Smartphones have emerged as a revolutionary technology for monitoring everydaylife, and they have played an important role in Human Activity Recognition (HAR) due to itsubiquity. The sensors embedded in these devices allows recognizing human behaviors using machinelearning techniques. However, not all solutions are feasible for implementation in smartphones,mainly because of its high computational cost. In this context, the proposed method, called HAR-SR,introduces information theory quantifiers as new features extracted from sensors data to create simpleactivity classification models, increasing in this way the efficiency in terms of computational cost.Three public databases (SHOAIB, UCI, WISDM) are used in the evaluation process. The results haveshown that HAR-SR can classify activities with 93% accuracy when using a leave-one-subject-outcross-validation procedure (LOSO).