研究者業績

Satoru Aikawa

  (相河 聡)

Profile Information

Affiliation
Professor, Graduate School of Engineering, University of Hyogo
Degree
Doctor of Engineering, Ph.D(Dec, 1995, University of Tokyo)

J-GLOBAL ID
201801006797934700
researchmap Member ID
B000299957

Research History

 9

Education

 1

Papers

 91
  • Shota Nakayama, Satoru Aikawa, Shinichiro Yamamoto
    IEICE Communications Express, 1-4, 2024  
  • Ryoga Ozaki, Satoru Aikawa, Shinichiro Yamamoto
    IEICE Communications Express, 12(10) 564-567, Oct, 2023  
  • TSUDA Takaya, YAMAMOTO Shinichiro, AIKAWA Satoru, HATAKEYAMA Kenichi
    J106-B(4) 260-263, Apr 1, 2023  Peer-reviewed
    In this study, transmission coils were placed in a metallic enclosure with an open surface, and the near magnetic field leaking from the enclosure was investigated. In addition, a perforated metal plate that can improve the electromagnetic shielding effect was considered.
  • Konishi Yohei, Aikawa Satoru, Yamamoto Shinichiro
    IEICE Communications Express, 12(3) 66-71, Mar 1, 2023  Peer-reviewed
    The fingerprint technique is used as an indoor localization method. This study uses a CNN-based indoor fingerprint localization method. The estimation accuracy of CNN improves as the number of AP information (AP identifiers and received signal strength indicator) increases. However, gathering AP information is time-consuming and costly. The problem can be solved using UD (AP information users measured). However, the UD measuring method does not know the user’s exact location. Therefore, it is essential to choose UD that is accurately estimate and use it for CNN training. In this study, we propose a method for selecting UDs that makes use of the RSSI similarity between AP information and UD.
  • Yu Sakanishi, Satoru Aikawa, Shinichiro Yamamoto
    IEICE COMMUNICATIONS EXPRESS, 11(10) 673-678, Oct, 2022  Peer-reviewed
    In this study, we performed indoor location estimation using wireless LAN. The estimation method is based on the Finger Print method [1]. We measure the database (DB) and user data (UD) using wireless LAN radio waves to improve the location estimation accuracy of Finger Print indoor location estimation. The Neural Network (NN) that compares UD and DB is ResNet (Residual Network), which is a derivative of CNN (Convolutional Neural Network). The number of layers that provide the best accuracy varies depending on the environment. To confirm this, we experimentally verified the relationship between the number of layers and the estimation accuracy in different environments, and clarified the design method.

Misc.

 329
  • 志田勇介, 相河聡, 山本真一郎
    電子情報通信学会 関西支部 第 28 回 学生会研究発表講演会, Mar, 2023  
  • 四宮東悟, 相河聡, 山本真一郎
    電子情報通信学会 関西支部 第 28 回 学生会研究発表講演会, Mar, 2023  
  • 谷口雄視, 山本真一郎, 相河 聡, 松岡茂樹, 長尾正揮
    信学技報, 122(372) 33-38, Jan 20, 2023  
  • Soma Takeda, Shinichiro Yamamoto, Satoru Aikawa, Teruhiro Kasagi
    IEICE Proceeding Series, 72 S12-5, Nov 29, 2022  
    With the recent expansion of electromagnetic (EM) waves, undesired EM waves generated by device can cause malfunctions of other electronic equipment and communication failure. EM wave absorbers are widely used as countermeasures against these problems. Therefore, EMC (Electromagnetic Compatibility) technology is reguired to improve the electromagnetic environment. In this study, a microwave metamaterial EM wave absorbers using a sheet with a periodic array of square metal patterns were designed and its reflection characteristics at vertical incidence were experimentally evaluated.
  • Shota Nakayama, Satoru Aikawa, Shinichiro Yamamoto
    IEICE Proceeding Series, 72 O3-4, Nov 29, 2022  
    This contribution focuses on the accuracy and measurement cost of indoor Area Estimation using wireless LAN. The system estimates the area, such as a room or a shopping store, where the user is located. The user-measured AP information (UD), and the pre-measured AP information (DB) are used in the FP method. In the previous study, RSSI probability distributions were obtained from the measured DB and UD. The area with the largest overlap in probability distribution was selected as the estimation result. In this study, we propose Area Estimation by CNN using data measured while walking at various locations within an area. The method using CNN improved the estimation accuracy compared to conventional Area Estimation. Moreover, the method measuring AP information while walking reduced the measurement time.

Books and Other Publications

 9

Presentations

 305

Major Teaching Experience

 14