■Faculty | Department of Electrical and Communication Engineering / Graduate School of Industory |

■Position | Associate Professor |

■Degree | |

■Commentator Guide | https://www.kindai.ac.jp/meikan/454-shiratsuchi-hiroshi.html |

■URL | |

Last Updated :2019/07/19

- - 1999 , Kyushu Institute of Technology, Graduate School, Division of Information Engineering
- - 1994 , Kinki University, Faculty of Engineering

- Informatics, Intelligent informatics
- Electrical and electronic engineering, Communication/Network engineering

- Neural Network

- Frequency domain blind channel estimation without phase ambiguity for QAM-OFDM systems., Hiroshi Shiratsuchi,Hiromu Gotanda, 9th International Conference on Signal Processing and Communication Systems, ICSPCS 2015, Cairns, Australia, December 14-16, 2015, 1 - 8, 2015 , Refereed
- Semi-Blind Channel Estimation for QAM-OFDM System, 五反田 博, 松崎 隆哲, 白土 浩, 十川勇人, 田中 宏典, The 45th ISCIE International Symposium on Stochastic Systems Theory and Its Applications, SB2-4, Nov. 2013
- Studies on Real Time DOA Estimation Based on DUET, 五反田 博, 平野 剛, 松崎 隆哲, 白土 浩, 岩崎宣生, 井上勝裕, International Conference on Innovative Computing, Information and Control, 5(2), Sep. 2013
- Educational simulators for understanding OFDM principles, 白土 浩, 五反田 博, 近畿大学産業理工学部 研究報告, (14), 28 - 36, Jul. 2011
- Blind Carrier Frequency Offset and Channel Estimation Using ICA in QAM-OFDM Systems, 五反田 博, 白土 浩, 原谷 直実, 中野吉正, 石橋孝昭, Proc. of IEEE Region 10 Conference(TENCON2010), 1330 - 1335, Nov. 2010
- SN ratio estimation and separation ability of permutation correction in Independent Component Analysis, 岩崎 宣生, 石橋 孝昭, 白土 浩, Kayanomori, 0(12), 22 - 30, 2010 Summary:かやのもり１１ 再録論文In a real world environment where acoustic signals are contaminated with various noises, it is difficult to estimate the signal-to-noise (SN) ratio only from signals observed at microphones; The knowledge of acoustic transfer functions and original source signals is inevitable for SN ratio estimation. The present paper proposes a method to estimate the SN ratio approximately in the real world environment without the knowledge of transfer functions and source signals: the SN ratio is estimated after application of Independent Cotnponcnt Analysis (ICA) to the signals observed at m...
- Blind Source Deconvolution Based on Frequency Domain Convolution Model Under Highly Reverberant Environments, KOYA Takeshi, ISHIBASHI Takaaki, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, Transactions of the Institute of Systems, Control and Information Engineers, 22(8), 287 - 294, Aug. 15 2009 Summary:In order to solve the blind source deconvolution, a convolved mixing process in the time domain is often transformed into an instantaneous mixing model in the frequency domain. However, the model is only an approximated one and thus does not work effectively under highly reverberant environments. By dividing the impulse response properly, Servi?re has precisely transformed the time-domain convolved mixture to a frequency-domain convolved mixture and has proposed a new FDICA approach available under high reverberation. In the approach, however, the permuation and scaling problems are unresol...
- A Blind Estimation of Carrier Frequency Offset and Channel in QAM-OFDM, SAYVISITH Vithaya, KIMURA Tetsuya, NAKAGAWA Fuminari, SHIRATSUCHI Hiroshi, HARATANI Naomi, GOTANDA Hiromu, The Transactions of the Institute of Electronics, Information and Communication Engineers. A, 92(3), 141 - 149, Mar. 01 2009 Summary:本論文では,周波数オフセット(CFO : Carrier Frequency Offset)と周波数選択性フェージングの影響を受けたQAM-OFDMについて,フェージング係数の位相が±π/4未満のとき,フェージング係数をパイロットシンボルを使わずにブラインド的に推定する方法を提案する.具体的には,まず,周波数選択性フェージングのあるもとでCFOに起因するキャリヤ間干渉(ICI : Inter-Carrier Interference)をICA(lndependent Component Analysis)モデルで定式化して,ICAに付随する成分置換やスケール不定性の解消法やCFOの推定法を提案する.次に,各サブキャリヤのコンステレーションがフェージング係数の値に応じて伸縮・回転することを利用して,CFOの推定結果をもとにフェージング係数を推定する.そして,その係数の推定結果を用いて未知の送信シンボルを復元する.最後に,提案法の有効性を16QAM-OFDMに対するシミュレーションで確認する.
