Online context recognition with mobile phone sensing

Activity Recognition (AR) or in other saying Context Recognition is an active area of research in the domain of pervasive and mobile computing that has direct applications about life quality and health of the users. Previous studies aim to classify different daily human activities with high accuracy rates using various types of sensors. Becoming a substantial part in our daily lives with their sensing capabilities, smartphones are becoming increasingly sophisticated and the latest generations of smart cell phones now incorporate many diverse and powerful sensors. Therefore, they are now considered feasible platforms that enable people to make use of AR technologies without being obliged to use or wear some extra devices. Nevertheless, due to power and computational constraints of these devices, it becomes a challenging task to attain accurate results by using power and CPU-intensive classifiers. In this study, we present a research based on other works in the literature that analyze the performance of the classification methods for online AR systems on smart phones. The previous studies generally focus on single phone location of the users despite the fact that users carry their phones in various positions. Hence, we also focus on phone position uncertainty problem and compare the classification results with position independent and position dependent classification models. Finally, we propose our own implementations to make and run an activity recognition system on an Android based smartphone.