| dc.description.abstract | The sedentary lifestyle is becoming popular especially for intellectual works. Although a physical inactivity lifestyle may cause many unexpected illnesses, it is complicated to build up a positive lifestyle due to the lack of reminder systems to manage and monitor physical activities of people. This research represents an effective way for daily activity monitoring using accelerometer and gyroscope sensors embedded in a smartphone. Signals were recorded from accelerometer and gyroscope sensors while a user was wearing the smartphone and performing different activities (going downstairs, going upstairs, sitting with the phone in a pocket, driving and putting the phone on the table). For offline analysis, the classification algorithms with k-nearest-neighbor (kNN), artificial neural network (ANN) and support vector machine (SVM) were applied to recognize user’s activities. The overall accuracy of recognizing five activities was 74% for kNN, 75.3% for ANN and 94.5% for SVM respectively. The kNN and SVM classification were later on implemented on the smartphone for analysis and comparison. Based on the recognized activities during a day, users are able to manage their daily activities for a better life.
Keywords — Smartphone, activity recognition, activity monitoring. | en_US |
