In recent years, there has been a significant growth of context-aware applications, which extract the user's context from multiple embedded sensors in smartphones and wearable sensors. However, running multiple context-aware applications simultaneously causes extensive battery drainage for mobile devices. To alleviate the energy limitation in multi-context setting, we propose EGO: an ontology-based framework for group sensor selection to achieve synergy across applications while trading off energy consumption, accuracy, and delay in context recognition. A new context recognition ontology is designed to capture context recognition models. It captures the alternative groups of sensors for each context and the parameters for context recognition models. EGO includes an adaptive sensor selection mechanism that selects the appropriate sensors based on the current user state, the available resources, and the requested accuracies by running applications. The framework provides an open architecture that allows integration with other sensor optimization modules for sensor scheduling. EGO is validated using a real test-bed implemented on an Android platform that provides accessibility to on-board mobile sensors and external sensors. Results show that EGO provides better trade-off than previous state-of-the-art methods. Furthermore, EGO provides 63 percent energy saving with comparable accuracy when compared to the most accurate group of sensors.

Monitoring context depends on continuous collection of raw data from sensors which are either embedded in smart mobile devices or worn by the user. However, continuous sensing constitutes a major source of energy consumption; on the other hand, lowering the sensing rate may lead to missing the detection of critical contextual events. In this paper, we propose VCAMS: a Viterbi-based Context Aware Mobile Sensing mechanism that adaptively finds an optimized sensing schedule to decide when to trigger the sensors for data collection while trading off the sensing energy and the delay to detect a state change. The sensing schedule is adaptive from two aspects: 1) the decision rules are learned from the user's past behavior, and 2) these rules are updated over real time whenever there is a significant change in the user's behavior. VCAMS is validated using multiple experiments, which include evaluation of model success when considering binary and multi-user states. We also implemented VCAMS on an Android-based device to estimate its computational costs under realistic operational conditions. Test results show that our proposed strategy provides better trade-off than previous state-of-the-art methods under comparable conditions. Furthermore, the method provides 78 percent energy saving when compared to continuous sensing.

Modern mobile pervasive applications focus on context awareness that monitors a diverse range of personal domains. In order to infer contextual information, most of these applications require the collection of raw data from sensors which are either embedded in personal smartphones or worn by the user. Critical context-aware applications rely on continuous accurate monitoring of the user's current context. Continuous sensing mechanisms in sensors cost high energy consumption to support accurate contextual detection. Hence, there is a trade-off between the classification accuracy and the energy consumption. In this paper, we exploit the advantages of Deep Neural Network (DNN) with ensemble classification of other complementary machine learning approaches to determine the best sensor sampling frequency for the recognition of a given context. DNN relies on raw data for classification while the other complementary methods (such as Decision Tree and Naïve Bayes) use feature recognition to classify data. Therefore, our approach provides a range of granularity from raw data. We prove the robustness of our approach in experiments which show high accuracy in context recognition. In addition, real experiments demonstrate the energy gains of the proposed algorithm which reach 87% reduction in energy consumption when compared to continuous sensing.