※苗字と名前の間にスペースをあけ、入力してください

YAMADA Kazuaki

Faculty
Department of Mechanical Engineering
Research Institute of Industrial Technology
Course of Advanced Mechatronics Systems
PositionAssociate Professor
Mail
HomepageURL
Birthday
Last Updated :2017/06/27

Researcher Profile and Settings

Association Memberships

  • THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE
  • INFORMATION PROCESSING SOCIETY OF JAPAN
  • THE ROBOTICS SOCIETY OF JAPAN

Academic & Professional Experience

  •   2015 04  - 現在, Toyo University, Department of Mechanical Engineering, Associate Professor
  •   2009 04  - 2015 03 , Toyo University, Department of Mechanical Engineering, Assistant Professor

Research Activities

Research Areas

  • Informatics, Intelligent informatics
  • Informatics, Web informatics, Service informatics
  • Social/Safety system science, Social systems engineering/Safety system

Published Papers

  • Cooperative Behavior Acquisition of Autonomous Arm Robots through Reinforcement Learning, YAMADA Kazuaki, OHKURA Kazuhiro, UEDA Kanji, Transactions of the Society of Instrument and Control Engineers, 計測自動制御学会論文集, 39, (3) 266 - 275, 03
  • Reinforcement Learning with Autonomous Segmentation for Continuous State and Action Spaces, YAMADA Kazuaki, OHKURA Kazuhiro, UEDA Kanji, Transactions of the Institute of Systems, Control and Information Engineers, システム制御情報学会論文誌, 15, (9) 477 - 485, 09
  • Behavior Acquisition of Autonomous Mobile Robots Using Instance-Based Classifier Generator, NAKAMURA Yoichiro, KUROYAMA Kazuhiro, YAMADA Kazuaki, OHKURA Kazuhiro, UEDA Kanji, Journal of the Robotics Society of Japan, 日本ロボット学会誌, 17, (3) 371 - 379, 04

