Wi-Fi-CSI-based Fall Detection by Spectrogram Analysis with CNN

Takashi Nakamura, Mondher Bouazizi, Kohei Yamamoto, Tomoaki Ohtsuki

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Fall detection system has a great demand for elderly people living alone. Wi-Fi CSI (Channel State Information) based fall detection method can be used to build non-intrusive and nonspace- limited fall detection systems. In the conventional work on Wi-Fi CSI based fall detection, a classification performance degradation has been observed when data in different environments is used for learning and testing data. Also, that method can not capture accurate features of motion due to the signal distortion during the noise reduction, and it can not segment signals accurately when the SNR (Signal to Noise power Ratio) is small. In this paper, we propose a spectrogram image-based fall detection using Wi-Fi CSI. Unlike the conventional method, CSI is segmented with a certain sliding time window, and then the classifier detects fall by using the spectrogram image generated from segmented CSI. We use a CNN (Convolutional Neural Network) for binary classification of the spectrogram images of the fall and non-fall motions. We carried out experiments to evaluate the classification performance of our proposed method against the conventional one by using motion data in two different rooms for learning and testing data. As a result, we confirmed that our proposed method outperformed conventional one and reached 0.90 accuracy.

本文言語English
ホスト出版物のタイトル2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781728182988
DOI
出版ステータスPublished - 2020 12
イベント2020 IEEE Global Communications Conference, GLOBECOM 2020 - Virtual, Taipei, Taiwan, Province of China
継続期間: 2020 12 72020 12 11

出版物シリーズ

名前2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings

Conference

Conference2020 IEEE Global Communications Conference, GLOBECOM 2020
CountryTaiwan, Province of China
CityVirtual, Taipei
Period20/12/720/12/11

ASJC Scopus subject areas

  • Media Technology
  • Modelling and Simulation
  • Instrumentation
  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Software
  • Safety, Risk, Reliability and Quality

フィンガープリント 「Wi-Fi-CSI-based Fall Detection by Spectrogram Analysis with CNN」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル