ICHIMURA Takumi

J-GLOBAL         Last updated: Sep 27, 2019 at 17:23
 
Avatar
Name
ICHIMURA Takumi
Affiliation
Prefectural University of Hiroshima
Research funding number
10295842
ORCID ID
0000-0003-0518-0269

Research Areas

 
 

Academic & Professional Experience

 
Apr 2010
 - 
Mar 2014
Prefectural University of Hiroshima
 

Education

 
 
   
 
Graduate School, Division of Engineering, Toin University of Yokohama
 
 
   
 
Faculty of Engineering, Toin University of Yokohama
 

Awards & Honors

 
Sep 2017
Best Paper Award, FAN2017
Winner: KAMADA Shin, ICHIMURA Takumi
 
Mar 2017
MHSAX-based Time Series Classification using Local Sequence Alignment Technique, Best Paper Presentation Award, IMECS2017
Winner: TAMURA Keiichi, ICHIMURA Takumi
 
Dec 2016
Contribution Award
 
Nov 2016
A Recommendation System of Grants to Acquire External Funds, Best Presentation Award, IEEE SMC Hiroshima Chapter
Winner: KAMADA shin, ICHIMURA Takumi
 
Oct 2016
An adaptive learning method of Restricted Boltzmann Machine by neuron generation and annihilation algorithm, Best Student Paper Award Finalist, IEEE SMC Society
Winner: Shin Kamada, ICHIMURA Takumi
 

