Predicting Bus Travel Time with Hybrid Incomplete Data – A Deep Learning Approach
The application of predicting bus travel time with real-time information, including Global Positioning System (GPS) and Electronic Smart Card (ESC) data is effective to advance the level of service by reducing wait time and improving schedule adherence. However, missing information in the data strea...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Zagreb, Faculty of Transport and Traffic Sciences
2022-09-01
|
| Series: | Promet (Zagreb) |
| Subjects: | |
| Online Access: | https://traffic2.fpz.hr/index.php/PROMTT/article/view/83 |
| _version_ | 1797902631367081984 |
|---|---|
| author | Ruisen Jiang Dawei Hu Steven I-Jy Chien Qian Sun Xue Wu |
| author_facet | Ruisen Jiang Dawei Hu Steven I-Jy Chien Qian Sun Xue Wu |
| author_sort | Ruisen Jiang |
| collection | DOAJ |
| description | The application of predicting bus travel time with real-time information, including Global Positioning System (GPS) and Electronic Smart Card (ESC) data is effective to advance the level of service by reducing wait time and improving schedule adherence. However, missing information in the data stream is inevitable for various reasons, which may seriously affect prediction accuracy. To address this problem, this research proposes a Long Short-Term Memory (LSTM) model to predict bus travel time, considering incomplete data. To improve the model performance in terms of accuracy and efficiency, a Genetic Algorithm (GA) is developed and applied to optimise hyperparameters of the LSTM model. The model performance is assessed by simulation and real-world data. The results suggest that the proposed approach with hybrid data outperforms the approaches with ESC and GPS data individually. With GA, the proposed model outperforms the traditional one in terms of lower Root Mean Square Error (RMSE). The prediction accuracy with various combinations of ESC and GPS data is assessed. The results can serve as a guideline for transit agencies to deploy GPS devices in a bus fleet considering the market penetration of ESC. |
| first_indexed | 2024-04-10T09:20:42Z |
| format | Article |
| id | doaj.art-3f9566a6b7c940a29ff9c639a9d90a25 |
| institution | Directory Open Access Journal |
| issn | 0353-5320 1848-4069 |
| language | English |
| last_indexed | 2024-04-10T09:20:42Z |
| publishDate | 2022-09-01 |
| publisher | University of Zagreb, Faculty of Transport and Traffic Sciences |
| record_format | Article |
| series | Promet (Zagreb) |
| spelling | doaj.art-3f9566a6b7c940a29ff9c639a9d90a252023-02-20T12:30:30ZengUniversity of Zagreb, Faculty of Transport and Traffic SciencesPromet (Zagreb)0353-53201848-40692022-09-0134567368510.7307/ptt.v34i5.405283Predicting Bus Travel Time with Hybrid Incomplete Data – A Deep Learning ApproachRuisen Jiang0Dawei Hu1Steven I-Jy Chien2Qian Sun3Xue Wu4School of Transportation Engineering, Chang'an UniversitySchool of Transportation Engineering, Chang'an UniversitySchool of Transportation Engineering, Chang'an UniversitySchool of Transportation Engineering, Chang'an UniversitySchool of Transportation Engineering, Chang'an UniversityThe application of predicting bus travel time with real-time information, including Global Positioning System (GPS) and Electronic Smart Card (ESC) data is effective to advance the level of service by reducing wait time and improving schedule adherence. However, missing information in the data stream is inevitable for various reasons, which may seriously affect prediction accuracy. To address this problem, this research proposes a Long Short-Term Memory (LSTM) model to predict bus travel time, considering incomplete data. To improve the model performance in terms of accuracy and efficiency, a Genetic Algorithm (GA) is developed and applied to optimise hyperparameters of the LSTM model. The model performance is assessed by simulation and real-world data. The results suggest that the proposed approach with hybrid data outperforms the approaches with ESC and GPS data individually. With GA, the proposed model outperforms the traditional one in terms of lower Root Mean Square Error (RMSE). The prediction accuracy with various combinations of ESC and GPS data is assessed. The results can serve as a guideline for transit agencies to deploy GPS devices in a bus fleet considering the market penetration of ESC.https://traffic2.fpz.hr/index.php/PROMTT/article/view/83bus travel time predictiongps dataelectronic smart card datalong short-term memory modelgenetic algorithm |
| spellingShingle | Ruisen Jiang Dawei Hu Steven I-Jy Chien Qian Sun Xue Wu Predicting Bus Travel Time with Hybrid Incomplete Data – A Deep Learning Approach Promet (Zagreb) bus travel time prediction gps data electronic smart card data long short-term memory model genetic algorithm |
| title | Predicting Bus Travel Time with Hybrid Incomplete Data – A Deep Learning Approach |
| title_full | Predicting Bus Travel Time with Hybrid Incomplete Data – A Deep Learning Approach |
| title_fullStr | Predicting Bus Travel Time with Hybrid Incomplete Data – A Deep Learning Approach |
| title_full_unstemmed | Predicting Bus Travel Time with Hybrid Incomplete Data – A Deep Learning Approach |
| title_short | Predicting Bus Travel Time with Hybrid Incomplete Data – A Deep Learning Approach |
| title_sort | predicting bus travel time with hybrid incomplete data a deep learning approach |
| topic | bus travel time prediction gps data electronic smart card data long short-term memory model genetic algorithm |
| url | https://traffic2.fpz.hr/index.php/PROMTT/article/view/83 |
| work_keys_str_mv | AT ruisenjiang predictingbustraveltimewithhybridincompletedataadeeplearningapproach AT daweihu predictingbustraveltimewithhybridincompletedataadeeplearningapproach AT stevenijychien predictingbustraveltimewithhybridincompletedataadeeplearningapproach AT qiansun predictingbustraveltimewithhybridincompletedataadeeplearningapproach AT xuewu predictingbustraveltimewithhybridincompletedataadeeplearningapproach |