Conference Activities & Talks

  • Value estimation method of products / services using wisdom of crowd, Kazuaki Yamada, CIRP International Computation in Manufacturing Engineering (ICME 2016),   2016 07 20
  • A Study of Learning Process for Learning Predictive Control System - Application to Ball Catch Problem -, Toru Aizawa, Kazuaki Yamada, 2016 JSME Conference on Robotics and Mechatronics (ROBOMECH2016),   2016 06 09
  • Particle Filter using Ensemble Average - Relationship Between The Number of Particle Sets and Estimation Accuracy -, Kazuaki Yamada, SICE 7th Symposium on Decentralized Autonomous Systems,   2016 01 22
  • Specialization in Swarm Robotics Using a Response Threshold Model, Kazuaki Yamada, The First International Symposium on Swarm Behavior and Bio-Inspired Robotics (Swarm 2015), pp.316-321,   2015 10 29
  • Estimation of Product / Service Evaluations on Information Reputation Sites - An Approach based on Particle Filter and Smoothing -, Azusa Takahashi, Kazuaki Yamada, Kumiyo Nakakoji, Yasuhiro Yamamoto, The 29th Annual Conference of the Japanese Society for Artificial Intelligence, 2015,   2015 06 01
  • Particle Filter using An Ensemble Learning, Kazuaki Yamada, The 29th Annual Conference of the Japanese Society for Artificial Intelligence, 2015,   2015 05 31
  • An Interaction Pattern Library for Reputation Information Sites, Shota Kodama, Azusa Takahashi, Kazuaki Yamada, Kumiyo Nakakoji, Yasuhiro Yamamoto, The 29th Annual Conference of the Japanese Society for Artificial Intelligence, 2015,   2015 05 30
  • A Specialization Approach Using A Response Threshold Model for Multi-Robot Systems, K. Yamada, Y. Yamazaki,   2015 05 19
  • A Long Term Prediction System Using Recurrent RBF Networks - The improvement of Learning Performance by Parameter Adjustment -, T. Aizawa, K. Yamada, T. Goto,   2015 05 19
  • A Particle Filter Approach for Reputation Information Systems - Performance Evaluations by A Multi-Agent Simulation -, Kazuaki Yamada, 2014 IEEE/SICE International Symposium on System Integration,   2014 12 13 , IEEE/SICE
  • A Long Term Prediction System Using Recurrent RBF Networks - Improvement of Learning Speed Using BPTT -, Kazuaki Yamada, The 24th Fuzzy, Artificial Intelligence, Neural Networks and Computational Intelligence,   2014 09 18
  • Estimating Product / Service Value On Reputation Information Sites -Application of Particle Filter-, Kazuaki Yamada, The 24th Fuzzy, Artificial Intelligence, Neural Networks and Computational Intelligence,   2014 09 18
  • Content Value Estimations using Reputation Information, The Robotics and Mechatronics Conference 2015,   2014 05 27
  • A Long Term Prediction System using Recurrent RBF Networks, The Robotics and Mechatronics Conference 2015,   2014 05 26
  • Long-Term State Prediction of A Controlled Object using RRBFN, The Confference of Information, Intelligence and Precision Equipment 2014,   2014 03 18
  • A Predictive Control System using RRBFN and Fuzzy Rule, Kazuaki Yamada, The 26th Decentralized Autonomous Systems Symposium,   2014 01 23
  • Rule Propagation Approaches Between Agents for Multi-Agent Reinforcement Learning, SSI2013,   2013 12 18
  • Rule Propagation Approaches Between Agents for Multi-Agent Reinforcement Learning, SSI2013,   2013 11 18
  • Acquisition of Conflict Avoidance Behaviors in Multi-Agent Systems - An Approach by Replication of Policies -, Robomech2013,   2013 05 24
  • Prediction Control System using RNN and Fuzzy Rules - An Adaptation to The Fly Ball Catch Problem -, Robomech2013,   2013 05 23
  • Acquisition of Conflict Avoidance Behaviors by Agents Having Different Preference, SYS48,   2013 03 06
  • Building Maps based on Landmarks for Autonomous Robots, SI2012,   2012 12 18
  • Reliability-based Reinforcement Learning Approaches for Multi-Agent Systems -Relationship between Agents’ Identification and Learning Performance-, SI2012,   2012 12 18
  • redictive Control Systems using RNN and Fuzzy, SI2012,   2012 12 18
  • Neural Network Reinforcement Learning - Extension to Multi-agent Environment -, SI2012,   2012 12 18
  • Reinforcement Learning Approaches for Dispersion Games, Kazuaki Yamada, IEEE/SICE International Symposium on System Integration (SII2012),   2012 12 16 , IEEE/SICE
  • Mechanism Design for Knowledge Share Community, Web Intelligence and Interaction,   2012 12 15
  • Reliability-Based Reinforcement Learning for Multi-Agent Systems, Robomec2012,   2012 05 28
  • Predictive Control Systems using Recurrent Neural Networks, Robomech2012,   2012 05 28
  • Neural Network Reinforcement Learning for Different-Species Sensor Integration, Robomec2012,   2012 05 28
  • Reliability-based Q-learning Approaches for Multi-Agent Systems, SYS46,   2012 03 08
  • An Action Value Function Approximation using Neural Networks and CMAC for Q-learning, SYS46,   2012 03 08
  • Reinforcement Learning Approaches for Acquiring Conflict Avoidance Behaviors in Multi-Agent Systems, Kazuaki Yamada, Satoru Takano, Satomi Watanabe, 2011 IEEE/SICE International Symposium on System Integration,   2011 12 20
  • Reinforcement Learning using Sigmoid Networks and Griddy-Gibbs Sampler for Mobile Robots,   2010 12 10
  • Setting Methods of Network Parameters for Reinforcement Learning Equipped with Artificial Neural Networks, The 14th Asia Pacific Symposium on Intelligent and Evolutionary Systems, 2010(IES2010),   2010 11 20
  • Visualization of Development Process in Online Community, YAMADA Kazuaki, Technical report of IEICE. KBSE,   2007 01 15 , This paper proposes the visualization method of histories of online community activities, which was recorded for long time period in order to understand how the relationships among online community members alter with time. In order to create the new internet services and support to organize open source software development communities, it is important to understand how the community members take advantage of the internet, what interests members have had and how members construct the relationship among them and other members. The goal of our research is to model the transition processes of m...
  • Sound Attributes and the Ease of Problem Solving in Auditory Interaction Design, JO Kazuhiro, YAMADA Kazuaki, NAKAKOJI Kumiyo,   2005 11 17 , We have conducted several experiments using auditory representations of the Tower of Hanoi problem to explore how sound attributes affect the understanding, rememberance, and comparisons of auditory expressions in problem solving. This paper reports some of our recent findings from the experiments, and discusses auditory interaction design guidelines.
  • 2A1-S-068 Extracting The Transition Patterns of The Internet User Interest Through Web Access Log(Evolution and Learning for Robotics 4,Mega-Integration in Robotics and Mechatronics to Assist Our Daily Lives), Yamada Kazuaki, Nakakoji Kumiyo, Ueda Kanji,   2005 06 09
  • Decision-making Model Based on User Information for Multi-agent Simulation, Yamada K, Ohkura K, Ueda K,   2004 06 18
  • Summarizations and Representations of Interaction Histories, Shirai Yoshinari, Nakakoji Kumiyo, Yamada Kazuaki,   2004 02 06 , The goal of our research is to develop an interaction design framework for the use of interaction histories of objects. Ubiquitous computing enables each of a variety of objects (including humans) to keep track of its/his/her interactions with other objects over a very long period of time. Little research has been done in support of how to design representations and operations to use such interaction histories of a large number of heterogeneous objects. This paper focuses on summarization and browsing techniques for interaction histories. We present a taxonomy for interaction history browsi...
  • Designing and Assessing Educational Interface for Mobile-based Learning, Morita Masayasu, Yamada Kazuaki,   2003 05 16 , The latest breakthrough in the cellular phone technology had opened the door to new learning possibility in Japan. Today, about 73 million mobile phones are subscribed and about 3/4 of those mobile phones are capable of browsing mobile internet in Japan. The paper explains a design process of mobile-based learning (MBL) system called 'Pocket Eijiro' and its assessment results.
  • Input-output Model Evaluation of A Reinforcement Learning Agent through An Information Criterion, Yamada K., Ohkura K., Ueda K.,   2003
  • Acquisition of Cooperative Behavior for Lifting up of Object by Multi-Armrobot, KOJIMA Fumihiro, YAMADA Kazuaki, OHKURA Kazuhiro, UEDA Kanji,   2002 01 25
  • Reinforcement Learning Control of Autonomous Arm Robots, Yamada K., Ohkura K., Ueda K.,   2002
  • 2P1-L5 Segmentation of the State Space based on Bayesian Discrimination for Reinforcement Learning, Yamada K., Ookura K., Ueda K.,   2001 06 08

Awards & Honors

  •   2014 09 , The 24th Fuzzy, Artificial Intelligence, Neural Networks and Computational Intelligence, Best Paper Award, Estimating Product / Service Value On Reputation Information Sites