- A blind channel estimation under inter-carrier interference in QAM-OFDM, 五反田 博, 白土 浩, 原谷 直実, Proc. the 40th ISCIE International Symposium on Stochastic Systems Theory and Its Applications, 204 - 209, Nov. 2008
- Estimation of OFDM Carrier Frequency Offset and Symbol Recovery by ICA, NAKAGAWA Fuminari, TAKASE Shigefumi, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, The Transactions of the Institute of Electronics, Information and Communication Engineers. A, 91(4), 448 - 457, Apr. 01 2008 Summary:直交周波数分割多重は,周波数オフセット(CFO)がある場合,サブキャリヤ間の直交性が崩れるため,サブキャリヤ間干渉(ICI)を引き起こして通信性能が劣化する.そのため,様々な周波数オフセット推定法が開発されている.本論文では,新しく独立成分分析(ICA)に基づいてICIを解消する方法を提案する.すなわち,まず,ICI問題をICAモデルの枠組みで定式化する.次に,ICAに付随して起きる成分置換やスケール不定の解法原理を明確にして,拘束条件付き自然こう配(NG)アルゴリズムを提案する.最後に,ICAによる結果を利用して,CFOを推定するとともに,未知の送信シンボルを復元する.提案法の有効性はシミュレーションにより確認した.
- On Resolution for Inter-Carrier Interference in OFDM Based on ICA, SAYVISITH Vithaya, KIMURA Tetsuya, NAKAGAWA Fuminari, SHIRATUCHI Hiroshi, HARATANI Naomi, GOTANDA Hiromu, IEICE technical report. Circuits and systems, 107(527), 23 - 28, Feb. 29 2008 Summary:Carrier frequency offset (CFO) causes inter-carrier interference (ICI) between the sub-carriers in Orthogonal Frequency Division Multiplexing (OFDM) systems, which degrades the system performance. In this paper, a new approach based on independent component analysis (ICA) is proposed to cancel the ICI, to estimate the flat-fading sub-channel and to restore the transmitted symbols, by using only the received symbols. First, the ICI problem is formulated as an ICA model under the flat-fading sub-channels. Next, the permutation and the scaling indeterminacy inherent in ICA are resolved. Then t...
- Effects of Initialization on Rule Extraction in Structural Learning, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, INOUE Katsuhiro, KUMAMARU Kousuke, Journal of Advanced Computational Intelligence and Intelligent Informatics, 12(1), 57 - 62, Jan. 2008 Summary:本論文では階層型ニューラルネットワークの学習によって得られる最終的なネットワーク構造から入出力間の関連性をルールとして抽出するための学習である構造学習において最適構造が得られやすくなるための初期条件について考察し，初期値設定法として提案した
- Resolution to solve the inter carrier interference in OFDM by independent component analysis, 中河 史成, 高瀬 成史, 白土 浩, Kayanomori, 0(6), 7 - 14, 2007
- Separability Conditions for Multilayer Nets Having Solutions and Convergent Superiority of Bipolar Nets, 白土 浩, Journal of Advanced Computational Intelligence and Intelligent Informatics, 8(6), 621 - 626, Dec. 2004 Summary:階層型ニューラルネットワークの学習特性を解析し，これまで実験的に示されてきた両極型ユニットによる学習性能の向上についてニューラルネットワークの各ユニットが成す分離超平面による幾何学的な解析により理論的に明らかにした．
- Studies on Effects of Initialization on Structure Formation and Generalization of Structural Learning with Forgetting, 白土 浩, Journal of Advanced Computational Intelligence and Intelligent Informatics, 8(6), 627 - 632, Dec. 2004 Summary:階層型ニューラルネットワークを対象とした構造付き忘却学習において著者らの提案する初期値設定法を適用した際の構造決定過程の解析と生成されるネットワーク構造の最適性について示した．