Published Papers

 
Knowledge Extraction of Adaptive Structural Learning of Deep Belief Network for Medical Examination Data
Shin Kamada, Takumi Ichimura, and Toshihide Harada
International Journal of Semantic Computing      2019   [Refereed]
Keiichi Tamura; Takumi Ichimura
International Journal of Computational Intelligence Studies   7(3-4) 192-213   Nov 2018   [Refereed]
Time series classification is one of the most active research topics in time series data mining, because it covers a broad range of applications in many different domains. Representation for time series is a technique that converts time series to ...
Shin Kamada, Takumi Ichimura and Hidetoshi Harada
Adaptive Structural Learning of Deep Belief Network for Medical Examination Data and Its Knowledge Extraction by using C4.5   33-40   Sep 2018   [Refereed]
Deep Learning has a hierarchical network architecture to represent the complicated feature of input patterns. The adaptive structural learning method of Deep Belief Network (DBN) has been developed. The method can discover an optimal number of hid...
54(8) 628-639   Aug 2018   [Refereed]
抄録
Deep Belief Network (DBN), which is well known to be a kind of Deep Learning methods, has a deep network architecture that can represent multiple features of input patterns hierarchically. Each layer employs a pre-trained Restricted Boltzmann M...
Shin Kamada, Takumi Ichimura, Akira Hara, Kenneth J. Mackin
Neural Computing and Applications   1-15   Jul 2018   [Refereed]
Recently, deep learning is receiving renewed attention in the field of artificial intelligence. Deep belief network (DBN) has a deep network architecture that can represent multiple features of input patterns hierarchically, using pre-trained rest...
Shin Kamada and Takumi Ichimura,
International Journal Computational Intelligence Studies   7(3-4) 169-191   Nov 2018   [Refereed]
Recently, deep learning has been applied in the techniques of artificial
intelligence. Especially, their new architectures performed good results in the field
of image recognition. However, the method is required to train not only image
data, but ...
Keiichi Tamura, Takumi Ichimura
Proc. of The 2017 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2017)   2041-2048   Dec 2017   [Refereed]
Clustering of time series is one of the best-known grand challenges in time series analysis because of its application potentialities and difficulty. It is like data clustering and the task of partitioning time series into several groups based on ...
Keiichi Tamura, Takumi Ichimura
Proc. of the International Multi Conference of Engineers and Computer Scientists 2017 (IMECS2017)   1 286-291   Mar 2017   [Refereed]
Takumi Ichimura, Takuya Uemoto, and Shin Kamada
, IAENG Transactions on Engineering Sciences   54-67   2017   [Refereed]
Recently, social collaboration that helps more people or groups interact and share information to reach their common goal has been receiving a lot of attention. In the process of developing software, the social collaboration is required because th...
Keiichi Tamura,Takumi Ichimura
IAENG International Journal of Computer Science   44(4) 462-470   2017   [Refereed]
Time series classification is the task of predicting the class label of an unclassified time series. In the era of
big data, time series classification is one of the best-known grand challenges because of its many fields of application and difficu...
Shin Kamada,Takumi Ichimura
2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017, Banff, AB, Canada, October 5-8, 2017   825-830   2017   [Refereed]
Recently, the market on deep learning including not only software but also hardware is developing rapidly. Big data is collected through IoT devices and the industry world will analyze them to improve their manufacturing process. Deep Learning has...
Takumi Ichimura,Shin Kamada
2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, AK, USA, May 14-19, 2017   2346-2353   2017   [Refereed]
Deep Learning has the hierarchical network architecture to represent the complicated features of input patterns. Such architecture is well known to represent higher learning capability compared with some conventional models if the best set of para...
Keiichi Tamura,Takumi Ichimura
10th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2017, Hiroshima, Japan, November 11-12, 2017   135-140   2017   [Refereed]
Time series classification is the most active research topics in time series data mining, because they cover a broad range of applications in many different domains. There are three important things that we need to consider in time series classifi...
Yoshitaka Fujii,Takumi Ichimura
10th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2017, Hiroshima, Japan, November 11-12, 2017   103-108   2017   [Refereed]
Recently, Deep Learning models have come to be widely used for many real problems. Their results showed high classification capabilities. However, we must decide some parameters while searching a Deep Learning architecture with an optimal structur...
Shin Kamada,Takumi Ichimura
10th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2017, Hiroshima, Japan, November 11-12, 2017   97-102   2017   [Refereed]
Shin Kamada,Takumi Ichimura
International Journal Computational Intelligence Studies   6(4) 333-348   2017   [Refereed]
We have proposed an adaptive structure learning of deep belief network (DBN) that can determine the suitable number of hidden layers and hidden neurons of restricted Boltzmann machines (RBMs). The method shows high classification performance to th...
Takumi Ichimura,Takuya Uemoto,Shin Kamada
International Journal Computational Intelligence Studies   6(4) 270-287   2017   [Refereed]
We have already developed the recommendation system of sightseeing information on SNS by using smartphone based user participatory sensing system. Our smartphone application can collect tourist subjective data which includes jpeg files with GPS, g...
Takumi Ichimura, Takuya Uemoto, Shin Kamada
Proc. of the International Multi Conference of Engineers and Computer Scientists 2016(IMECS2016)   1 46-51   Mar 2016   [Refereed]
Recently, social collaboration that helps more people or groups interact and share information to reach their common goal has been receiving a lot of attention. In the process of developing software, the social collaboration is required because th...
Shin Kamada, Takumi Ichimura
Proc. of 2016 IEEE Region 10 Conference (TENCON2016)   2971-2974   2016   [Refereed]
