Kazuhiro Tokunaga

J-GLOBAL         Last updated: Feb 26, 2019 at 18:14
 
Avatar
Name
Kazuhiro Tokunaga
E-mail
tokunagafish-u.ac.jp
Affiliation
Kyushu Institute of Technology
Research funding number
00432956

Research Areas

 
 

Published Papers

 
NAKAMURA Makoto, WATANABE Toshiaki, SHIIGI Tomoo, TOKUNAGA Kazuhiro, OHTA Hiromitsu, MAEDA Toshimichi
J. SOFT   30(1) 509-516   2018
<p>This research intends to improve quality control while maintaining the skill level of distributers of marine products by designing models which ensure accurate non-destructive estimates of the freshness of fish meat (K value) by using fuzzy inf...
中村 誠, 太田 博光, 渡邉 敏晃, 徳永 憲洋, 川口 健太郎, 前田 俊道
人間工学 = The Japanese journal of ergonomics   53(4) 107-115   Aug 2017
鴻上 健一郎, 中村 誠, 太田 博光, 徳永 憲洋, 前田 俊道
水産大学校研究報告   64(1) 29-45   Dec 2015
Experienced puffer fish chefs can quickly distinguish between species and between natural and cultivated fish based on the appearance of dressed puffer fish. This study aims to construct a system of differentiating between puffer fish based on the...
NAKAMURA Makoto, OHTA Hiromitsu, TOKUNAGA Kazuhiro, KOGAMI Kenivhiro
JES Ergonomics   51(0) S166-S167   Jun 2015
NAKAMURA MAKOTO, KOGAMI KEN'ICHIRO, AKETAGAWA MASAKO, OTA HIROMITSU, TOKUNAGA KAZUHIRO
人間工学   50(5) 294-299   Oct 2014

Misc

 
徳永憲洋
電子情報通信学会技術研究報告   118(346(SIS2018 21-36)) 31‐36   Nov 2018
椎木友朗, 徳永憲洋
農業環境工学関連学会合同大会講演要旨集(CD-ROM)   2018 ROMBUNNO.OS2‐8   2018
佐伯千尋, 徳永憲洋, 谷口真市, 中野新太, 太田博光, 中村誠
電子情報通信学会大会講演論文集(CD-ROM)   2017 ROMBUNNO.A‐4‐8   Aug 2017
松山恵也, 松田弦也, 太田博光, 渡邉敏晃, 徳永憲洋, 椎木友朗, 福井良輔
日本機械学会評価・診断に関するシンポジウム講演論文集   16th(0) 60‐64   Nov 2017
眞鍋智史, 徳永憲洋, 太田博光, 中村誠
電気・情報関連学会中国支部連合大会講演論文集(CD-ROM)   69th ROMBUNNO.R18‐14‐11   Oct 2018
渡邉敏晃, 中村誠, 太田博光, 徳永憲洋
日本水産工学会学術講演会講演論文集   2017 192‐193   May 2017
佐伯千尋, 徳永憲洋, 谷口真市, 中野新太, 大田博光, 中村誠
日本水産工学会学術講演会講演論文集   2017 208‐211   May 2017
徳永 憲洋, 佐伯 千尋, 谷口 真市, 中野 新太, 太田 博光, 中村 誠
ファジィシステムシンポジウム講演論文集   34 388-392   Sep 2018
TOKUNAGA KAZUHIRO, SATO FUMIHIKO, MATSUDA SEIGO
電子情報通信学会大会講演論文集(CD-ROM)   2015 ROMBUNNO.D-2-1   Feb 2015
徳永憲洋, 佐伯千尋, 谷口真市, 中野新太, 太田博光, 中村誠
農業環境工学関連学会合同大会講演要旨集(CD-ROM)   2018 ROMBUNNO.OS2‐4   2018
佐伯 千尋, 徳永 憲洋, 太田 博光, 中村 誠
ファジィシステムシンポジウム講演論文集   32 515-520   Aug 2016
徳永憲洋, 佐伯千尋, 谷口真市, 中野新太, 太田博光, 中村誠
ファジィシステムシンポジウム講演論文集(CD-ROM)   34th ROMBUNNO.TD1‐1   2018
NAKAMURA MAKOTO, KOGAMI KEN'ICHIRO, OTA HIROMITSU, TOKUNAGA KAZUHIRO
ファジィシステムシンポジウム講演論文集(CD-ROM)   30th(0) ROMBUNNO.WF1-3-853   2014
In this paper, the models which enable the veriufication of the species by the color of the puffer meat is proposed. A total of 185 fish dressed by the cooks (Migaki) were examined to determine what aspects of the surface color of the fish the coo...
