TY  - JOUR
ID  - SisLab1897
UR  - http://doi.org/10.1007/978-3-319-49073-1_39
A1  - Lu, Dang Nhac
A1  - Nguyen, Thu Trang
A1  - Ngo, Thi Thu Trang
A1  - Nguyen, Thi Hau
A1  - Nguyen, Ha Nam
Y1  - 2016///
N2  - In this paper, we propose an efficient and flexible framework for activity recognition based on smartphone sensors. We develop a mobile application that integrates data collection, training and recognition, feedback monitoring. This system allows user smartphones are randomly placed in any position and at any direction. In the proposed framework, a set of power based and frequency-based features is extracted from sensor data. Then, we deploy Random Forest, Naïve Bayes, K-Nearest Neighbor (KNN), Support Vector Ma-chine (SVM) classification algorithms for recognizing a set of user activities. Our framework dynamically takes into account real-time user feedbacks to increase the prediction accuracy. Our framework will be able to apply for intelligent mo-bile applications. A number of experiments were carried out to show the high ac-curacy of the proposed framework for detecting user activities when walking or driving a motorbike.
JF  - Advances in Information and Communication Technology
VL  - 538
SN  - 2194-5357
TI  - Mobile Online Activity Recognition System Based on Smartphone Sensors
SP  - 357
AV  - none
EP  - 366
ER  -