Inferring the Accurate Locations of Noise Records in Mobile Phone Location Data

The positioning uncertainty of mobile phone location (MPL) data greatly influences location services and crowd behavior analysis. Although many achievements have been made in controlling its main sources (signal drift and ping-pong effects), several problems, such as single-oscillation patterns, insufficient position optimization, and a lack of effective evaluation, remain. In this study, a set of MPL data quality optimization methods are proposed. First, the characteristics of drift records and the oscillation patterns of ping-pong records are discussed. The quality of the MPL data is subsequently controlled with the proposed feature-based drift-record detection method, complex oscillation pattern-based ping-pong-record detection method, and cumulative duration weighting-based ping-pong-record optimization method. These methods are applied to the MPL dataset of a major operator in Nanjing city, and the optimization effect is evaluated with GPS data collected synchronously. The results show that the proposed detection and optimization methods can effectively improve the accuracy of MPL data.