渡邉敏晃, 中村誠, 太田博光, 徳永憲洋
空気調和・冷凍連合講演会講演論文集(CD-ROM)   50th ROMBUNNO.8   Apr 2016
NAKAMURA MAKOTO, KOGAMI KEN'ICHIRO, OTA HIROMITSU, AKETAGAWA MASAKO, TOKUNAGA KAZUHIRO, MAEDA TOSHIMICHI
ファジィシステムシンポジウム講演論文集(CD-ROM)   30th(0) ROMBUNNO.WF1-2-849   2014
This study aims to develop a quality evaluation system by analyzing the skills of experienced puffer cooks from well-established intermediary wholesalers in order to create a model for quality evaluation. A total of 80 natural tiger puffers dresse...
TOKUNAGA KAZUHIRO, SUETAKE NORIAKI
電子情報通信学会技術研究報告   114(370(SIS2014 67-90)) 43-48   Dec 2014
徳永憲洋
電子情報通信学会技術研究報告   115(505(SIS2015 48-72)) 49‐54   Mar 2016
UEDA CHIAKI, SATO YUINA, TOKUNAGA KAZUHIRO, SUETAKE NORIAKI, UCHINO EIJI
電気・情報関連学会中国支部連合大会講演論文集(CD-ROM)   64th 47-48   Oct 2013
Tokunaga Kazuhiro
Proceedings of the Fuzzy System Symposium   31(0) 452-457   2015
This study aims to develop a learning algorithm for increasing a learning speed and stability in a growing self-organizing map. In this presentation, I propose the growing self-organizing map based on a learning theory of a gaussian mixture model....
徳永 憲洋
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   115(505) 49-54   Mar 2016
上田 千晶, 徳永 憲洋, 末竹 規哲, 内野 英治
研究報告オーディオビジュアル複合情報処理(AVM)   2013(2) 1-5   Sep 2013
本報告では,モノクロ画像を自動で着色するためにベクトルメディアンによる色選択に基づいた新しい方法を提案する.提案手法では,モノクロ画像と似た対象物が写った参照カラー画像を用意し,その参照カラー画像の持つ色彩情報を用いてモノクロ画像を着色する.まず参照カラー画像を局所分散の値により 2 つに分け,さらに明度毎に分割する.各グループからベクトルメディアン法により代表色を選択することで,着色パレットを作成する.次にモノクロ画像の局所分散と,明度調整したモノクロ画像の明度を用いて,着色パレットから...
UEDA CHIAKI, SATO YUINA, TOKUNAGA KAZUHIRO, SUETAKE NORIAKI, UCHINO EIJI
電子情報通信学会技術研究報告   113(202(SIS2013 14-26)) 13-18   Sep 2013
本報告では,24 ビットカラーの多値画像を,誤差拡散法と減色処理に基づいて,色数の制限された限定色画像に変換する方法を提案する.提案手法では,様々な減色処理手法とベクトル誤差拡散法を用いて限定色画像を作成する.具体的には,多値画像をベクトル誤差拡散法を用いて減色処理に適した色数まで減色した後,減色処理を行い目的の色数を持つ限定色パレットを作成する.作成されたパレットの色をベクトル誤差拡散法を用いて原画像に割り当てることで限定色画像を生成する.減色処理では従来手法である PA 法とメディアン...
