No abstract

No abstract

International audienceSensing cost and data quality are two primary concerns in mobile crowdsensing. In this article, we propose a new crowdsensing paradigm, sparse mobile crowdsensing, which leverages the spatial and temporal correlation among the data sensed in different sub-areas to significantly reduce the required number of sensing tasks allocated, thus lowering overall sensing cost (e.g., smartphone energy consumption and incentives) while ensuring data quality. Sparse mobile crowdsensing applications intelligently select only a small portion of the target area for sensing while inferring the data of the remaining unsensed area with high accuracy. We discuss the fundamental research challenges in sparse mobile crowdsensing, and design a general framework with potential solutions to the challenges. To verify the effectiveness of the proposed framework, a sparse mobile crowdsensing prototype for temperature and traffic monitoring is implemented and evaluated. With several future research directions identified in sparse mobile crowdsensing, we expect that more research interests will be stimulated in this novel crowdsensing paradig

If it is the author's pre-published version, changes introduced as a result of publishing processes such as copy-editing and formatting may not be reflected in this document. For a definitive version of this work, please refer to the published version.

Recommender systems have been playing an increasingly important role in our daily life due to the explosive growth of information. Accuracy and explainability are two core aspects when we evaluate a recommendation model and have become one of the fundamental trade-offs in machine learning. In this paper, we propose to alleviate the trade-off between accuracy and explainability by developing an explainable deep model that combines the advantages of deep learning-based models and existing explainable methods. The basic idea is to build an initial network based on an explainable deep hierarchy (e.g., Microsoft Concept Graph) and improve the model accuracy by optimizing key variables in the hierarchy (e.g., node importance and relevance). To ensure accurate rating prediction, we propose an attentive multi-view learning framework. The framework enables us to handle sparse and noisy data by co-regularizing among different feature levels and combining predictions attentively. To mine readable explanations from the hierarchy, we formulate personalized explanation generation as a constrained tree node selection problem and propose a dynamic programming algorithm to solve it. Experimental results show that our model outperforms state-of-the-art methods in terms of both accuracy and explainability.

Device-free sensing using ubiquitous Wi-Fi signals has recently attracted lots of attention. Among the sensed information, two important basic contexts are (i) whether a target is still or not and (ii) where the target is located. Continuous monitoring of these contexts provides us with rich datasets to obtain important high-level semantics of the target such as living habits, physical conditions and emotions. However, even to obtain these two basic contexts, offline training and calibration are needed in traditional methods, limiting the real-life adoption of the proposed sensing systems. In this paper, using the commodity Wi-Fi infrastructure, we propose a training-free human vitality sensing platform, WiVit. It could capture these two contexts together with the target's movements speed information in real-time without any human effort in offline training or calibration. Based on our extensive experiments in three typical indoor environments, the precision of activity detection is higher than 98% and the area detection accuracy is close to 100%. Moreover, we implement a short-term activity recognition system on our platform to recognize 4 types of actions, and we can reach an average accuracy of 94.2%. We also take a feasibility study of monitoring long-term activities of daily living to show our platform's potential applications in practice.

No abstract

No abstract