Activity recognition in WSN: A data-driven approach

Activity recognition is a key component in identifying the context of a user for providing services based on the application. In this study, we propose a model that is based on the recognition of users´ activities through wireless sensors network technologies. The model is composed of four components: set of sensors, set of activities, backend server with machine learning algorithms and a GUI application for the interaction with the user. New sensors can be added to the system based on the novel activities. In order to train the model, a sequence of steps involved in an activity need to be performed and then the model is applied for the identification of the same activity in future and visualize through GUI application. A prototype is developed to show the usability of the proposed model. As a pilot testing only accelerometer data of android phone is used to identify the activities of daily living (ADL); sitting, standing, walking and jogging. The model is trained by getting the sensors data while performing activities and tested on real data. A good accuracy of results i.e. about 96% on average is achieved in all activities.