TANAKA HIROKI, TOKUNAGA KAZUHIRO, MISAWA HIDEAKI, SUETAKE NORIAKI, UCHINO EIJI
バイオメディカル・ファジィ・システム学会年次大会講演論文集   25th 88-91   Dec 2012
TOKUNAGA KAZUHIRO, MISAWA HIDEAKI, SUETAKE NORIAKI, UCHINO EIJI
バイオメディカル・ファジィ・システム学会年次大会講演論文集   25th 123-126   Dec 2012
Tokunaga Kazuhiro, Sato Fumihiko, Matsuda Seigo
Proceedings of the IEICE General Conference   2015(1)    Feb 2015
UEDA CHIAKI, TOKUNAGA KAZUHIRO, SUETAKE NORIAKI, UCHINO EIJI
計測自動制御学会中国支部学術講演会論文集   21st 164-165   Nov 2012
KURAMOTO YOHEI, TOKUNAGA KAZUHIRO, SUETAKE NORIAKI, UCHINO EIJI
計測自動制御学会中国支部学術講演会論文集   21st 166-167   Nov 2012
久保坂 史耶, 徳永 憲洋, 末竹 規哲
ファジィシステムシンポジウム講演論文集   28 518-521   Sep 2012
徳永 憲洋, 末竹 規哲
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   114(370) 43-48   Dec 2014
TOKUNAGA Kazuhiro, SUETAKE Noriaki
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   114(370) 43-48   Dec 2014
This work aims to verify a performance of a color quantization using growing self-organizing map. Authors have proposed a stochastically-growing self-organizing map based on a learning algorithm of an evolving self-organizing map (ESOM) proposed b...
TOKUNAGA KAZUHIRO, TANAKA HIROKI, VACHKOV GANCHO, SUETAKE NORIAKI, UCHINO EIJI
バイオメディカル・ファジィ・システム学会年次大会講演論文集   24th 301-304   Oct 2011
階層型k近隣法(HkNN)による冠動脈組織性状判別を高速、高精度で行うため、ニューラルガスを用いた訓練ベクトルの選別法を提案し、有効性を示した。実験はニューラルガスを用いた場合と用いない場合について判別速度と判別精度を比較した。訓練ベクトルの選別は脂質性組織、線維性組織、それ以外のプラーク内組織の3組織で行った。脂質性および線維性組織において、ニューラルガスを用いない場合は分散が大きく、結果にばらつきがあった。ニューラルガスを用いると、分散が小さく結果に安定性があり、さらに脂質性組織での真...
UEDA CHIAKI, TOKUNAGA KAZUHIRO, SUETAKE NORIAKI, UCHINO EIJI
電子情報通信学会技術研究報告   112(78(SIS2012 1-15)) 41-46   Jun 2012
In this report, in order to realize automatic and photorealistic colorization of a monochrome image, a new colorization method is proposed. In this method, firstly, a reference color image including the subjects similar to those of the monochrome ...
UEDA Chiaki, TOKUNAGA Kazuhiro, SUETAKE Noriaki, UCHINO Eiji
電子情報通信学会技術研究報告. SIS, スマートインフォメディアシステム   113(202) 7-11   Sep 2013
In this report, in order to realize automatic colorization of a monochrome image, a new colorization method is proposed. In this method, a reference color image including the subjects similar to those of the monochrome image should be prepared bef...
TOKUNAGA KAZUHIRO, FURUKAWA TETSUO
システム制御情報学会研究発表講演会講演論文集(CD-ROM)   54th(0) ROMBUNNO.W32-8-91   May 2010
We propose the self evolving graph network as the method in which the environmental model is dynamically and real-time built. In our proposal method, node and path represent a symbolic memory of local environment and relationships between memories...
