Human activity recognition is widely used in many fields, such as the monitoring of smart homes, fire detecting and rescuing, hospital patient management, etc. Acoustic waves are an effective method for human activity recognition. In traditional ways, one or a few ultrasonic sensors are used to receive signals, which require many feature quantities of extraction from the received data to improve recognition accuracy. In this study, we propose an approach for human activity recognition based on a two-dimensional acoustic array and convolutional neural networks. A single feature quantity is utilized to characterize the sound of human activities and identify those activities. The results show that the total accuracy of the activities is 97.5% for time-domain data and 100% for frequency-domain data. The influence of the array size on recognition accuracy is discussed, and the accuracy of the proposed approach is compared with traditional recognition approaches such as k-nearest neighbor and support vector machines where it outperformed them.
Skip Nav Destination
A single feature for human activity recognition using two-dimensional acoustic array
,
,
,
,
,
Article navigation
27 May 2019
Research Article|
May 28 2019
A single feature for human activity recognition using two-dimensional acoustic array
Available to Purchase
Xinhua Guo;
Xinhua Guo
a)
1
School of Mechanical and Electronic Engineering, Wuhan University of Technology
, Wuhan 430070, China
2
Hubei Provincial Engineering Technology Research Center for Magnetic Suspension
, Wuhan 430070, China
Search for other works by this author on:
Rongcheng Su;
Rongcheng Su
1
School of Mechanical and Electronic Engineering, Wuhan University of Technology
, Wuhan 430070, China
Search for other works by this author on:
Chaoyue Hu;
Chaoyue Hu
1
School of Mechanical and Electronic Engineering, Wuhan University of Technology
, Wuhan 430070, China
Search for other works by this author on:
Xiaodong Ye;
Xiaodong Ye
1
School of Mechanical and Electronic Engineering, Wuhan University of Technology
, Wuhan 430070, China
Search for other works by this author on:
Huachun Wu;
Huachun Wu
1
School of Mechanical and Electronic Engineering, Wuhan University of Technology
, Wuhan 430070, China
2
Hubei Provincial Engineering Technology Research Center for Magnetic Suspension
, Wuhan 430070, China
Search for other works by this author on:
Kentaro Nakamura
Kentaro Nakamura
3
Laboratory for Future Interdisciplinary Research of Science and Technology, Tokyo Institute of Technology
, 4259 Nagatsuta-cho, Midori-ku, Yokohama 226-8503, Japan
Search for other works by this author on:
Xinhua Guo
1,2,a)
Rongcheng Su
1
Chaoyue Hu
1
Xiaodong Ye
1
Huachun Wu
1,2
Kentaro Nakamura
3
1
School of Mechanical and Electronic Engineering, Wuhan University of Technology
, Wuhan 430070, China
2
Hubei Provincial Engineering Technology Research Center for Magnetic Suspension
, Wuhan 430070, China
3
Laboratory for Future Interdisciplinary Research of Science and Technology, Tokyo Institute of Technology
, 4259 Nagatsuta-cho, Midori-ku, Yokohama 226-8503, Japan
b)Present address: Institute of Innovative Research, Tokyo Institute of Technology, Yokohama 226-8503, Japan.
Appl. Phys. Lett. 114, 214101 (2019)
Article history
Received:
March 19 2019
Accepted:
April 23 2019
Citation
Xinhua Guo, Rongcheng Su, Chaoyue Hu, Xiaodong Ye, Huachun Wu, Kentaro Nakamura; A single feature for human activity recognition using two-dimensional acoustic array. Appl. Phys. Lett. 27 May 2019; 114 (21): 214101. https://doi.org/10.1063/1.5096572
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
Attosecond physics and technology
O. Alexander, D. Ayuso, et al.
Significant improvement of breakdown voltage of Al0.86Ga0.14N Schottky barrier diodes by atomic layer etching
Tingang Liu, Zhiyuan Liu, et al.
Roadmap on photonic metasurfaces
Sebastian A. Schulz, Rupert. F. Oulton, et al.
Related Content
Translating audio into movement: A semantic gesture generation approach using conditional GANs
AIP Conf. Proc. (April 2025)
Conceptual exploration and comparative study on the use of deep learning approach in HAR models
AIP Conf. Proc. (December 2022)
Analysis of human action recognition using CNN algorithm in comparison with ANN algorithm
AIP Conf. Proc. (November 2024)
Evaluating machine learning architectures for sound event detection for signals with variable signal-to-noise-ratios in the Beaufort Sea
J. Acoust. Soc. Am. (October 2023)