Deep Belief Network (DBN) has a deep architecture that represents multiple features of input patterns hierarchically with the pre-trained Restricted Boltzmann Machines (RBM). A traditional RBM or DBN model cannot change its network structure durin...
Keiichi Tamura,Tatsuhiro Sakai,Takumi Ichimura
2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016, Budapest, Hungary, October 9-12, 2016   2419-2424   2016   [Refereed]
Time series classification is one of the most well-known grand challenges in many different application domains. Time series classification is the task of assigning a discrete class label to an unclassified time series. Three important key points ...
Shin Kamada,Takumi Ichimura
2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016, Budapest, Hungary, October 9-12, 2016   1273-1278   2016   [Refereed]
Restricted Boltzmann Machine (RBM) is a generative stochastic energy-based model of artificial neural network for unsupervised learning. Recently, RBM is well known to be a pre-training method of Deep Learning. In addition to visible and hidden ne...
Shin Kamada,Takumi Ichimura
Neural Information Processing - 23rd International Conference, ICONIP 2016, Kyoto, Japan, October 16-21, 2016, Proceedings, Part IV   372-380   2016   [Refereed]
Restricted Boltzmann Machine (RBM) is a generative stochastic energy-based model of artificial neural network for unsupervised learning. The adaptive learning method that can discover the optimal number of hidden neurons according to the input spa...
Shin Kamada,Takumi Ichimura,Takanobu Watanabe
9th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2016, Hiroshima, Japan, November 5, 2016   125-130   2016   [Refereed]
The recommendation system of the competitive grants to university researchers by using the Grants-in-Aid for Scientific Research (KAKEN) keywords has been developed. The system can determine the recommendation order of researchers to each grant by...
Shin Kamada,Takumi Ichimura
9th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2016, Hiroshima, Japan, November 5, 2016   119-124   2016   [Refereed]
We developed an adaptive structure learning method of Restricted Boltzmann Machine (RBM) which can generate/annihilate neurons by self-organizing learning method according to input patterns. Moreover, the adaptive Deep Belief Network (DBN) in the ...
Takumi Ichimura,Takuya Uemoto,Shin Kamada
9th IEEE International Workshop on Computational Intelligence and Applications, IWCIA 2016, Hiroshima, Japan, November 5, 2016   45-50   2016   [Refereed]
We have already developed the recommendation system of sightseeing information on SNS by using smartphone based user participatory sensing system. The system can post the attractive information for tourists to the specified Facebook page by our de...
Shin Kamada,Takumi Ichimura
2015 IEEE International Conference on Systems, Man, and Cybernetics, Kowloon Tong, Hong Kong, October 9-12, 2015   2660-2665   2015   [Refereed]
Recently, a high technique of image processing is required to extract the image features in real time. In our research, the tourist subject data are collected from the Mobile Phone based Participatory Sensing (MPPS) system. Each record consists of...
Takumi Ichimura,Takuya Uemoto
IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015, Hiroshima, Japan, November 6-7, 2015   149-153   2015   [Refereed]
The social community in open source software developers has a complex network structure. The network structure represents the relations between the project and the engineer in the software developer's community. A project forms some teams which co...
Shin Kamada,Takumi Ichimura,Takanobu Watanabe
IEEE 8th International Workshop on Computational Intelligence and Applications, IWCIA 2015, Hiroshima, Japan, November 6-7, 2015   143-148   2015   [Refereed]
The grant for the research gives the researcher the important opportunity to make fruitful research results. Recently, the notification of the government grants and some Foundation grants in the various fields informs the researchers through Inter...
Takumi Ichimura and Shin Kamada
Intl. J. Biomedical Soft Computing and Human Sciences   19(2) 7-18   2014   [Refereed]
The Coronary Heart Disease Database (CHD_DB) is based on actual measurements of
the Framingham Heart Study - one of the most famous prospective studies of cardiovascular disease.
The CHD_DB includes more than 6,500 records indicating the developme...
Takumi Ichimura, Kousuke Tanabe, and Toshiyuki Yamashita
Proc. of IEEE 7th International Workshop on Computational Intelligence and Applications (IWCIA2014)   71-76   2014   [Refereed]
Mental State Transition Network (MSTN) is a basic concept of approximating to human psychological and mental responses. A stimulus calculated by Emotion Generating Calculations (EGC) method can cause the transition of mood from an emotional state ...
Takumi Ichimura and Issei Tachibana
Proc. of IEEE 7th International Workshop on Computational Intelligence and Applications (IWCIA2014)   9-14   2014   [Refereed]
An emotion orientated intelligent interface consists of Emotion Generating Calculations (EGC) and Mental State Transition Network (MSTN). We have developed the Android EGC application software which the agent works to evaluate the feelings in the ...
Ichimura T, Uemoto T, Hara A, Mackin KJ
SpringerPlus   3 712   2014   [Refereed]
Army ants perform the altruism behavior that an ant sacrifices its own well-being for the benefit of another ants. They build bridges using their own bodies along the path from a food to the nest. We developed the army ant inspired social evolutio...
Kamada S, Ichimura T, Shigeyasu T, Takemoto Y
SpringerPlus   3 761   2014   [Refereed]
Near Field Communication (NFC) standard covers communication protocols and data exchange formats. NFC technology is one of radio-frequency identification (RFID) standards. In Japan, Felica card is a popular way to identify the unique ID. We develo...
Takumi Ichimura,Takuya Uemoto,Akira Hara
2014 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2014, San Diego, CA, USA, October 5-8, 2014   170-175   2014   [Refereed]
Army ants perform the altruism that an ant sacrifices its own well-being for the benefit of another ants. Army ants build bridges using their own bodies along the path from a food to the nest. We developed the army ant inspired social evolutionary...
Takumi Ichimura and Issei Tachibana
Proc. of IEEE 6th International Workshop on Computational Intelligence and Applications (IWCIA2013)   15-20   2013   [Refereed]
