then, in this paper, the automatic method of dividing the record of the lesson is proposed so that it may refer to the specific advice directly. We developed a prototype system that records activities in the lesson and constructs a database for sharing among teachers. We confirmed the effectiveness of our system through the experiment.

DOI

Construction of Conscious Model Using Reinforcement Learning.

Masafumi Kozuma, Hirokazu Taki, Noriyuki Matsuda, Hirokazu Miura, Satoshi Hori, Norihiro Abe

In: Negoita M.G., Howlett R.J., Jain L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2004. Lecture Notes in Computer Science ( Springer )  3214   175 - 180   2004年  [査読有り]

　概要を見る

This paper describes the agent system which predicts other agent actions using the reinforcement learning. We have been developing the agent which determines actions being conscious of the effect of action. In the system, the agent not only constructs its self-conscious action model, but also learns the model of other agent actions. We also consider the effective action determination method of agents.

DOI