KUROIWA Jousuke

FacultyDepartment of Human and Artificial Intelligent Systems Division of Advanced Informatics and Machinery
Teacher OrganizationDepartment of Human and Artificial Intelligent Systems Division of Advanced Informatics and Machinery
Education and
 Research Organization
Faculty of Engineering /Graduate School of Engineering
PositionProfessor
Last Updated: 19/11/26 14:55

Researcher Profile & Settings

Name

    KUROIWA Jousuke

Affiliation

  •  Department of Human and Artificial Intelligent Systems Division of Advanced Informatics and Machinery Professor

Education

  • 1996Tohoku University 電気及通信工学専攻
  • 1991Hirosaki University Department of Physics

Research Activities

Published Papers

  • Randomness of memory patterns plays important roles in sensitive response to memory pattern fragments
    Hatano Hiroto;Kuroiwa Jousuke;Odaka Tomohiro;Suwa Izumi;Shirai Haruhiko
    NOLTA 6(4) 542-555 2015 Refereed
    In the present paper, we investigate roles of the randomness of memory patterns in the sensitive response of the chaotic associative memory dynamics to memory pattern fragments in the chaotic neural network model referred to as CNN hereafter. In order to realize a memory search for hierarchical memory patterns, we overcome the problem how to construct the hierarchical memory patterns, whose basin volumes and visiting measures are sufficiently large. Therefore, we investigate (i) how to construct the memory patterns which gives sufficiently large basin volumes of theirs in a recurrent neural network model referred to as RNN hereafter, and (ii) the sensitivity of the chaotic associative memory dynamics in CNN to memory pattern fragments, focusing on the randomness in the memory patterns. From computer experiments, the basin volumes of the memory patterns become much larger as the randomness increases. In addition, the sensitive and robust response to the memory pattern fragments is achieved as the randomness becomes larger. Thus, ensuring sufficient large basin volumes and visiting measures with the same frequency, and the quite sensitive and robust response to the memory pattern fragments, the randomness in memory patterns is practical, which introduces the small overlap among each inter-cycle pattern.
  • Three-rules set of one dimensional cellular automata with two states and three neighbors improves description ability
    Terai Rika;Kuroiwa Jousuke;Odaka Tomohiro;Suwa Izumi;Shirai Haruhiko
    NOLTA 6(4) 534-541 2015 Refereed
    In the present paper, we investigate the description ability of digital sound data by the rule set of one dimensional cellular automata with two state and three neighbors referred to as 1-2-3 CA hereafter. It has been shown that the two-rules set of (#90, #180) has the highest description ability of all the possible two-rules sets. For several sound data, however, the data amount of the resultant codes becomes larger than original data, originating into the limitations of the two-rules set of (#90, #180). In order to overcome the limitations, we try to improve the description ability of digital sound data by adding another rule to (#90, #180). Therefore, we evaluate the description ability for the all the possible sets, where we add another rule to (#90, #180). From computer experiments, for the three-rules set of (#45, #90, #180), the averaged length of the rule sequences of the resultant codes becomes shorter, and a ratio of the reduced search number takes larger for all the data. Thus, we succeed to improve the description ability.
  • Description Ability of Sound with Three-Rules Set of One Dimensional Cellular Automata with Two States and Three Neighbors
    R.Terai, J.Kuroiwa, T.Odaka, I.Suwa, H.Shirai
     136-139 Sep.  2014 Refereed
  • Effectivity of Randomness in Memory Patterns of Recurrent Neural Network Model
    H.Hatano, J.Kuroiwa, T.Odaka, I.Suwa, H.Shirai
     524-527 Sep.  2014 Refereed
  • An Artificial Fish Swarm Algorithm for the Multicast Routing Problem
    Q. Liu, T.Odaka, J.Kuroiwa, H.Shirai, H.Ogura
    IEICE Trans. on Communications E97-B(5) 996-1011 May  2014 Refereed
  • A New Artificial Fish Swarm Algorithm for the Multiple Knapsack Problem
    Q. Liu, T.Odaka, J.Kuroiwa, H.Shirai, H.Ogura
    IEICE Trans. Information and Systems E97-D(3) 455-468 Mar.  2014 Refereed
  • A New Artificial Fish Swarm Algorithm for the Multiple Knapsack Problem
    Liu, Qing;Odaka, Tomohiro;Kuroiwa, Jousuke;Shirai, Haruhiko;Ogura, Hisakazu
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E97D(3) 455-468 2014
  • An Artificial Fish Swarm Algorithm for the Multicast Routing Problem
    Liu, Qing;Odaka, Tomohiro;Kuroiwa, Jousuke;Shirai, Haruhiko;Ogura, Hisakazu
    IEICE TRANSACTIONS ON COMMUNICATIONS E97B(5) 996-1011 2014
  • An Artificial Fish Swarm Algorithm for the Multicast Routing Problem
    LIU Qing;ODAKA Tomohiro;KUROIWA Jousuke;SHIRAI Haruhiko;OGURA Hisakazu
    IEICE Trans. Commun. 97(5) 996-1011 2014
    This paper presents an artificial fish swarm algorithm (AFSA) to solve the multicast routing problem, which is abstracted as a Steiner tree problem in graphs. AFSA adopts a 0-1 encoding scheme to represent the artificial fish (AF), which are then subgraphs in the original graph. For evaluating each AF individual, we decode the subgraph into a Steiner tree. Based on the adopted representation of the AF, we design three AF behaviors: randomly moving, preying, and following. These behaviors are organized by a strategy that guides AF individuals to perform certain behaviors according to certain conditions and circumstances. In order to investigate the performance of our algorithm, we implement exhaustive simulation experiments. The results from the experiments indicate that the proposed algorithm outperforms other intelligence algorithms and can obtain the least-cost multicast routing tree in most cases.