- Conversion to Taste Substance Concentration from the Taste Sensor Output Using a Neural Network, WATANABE Hiromasa, EZAKI Shu, GOTANDA Hiromu, SHIRATSUCHI Hiroshi, Reports of Kyushu school of Engineering, Kinki University, 32(0), 59 - 65, Mar. 01 2004 Summary:A multichannel taste sensor composed of lipid/polymer membranes for transforming to electric potential outputs different patterns for substances with different taste qualities. Because of mutual interaction between taste substances, it was still difficult to decompose into the components from the response to the solution containing more than two taste qualities. In this paper, the estimation of the concentrations from the response to mixed taste solution is well done using a neural network system. The error between the estimated concentration and the genuine one was much smaller than the er...
- On Initializations of BP Networks with a Single Hidden Layer and Normalizations of Training Data, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, INOUE Katsuhiro, KUMAMARU Kousuke, Transactions of the Institute of Systems,Control and Information Engineers, 15(10 532-538), 2002
- Effects of initialization on Structure Formation and Generalization of Neural Networks, 白土 浩, 五反田 博, Proc. IEEE Joint of Conference on Neural Networks, WashingtonD.C, 2644 - 2649, Jul. 2001
- Studies on Initialization for Multilayer Networks, 白土 浩, 五反田 博, Proc. IFAC2000 Symposium on System Identification, California, (1), 49 - 54, Jun. 2000
- Difference of Solution Regions Due to Net's Polarity, GOTANDA Hiromu, SHIRATSUCHI Hiroshi, INOUE Katsuhiro, KUMAMARU Kousuke, The Institute of Electronics, Information and Communication Engineers, 80(2), 696 - 699, Feb. 25 1997 Summary:非線形ユニットがしきい値関数で与えられる場合について, XOR問題の解を分離超平面に直交する法ベクトルで定式化して, 解領域の形状が両極型と片極型ネットで異なることを示す. この結果からBP学習のアトラクタはネット極性に依存することが示唆される.
- Formulation of Necessary Conditions for Multilayer Neural Networks to Have Solutions, GOTANDA Hiromu, SHIRATSUCHI Hiroshi, INOUE Katsuhiro, KUMAMARU Kousuke, Reports of the Faculty of Engineering, Kinki University in Kyushu. Science and technology section, 25(0), 35 - 42, Dec. 01 1996 Summary:This paper formulates a necessary condition for unit's weights and bias to become the elements of solutions for multilayer nets in terms of normal vectors orthogonal to separation hyperplanes. Then it depicts the distribution of normal vectors of two-dimension satisfying the condition, and elucidates that the distributing domain for unipolar units activating from 0 to 1 is significantly different from that for bipolar units activating from -0.5 to 0.5. At the same time, it depicts the initial distribution of normal vectors with the weights and biases given ordinarily by random numbers with ...
- Studies on Cardinarity of Solutions for Multilayer Nets and a Scaling Method in Hardware Implementations, GOTANDA HIROMU, SHIRATSUCHI HIROSHI, INOUE KATSUHIRO, KUMAMARU KOUSUKE, IPSJ Journal, 37(8), 1535 - 1542, Aug. 15 1996 Summary:This paper elucidates that multilayer nets of equal structure allow the same cardinarity of admissible solutions for learning tasks of which input patterns are related by Affine transform, even if their sigmoid functions are different in polarity and range. This result can be applied to a scaling problem arising on building the nets in analog hardware. In the case of the input patterns and the sigmoid functions multiplied by a scaling factor k, the separation and generalization abilities can be preserved if the weight values are set to 1/k times the original ones with keeping the bias value...
- Studies on Cardinality of Solutions fot Multilayer Nets and Scaling Method in Hardware Implementations, J. Robotics and Mechatronics, 9(5), 398 - 405, 1997
- Difference of Solution Regions due to Net Polarity, J. Robotics and Mechatronics, 9(5), 393 - 397, 1997
- Solution space and BP Learning Behaviour of multilayer networks whose units are different in polarity",, J. Robotics and Mechatronics, 7(4), 336 - 343, 1995

