Abstract
Human Activity Recognition (HAR) using embedded sensors in smartphones and smartwatch has gained popularity in extensive applications in health care monitoring of elderly people, security purpose, robotics, monitoring employees in the industry, and others. However, human behavior analysis using the accelerometer and gyroscope data are typically grounded on supervised classification techniques, where models are showing sub-optimal performance for qualitative and quantitative features. Considering this factor, this paper proposes an efficient and reduce dimension feature extraction model for human activity recognition. In this feature extraction technique, the Enveloped Power Spectrum (EPS) is used for extracting impulse components of the signal using frequency domain analysis which is more robust and noise insensitive. The Linear Discriminant Analysis (LDA) is used as dimensionality reduction procedure to extract the minimum number of discriminant features from envelop spectrum for human activity recognition (HAR). The extracted features are used for human activity recognition using Multi-class Support Vector Machine (MCSVM). The proposed model was evaluated by using two benchmark datasets, i.e., the UCI-HAR and DU-MD datasets. This model is compared with other state-of-the-art methods and the model is outperformed.
Highlights
Human activity recognition has (HAR) become a fascinating research area for researchers in the field of ubiquitous computing, and human-computer interaction because of its important contribution to monitoring daily human life activities [1,2,3]
Sensors are a good example for such signals. This powerful Enveloped Power Spectrum (EPS) technique is measured from sensor signals with the help of Fast Fourier Transform (FFT)
A signal belonging to one class may be misclassified as belonging to another, creating a false positive recognition (Fp ) of that class, while a signal belonging to another class may be misclassified as belonging to that class, creating a false negative (Fn ) recognition of that class
Summary
College of Aeronautics and Engineering, Kent State University, Kent, OH 44240, USA. Department of Computer Science and Engineering, University of Asia Pacific, Dhaka 1205, Bangladesh.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have