Metagraph-Based Life Pattern Clustering With Big Human Mobility Data

Life pattern clustering is essential for abstracting the groups' characteristics of daily life patterns and activity regularity. Based on millions of GPS records, this research proposes a framework on the life pattern clustering which can efficiently identify the groups that have similar life patterns. The proposed method can retain original features of individual life pattern data without aggregation. Metagraph-based data structure is proposed for presenting the diverse life pattern. Spatial-temporal similarity includes significant places semantics, time-sequential properties and frequency are integrated into this data structure, which captures the uncertainty of an individual and the diversities between individuals. Non-negative-factorization-based method is utilized for reducing the dimension. The results show that our proposed method can effectively identify the groups that have similar life pattern in long term and takes advantage in computation efficiency and representational capacity compared with the traditional methods. We reveal the representative life pattern groups and analyze the group characteristics of human life patterns during different periods and different regions. We believe our work helps in future infrastructure planning, services improvement and policy making related to urban and transportation, thus promoting a humanized and sustainable city.

Automated summary

Life pattern clustering is crucial for capturing the characteristics and regularity of daily life patterns. This study proposes a framework that efficiently identifies groups with similar life patterns based on millions of GPS records. The proposed method retains the original features of individual life pattern data and employs a metagraph-based data structure to capture the spatial-temporal similarity and diversity between individuals. Non-negative-factorization-based dimension reduction is used and the results show that our method effectively identifies similar life pattern groups, showcasing better computation efficiency and representational capacity compared to traditional methods. The insights gained from analyzing group characteristics can aid future urban and transportation planning, service improvement, and policy-making.