- A-4-37 Blind Channel Estimation in QAM OFDM Systems, Tanaka Hironori, Iwasaki Nobuo, Shiratsuchi Hiroshi, Gotanda Hiromu, Proceedings of the Society Conference of IEICE, 2011 08 30
- On Resolution for Inter-Carrier Interference in OFDM Based on ICA, SAYVISITH Vithaya, KIMURA Tetsuya, NAKAGAWA Fuminari, SHIRATUCHI Hiroshi, HARATANI Naomi, GOTANDA Hiromu, IEICE technical report. Communication systems, 2008 02 29 Summary:Carrier frequency offset (CFO) causes inter-carrier interference (ICI) between the sub-carriers in Orthogonal Frequency Division Multiplexing (OFDM) systems, which degrades the system performance. In this paper, a new approach based on independent component analysis (ICA) is proposed to cancel the ICI, to estimate the flat-fading sub-channel and to restore the transmitted symbols, by using only the received symbols. First, the ICI problem is formulated as an ICA model under the flat-fading sub-channels. Next, the permutation and the scaling indeterminacy inherent in ICA are resolved. Then t...
- On Resolution for Inter-Carrier Interference in OFDM Based on ICA, SAYVISITH Vithaya, KIMURA Tetsuya, NAKAGAWA Fuminari, SHIRATUCHI Hiroshi, HARATANI Naomi, GOTANDA Hiromu, IEICE technical report, 2008 02 29 Summary:Carrier frequency offset (CFO) causes inter-carrier interference (ICI) between the sub-carriers in Orthogonal Frequency Division Multiplexing (OFDM) systems, which degrades the system performance. In this paper, a new approach based on independent component analysis (ICA) is proposed to cancel the ICI, to estimate the flat-fading sub-channel and to restore the transmitted symbols, by using only the received symbols. First, the ICI problem is formulated as an ICA model under the flat-fading sub-channels. Next, the permutation and the scaling indeterminacy inherent in ICA are resolved. Then t...
- Studies on Coral Health Evaluation by Satellite Remote Sensing Images, SHIRATSUCHI Hiroshi, TOMORI Yoshimi, IEICE technical report. Neurocomputing, 2005 06 17 Summary:This report studies the coral health evaluation using a neural network, which is made to learn Ikema's water depth adjusting algorithms for extraction of the bottom features at optional points from remote sensing images. The IKONOS satellite images were used with high resolution of 82cm. Our previously proposed structural learning algorithm is applied to improve the generalization ability, since the training data, i.e., the measurements for correction of actual water depth are limited in number.
- Studies on Effects of Initialization for the Rule Extraction on Structural Learning with Forgetting, MIYAGI Tomokazu, SHIRATSUCHI Hiroshi, IEICE technical report. Neurocomputing, 2003 03 11 Summary:This report studies how our proposed initialization effects the rule extraction of neural networks by structural learning with forgetting. This proposed initialization consists of two steps: weights of hidden units are initialized so that their hyperplanes should pass through the center of input pattern set, and those of output units are initialized to zero. From simulation result on descovery of boolean function problem which has 5 and 7 inputs, it was confirmed that proposed initialization gives more simple network structure and higher rule extraction ability from improving the convergenc...
- Studies on An Redundant Units Discrimination Based on Geometrically Viewpoint, HIGA Naoki, SHIRATSUCHI Hiroshi, IEICE technical report. Neurocomputing, 2003 03 10 Summary:This report studies on an additional pruning algorithm with structure learning with forgetting(SLF) for the redundant units of neural networks. Two types redundancy criteria of hidden units are considered : differences between two hidden unit outputs, and using separation hyperplane's angle, norm and distance. Through the analysis of similarity progresses in SLF, in case of large number of initial hidden units, it is shown that the redundant hidden units are still remain at the end of learning. Proposal learning algorithm eliminates redundant the hidden units, which have the high similarity...
- Concentration estimation of mixed substances from the response pattern of taste sensor using a neural network, WATANABE Hiromasa, EZAKI Shu, GOTANDA Hiromu, SHIRATSUCHI Hiroshi, IEICE technical report. ME and bio cybernetics, 2003 01 17 Summary:A multichannel taste sensor composed of lipid/polymer membranes for transforming to electric potential outputs different patterns for substances with different taste qualities. Because of mutual interaction between taste substances, it was still difficult to decompose into the components from the response to the solution containing more than two taste dualities. In this paper, the estimation of the concentrations from the response to mixed taste solution is well done using a neural network system.
- Studies on an Initialization Based on Geometrical Approach for Structural Learning with Forgetting, MIYAGI Tomokazu, SHIRATSUCHI Hiroshi, IEICE technical report. Neurocomputing, 2002 06 21 Summary:This report studies how our proposed initialization effects the structure determination of neural networks by structural learning with forgetting. This proposed initialization consists of two steps: weights of hidden units are initialized so that their hyperplanes should pass through the center of input pattern set, and those of output units are initialized to zero. From simulation result performed on iris classification problem, it was confirmed that proposed initialization gives more simple network structure and higher generalization ability.
- Studies on An Algorithm for Reducing Redundant Units Based on Geometrical Approach, HIGA Naoki, SHIRATSUCHI Hiroshi, IEICE technical report. Neurocomputing, 2002 06 21 Summary:This report studies how our proposed additional learning algorithm for structural learning with forgetting effects the structure determination of neural networks. The proposed learning algorithm eliminates redundant hidden units, which have the high similarity between hidden units, from neural networks. From simulation result performed on iris classification problem, it was confirmed that the proposed learning algorithm gives better network structure and higher generalization ability.
