Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern Discovery
Understanding human movement patterns is of fundamental importance in transportation planning and management. We propose to examine complex public transit travel patterns over a large-scale transit network, which is challenging since it involves thousands of transit passengers and massive data from...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-09-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/8/10/434 |
| _version_ | 1819066455850745856 |
|---|---|
| author | Tong Zhang Jianlong Wang Chenrong Cui Yicong Li Wei He Yonghua Lu Qinghua Qiao |
| author_facet | Tong Zhang Jianlong Wang Chenrong Cui Yicong Li Wei He Yonghua Lu Qinghua Qiao |
| author_sort | Tong Zhang |
| collection | DOAJ |
| description | Understanding human movement patterns is of fundamental importance in transportation planning and management. We propose to examine complex public transit travel patterns over a large-scale transit network, which is challenging since it involves thousands of transit passengers and massive data from heterogeneous sources. Additionally, efficient representation and visualization of discovered travel patterns is difficult given a large number of transit trips. To address these challenges, this study leverages advanced machine learning methods to identify time-varying mobility patterns based on smart card data and other urban data. The proposed approach delivers a comprehensive solution to pre-process, analyze, and visualize complex public transit travel patterns. This approach first fuses smart card data with other urban data to reconstruct original transit trips. We use two machine learning methods, including a clustering algorithm to extract transit corridors to represent primary mobility connections between different regions and a graph-embedding algorithm to discover hierarchical mobility community structures. We also devise compact and effective multi-scale visualization forms to represent the discovered travel behavior dynamics. An interactive web-based mapping prototype is developed to integrate advanced machine learning methods with specific visualizations to characterize transit travel behavior patterns and to enable visual exploration of transit mobility patterns at different scales and resolutions over space and time. The proposed approach is evaluated using multi-source big transit data (e.g., smart card data, transit network data, and bus trajectory data) collected in Shenzhen City, China. Evaluation of our prototype demonstrates that the proposed visual analytics approach offers a scalable and effective solution for discovering meaningful travel patterns across large metropolitan areas. |
| first_indexed | 2024-12-21T16:02:38Z |
| format | Article |
| id | doaj.art-a19fffeada7741f081b0bdfa4eb84c76 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-12-21T16:02:38Z |
| publishDate | 2019-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-a19fffeada7741f081b0bdfa4eb84c762022-12-21T18:57:58ZengMDPI AGISPRS International Journal of Geo-Information2220-99642019-09-0181043410.3390/ijgi8100434ijgi8100434Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern DiscoveryTong Zhang0Jianlong Wang1Chenrong Cui2Yicong Li3Wei He4Yonghua Lu5Qinghua Qiao6State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaShenzhen Investigation and Research Institute Co., Ltd, Shenzhen 518026, ChinaChinese Academy of Surveying & Mapping, Beijing 100830, ChinaUnderstanding human movement patterns is of fundamental importance in transportation planning and management. We propose to examine complex public transit travel patterns over a large-scale transit network, which is challenging since it involves thousands of transit passengers and massive data from heterogeneous sources. Additionally, efficient representation and visualization of discovered travel patterns is difficult given a large number of transit trips. To address these challenges, this study leverages advanced machine learning methods to identify time-varying mobility patterns based on smart card data and other urban data. The proposed approach delivers a comprehensive solution to pre-process, analyze, and visualize complex public transit travel patterns. This approach first fuses smart card data with other urban data to reconstruct original transit trips. We use two machine learning methods, including a clustering algorithm to extract transit corridors to represent primary mobility connections between different regions and a graph-embedding algorithm to discover hierarchical mobility community structures. We also devise compact and effective multi-scale visualization forms to represent the discovered travel behavior dynamics. An interactive web-based mapping prototype is developed to integrate advanced machine learning methods with specific visualizations to characterize transit travel behavior patterns and to enable visual exploration of transit mobility patterns at different scales and resolutions over space and time. The proposed approach is evaluated using multi-source big transit data (e.g., smart card data, transit network data, and bus trajectory data) collected in Shenzhen City, China. Evaluation of our prototype demonstrates that the proposed visual analytics approach offers a scalable and effective solution for discovering meaningful travel patterns across large metropolitan areas.https://www.mdpi.com/2220-9964/8/10/434geovisual analyticsmachine learningsmart card datatransit corridormobility communitytrip |
| spellingShingle | Tong Zhang Jianlong Wang Chenrong Cui Yicong Li Wei He Yonghua Lu Qinghua Qiao Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern Discovery ISPRS International Journal of Geo-Information geovisual analytics machine learning smart card data transit corridor mobility community trip |
| title | Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern Discovery |
| title_full | Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern Discovery |
| title_fullStr | Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern Discovery |
| title_full_unstemmed | Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern Discovery |
| title_short | Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern Discovery |
| title_sort | integrating geovisual analytics with machine learning for human mobility pattern discovery |
| topic | geovisual analytics machine learning smart card data transit corridor mobility community trip |
| url | https://www.mdpi.com/2220-9964/8/10/434 |
| work_keys_str_mv | AT tongzhang integratinggeovisualanalyticswithmachinelearningforhumanmobilitypatterndiscovery AT jianlongwang integratinggeovisualanalyticswithmachinelearningforhumanmobilitypatterndiscovery AT chenrongcui integratinggeovisualanalyticswithmachinelearningforhumanmobilitypatterndiscovery AT yicongli integratinggeovisualanalyticswithmachinelearningforhumanmobilitypatterndiscovery AT weihe integratinggeovisualanalyticswithmachinelearningforhumanmobilitypatterndiscovery AT yonghualu integratinggeovisualanalyticswithmachinelearningforhumanmobilitypatterndiscovery AT qinghuaqiao integratinggeovisualanalyticswithmachinelearningforhumanmobilitypatterndiscovery |