徳永 憲洋
ファジィシステムシンポジウム講演論文集   26 1107-1110   Sep 2010
UEDA Chiaki, SATOH Yuina, TOKUNAGA Kazuhiro, SUETAKE Noriaki, UCHINO Eiji
電子情報通信学会技術研究報告. SIS, スマートインフォメディアシステム   113(202) 13-18   Sep 2013
In this report, we propose a new color image quantization method for color images. In the proposed method, a vector error diffusion method and a quantization method are used. The vector error diffusion method is used for brief color reduction and ...
KAWABATA NOBUYUKI, TOKUNAGA KAZUHIRO, FURUKAWA TETSUO
日本神経回路学会全国大会講演論文集   18th 136-137   Sep 2008
TOKUNAGA KAZUHIRO, KOGA KOJIRO, FURUKAWA TETSUO
電子情報通信学会技術研究報告   109(461(NC2009 87-175)) 125-130   Mar 2010
In recent years, we have proposed a evolving type of modular network called "SEEM". The SEEM has an incremental graph structure in which the nodes (modules) are grown incrementally. The modules and paths represent functions and the similarities be...
KAWABATA NOBUYUKI, TOKUNAGA KAZUHIRO, FURUKAWA TETSUO
電子情報通信学会大会講演論文集   2008 16   Mar 2008
TOKUNAGA KAZUHIRO, MASUOKA TAKANORI, FURUKAWA TETSUO
電子情報通信学会大会講演論文集   2008 20   Mar 2008
FURUKAWA TETSUO, TOKUNAGA KAZUHIRO, TAMUKO HAKARU
電子情報通信学会大会講演論文集   2008 SSS.30-SSS.31   Mar 2008
MORI MASANORI, KAMEI YUTA, GUN'YA KOICHI, OTANI MAKOTO, TOKUNAGA KAZUHIRO, FURUKAWA TETSUO
電子情報通信学会大会講演論文集   2008 19   Mar 2008
川畑 宣之, 徳永 憲洋, 古川 徹生
ファジィシステムシンポジウム講演論文集   25 ROMBUNNO.2B3-03   Jul 2009
TOKUNAGA Kazuhiro, MISAWA Hideaki, SUETAKE Noriaki, UCHINO Eiji
バイオメディカル・ファジィ・システム学会大会講演論文集 : BMFSA   25(25) 123-126   Dec 2012
We propose a technique for tissue characterization using instant features of intravascular ultrasound (IVUS) radiofrequency signals. In the proposed technique, the modular network self-organizing map (mnSOM) is used to classify the instant pattern...
TANAKA Hiroki, TOKUNAGA Kazuhiro, MISAWA Hideaki, SUETAKE Noriaki, UCHINO Eiji
バイオメディカル・ファジィ・システム学会大会講演論文集 : BMFSA   25(25) 88-91   Dec 2012
We propose an algorithm applied to an intravascular ultrasound (IVUS) -based tissue characterization of coronary plaque. In the proposed algorithm, the probability density of each plaque is calculated by Kernel density estimation. The probability ...
UEDA Chiaki, TOKUNAGA Kazuhiro, SUETAKE Noriaki, UCHINO Eiji
電子情報通信学会技術研究報告. SIS, スマートインフォメディアシステム   112(78) 41-46   Jun 2012
OHKUBO Takashi, TSUJI Jun-ichi, TOKUNAGA Kazuhiro, FURUKAWA Tetsuo
IEICE technical report. Neurocomputing   108(480) 381-386   Mar 2009
The purpose of this work is to develop a neural network architecture which enables us to deal with a group of dynamical systems. The architecture, which is refered as Multi-Dynamics Learning Network (MDLN), is expected to satisfy the following thr...
TOKUNAGA Kazuhiro, MISAWA Hideaki, SUETAKE Noriaki, UCHINO Eiji
Proceedings of the Annual Conference of Biomedical Fuzzy Systems Association   25(0) 123-126   2012
We propose a technique for tissue characterization using instant features of intravascular ultrasound (IVUS) radiofrequency signals. In the proposed technique, the modular network self-organizing map (mnSOM) is used to classify the instant pattern...
