Human activity recognition based on LPA
- PDF / 1,148,982 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 10 Downloads / 201 Views
Human activity recognition based on LPA Ruixiang Li 1
1
& Hui Li & Weibin Shi
1
Received: 15 July 2019 / Revised: 6 April 2020 / Accepted: 28 May 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Human activity recognition and fall detection have been popular research topics because of its wide area of application. Traditional activity recognition methods have complex feature extraction steps. We propose a new feature extraction method based on linear prediction analysis(LPA) to reduce computational complexity involved with engineering features. The feature extraction method we propose establishes a link between human activity and the signal system and regards acceleration signals as the output of the human activity. Using the relationship between the human activity and the output signal, linear predictive analysis can isolate information about human activity and transform it into a compact representation through linear prediction coefficients (LPC). In order to verify the effectiveness of the method, we design an activity recognition system based on linear prediction analysis and feature extraction. At the same time, we study the performance of the combination of linear prediction coefficients and time domain features. We use data from the public dataset SCUT-NAA, which contains ten different activities, and another public dataset, which records people falling. A random forest classification algorithm based on ensemble learning is used for activity recognition and fall detection. The results show that the combined vector of linear prediction coefficient and time domain activity amplitude feature obtained a 93% accuracy rate and the system evaluation index F1 of 0.92 on the SCUT-NAA dataset. Additionally, we achieved an accuracy rate of 97% in fall detection. Keywords Linear prediction coefficient . Human activity recognition . Fall detection . Feature extraction
* Ruixiang Li [email protected]
1
School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
Multimedia Tools and Applications
1 Introduction In recent years, human activity recognition has attracted the interest of researchers because of its wide potential areas for application. Human activity recognition is widely used in surveillance [10, 15, 21, 24], security [1, 19, 25], education [12], sports [6], entertainment [13], medical [16, 18], and other fields. In the medical field, for instance, patient’s activity status is monitored so that doctors may use this information in real time to prevent accidents. At the same time, as the population ages, more and more elderly people live alone, unattended, making falling down one of the biggest health hazards in their day-to-day lives. It is thus an important task to monitor and identify falling activities, in particular of the more elderly population. With the development of machine learning technology, more and more activities can be recognized with near perfect accuracy. Yet, despite the advances in
Data Loading...
