In this paper, we explore the role

In this paper, we explore the role of these two devices inrecognizing 13 different human activities using three classi-fiers, such as SVM, KNN and decision tree (J48). We studythe strengths and weaknesses of these two devices in terms ofrecognition performance. We are interested in their combina-tion because they provide us with richer context informationdue to their different positions on the human body. We explorean intelligent fusion of these two devices in relationship withdifferent sampling rates, that can lead to energy efficiency.We also study the impact of increasing window sizes whilesampling the sensors for the recognition performance of theseactivities. Moreover, we study the effects that the possible syn-chronization delays can have on the recognition performance.We summarize the main contributions of this paper as follows