  • A New Artificial Fish Swarm Algorithm for the Multiple Knapsack Problem
    LIU Qing;ODAKA Tomohiro;KUROIWA Jousuke;SHIRAI Haruhiko;OGURA Hisakazu
    IEICE Trans. Inf. & Syst. 97(3) 455-468 2014
    A new artificial fish swarm algorithm (AFSA) for solving the multiple knapsack problem (MKP) is introduced in this paper. In the proposed AFSA, artificial fish (AF) individuals are only allowed to search the region near constraint boundaries of the problem to be solved. For this purpose, several behaviors to be performed by AF individuals, including escaping behavior, randomly moving behavior, preying behavior and following behavior, were specially designed. Exhaustive experiments were implemented in order to investigate the proposed AFSA's performance. The results demonstrated the proposed AFSA has the ability of finding high-quality solutions with very fast speed, as compared with some other versions of AFSA based on different constraint-handling methods. This study is also meaningful for solving other constrained problems.
  • A Symbiosis-based Artificial Fish Swarm Algorithm
    Liu Qing, T.Odaka, J. Kuroiwa, H. Shirai, H. Ogura
     DayB_PmA_RmA_8 Jul.  2013 Refereed
  • Application of an artificial fish swarm algorithm in symbolic regression
    Q. Liu, T.Odaka, J.Kuroiwa, H.Ogura
    IEICE Trans. Information and Systems E96-D(4) 872-885 Apr.  2013 Refereed
  • Effect of configuration of inhibited in-coming synaptic connections in sensitive response of chaotic wandering states
    T.Hamada, J.Kuroiwa, T.Odaka, I.Suwa, H.Shiraia
     4(4) 419-429 Jan.  2013 Refereed
  • Errorless Description with two Rules of Cellular Automata for Digital Sound Data
    J.Kuroiwa, S.Nara
     23(8) 1350148-1--8 2013 Refereed
  • Recycling Lethal Chromosomes Based on Immune Operation in Genetic Algorithm for Multi-Knapsack Problem
    J.Guo, J.Kuroiwa, H.Ogura, I.Suwa, H.Shirai, T.Odaka
     219-222 Jan.  2012 Refereed
  • Dependence of Sensitive responses of chaotic wandering states on configuration of inhibited in-coming connections
    T.Hamada, J.Kuroiwa, H.Ogura, T.Odaka, I.Suwa, H.Shirai
     644-647 Jan.  2012 Refereed
  • An N-Gram and STF-IDF model for masquerade detection in a UNIX environment
    D. Geng, T.Odaka, J.Kuroiwa, H.Ogura
    Journal in Computer Virologye 7(2) 133-142 May  2011 Refereed
  • Fish Swarm Optimization Method for the Two-Dimensional Guillotine Cutting Problem
    Z.Yalong, H.Ogura, J.Kuroiwa, T.Odaka
     15(3) 225-234 May  2011 Refereed
  • Effect of overlap among memory patterns in delay feedback control of chaotic neural network model
    K.Teramoto, J.Kuroiwa, H.Ogura, T.Odaka, I.Suwa, H.Shirai
     11(2) 17-22 Nov.  2010 Refereed
  • Dependence on memory patterns in sensitive responses of memory fragments among three types of chaotic neural network models
    T.Hamada, J.Kuroiwa, H.Ogura, T.Odaka, H.Shirai
     1 223-231 Nov.  2010 Refereed
  • Response Properties to Inputs of Memory Pattern Fragments in Three Types of Chaotic Neural Network Models
    T.Hamada, J.Kuroiwa, H.Ogura, T.Odaka, H.Shirai
     2 544-551 Sep.  2009 Refereed
  • A Genetic Algorithm with Utilizing Lethal Chromosomes
    Y.Zhang, X.Ma, J.Kuroiwa, T.Odaka, H.Ogura
     2047-2050 Aug.  2009 Refereed
  • Practical Preprocessing in Realizing Errorless and Compressive Description Method of Digital Sounds in Cellular Automata
    T.Katoh, J.Kuroiwa, H.Ogura, T.Odaka, H.Shirai
     415-418 Jan.  2009 Refereed
  • Effect of Pattern Overlap in Delay Feedback Control Method for Chaotic Neural Network
    K.Teramoto, J.Kuroiwa, H.Ogura, T.Odaka, H.Shirai
     483-486 Jan.  2009 Refereed
  • Improvement of low-dows MDCT images by applying a novel adaptive median filter with local averaging
    J.Deng, K. Hiratsuka, T. Ishida, H. Shirai, J.Kuroiwa, T.Odaka, H.Ogura
     3(1) 31-42 2009 Refereed
  • Experience Learning Support System in Integraed Study with use of Cellular Phone
     25(1) 42203 Jan.  2008 Refereed
  • Robustness in Time Series Prediction based on Local Orbit Instability Method
    Hironori Sawayanagi, J.Kuroiwa, Haruhiko Shirai, T.Odaka, H.Ogura
    Proceedings of 2007 International Symposium on Nonlinear Theory and its Applications (NOLTA 2007, Vancouver, Canada) 200-203 Sep.  2007 Refereed
  • Spatio-Temporal Patterns Produced by Cellular Automata Rule-Sequence of CML Data
    T. Yamada, J.Kuroiwa, H. Shirai, I.Takahashi, T.Odaka, H.Ogura
     329-332 Mar.  2007
  • Local Trajectory instability and Chaotic Temporal Series Prediction
    H. Sawayanagi, J.Kuroiwa, H. Shirai, I.Takahashi, T.Odaka, H.Ogura
     345-348 Mar.  2007
  • Passive Dynamical Walking and Coexistence of Different Walking Pattern Attractors
    N. Toyoda, J.Kuroiwa, H. Shirai, I.Takahashi, T.Odaka, H.Ogura
     241-244 Mar.  2007
  • L-010 Hand motion based authentication system using accelerometer on mobile terminals
    KOGA Takashi;ODAKA Tomohiro;KUROIWA Jousuke;SHIRAI Haruhiko
     14(4) 187-188 Aug.  2015

