Afiya Ayman, Juan Martinez, Philip Pugliese, Abhishek Dubey, Aron Laszka
8th IEEE International Conference on Smart Computing (SMARTCOMP) 2022
Accurately predicting transit ridership is essential for optimizing vehicle deployment and service planning while reducing operational costs and improving passenger experience. This work is significant because it addresses the challenge of automating neural network design for transportation applications without requiring extensive manual tuning by experts. The multi-objective optimization balances prediction accuracy with model efficiency.
This paper presents a neural architecture search approach for predicting ridership of public transportation routes, optimizing both the architecture design and feature selection of deep neural networks. The authors use a randomized local search algorithm that minimizes both prediction error and model complexity. The approach is applied to predict maximum occupancy of transit vehicles across different routes and time periods.
Using real-world ridership data from Chattanooga, the neural architecture search approach identified optimized architectures that performed significantly better than baseline generic models. The randomized local search algorithm efficiently discovered architectures with lower complexity while maintaining prediction accuracy. Results demonstrated that task-specific architecture optimization substantially improves forecasting performance compared to standard approaches.
@inproceedings{ayman2022neural,
author = {Ayman, Afiya and Martinez, Juan and Pugliese, Philip and Dubey, Abhishek and Laszka, Aron},
booktitle = {8th IEEE International Conference on Smart Computing (SMARTCOMP)},
title = {Neural Architecture and Feature Search for Predicting the Ridership of Public Transportation Routes},
year = {2022},
month = {jun},
acceptance = {30},
abstract = {Accurately predicting the ridership of public-transit routes provides substantial benefits to both transit agencies, who can dispatch additional vehicles proactively before the vehicles that serve a route become crowded, and to passengers, who can avoid crowded vehicles based on publicly available predictions. The spread of the coronavirus disease has further elevated the importance of ridership prediction as crowded vehicles now present not only an inconvenience but also a public-health risk. At the same time, accurately predicting ridership has become more challenging due to evolving ridership patterns, which may make all data except for the most recent records stale. One promising approach for improving prediction accuracy is to fine-tune the hyper-parameters of machine-learning models for each transit route based on the characteristics of the particular route, such as the number of records. However, manually designing a machine-learning model for each route is a labor-intensive process, which may require experts to spend a significant amount of their valuable time. To help experts with designing machine-learning models, we propose a neural-architecture and feature search approach, which optimizes the architecture and features of a deep neural network for predicting the ridership of a public-transit route. Our approach is based on a randomized local hyper-parameter search, which minimizes both prediction error as well as the complexity of the model. We evaluate our approach on real-world ridership data provided by the public transit agency of Chattanooga, TN, and we demonstrate that training neural networks whose architectures and features are optimized for each route provides significantly better performance than training neural networks whose architectures and features are generic.},
contribution = {colab},
keywords = {neural architecture search, ridership prediction, transit planning, deep learning, time series forecasting},
month_numeric = {6}
}