Abstract
Smartphones have emerged as a revolutionary technology for monitoring everyday life, and they have played an important role in Human Activity Recognition (HAR) due to its ubiquity. The sensors embedded in these devices allows recognizing human behaviors using machine learning techniques. However, not all solutions are feasible for implementation in smartphones, mainly because of its high computational cost. In this context, the proposed method, called HAR-SR, introduces information theory quantifiers as new features extracted from sensors data to create simple activity classification models, increasing in this way the efficiency in terms of computational cost. Three public databases (SHOAIB, UCI, WISDM) are used in the evaluation process. The results have shown that HAR-SR can classify activities with 93% accuracy when using a leave-one-subject-out cross-validation procedure (LOSO).
Highlights
Recent advances in sensing technologies have made smartphones one of the most promising devices to the real-time monitoring of human behaviors in different domains such as health care, fitness track, behavior detection, elderly care, and rehabilitation [1,2,3,4]
We propose a low-cost solution called Human Activity Recognition based on Symbolic Representation HAR-SR), which is capable of extracting features from sensors data using symbolic representation algorithms by transforming a time series, represented by real values obtained from sensors, into a set of symbols belonging to the discrete domain
The results presented in Ignatov, Lockhart and Weiss show that classifiers tend to lose performance when using the leave-one-subject-out cross-validation (LOSO) instead of k-fold cross-validation (k-CV) validation procedure
Summary
Recent advances in sensing technologies have made smartphones one of the most promising devices to the real-time monitoring of human behaviors in different domains such as health care, fitness track, behavior detection, elderly care, and rehabilitation [1,2,3,4]. For instance, the recognition of physical activities from smartphone sensor data have contributed to avoiding negative outcomes linked with a sedentary lifestyle. The task of human activity recognition (HAR) consists mainly of four steps: sensing (data acquisition), segmentation, feature extraction, and classification [2,5,6]. While all these steps are important, feature extraction and selection are the core of most studies in the HAR area [1,6,7].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