- Studies on the Intrusion Detection System using Modular Neural Networks, SHIRATSUCHI Hiroshi, SHIMABUKURO Kazuki, HIGA Naoki, IEICE technical report. Neurocomputing, 2002 03 13 Summary:This report studies that the Intrusion Detection System(IDS) using modular neural networks(MNN) improves the unknown attacks detection. It is proposed that the learning method for composing the personal profile at the normally situation on each module of the MNN. Each UNIX's commands with packet capturing are encoded by the characteristic attributes. These attributes are selected from among the behavior, which can guess the intruder, for example execute capability, using network ports, important keywords matching. From the simulation, using the actual network packet, it is shown that the pr...
- Studies on a design of a neural network library for C language, HIGA Naoki, SHIRATSUCHI Hiroshi, IEICE technical report. Neurocomputing, 2001 06 22 Summary:In this report, a designed of neural network library for C language is studied. By expressing each parameter layout with hierarchy structure, each function requires only on structural argument which indicating the whole of neural nets. Even if complicated preprocessing stage such as the memory management or the structural design is not considered by using proposed library, the hierarchy neural network can be realized as a program. In addition, it is considered that expansion of nets structure and design of new function can be easily realize due to the proposed model has hierarchical structu...
- Recognition of Time Series Signals Using a Modular Neural Net, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, IKEMASU Yousuke, INOUE Katsuhiro, KUMAMARU Kousuke, IEICE technical report. Neurocomputing, 2001 03 15 Summary:In this report, it is studied that the method for recognition the time series signal by the multilayer neural net with preprocessing functions such as feature extraction and pattern normalization. The nets consist of modular subnets, each being specialized to preprocess its own signal and initialized to improve in signal recognition. As a simulation result, it is considered that the converging and recognizing performance of the nets is improved than ordinary method such as learning multiple signal as one net and using same preprocessing function for all signals.
- Studies on Removing Redundant Hidden Units for Multilayer Nets, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, INOUE Katsuhiro, KUMAMARU Kousuke, IEICE technical report. Neurocomputing, 2000 03 14 Summary:This paper studies how our proposed initialization effects the structure determination of neural networks by structural leaning with forgetting. The proposed initialization consists of two steps: weights of hidden units are initialized so that their hyperplanes should pass through the center of input pattern set, and those of output units are initializedto zero. Then, in additional initialization which removes redundant hidden units at the outset of learning is described. From simulation result performed on iris classification problem and chaos prediction problem, it was confirmed that the ...
- A Study on Initialization for Structural Learning with Forgetting, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, SHIMADA Masaaki, INOUE Katsuhiro, KUMAMARU Kousuke, IEICE technical report. Neurocomputing, 1999 11 26 Summary:This paper studies how our proposed initialization effects the structure determination of neural networks by structural learning with forgetting. The proposed initialization consists of two steps: weights of hidden units are initialized so that their hyperplanes should pass through the center of input pattern set, and those of output units are initialized to zero. From simulation result performed on Iris problem, it was confirmed that the initialization gives better network structure and higher generalization ability.
- A Study on Initialization for MultiLayer Nets, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, INOUE Katsuhiro, KUMAMARU Kousuke, IEICE technical report. Neurocomputing, 1998 10 24 Summary:This report studies an initialization of bipolar networks with single hidden layer trained for pattern classification problems. Weights of the hidden layer are initialized so that separation hyperpalnes should pass through the center of input pattern set, and those of the output layer are initialized zero. From simulation results for MONK's problem, Iris classification problem and Soner target identification problem, it is confirm that the proposed initialization gives better convergence in wider range of initial values and learning coefficent that the ordinal initialization that the weight...
- Input Set Separability and Superiority of Bipolar Nets in Convergence, SHIRATSUCHI Hiroshi, GOTANDA Hiromu, INOUE Katsuhiro, KUMAMARU Kousuke, IEICE technical report. Neurocomputing, 1997 11 17 Summary:This paper formulates a separability condition by normal vectors so that the separation hyperplanes should pass through a rectangle surrouding the input set. Then it depicts the distributions of two-dimensional normal vectors satisfying the condition. These distributions elucidate that the condition for the first hidden layer varies significantly even if the input patterns are simply translated, and that those conditions (in a wider sense) for the other layers are different between unipolar and bipolar units. It, also depicts an initial distribution of normal vectors with the weights initia...
- Initidlizdtion for MultiLayer Nets Based on Geometorical Approach, GOTANDA Hiromu, SHIRATSUCHI Hirosh, KUMAMARU Kousuke, INOUE Katsuhiro, IEICE technical report. Neurocomputing, 1997 03 18 Summary:In this report, three conditions on weights and biases of hidden units in any layers are derived: The first is for their separation hyperplanes passing through their input set so as to match their active-regions with the input set; The secod is for fixing their activ-regions κ times as wide as the input set ; The third is for matching the network outputs with the targets. Three conditions are incorporated into a new initialization scheme of the back propagation algorithm. Simulation results on parity and sonar problems show that the initialization gives better convergence than usual random ...

