Deep Neural Network-based Telco Outdoor Localization

When Telecommunication (Telco) networks provide phone call and data services for mobile users, measurement record (MR) data is generated by mobile devices during each call/session. MR data reports the connection states, e.g., signal strength, between mobile devices and nearby base stations. Given the MR data, the literature has proposed various Telco localization approaches, to localize mobile devices. Unfortunately, such approaches typically estimate the individual position independently, and could compromise the temporal and spatial locality in underlying mobility patterns. To address this issue, in this paper, we propose a deep neural network-based localization approach, namely RecuLSTM, to automatically extract contextual features and predict the positions of mobile devices from an input sequence of MR data. Our preliminary experiment validates that RecuLSTM greatly outperforms three recent works [1, 2, 4] which suffer from 3.2×, 1.91× and 3.56× median errors on the dataset in a 2G GSM suburban area, respectively.