A context detection approach using GPS module and emerging sensors in smartphone platform

Nowadays smartphones are equipped with various sensors and powerful processing modules, and are accessible to flexible communication networks, thus enabling complex applications such as context awareness, activity recognition, health care monitoring and so forth. These applications typically require contextual information to optimize the effectiveness, e.g. indoor/outdoor identification. This paper develops an indoor/outdoor detection method based on a generic smartphone platform, utilizing the information extracted from the internal clock, GPS module and light intensity sensor. The vote principle is used in the detection. The approach has been tested in multiple locations in order to evaluate performance. This includes residences, office space, roads, restaurants, markets and so forth. Two kinds of detection results consisting of static and walking scenarios are shown in the paper. This method can output detection results with good accuracy in both day and night and all weather conditions. The approach can operate on different smartphone profiles from low-end to high-end. An optimized method also presents for some advanced smartphones with GPS satellite signal noise ratio output, which has been shown more effective in real-time response and detection accuracy.