Understanding how congestion cascades through networks is essential for effective traffic management and congestion mitigation strategies. This work is innovative because it uses specialized neural network architectures that explicitly capture neighborhood information and spatial dependencies in traffic data. The connected LSTM fabric enables multi-timestep ahead predictions that account for how congestion propagates through interconnected road segments.
This paper analyzes cascading effects of traffic congestion using LSTM networks to predict traffic propagation patterns in city-wide networks. The approach models the transportation network as a directed graph and develops connected LSTM fabric architectures that capture spatial-temporal dependencies in traffic flow. The framework handles congestion forecasting at multiple timescales.
The approach achieved average precision of 0.9269 and average recall of 0.9118 in identifying congestion events when tested over ten congestion scenarios in Nashville. The system successfully predicted traffic speed with high accuracy by leveraging neighborhood information from connected LSTM architectures. The framework demonstrated ability to predict multiple timesteps ahead with degrading accuracy proportional to prediction horizon.
@inproceedings{Basak2019,
author = {Basak, Sanchita and Sun, Fangzhou and Sengupta, Saptarshi and Dubey, Abhishek},
booktitle = {Big Data Analytics - 7th International Conference, {BDA} 2019, Ahmedabad, India},
title = {Data-Driven Optimization of Public Transit Schedule},
year = {2019},
pages = {265--284},
abstract = {Bus transit systems are the backbone of public transportation in the United States. An important indicator of the quality of service in such infrastructures is on-time performance at stops, with published transit schedules playing an integral role governing the level of success of the service. However there are relatively few optimization architectures leveraging stochastic search that focus on optimizing bus timetables with the objective of maximizing probability of bus arrivals at timepoints with delays within desired on-time ranges. In addition to this, there is a lack of substantial research considering monthly and seasonal variations of delay patterns integrated with such optimization strategies. To address these, this paper makes the following contributions to the corpus of studies on transit on-time performance optimization: (a) an unsupervised clustering mechanism is presented which groups months with similar seasonal delay patterns, (b) the problem is formulated as a single-objective optimization task and a greedy algorithm, a genetic algorithm (GA) as well as a particle swarm optimization (PSO) algorithm are employed to solve it, (c) a detailed discussion on empirical results comparing the algorithms are provided and sensitivity analysis on hyper-parameters of the heuristics are presented along with execution times, which will help practitioners looking at similar problems. The analyses conducted are insightful in the local context of improving public transit scheduling in the Nashville metro region as well as informative from a global perspective as an elaborate case study which builds upon the growing corpus of empirical studies using nature-inspired approaches to transit schedule optimization.},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/bib/conf/bigda/BasakSSD19},
category = {selectiveconference},
contribution = {lead},
doi = {10.1007/978-3-030-37188-3\_16},
file = {:Basak2019-Data_Driven_Optimization_of_Public_Transit_Schedule.pdf:PDF},
keywords = {traffic congestion, cascading failures, LSTM networks, spatial-temporal modeling, congestion prediction, network analysis},
project = {smart-cities,smart-transit},
tag = {ai4cps,transit},
timestamp = {Fri, 13 Dec 2019 12:44:00 +0100},
url = {https://doi.org/10.1007/978-3-030-37188-3\_16}
}