We developed an Android Smartophone application software for tourist information system. Especially, the agent system recommends the sightseeing spot and local hospitality corresponding to the current feelings. The system such as concierge can est...
Takumi Ichimura,Shin Kamada
2013 IEEE International Conference on Systems, Man, and Cybernetics, Manchester, SMC 2013, United Kingdom, October 13-16, 2013   2085-2090   2013   [Refereed]
Mobile Phone based Participatory Sensing (MPPS) system involves a community of users sending personal information and participating in autonomous sensing through their mobile phones. Sensed data can also be obtained from external sensing devices t...
Keiichi Tamura,Takumi Ichimura
2013 IEEE International Conference on Systems, Man, and Cybernetics, Manchester, SMC 2013, United Kingdom, October 13-16, 2013   2079-2084   2013   [Refereed]
Nowadays, with the increasing attention being paid to social media, a huge number of georeferenced documents, which include location information, are posted on social media sites. People transmit and collect information over the Internet through t...
Takashi Hasuike,Takumi Ichimura
Journal of Intelligent and Fuzzy Systems   24(2) 251-259   2013   [Refereed]
This paper proposes an approach to analyze the tourism information and data derived from the Web, particularly seat availability data of bullet trains in Japan, and to discover some useful knowledge for the tourism. For the fast development of inf...
Takumi Ichimura and Shin Kamada
2013 IEEE 6th International Workshop on Computational Intelligence and Applications (IWCIA2013)   191-196   2013   [Refereed]
Near Field Communication (NFC) standards cover communications protocols and data exchange formats. They are based on existing radio-frequency identification (RFID) standards. In Japan, Felica card is a popular way to identify the unique ID. Recent...
Tetsuya Shigeyasu and Takumi Ichimura
2013 IEEE 6th International Workshop on Computational Intelligence and Applications (IWCIA2013)   185-190   2013   [Refereed]
For realizing convincing daily shopping, collecting useful market information is very important. Generally, useful market information for shopper relies heavily on time and place in addition to the person's interest. Then, we have considered a new...
Takumi Ichimura and Daisuke Igaue,
2013 IEEE 6th International Workshop on Computational Intelligence and Applications (IWCIA2013)   125-130   2013   [Refereed]
Hierarchical Modular Reinforcement Learning (HMRL), consists of 2 layered learning where Profit Sharing works to plan a prey position in the higher layer and Q-learning method trains the state-actions to the target in the lower layer. In this pape...
Takumi Ichimura and Kosuke Tanabe
2013 IEEE 6th International Workshop on Computational Intelligence and Applications (IWCIA2013)   21-26   2013   [Refereed]
Emotion Generating Calculations (EGC) method based on the Emotion Eliciting Condition Theory can decide whether an event arouses pleasure or not and quantify the degree under the event. An event in the form of Case Frame representation is classifi...
Takumi Ichimura, Kazuya Mera
International Journal Computational Intelligence Studies   2(1) 26-51   2013   [Refereed]
Mental state transition network which consists of mental states connected to one another is a basic concept of approximating human psychological and mental responses. It can represent transition from an emotional state to another with stimulus cal...
Takumi Ichimura, Takashi Yamaguchi, and Kenneth James Mackin
Handbook on Reasoning-based Intelligent System   603-632   2013   [Refereed]
This chapter models the conceptual process of the classification of data for reasoning by using Tree Structure SOM and Lattice Structure SOM. We propose a new variant of structure growing SOM that puts appropriate neurons in the region on the map ...
Takumi Ichimura, Shin Kamada and Kosuke Kato
Proc. of 4th International Conference on Intelligent Decision Technologies (KES IDT 2012)   225-235   2012   [Refereed]
A self organizing map (SOM) is trained using unsupervised learning to produce a two-dimensional discretized representation of input space of the training cases. Growing Hierarchical SOM is an architecture which grows both in a hierarchical way rep...
Takumi Ichimura and Shin Kamada
2012 IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2012)   3(2) 110-115   2012   [Refereed]
Mobile Phone based Participatory Sensing (MPPS) systems involve a community of users sending personal information and participating in autonomous sensing through their mobile phones. Sensed data can also be obtained from external sensing devices t...
Takumi Ichimura, Kosuke Tanabe, and , Issei Tachibana
Proc. of The 6th International conference on Soft Computing and Intelligent Systems and The 13th International Symposium on Advanced Intelligent Systems(SCIS-ISIS 2012)   1578-1583   2012   [Refereed]
Mental State Transition Network which consists of mental states connected to each other is a basic concept of approximating to human psychological and mental responses. It can represent transition from an emotional state to other one with stimulus...
Takumi Ichimura and Yoshiaki Douzono
Proc. of The 6th International conference on Soft Computing and Intelligent Systems and The 13th International Symposium on Advanced Intelligent Systems(SCIS-ISIS 2012)   1357-1362   2012   [Refereed]
Army ants perform the altruism, in which an ant sacrifices its own well-being for the benefit of another ants. Army ants build bridges using their own bodies along the path from a food to the nest. We developed the army ant inspired social evoluti...
Takumi Ichimura and Shin Kamada
Proc. of the 6th International conference on Soft Computing and Intelligent Systems and The 13th International Symposium on Advanced Intelligent Systems(SCIS-ISIS 2012)   1351-1356   2012   [Refereed]
The clonal selection principle explains the basic features of an adaptive immune response to a antigenic stimulus. It established the idea that only those cells that recognize the antigens are selected to proliferate and differentiate. This paper ...
Akira Hara, Haruko Tanaka, Takumi Ichimura, and Tetsuyuki Takahama
Intl. J. Knowledge and Web Intelligence   3(2) 180-201   2012   [Refereed]
Rule extraction from database by soft computing methods is important for knowledge acquisition. For example, knowledge from the web pages can be useful for information retrieval. When genetic programming (GP) is applied to rule extraction from a d...

