The search functionality is under construction.
The search functionality is under construction.

Author Search Result

[Author] Yuji KOBAYASHI(2hit)

1-2hit
  • An Algorithm for Finding All Solutions of a Hysteresis Neural Network

    Yuji KOBAYASHI  Kenya JIN'NO  Toshimichi SAITO  

     
    PAPER-Numerical Analysis and Optimization

      Vol:
    E82-A No:1
      Page(s):
    167-172

    We consider an algorithm for finding all solutions in order to clarify all the stable equilibrium points of a hysteresis neural network. The algorithm includes sign test, linear programming test and a novel subroutine that divides the solution domain efficiently. Using the hysteresis network, we synthesize an associative memory whose cross connection parameters are trinalized. Applying the algorithm to the case where 10 desired memories are stored into 77 cells network, we have clarified all the solutions. Especially, we have confirmed that no spurious memory exists as the trinalization is suitable.

  • Demonstration Experiment of a 5G Touchless Gate Utilizing Directional Beam and Mobile Edge Computing

    Naoto TSUMACHI  Masaya SHIBAYAMA  Ryuji KOBAYASHI  Issei KANNO  Yasuhiro SUEGARA  

     
    PAPER

      Pubricized:
    2021/03/23
      Vol:
    E104-B No:9
      Page(s):
    1017-1025

    In March 2020, the 5th generation mobile communication system (5G) was launched in Japan. Frequency bands of 3.7GHz, 4.5GHz and 28GHz were allocated for 5G services, and the 5G use cases fall into three broad categories: Enhanced Mobile Broadband (eMBB), Massive Machine Type Communication (mMTC) and Ultra-Reliable Low Latency Communication (URLLC). The use cases and services that take advantage of the characteristics of each category are expected to be put to practical use, and experiments of practical use are underway. This paper introduces and demonstrates a touchless gate that can identify, authenticate and allow passage through the gate by using these features and 5G beam tracking to estimate location by taking advantage of the low latency of 5G and the straightness of the 28GHz band radio wave and its resistance to spreading. Since position estimation error due to reflected waves and other factors has been a problem, we implement an algorithm that tracks the beam and estimates the user's line of movement, and by using an infrared sensor, we made it possible to identify the gate through which the user passes with high probability. We confirmed that the 5G touchless gate is feasible for gate passage. In addition, we demonstrate that a new service based on high-speed high-capacity communication is possible at gate passage by taking advantage of the wide bandwidth of the 28GHz band. Furthermore, as a use case study of the 5G touchless gate, we conducted a joint experiment with an airline company.