N
Nobuyuki Matsui
Researcher at University of Hyogo
Publications - 196
Citations - 2148
Nobuyuki Matsui is an academic researcher from University of Hyogo. The author has contributed to research in topics: Artificial neural network & Cellular automaton. The author has an hindex of 23, co-authored 195 publications receiving 1980 citations. Previous affiliations of Nobuyuki Matsui include Hyogo University & Artificial Intelligence Center.
Papers
More filters
Book ChapterDOI
Three-dimensional classification of insect neurons using self-organizing maps
Hiroki Urata,Teijiro Isokawa,Yoich Seki,Naotake Kamiura,Nobuyuki Matsui,Hidetoshi Ikeno,Ryohei Kanzaki +6 more
TL;DR: In this paper, systematic three-dimensional classification is presented for sets of interneuron slice images of silkworm moths, using self-organizing maps, with as high accuracy as the manual classification made by neuroscientists.
Book ChapterDOI
A Comparison of Grouping Behaviors on Rule-Based and Learning-Based Multi-agent Systems
TL;DR: In this paper, the authors adopt quantities obtained from trails of agents, in order to investigate the properties for grouping behaviors of agents and also evaluate rule-based and learning-based models by using these quantities under the environments with and without predatory agents.
Journal ArticleDOI
Performance Improvement of Extended Boundary Node Method
TL;DR: In this article, an extended boundary node method (X-BNM) with the radial point interpolation method (RPIM) shape function is proposed and its performance is numerically investigated by comparing with the dual reciprocity boundary element method (DRM).
Patent
Moving image processor, moving image processing method and moving image processing program
Isogawa Teijiro,Kenji Iwatani,Naotake Kamiura,Nobuyuki Matsui,Yuzo Ogawa,Akitsugu Otsuka,尚武 上浦,晃嗣 大塚,雄三 小川,憲司 岩谷,伸之 松井,悌次郎 礒川 +11 more
TL;DR: In this article, the authors proposed a method to detect a moving object in an moving image using a self-organizing map, where a composite video signal output from a camera is converted into color image data by an input conversion part 50.
Journal ArticleDOI
Swarm Networks in Brownian Environments
TL;DR: A Swarm Network in which connections can be changed dynamically, and in which the cells (called “agents”) are subject to Brownian motion is presented, which is capable of universal computation by constructing a universal Brownian circuit based on it.