DMM: fast map matching for cellular data

Map matching for cellular data is to transform a sequence of cell tower locations to a trajectory on a road map. It is an essential processing step for many applications, such as traffic optimization and human mobility analysis. However, most current map matching approaches are based on Hidden Markov Models (HMMs) that have heavy computation overhead to consider high-order cell tower information. This paper presents a fast map matching framework for cellular data, named as DMM, which adopts a recurrent neural network (RNN) to identify the most-likely trajectory of roads given a sequence of cell towers. Once the RNN model is trained, it can process cell tower sequences as making RNN inference, resulting in fast map matching speed. To transform DMM into a practical system, several challenges are addressed by developing a set of techniques, including spatial-aware representation of input cell tower sequences, an encoder-decoder framework for map matching model with variable-length input and output, and a reinforcement learning based model for optimizing the matched outputs. Extensive experiments on a large-scale anonymized cellular dataset reveal that DMM provides high map matching accuracy (precision 80.43% and recall 85.42%) and reduces the average inference time of HMM-based approaches by 46.58×.