Technological advances in sensing and portable computing devices and wireless communication has lead to an increase in the number and variety of sensing enabled devices (e.g. smartphones or sensing garments). Pervasive computing and activity recognition systems should be able to take advantage of these sensors, even if they are not always available, or appear during the system operation. These sensors can be integrated into an ensemble where information from each sensor is then fused to obtain the system decisions. There is therefore a need for mechanisms to select which sensors should compose the ensemble, as well as techniques for dynamically reconfigure the ensemble so as to integrate new sensors. From the machine learning point of view, this approach corresponds to the combination of classifiers where measures of the accuracy and diversity of the ensemble are used to select the elements that may lead to the highest performance. Recent works have proposed measures of accuracy and diversity based on an information theoretical approach. In this paper we study the use of these measures for selecting ensembles in activity recognition based on body sensor networks. In addition to compare the obtained performance with traditional diversity measures (e.g., Q-, κ-statistics) we also present mechanisms to exploit these measures for the dynamic reconfiguration of the ensemble and detection of changes in the network (e.g. due to sensor noise or malfunction).