Conference Activities & Talks

  • Description Ability of Sound with Three-Rules Set of One Dimensional Cellular Automata with Two States and Three Neighbors
    R.Terai, J.Kuroiwa, T.Odaka, I.Suwa, H.Shirai
     Sep.  2014
  • Effectivity of Randomness in Memory Patterns of Recurrent Neural Network Model
    H.Hatano, J.Kuroiwa, T.Odaka, I.Suwa, H.Shirai
     Sep.  2014
  • Dependence of sensitive responses of chaotic wandering states on configuration of inhibited in-coming synaptic connections
    T.Hamada, J.Kuroiwa, H.Ogura, T.Odaka, I.Suwa, H.Shirai
     Sep.  2012
  • Recycling Lethal Chromosomes Based on Immune Operation in Genetic Algorithm for Multi-Knapsack Problem
    J.Guo, J.Kuroiwa, H.Ogura, I.Suwa, H.Shirai, T.Odaka
     Jan.  2012
  • Recycling Lethal Chromosomes Based on Immune Operation in Genetic Algorithm for Multi-Knapsack Problem
    J.Guo, Y.Zhang, H.Ogura, J.Kuroiwa, T.Odaka, I.Suwa, H.Shirai
     Sep.  2011
  • Effect of overlap among memory patterns in delay feedback control of chaotic neural network model
    K.Teramoto, 黒岩 丈介, H.Ogura, T.Odaka, I.Suwa, H.Shirai
     Nov.  2010
  • Dependence on memory patterns in sensitive responses of memory fragments among three types of chaotic neural network models
    T.Hamada, J.Kuroiwa, H.Ogura, T.Odaka, H.Shirai
     Nov.  2010
  • Response Properties to Inputs of Memory Pattern Fragments in Three Types of Chaotic Neural Network Models
    T.Hamada, J.Kuroiwa, H.Ogura, T.Odaka, H.Shirai, Y.Kato
     Sep.  2009
  • A Genetic Algorithm with Utilizing Lethal Chromosomes
    Y.Zhang, X.Ma, J.Kuroiwa, T.Odaka, H.Ogura
     Aug.  2009
  • Practical Preprocessing in Realizing Errorless and Compressive Description Method of Digital Sounds in Cellular Automata
    T.Katoh, J.Kuroiwa, H.Ogura, H.Shirai, T.Odaka
     Jan.  2009
  • Effect of Pattern Overlap in Delay Feedback Control Method for Chaotic Neural Network
    K.Teramoto, J.Kuroiwa, H.Ogura, H.Shirai, T.Odaka
     Jan.  2009