A pervasive indoor and outdoor scenario identification algorithm based on the sensing data and human activity
Yang An Zhang, Zhao Fang, Wenhua Shao, Haiyong Luo · 2016
The location and context switching, especially the indoor and outdoor scenario switching, provide basic and original information for various mobile applications. Diverse smartphone placements and limited battery supply pose challenge for the accurate and robust indoor-outdoor identification. In this paper, a pervasive indoor and outdoor scenario identification algorithm is proposed, which utilizes both the sensing data collected by the commodity smartphones and recognized human activity information. The indoor and outdoor scenario identification is modelled as a binary classification problem. To better utilize the collected sensor data and inferred human activities, two time-dependent Adaboost classifiers are developed to perform stateless and instance-based scene detection. The stateless detection result is further used as the observation of a hidden Markov model (HMM) to obtain the final scene estimation. The adoption of the stateful HMM filter can effectively eliminate the occasional noises and improve detection accuracy. Furthermore, to meet the high-accuracy detection demand on the indoor-outdoor transition scenario, invoking GPGSV on demand is introduced to improve the detection confidence. Extensive experimental results confirm that the proposed pervasive indoor-outdoor identification algorithm outperforms the state-of-the-art JODetector with more than 97% detection accuracy under various weather condition and smartphone placements, especially in the cloudy daytime, at night and being put in pocket.