TANAKA Hiroki, TOKUNAGA Kazuhiro, MISAWA Hideaki, SUETAKE Noriaki, UCHINO Eiji
Proceedings of the Annual Conference of Biomedical Fuzzy Systems Association   25(0) 88-91   2012
We propose an algorithm applied to an intravascular ultrasound (IVUS) -based tissue characterization of coronary plaque. In the proposed algorithm, the probability density of each plaque is calculated by Kernel density estimation. The probability ...
TOKUNAGA Kazuhiro, TANAKA Hiroki, VACHKOV Gancho, SUETAKE Noriaki, UCHINO Eiji
Proceedings of the Annual Conference of Biomedical Fuzzy Systems Association   24(0) 301-304   2011
In this paper, we propose a method to advance the speed and accuracy for tissue classification of Intravascular Ultrasound (IVUS) data using Hierarchical k-Nearest Neighbor (HkNN). In this method, the neural gas is used to decide several represent...
Kubosaka Fumiya, Tokunaga Kazuhiro, Suetake Noriaki, Uchino Eiji, Matsuyama Hideyasu
Proceedings of the Fuzzy System Symposium   28(0) 518-521   2012
Centrosome is a tissue which evenly distributes chromosomes to two cells during cell division. There are usually two centrosomes in a cell, but some cells have more than two. This phenomenon is called centrosome hyperamplification (CH). CH affects...
MASUOKA TAKANORI, TOKUNAGA KAZUHIRO, FURUKAWA TETSUO
電子情報通信学会技術研究報告   107(413(NC2007 87-111)) 91-96   Jan 2008
KAWABATA NOBUYUKI, TOKUNAGA KAZUHIRO, FURUKAWA TETSUO
電子情報通信学会技術研究報告   107(413(NC2007 87-111)) 141-146   Jan 2008
TOKUNAGA Kazuhiro, TANAKA Hiroki, VACHKOV Gancho, SUETAKE Noriaki, UCHINO Eiji
バイオメディカル・ファジィ・システム学会大会講演論文集 : BMFSA   24(24) 301-304   Oct 2011
In this paper, we propose a method to advance the speed and accuracy for tissue classification of Intravascular Ultrasound (IVUS) data using Hierarchical k-Nearest Neighbor (HkNN). In this method, the neural gas is used to decide several represent...
Tokunaga Kazuhiro
Proceedings of the Fuzzy System Symposium   26(0) 253-253   2010
Recently, we have proposed Self-Evolving Modular network (SEEM), in which number of modules is increased depending on input data episodes in self-organizing manner.While SEEM can find the number of modules for a task, it is necessary to preliminar...
HAYASHIDA SEIYA, TOKUNAGA KAZUHIRO, FURUKAWA TETSUO
電子情報通信学会技術研究報告   106(501(NC2006 100-115)) 41-46   Jan 2007
This paper aims to develop a novel style of parallel processing method based on self-organizing map (SOM) with modular network structure (mnSOM). The mnSOM is a generalization of SOM in which all reference vector units are replaced by a set of fun...
Kawabata Nobuyuki, Tokunaga Kazuhiro, Furukawa Tetsuo
Proceedings of the Fuzzy System Symposium   25(0) 111-111   2009
We propose a method to build topological maps from vision sensor information for mobile robots navigations. The method is based on Evolving Self-Organizing Maps (ESOM) proposed by Deng.Nodes and paths represent essential visual information in loca...
KIMOTSUKI KENJI, TOKUNAGA KAZUHIRO, YASUI SHOZO, FURUKAWA TETSUO
電子情報通信学会技術研究報告   103(732(NC2003 135-164)) 35-40   Mar 2004
徳永 憲洋, 古川 徹生
ファジィシステムシンポジウム講演論文集   22 87-90   Sep 2006
Masuoka Takanori, Tokunaga Kazuhiro, Furukawa Tetsuo
Proceedings of the Fuzzy System Symposium   23(0) 677-677   Aug 2007
A robot has to autonomously acquire the environmental map by interaction with its environment to per form the self-localization and the behavior planning in unknown environment. The methods for acquiring the environmental map using the topology pr...
