Advertisement
Published in:
2017 | OriginalPaper | Chapter
Mobile Online Activity Recognition System Based on Smartphone Sensors
Authors : Dang-Nhac Lu, Thu-Trang Nguyen, Thi-Thu-Trang Ngo, Thi-Hau Nguyen, Ha-Nam Nguyen
Published in: Advances in Information and Communication Technology
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
In this paper, we propose an efficient and flexible framework for activity recognition based on smartphone sensors, so called Mobile Online Activity Recognition System (MOARS). This system comprises data collection, training, activity recognition, and feedback monitoring. It allows users to put their smartphones in any position and at any direction. In our proposed framework, a set of power-based and frequency-based features is extracted from sensor data. Then, Random Forest, Naïve Bayes, K-Nearest Neighbor (KNN), and Support Vector Machine (SVM) classification algorithms are deployed for recognizing a set of user activities. Our framework dynamically takes into account real-time user feedbacks to increase the accuracy of activity prediction. This framework is able to apply for intelligent mobile applications. A number of experiments are carried out to show the high accuracy of MOARS in detecting user activities when walking or driving a motorbike.