Takashi Nakamura
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Takashi Nakamura has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
Kohei Yamamoto
Graduate School of Science and Technology, Keio University, Yokohama, Japan
1 shared publication- Mondher Bouazizi
Faculty of Science and Technology, Keio University, Yokohama, Japan
1 shared publication - Tomoaki Ohtsuki
Keio University
1 shared publication
Latest Publications
- 17 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 9 (18) , 17220-17234
Wi-Fi-Based Fall Detection Using Spectrogram Image of Channel State Information
Wi-Fi CSI (Channel State Information) based fall detection systems have a great potential compared with other alternatives since they are non-intrusive and non-space limited. However, in the conventional work on Wi-Fi CSI based fall detection, a phenomenon is commonly observed: the classification performance degrades when data in different environments are used for learning and testing. Nonetheless, when the SNR (Signal to Noise power Ratio) is small, the conventional methods cannot capture features of motion and cannot segment signals accurately. Therefore, there is a need to address these problems in order to build a robust fall detection system. 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 the segmented CSI. We use a pre-trained CNN (Convolutional Neural Network) optimized 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. As a result, we confirmed that our proposed method outperforms the conventional one and reaches over 0.92 accuracy. In addition, compared with the conventional method, the fall detection performance of our method does not degrade even when using different environment data for learning and testing.
- 17 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 9 (18) , 17220-17234
Wi-Fi-Based Fall Detection Using Spectrogram Image of Channel State Information
Wi-Fi CSI (Channel State Information) based fall detection systems have a great potential compared with other alternatives since they are non-intrusive and non-space limited. However, in the conventional work on Wi-Fi CSI based fall detection, a phenomenon is commonly observed: the classification performance degrades when data in different environments are used for learning and testing. Nonetheless, when the SNR (Signal to Noise power Ratio) is small, the conventional methods cannot capture features of motion and cannot segment signals accurately. Therefore, there is a need to address these problems in order to build a robust fall detection system. 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 the segmented CSI. We use a pre-trained CNN (Convolutional Neural Network) optimized 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. As a result, we confirmed that our proposed method outperforms the conventional one and reaches over 0.92 accuracy. In addition, compared with the conventional method, the fall detection performance of our method does not degrade even when using different environment data for learning and testing.