A Novel Sparse Representation and Softmax Method for Human Activity Identification in Healthcare Systems
Human activity identification has been attracting extensive research attention due to its prominent applications in healthcare systems such as healthcare monitoring and rehabilitation process. Traditional methods are greatly dependent on hand-crafted feature extraction, hampering their
generalization performance. In this research, a novel sparse representation and softmax (SRS) method is presented for human activity identification to reduce the computation complexity of the task and improve the accuracy of classification. The multi-class classifier based on the softmax function
is firstly introduced to improve sensor data classification performance. Sparse representation technology is then applied in our work to extract human activity features from sensor data. The output of the classifier model, taking raw sensor data after transforming into a high-dimensional feature
space as input, provides a normalization of the probability distribution of activity categories, thereby ensuring accuracy and efficiency under diverse human activities. Experiments on a collection of raw sensor data from wireless sensor networks demonstrate the identification accuracy of
our approach compared with nearest neighbor, naive Bayesian classifier, and support vector machine methods. The F1-score of the proposed method is respectively 14.1%, 19.6%, and 6.8% higher than the approaches mentioned above, indicating the effectiveness of SRS.
Keywords: Activity Recognition; Softmax; Sparse Representation; Wireless Sensor
Document Type: Research Article
Affiliations: 1: School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, 310018, China 2: School of Management, Zhejiang University of Technology, Hangzhou, 310023, China
Publication date: 01 July 2020
- Journal of Medical Imaging and Health Informatics (JMIHI) is a medium to disseminate novel experimental and theoretical research results in the field of biomedicine, biology, clinical, rehabilitation engineering, medical image processing, bio-computing, D2H2, and other health related areas.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Ingenta Connect is not responsible for the content or availability of external websites
- Access Key
- Free content
- Partial Free content
- New content
- Open access content
- Partial Open access content
- Subscribed content
- Partial Subscribed content
- Free trial content