A Spatiotemporal Constraint Non-Negative Matrix Factorization Model to Discover Intra-Urban Mobility Patterns from Taxi Trips

Taxi services provide an urban transport option to citizens. Massive taxi trajectories contain rich information for understanding human travel activities, which are essential to sustainable urban mobility and transportation. The origin and destination (O-D) pairs of urban taxi trips can reveal the spatiotemporal patterns of human mobility and then offer fundamental information to interpret and reform formal, functional, and perceptual regions of cities. Matrices are one of the most effective models to represent taxi trajectories and O-D trips. Among matrix representations, non-negative matrix factorization (NMF) gives meaningful interpretations of complex latent relationships. However, the independence assumption for observations is violated by spatial and temporal autocorrelation in taxi flows, which is not compensated in classical NMF models. In order to discover human intra-urban mobility patterns, a novel spatiotemporal constraint NMF (STC-NMF) model that explicitly solves spatial and temporal dependencies is proposed in this paper. It factorizes taxi flow matrices in both spatial and temporal aspects, thus revealing inherent spatiotemporal patterns. With three-month taxi trajectories harvested in Beijing, China, the STC-NMF model is employed to investigate taxi travel patterns and their spatial interaction modes. As the results, four departure patterns, three arrival patterns, and eight spatial interaction patterns during weekdays and weekends are discovered. Moreover, it is found that intensive movements within certain time windows are significantly related to region functionalities and the spatial interaction flows exhibit an obvious distance decay tendency. The outcome of the proposed model is more consistent with the inherent spatiotemporal characteristics of human intra-urban movements. The knowledge gained in this research would be useful to taxi services and transportation management for promoting sustainable urban development.

[1]  D. Simon,et al.  Context-Adapted Urban Planning for Rapid Transitioning of Personal Mobility towards Sustainability: A Systematic Literature Review , 2019, Sustainability.

[2]  Junichiro Mori,et al.  Detecting and understanding urban changes through decomposing the numbers of visitors’ arrivals using human mobility data , 2019, Journal of Big Data.

[3]  Eduardo Graells-Garrido,et al.  Inferring modes of transportation using mobile phone data , 2018, EPJ Data Science.

[4]  Qingming Huang,et al.  Discovering Fine-Grained Spatial Pattern From Taxi Trips: Where Point Process Meets Matrix Decomposition and Factorization , 2018, IEEE Transactions on Intelligent Transportation Systems.

[5]  Chao Chen,et al.  TripImputor: Real-Time Imputing Taxi Trip Purpose Leveraging Multi-Sourced Urban Data , 2018, IEEE Transactions on Intelligent Transportation Systems.

[6]  Junfeng Zhao,et al.  Trip2Vec: a deep embedding approach for clustering and profiling taxi trip purposes , 2018, Personal and Ubiquitous Computing.

[7]  P. Borgnat,et al.  Tracking the evolution of temporal patterns of usage in bicycle-Sharing systems using nonnegative matrix factorization on multiple sliding windows , 2018 .

[8]  Yong Gao,et al.  Optimize taxi driving strategies based on reinforcement learning , 2018, Int. J. Geogr. Inf. Sci..

[9]  Shunjiang Ni,et al.  Uncovering stable and occasional human mobility patterns: A case study of the Beijing subway , 2018 .

[10]  Pengfei Wang,et al.  Human Mobility Synchronization and Trip Purpose Detection with Mixture of Hawkes Processes , 2017, KDD.

[11]  Zhong Zheng,et al.  Scaling laws of spatial visitation frequency: Applications for trip frequency prediction , 2017, Comput. Environ. Urban Syst..

[12]  Diansheng Guo,et al.  Urban event detection with big data of taxi OD trips: A time series decomposition approach , 2017, Trans. GIS.

[13]  Keechoo Choi,et al.  Dually sustainable urban mobility option: Shared-taxi operations with electric vehicles , 2017 .

[14]  Miaoyi Li,et al.  Examining the Interaction of Taxi and Subway Ridership for Sustainable Urbanization , 2017 .

[15]  Chao Yang,et al.  A Bayesian mixture model for short-term average link travel time estimation using large-scale limited information trip-based data , 2016 .

[16]  Chaogui Kang,et al.  Understanding operation behaviors of taxicabs in cities by matrix factorization , 2016, Comput. Environ. Urban Syst..

[17]  Yu Liu,et al.  Inferring trip purposes and uncovering travel patterns from taxi trajectory data , 2016 .

