A supervised learning based semantic location extraction method using mobile phone data

Various kinds of location-aware computing and applications are proliferating rapidly nowadays, which makes the location the most critical ingredient. However, on one hand, one location represented as the semantic meaning like “home” is more understandable than conveying the absolute physical coordinate; on the other hand, detected wireless data is a series of random sequence and the formed training vector has not equal-length feature, which may heavily leads to unstable accuracy of location extraction model because of varying human and environment factors. To robustly discover the user's semantic locations in dynamic wireless environment, we propose a novel Hidden Markov Model (HMM)-based Location Extraction algorithm called HLE, which adopts a supervised learning based method for extracting user's daily significant semantic locations using mobile phone data. We carry out the HLE algorithm on realistic wireless signal data, experimental results show that the proposed method is reasonable and effective for semantic location extraction in the real-world application.