The week's pick
Random Articles
Reseach Article
AI-Powered Bus Priority and Scheduling Optimization in Dhaka’s Overloaded Corridors: Leveraging GPS Data with a Gender-Sensitive Approach
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 16 |
| Year of Publication: 2025 |
| Authors: Araf Hasan Jhell |
10.5120/ijca2025925204
|
Araf Hasan Jhell . AI-Powered Bus Priority and Scheduling Optimization in Dhaka’s Overloaded Corridors: Leveraging GPS Data with a Gender-Sensitive Approach. International Journal of Computer Applications. 187, 16 ( Jun 2025), 23-28. DOI=10.5120/ijca2025925204
Abstract
Dhaka, Bangladesh’s capital with over 12 million residents, suffers from severe transit congestion and chronic under-service on its bus network. Crowded buses, long waits, and safety issues disproportionately affect women commuters. This paper proposes an AI-driven framework to optimize bus scheduling and priority in Dhaka’s busiest corridors using simulated historical GPS data and survey-informed gender safety metrics. Five algorithms – reinforcement learning (RL), decision trees, support vector machines (SVM), clustering, and neural networks – are developed and compared. We first generate synthetic multi-day GPS traces for buses on major routes and incorporate a simulated female commuter survey capturing concerns (e.g., harassment risk, overcrowding, waiting time). Each AI model is designed to predict or prescribe schedules that minimize total waiting time and delays while weighting gender-safety factors. Models are trained and tested on 80/20 splits of the data, with performance measured by efficiency metrics (average wait time, on-time rate, average delay) and a Gender Safety Index (GSI) improvement score. Results indicate that the RL-based approach yields the greatest overall efficiency gains, reducing average passenger delay by ~30% over baseline scheduling, while increasing the GSI by ~25%. Decision tree and SVM models provide moderate improvements (15–20% delay reduction) with lower computational cost, while clustering and neural networks achieve 10–15% delay reduction. All AI methods outperform a naive timetable heuristic, and importantly produce schedules that reduce female commuters’ exposure to high-risk conditions (e.g. fewer off-peak long waits). This study demonstrates the promise of leveraging AI on transit GPS data for urban contexts like Dhaka, and highlights that incorporating gender-sensitive objectives can measurably improve equity and safety in bus service.
References
- Ahmed, F., & Karim, M. M. (2019). Evaluation of public bus operations in Dhaka city. Transportation Research Procedia, 37, 165–172. https://doi.org/10.1016/j.trpro.2018.12.181
- Ahmed, S., & Wang, Y. (2023). Deep reinforcement learning for real-time bus signal priority control. IEEE Transactions on Intelligent Transportation Systems, 24(3), 2587–2598. https://doi.org/10.1109/TITS.2022.3189114
- Ai, Q., Yang, J., Chen, X., & Shen, Z.-J. M. (2021). Reinforcement learning approaches for optimizing bus operations. Transportation Research Part C: Emerging Technologies, 129, 103236. https://doi.org/10.1016/j.trc.2021.103236
- Bangladesh Institute of Planners (BIP). (n.d.-a). Urban transport challenges in Dhaka: A planning perspective. Retrieved from https://bip.org.bd
- Bangladesh Institute of Planners (BIP). (n.d.-b). Gender dimensions in Dhaka’s public transport. Retrieved from https://bip.org.bd
- BRAC. (2018). Harassment on public transport: Findings from BRAC survey. Retrieved from https://www.brac.net
- Ceder, A. (2020). Public transit planning and operation: Modeling, practice, and behavior (2nd ed.). CRC Press. https://doi.org/10.1201/9781315267585
- Chen, J., & Sun, W. (2023). Multi-line bus scheduling using reinforcement learning: A Markov decision process approach. Journal of Transportation Engineering, Part A: Systems, 149(2), 04022125. https://doi.org/10.1061/JTEPBS.0000730
- Chowdhury, S., & Imran, M. (2018). Urban transport system and socio-economic development: The case of Dhaka. Asian Transport Studies, 5(2), 623–638. https://doi.org/10.11175/eastsats.5.623
- Rahman, M. M., Hossain, M. A., & Ferdous, R. (2020). Urbanization and transport challenges in Dhaka: A critical analysis. Journal of Urban Management, 9(2), 160–174. https://doi.org/10.1016/j.jum.2020.03.001
- Rahman, M. S., Islam, M. N., & Sarker, A. (2021). Predicting public transport travel time using machine learning techniques: A case study in Dhaka. IEEE Access, 9, 11384–11397. https://doi.org/10.1109/ACCESS.2021.3050975
- Sultana, S., & Anwar, S. (2022). Women’s commuting experiences and safety concerns in Dhaka: A gendered perspective. Transportation Research Part F: Traffic Psychology and Behaviour, 88, 1–14. https://doi.org/10.1016/j.trf.2022.01.002
- The Daily Star. (2022). Online survey highlights harassment of women in public spaces. Retrieved from https://www.thedailystar.net
- The Financial Express. (2022). Aachol Foundation: Survey on harassment in public transport. Retrieved from https://thefinancialexpress.com.bd
- Urban Institute. (2021). Artificial intelligence and machine learning for public service optimization. Retrieved from https://www.urban.org
- Zhao, Z., Xu, J., & Li, X. (2022). Machine learning applications in public transport: A comprehensive review. Transportation Research Part C: Emerging Technologies, 139, 103693
Index Terms
Keywords