[18]  Chaogui Kang,et al.  Incorporating spatial interaction patterns in classifying and understanding urban land use , 2016, Int. J. Geogr. Inf. Sci..

[19]  Dominique Gillis,et al.  How to Monitor Sustainable Mobility in Cities? Literature Review in the Frame of Creating a Set of Sustainable Mobility Indicators , 2015 .

[20]  Hideyuki Suzuki,et al.  Tracking Time Evolution of Collective Attention Clusters in Twitter: Time Evolving Nonnegative Matrix Factorisation , 2015, PloS one.

[21]  Moshe Givoni,et al.  Sustainable mobility: Six research routes to steer transport policy , 2015, Nature.

[22]  Zhaohui Wu,et al.  City-Scale Social Event Detection and Evaluation with Taxi Traces , 2015, ACM Trans. Intell. Syst. Technol..

[23]  Yu Zheng,et al.  Trajectory Data Mining , 2015, ACM Trans. Intell. Syst. Technol..

[24]  Xiang Li,et al.  Detecting and Analyzing Mobility Hotspots using Surface Networks , 2014, Trans. GIS.

[25]  Xinlei Chen,et al.  Spatially correlated nonnegative matrix factorization , 2014, Neurocomputing.

[26]  Yong Yu,et al.  Inferring gas consumption and pollution emission of vehicles throughout a city , 2014, KDD.

[27]  Ruojing W. Scholz,et al.  Detection of dynamic activity patterns at a collective level from large-volume trajectory data , 2014, Int. J. Geogr. Inf. Sci..

[28]  Nicolas Gillis,et al.  The Why and How of Nonnegative Matrix Factorization , 2014, ArXiv.

[29]  Yifan Zhang,et al.  Correlation consistency constrained probabilistic matrix factorization for social tag refinement , 2013, Neurocomputing.

[30]  Daqing Zhang,et al.  From taxi GPS traces to social and community dynamics , 2013, ACM Comput. Surv..

[31]  Xi Liu,et al.  Revealing daily travel patterns and city structure with taxi trip data , 2013, ArXiv.

[32]  Nicholas Jing Yuan,et al.  T-Finder: A Recommender System for Finding Passengers and Vacant Taxis , 2013, IEEE Transactions on Knowledge and Data Engineering.

[33]  Sanjeev Arora,et al.  A Practical Algorithm for Topic Modeling with Provable Guarantees , 2012, ICML.

[34]  Peng Gao,et al.  Discovering Spatial Patterns in Origin‐Destination Mobility Data , 2012, Trans. GIS.

[35]  Pietro Liò,et al.  Collective Human Mobility Pattern from Taxi Trips in Urban Area , 2012, PloS one.

[36]  Yuan Tian,et al.  Understanding intra-urban trip patterns from taxi trajectory data , 2012, Journal of Geographical Systems.

[37]  Thomas S. Huang,et al.  Graph Regularized Nonnegative Matrix Factorization for Data Representation. , 2011, IEEE transactions on pattern analysis and machine intelligence.

[38]  Lin Sun,et al.  Hunting or waiting? Discovering passenger-finding strategies from a large-scale real-world taxi dataset , 2011, 2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops).

[39]  Xing Xie,et al.  Collaborative location and activity recommendations with GPS history data , 2010, WWW '10.

[40]  K. J. Ray Liu,et al.  Multiplicative update rules for nonnegative matrix factorization with co-occurrence constraints , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[41]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[42]  Bin Jiang,et al.  Characterizing the human mobility pattern in a large street network. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[43]  Lucie N. Hutchins,et al.  Position-dependent motif characterization using non-negative matrix factorization , 2008, Bioinform..

[44]  Michael W. Berry,et al.  Algorithms and applications for approximate nonnegative matrix factorization , 2007, Comput. Stat. Data Anal..

[45]  Pablo Tamayo,et al.  Metagenes and molecular pattern discovery using matrix factorization , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[46]  Jordi Vitrià,et al.  Non-negative Matrix Factorization for Face Recognition , 2002, CCIA.

[47]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[48]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[49]  Gérard Govaert,et al.  Convergence of an EM-type algorithm for spatial clustering , 1998, Pattern Recognit. Lett..

[50]  Gene H. Golub,et al.  Matrix computations (3rd ed.) , 1996 .

[51]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[52]  Peter J. Rousseeuw,et al.  Clustering by means of medoids , 1987 .

[53]  W. Tobler.  A Computer Movie Simulating Urban Growth in the Detroit Region , 1970 .