Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi Trajectories
Emerging on-line reservation services and special car services have greatly affected the development of the taxi industry. Surprisingly, taking a taxi is still a significant problem in many large cities. In this paper, we present an effective solution based on the Hidden Markov Model to predict the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/8/7/295 |
| _version_ | 1817984753924571136 |
|---|---|
| author | Chunchun Hu Jean-Claude Thill |
| author_facet | Chunchun Hu Jean-Claude Thill |
| author_sort | Chunchun Hu |
| collection | DOAJ |
| description | Emerging on-line reservation services and special car services have greatly affected the development of the taxi industry. Surprisingly, taking a taxi is still a significant problem in many large cities. In this paper, we present an effective solution based on the Hidden Markov Model to predict the upcoming services of vacant taxis that appear at some fixed locations and at specific times. The model introduces a weighted confusion matrix and a modified Viterbi algorithm, combining the factors of time of day and traffic conditions. In our framework, the hotspot or hidden states extraction is implemented through kernel density estimation (KDE) and fuzzy partitioning of traffic zones is done via a Fuzzy C Means (FCM) algorithm. We implement the proposed model on a large-scale dataset of taxi trajectories in Beijing. In this use case, tests demonstrate the high accuracy of the modeling framework in predicting the upcoming services of vacant taxis. We further analyze the factors affecting the predictive accuracy via a prediction accuracy analysis and prediction location evaluation. The findings of this paper can provide intelligence for the improvement of taxi services, to increase the passenger capacity of taxis and also to improve the probability of passengers finding taxis. |
| first_indexed | 2024-04-13T23:48:58Z |
| format | Article |
| id | doaj.art-5fe125e8bad744698dea14c53b1d8634 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-04-13T23:48:58Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-5fe125e8bad744698dea14c53b1d86342022-12-22T02:24:11ZengMDPI AGISPRS International Journal of Geo-Information2220-99642019-06-018729510.3390/ijgi8070295ijgi8070295Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi TrajectoriesChunchun Hu0Jean-Claude Thill1School of Geodesy and Geomatics, Wuhan University, Wuhan 430072, ChinaDepartment of Geography & Earth Sciences, University of North Carolina at Charlotte, Charlotte, NC 28223, USAEmerging on-line reservation services and special car services have greatly affected the development of the taxi industry. Surprisingly, taking a taxi is still a significant problem in many large cities. In this paper, we present an effective solution based on the Hidden Markov Model to predict the upcoming services of vacant taxis that appear at some fixed locations and at specific times. The model introduces a weighted confusion matrix and a modified Viterbi algorithm, combining the factors of time of day and traffic conditions. In our framework, the hotspot or hidden states extraction is implemented through kernel density estimation (KDE) and fuzzy partitioning of traffic zones is done via a Fuzzy C Means (FCM) algorithm. We implement the proposed model on a large-scale dataset of taxi trajectories in Beijing. In this use case, tests demonstrate the high accuracy of the modeling framework in predicting the upcoming services of vacant taxis. We further analyze the factors affecting the predictive accuracy via a prediction accuracy analysis and prediction location evaluation. The findings of this paper can provide intelligence for the improvement of taxi services, to increase the passenger capacity of taxis and also to improve the probability of passengers finding taxis.https://www.mdpi.com/2220-9964/8/7/295hidden Markov modeltaxi trajectorykernel density analysisweighted confusion matrix |
| spellingShingle | Chunchun Hu Jean-Claude Thill Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi Trajectories ISPRS International Journal of Geo-Information hidden Markov model taxi trajectory kernel density analysis weighted confusion matrix |
| title | Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi Trajectories |
| title_full | Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi Trajectories |
| title_fullStr | Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi Trajectories |
| title_full_unstemmed | Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi Trajectories |
| title_short | Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi Trajectories |
| title_sort | predicting the upcoming services of vacant taxis near fixed locations using taxi trajectories |
| topic | hidden Markov model taxi trajectory kernel density analysis weighted confusion matrix |
| url | https://www.mdpi.com/2220-9964/8/7/295 |
| work_keys_str_mv | AT chunchunhu predictingtheupcomingservicesofvacanttaxisnearfixedlocationsusingtaxitrajectories AT jeanclaudethill predictingtheupcomingservicesofvacanttaxisnearfixedlocationsusingtaxitrajectories |