Transfer Urban Human Mobility via POI Embedding over Multiple Cities

Abstract

Rapidly developing location acquisition technologies provide a powerful tool for understanding and predicting human mobility in cities, which is very significant for urban planning, traffic regulation, and emergency management. However, with the existing methodologies, it is still difficult to accurately predict millions of peoples’ mobility in a large urban area such as Tokyo, Shanghai, and Hong Kong, especially when collected data used for model training are often limited to a small portion of the total population. Obviously, human activities in city are closely linked with point-of-interest (POI) information, which can reflect the semantic meaning of human mobility. This motivates us to fuse human mobility data and city POI data to improve the prediction performance with limited training data, but current fusion technologies can hardly handle these two heterogeneous data. Therefore, we propose a unique POI-embedding mechanism, that aggregates the regional POIs by categories to generate an artificial POI-image for each urban grid and enriches each trajectory snippet to a four-dimensional tensor in an analogous manner to a short video. Then, we design a deep learning architecture combining CNN with LSTM to simultaneously capture both the spatiotemporal and geographical information from the enriched trajectories. Furthermore, transfer learning is employed to transfer mobility knowledge from one city to another, so that we can fully utilize other cities’ data to train a stronger model for the target city with only limited data available. Finally, we achieve satisfactory performance of human mobility prediction at the citywide level using a limited amount of trajectories as training data, which has been validated over five urban areas of different types and scales.

Big Data for Traffic Estimation and Prediction: A Survey of Data and Tools

“…Transfer learning is a potential solution for the data sparsity problem in different locations. A POI-embedding mechanism was proposed in [110] to fuse human mobility data and city POI data. Furthermore, CNN and LSTM were combined to capture both spatiotemporal and geographical information, and mobility knowledge was transferred from one city to another, which was proven effective for improving the prediction performance for the target city with only limited data available.…”

Automated Urban Planning for Reimagining City Configuration via Adversarial Learning: Quantification, Generation, and Evaluation

“…These works have had a lot of success, but they have one drawback: they require expert layout data in order to train AI models. In addition, some researchers use transfer learning to transfer spatial knowledge across many cities to increase the generalization of spatial AI models and learning efficiency [17,19]. These works are capable of perceiving human mobility patterns, which gives a decent foundation for urban planning, but they are unable to immediately develop successful urban layouts.…”

Analysis the Influencing Factors of Urban Traffic Flows by Using New and Emerging Urban Big Data and Deep Learning

“…Xu et al (2019) proposed a framework to identify urban mobility patterns based on POI data. Another study aggregated the regional POIs by categories to generate an artificial POI-image for each urban grid, which promotes the human mobility prediction at the citywide level (Jiang et al, 2021). In addition to POI, land cover of urban areas also influences the mobility trends.…”