Abstract
This paper presents a wearable device, fitted on the waist of a participant that recognizes six activities of daily living (walking, walking upstairs, walking downstairs, sitting, standing, and laying) through a deep-learning algorithm, human activity recognition (HAR). The wearable device comprises a single-board computer (SBC) and six-axis sensors. The deep-learning algorithm employs three parallel convolutional neural networks for local feature extraction and for subsequent concatenation to establish feature fusion models of varying kernel size. By using kernels of different sizes, relevant local features of varying lengths were identified, thereby increasing the accuracy of human activity recognition. Regarding experimental data, the database of University of California, Irvine (UCI) and self-recorded data were used separately. The self-recorded data were obtained by having 21 participants wear the device on their waist and perform six common activities in the laboratory. These data were used to verify the proposed deep-learning algorithm on the performance of the wearable device. The accuracy of these six activities in the UCI dataset and in the self-recorded data were 97.49% and 96.27%, respectively. The accuracies in tenfold cross-validation were 99.56% and 97.46%, respectively. The experimental results have successfully verified the proposed convolutional neural network (CNN) architecture, which can be used in rehabilitation assessment for people unable to exercise vigorously.
Highlights
With the popularization of wearable devices and reductions in their size and cost in recent years, sensors have been applied in human activity recognition (HAR)
The data are preprocessed through denoising and normalization, among other procedures, for subsequent feature extraction and for training HAR classifiers [13]
We placed the sensor on the waist for data collection, and the data were preprocessed by data normalization. It was used for subsequent feature extraction and training classifiers for related activity recognition
Summary
With the popularization of wearable devices and reductions in their size and cost in recent years, sensors have been applied in human activity recognition (HAR). We placed the sensor on the waist for data collection, and the data were preprocessed by data normalization It was used for subsequent feature extraction and training classifiers for related activity recognition. The main contribution of this paper is to propose multi-scale feature extraction through multi-scale parallel convolutional neural networks, thereby improving the accuracy of human activity recognitions. A belt was used to fasten the wearable device on the participants’ waists to prevent it from shaking with their movements This increased stability facilitated data collection by the accelerometer and gyroscope. The number of data entries corresponding to each activity of daily living in the training, testing, and verification sets was 1293, 693, and 324, respectively.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.