TOKUNAGA KAZUHIRO, FURUKAWA TETSUO, YASUI SHOZO
電子情報通信学会技術研究報告   102(628(NC2002 117-133)) 79-83   Feb 2003
TOKUNAGA KAZUHIRO, FURUKAWA TETSUO
電子情報通信学会技術研究報告   106(102(NC2006 22-37)) 75-80   Jun 2006
We proposed a modular network SOM (mnSOM) some years ago. The mnSOM is an extension and a generalization of the conventional SOM in which each nodal unit is replaced by a module such as a neural network. Therefore, it is expected that the mnSOM ex...
Furukawa Tetsuo, Tokunaga Kazuhiro, Tamukoh Hakaru
Proceedings of the IEICE General Conference   2008(1) "SSS-30"-"SSS-31"   Mar 2008
Mori Masanori, Kamei Yuta, Gunya Koichi, Otani Makoto, Tokunaga Kazuhiro, Furukawa Tetsuo
Proceedings of the IEICE General Conference   2008(1)    Mar 2008
Kawabata Nobuyuki, Tokunaga Kazuhiro, Furukawa Tetsuo
Proceedings of the IEICE General Conference   2008(1)    Mar 2008
Furukawa Tetsuo, Tokunaga Kazuhiro, Tamukoh Hakaru
Proceedings of the IEICE General Conference   2008 "SSS-30"-"SSS-31"   Mar 2008
Furukawa Tetsuo, Tokunaga Kazuhiro, Tamukoh Hakaru
Proceedings of the IEICE General Conference   2008(2) "SSS-30"-"SSS-31"   Mar 2008
Tokunaga Kazuhiro, Masuoka Takanori, Furukawa Tetsuo
Proceedings of the IEICE General Conference   2008(1)    Mar 2008
MORISHITA Kenji, TOKUNAGA Kazuhiro, YASUI Syozo, FURUKAWA Tetsuo
IEICE technical report. Neurocomputing   104(760) 99-104   Mar 2005
A new method proposed in this paper aims to generate a self-organizing map (SOM) of 3D objects by using their 2D projected images. Since it is known that a set of 2D images of a 3D object form various viewpoints forms a 2D manifold, the method nee...
Furukawa Tetsuo, Tokunaga Kazuhiro, Tamukoh Hakaru
Proceedings of the IEICE General Conference   2008(2) "SSS-30"-"SSS-31"   Mar 2008
Furukawa Tetsuo, Tokunaga Kazuhiro, Tamukoh Hakaru
Proceedings of the IEICE General Conference   2008(1) "SSS-30"-"SSS-31"   Mar 2008
Furukawa Tetsuo, Tokunaga Kazuhiro, Tamukoh Hakaru
Proceedings of the IEICE General Conference   2008(2) "SSS-30"-"SSS-31"   Mar 2008
Furukawa Tetsuo, Tokunaga Kazuhiro, Tamukoh Hakaru
Proceedings of the IEICE General Conference   2008(1) "SSS-30"-"SSS-31"   Mar 2008
MASUOKA Takanori, TOKUNAGA Kazuhiro, FURUKAWA Tetsuo
IEICE technical report. Neurocomputing   107(413) 91-96   Jan 2008
In this paper, a method for internal model acquirement of the outer environment is proposed. The proposed method is based on the SOM^2, in which each vector unit of the traditional SOM is replaced by an SOM itself. The SOM^2 is capable of generati...
KAWABATA Nobuyuki, TOKUNAGA Kazuhiro, FURUKAWA Tetsuo
IEICE technical report. Neurocomputing   107(413) 141-146   Jan 2008
In this paper, a novel Modular network called Self-Evolving Modular Network(SEEM) is proposed. The SEEM has the following two functions, (1) New nodal modules are incrementally added to adapt the network self-evolutionary, (2) Links are formed bet...