- Cooperation of education, medical care, universities and community supporters in operation of Web application system for pronunciation practice support, 勝瀬 郁代, 白土 浩, 岡野 亜希子, 堀内 幸造, かやのもり : 近畿大学産業理工学部研究報告 : reports of School of Humanity-Oriented Science and Engineering, Kinki University, 22, 7, 13, 2015 , http://ci.nii.ac.jp/naid/120005737583Summary:[Abstract]We developed a Web application system for children with pronunciation difficulties to practice pronunciation. The system users are assignedone of the following authorizations: student, teacher, medical worker, or speech evaluator. The teachers, medical workers, and speech evaluators are grouped by the student to whom they are linked and can access exercise records and student speech sounds by the Internet. The teachers can individually tailor practice words to each child's pronunciation needs. The medical workers and speech evaluators confirm the accuracy of the student's pronunciation and can share information with teachers. Thus, our system will encourage students to practice their pronunciation and promote the cooperation of teachers and medical workers for more effective instruction. This system is supported by the system management of the university and by the technological assistance of the local volunteer.
- アフリカ地域の学校教員を対象とした組込みシステム教育について, 松崎隆哲, 白土浩, 久良修郭, 情報処理学会全国大会講演論文集, 75th, 4, 4.419-4.420, 2013 03 06 , http://jglobal.jst.go.jp/public/201302255795488920
- Research on Neural Networks in Kumamaru and Inoue Laboratory, SHIRATSUCHI Hiroshi, 38, 3, 1999 03 , http://ci.nii.ac.jp/naid/10004318924
- A Study on Initialization for BP Networks, International Congerence on Neural Information Processing, 3, 1595, 1599, 1998
- Convergent Superiority of Bipolar Nets from the Viewpoint of Input Set Separability, Institute of System, Control and Information Engineers, 11, 4, 190, 197, 1998 , 10.5687/iscie.11.190
- Necessary Conditions for Multilayer Nets Having Solutions and Convergent Superiority of Bipolar Nets, Proc. IFAC System Ldentification, Kitakyushu, 2, 817, 822, 1997
- Studies on Cardinarity of Solutions for Multilaver Nets and a Scaling Method in Hardware Implementations, Information Processing Society of Japan, 37, 8, 1535, 1542, 1996

- Studies on Learning Property of Neural Nets