Misc

 
Takumi Ichimura,Takashi Yamaguchi
CoRR   abs/1804.02620    2018   [Refereed]
Takumi Ichimura,Issei Tachibana
CoRR   abs/1804.02657    2018   [Refereed]
Takumi Ichimura,Shin Kamada
CoRR   abs/1804.02628    2018   [Refereed]
Takumi Ichimura,Shin Kamada
CoRR   abs/1804.02677    2018   [Refereed]
Takumi Ichimura,Kousuke Tanabe,Toshiyuki Yamashita
CoRR   abs/1804.02813    2018   [Refereed]
Takumi Ichimura,Takuya Uemoto
CoRR   abs/1804.02822    2018   [Refereed]
Shin Kamada,Takumi Ichimura
CoRR   abs/1804.02816    2018   [Refereed]
Shin Kamada,Takumi Ichimura,Takanobu Watanabe
CoRR   abs/1804.03137    2018   [Refereed]
Takumi Ichimura,Kousuke Tanabe,Issei Tachibana
CoRR   abs/1805.00307    2018   [Refereed]
Takumi Ichimura,Kousuke Tanabe
CoRR   abs/1804.03994    2018   [Refereed]
Takumi Ichimura,Issei Tachibana
CoRR   abs/1804.04946    2018   [Refereed]
高野敏明, 市村匠, 加納政芳, 越野亮
知能と情報   25(4) 111-118   Aug 2013
市村匠
オペレーションズ・リサーチ   58(5) 275-280   May 2013
ICHIMURA Takumi
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics   23(4) 620-628   Aug 2011
ICHIMURA Takumi, MERA Kazuya
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics   23(3) 287-293   Jun 2011
ICHIMURA Takumi, KOGURE Yuichi
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics   23(3) 320-327   Jun 2011
Memoirs of Tokyo Metropolitan Institute of Technology   16 11-16   2002
Memoirs of Tokyo Metropolitan Institute of Technology   16 1-9   2002
Reasoning and learning Method for Fuzzy Rules Using Structure Level Adaptation(共著)
Proc. of 1993 Intl. Fuzzy Systems and Intelligent Controls Conf.   213-222   1993
Reasoning and learning Method for Fuzzy Rules Using Neural Networks with Adaptive Structured Genetic Algorithm共著
Proc. of IEEE Intl. Conf. on SMC   (4) 3269-3274   1995
A GA Search with Evaluation Method Using Royal Road Function and Its Application to TSPs共著
Methodologies for the Conception, Resign and Application of Soft Computing   (2) 825-828   1998
Synthesis of Reflective Neural Networks with Adaptive Module Structure共著
Proc. of IEEE Intl. Conf. on Neural Networks   Special(Session) 106-111   1996
Knowledge Based Approuch to Structure Level Adaptation of Neural Networks -Modeling of Occurence of Hyper tension-共著
Proc. of IEEE Intl. Conf on SMC   1 548-553   1997
Analyses of College Students' Concept by Fuzzy Structural Modeling (FSM) Method with Planar Lattice Neural Networks共著
Proc. of Intl. Conf. on IEEE SMC   (3) 298-303   1999
Adaptive evolutional learning method of Neural Networks using Genetic Algorithms in dynamic environments(共著)
Proc. of 4th Intl. Conf. on KES2000   2 742-745   2000
Fuzzy reasoning model of facial selection and its applications(共著)
Proc. of 4th Intl. Conf. on KES2000   2 860-863   2000

Conference Activities & Talks

 
Prediction of Seasonal Changes from Tourism Tweets by using Adaptive Structural Learning of Recurrent Deep Belief Network
Shin Kamada, Takumi Ichimura
20th Annuak Meeting of Self-Organizing Maps   8 Mar 2019   

Research Grants & Projects

 
Synthesis of Emotion oriented computer mteraction system
Extraction Method of Predicate Logic type Knowledge with Neural Networks of Structural Level Adaptation
Analytical system of health service needs among healthy elderly by using internet