| Title |
Frequent Origin-Destination Sequence Pattern Analysis from Taxi Trajectories |
| Authors |
이태영(Lee, Tae Young) ; 전승배(Jeon, Seung Bae) ; 정명훈(Jeong, Myeong Hun) ; 최연웅(Choi, Yun Woong) |
| DOI |
https://doi.org/10.12652/Ksce.2019.39.3.0461 |
| Keywords |
군집분석;순차패턴분석;기종점분석;이동데이터 Clustering analysis;Sequence pattern analysis;Origin-destination analysis;Movement data |
| Abstract |
Advances in location-aware and IoT (Internet of Things) technology increase the rapid generation of massive movement data. Knowledge discovery from massive movement data helps us to understand the urban flow and traffic management. This paper proposes a method to analyze frequent origin-destination sequence patterns from irregular spatiotemporal taxi pick-up locations. The proposed method starts by conducting cluster analysis and then run a frequent sequence pattern analysis based on identified clusters as a base unit. The experimental data is Seoul taxi trajectory data between 7 a.m. and 9 a.m. during one week. The experimental results present that significant frequent sequence patterns occur within Gangnam. The significant frequent sequence patterns of different regions are identified between Gangnam and Seoul City Hall area. Further, this study uses administrative boundaries as a base unit. The results based on administrative boundaries fails to detect the frequent sequence patterns between different regions. The proposed method can be applied to decrease not only taxis' empty-loaded rate, but also improve urban flow management. |