MORIYAMA Kenichirou, TOKUNAGA Kazuhiro, YASUI Shouzou, FURUKAWA Tetsuo
IEICE technical report. ME and bio cybernetics   104(644) 33-36   Jan 2005
The modular network SOM (mnSOM) is an extension of Kohonen's Self-organizing map (SOM) in which each nodal unit is replaced by a function module instead of a weight vector. By employing autoencoder MLP as the function module, the mnSOM acquires an...
Tetsuo Furukawa, Kazuhiro Tokunaga, Kenji Morishita, Syozo Yasui
Proceedings of the International Joint Conference on Neural Networks   3 1581-1586   Dec 2005
Kohonen's Self-Organizing Map (SOM), which performs topology-preserving transformation from a high-dimensional data vector space to a low-dimensional map space, provides a powerful tool for data analysis, classification and visualization in many a...
S. Kaneko, K. Tokunaga, T. Furukawa
WSOM 2005 - 5th Workshop on Self-Organizing Maps   537-544   Dec 2005
This paper proposes a generalized framework of SOM applicable to more extended data classes rather than vector data. The generalization is realized by adopting the idea of a modular network; thus it is called a modular network SOM (mnSOM), in whic...
K. Tokunaga, T. Furukawa
WSOM 2005 - 5th Workshop on Self-Organizing Maps   637-644   Dec 2005
We propose a method for realizing the nonlinear adaptive subspace SOM (nonlinear ASSOM). The proposed method is a variation of the modular network SOM (mnSOM) constituted by autoassociative neural networks (ANN-mnSOM). The mapping objects of ANN-m...
TOKUNAGA KAZUHIRO, FURUKAWA TETSUO, YASUI SHOZO
電子情報通信学会技術研究報告   103(153(NC2003 12-21)) 31-36   Jun 2003
Generalization of SOM called Modular Network SOM (MNSOM) is presented herein. In it, each unit of the conventional SOM is replaced by a functional module which is a multi-layer neural network. MNSOM learns a group of systems in terms of their inpu...
徳永 憲洋
日本神経回路学会誌   14(2) 157_2-158   2007
Tokunaga Kazuhiro, Furukawa Tetsuo
Proceedings of the Fuzzy System Symposium   22(0) 23-23   2006
A modular network SOM (mnSOM) proposed by authors is an extension and a generalization of a conventional SOM in which each nodal unit is replaced by a module such as a neural network. The mnSOM has thelearning algorithm in which both the supervise...
KIMOTSUKI Kenji, TOKUNAGA Kazuhiro, YASUI Syozo, FURUKAWA Tetsuo
IEICE technical report. Neurocomputing   103(732) 35-40   Mar 2004
Generalization of SOM called Modular Network SOM (MNSOM) is presented herein. In it, each unit of the conventional SOM is replaced by a functional module which is a multi-layer neural network. MNSOM learns a group of systems in terms of their inpu...
TOKUNAGA Kazuhiro, FURUKAWA Tetsuo, YASUI Syozo
IEICE technical report. Neurocomputing   102(628) 79-83   Jan 2003
This paper proposes Modular Netowork SOM (MNSOM) , in which the neuronal units of Self-Organizing Maps (SOM) are replaced by a set of Multi-Layer Perceptrons (MLP) . In order to show the effectiveness of MNSOM, MNSOM was made for a family of cubic...

Research Grants & Projects

 
Ministry of Education, Culture, Sports, Science and Technology: Grants-in-Aid for Scientific Research(若手研究(B))
Project Year: 2011 - 2012    Investigator(s): Kazhiro TOKUNAGA
In this study, a learning algorithm of a growing neural network was established theoretically from the view point of a generating model. Thus, the proposal method has robustness to following problems comparing with conventional growing neural netw...