Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering
Mining spatiotemporal mobility patterns is crucial for optimizing urban planning, enhancing transportation systems, and improving public safety by providing useful insights into human movement and behavior over space and time. As an unsupervised learning technique, time series clustering has gained...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/13/11/374 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846153407764627456 |
|---|---|
| author | Ziyi Zhang Diya Li Zhe Zhang Nick Duffield |
| author_facet | Ziyi Zhang Diya Li Zhe Zhang Nick Duffield |
| author_sort | Ziyi Zhang |
| collection | DOAJ |
| description | Mining spatiotemporal mobility patterns is crucial for optimizing urban planning, enhancing transportation systems, and improving public safety by providing useful insights into human movement and behavior over space and time. As an unsupervised learning technique, time series clustering has gained considerable attention due to its efficiency. However, the existing literature has often overlooked the inherent characteristics of mobility data, including high-dimensionality, noise, outliers, and time distortions. This oversight can lead to potentially large computational costs and inaccurate patterns. To address these challenges, this paper proposes a novel neural network-based method integrating temporal autoencoder and dynamic time warping-based K-means clustering algorithm to mutually promote each other for mining spatiotemporal mobility patterns. Comparative results showed that our proposed method outperformed several time series clustering techniques in accurately identifying mobility patterns on both synthetic and real-world data, which provides a reliable foundation for data-driven decision-making. Furthermore, we applied the method to monthly county-level mobility data during the COVID-19 pandemic in the U.S., revealing significant differences in mobility changes between rural and urban areas, as well as the impact of public response and health considerations on mobility patterns. |
| format | Article |
| id | doaj-art-fb8d0e4ca5f54aa89addb1c40f492413 |
| institution | Kabale University |
| issn | 2220-9964 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj-art-fb8d0e4ca5f54aa89addb1c40f4924132024-11-26T18:06:20ZengMDPI AGISPRS International Journal of Geo-Information2220-99642024-10-01131137410.3390/ijgi13110374Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series ClusteringZiyi Zhang0Diya Li1Zhe Zhang2Nick Duffield3Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USADepartment of Geography, Texas A&M University, College Station, TX 77843, USADepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USADepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USAMining spatiotemporal mobility patterns is crucial for optimizing urban planning, enhancing transportation systems, and improving public safety by providing useful insights into human movement and behavior over space and time. As an unsupervised learning technique, time series clustering has gained considerable attention due to its efficiency. However, the existing literature has often overlooked the inherent characteristics of mobility data, including high-dimensionality, noise, outliers, and time distortions. This oversight can lead to potentially large computational costs and inaccurate patterns. To address these challenges, this paper proposes a novel neural network-based method integrating temporal autoencoder and dynamic time warping-based K-means clustering algorithm to mutually promote each other for mining spatiotemporal mobility patterns. Comparative results showed that our proposed method outperformed several time series clustering techniques in accurately identifying mobility patterns on both synthetic and real-world data, which provides a reliable foundation for data-driven decision-making. Furthermore, we applied the method to monthly county-level mobility data during the COVID-19 pandemic in the U.S., revealing significant differences in mobility changes between rural and urban areas, as well as the impact of public response and health considerations on mobility patterns.https://www.mdpi.com/2220-9964/13/11/374spatiotemporal data miningmobility patternstime series clusteringdeep learning |
| spellingShingle | Ziyi Zhang Diya Li Zhe Zhang Nick Duffield Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering ISPRS International Journal of Geo-Information spatiotemporal data mining mobility patterns time series clustering deep learning |
| title | Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering |
| title_full | Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering |
| title_fullStr | Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering |
| title_full_unstemmed | Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering |
| title_short | Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering |
| title_sort | mining spatiotemporal mobility patterns using improved deep time series clustering |
| topic | spatiotemporal data mining mobility patterns time series clustering deep learning |
| url | https://www.mdpi.com/2220-9964/13/11/374 |
| work_keys_str_mv | AT ziyizhang miningspatiotemporalmobilitypatternsusingimproveddeeptimeseriesclustering AT diyali miningspatiotemporalmobilitypatternsusingimproveddeeptimeseriesclustering AT zhezhang miningspatiotemporalmobilitypatternsusingimproveddeeptimeseriesclustering AT nickduffield miningspatiotemporalmobilitypatternsusingimproveddeeptimeseriesclustering |