Trajectory Data Mining and Trip Travel Time Prediction on Specific Roads

TL;DR

This paper develops a trajectory data mining pipeline and applies advanced neural network models to predict trip travel times on specific roads in Islamabad, Pakistan, addressing local road condition challenges.

Contribution

It introduces a complete data mining pipeline and evaluates deep learning models for travel time prediction tailored to Pakistan's road network.

Findings

Average prediction error ranges from 30 seconds to 1.2 minutes.

Deep neural networks outperform traditional methods.

Effective for trips lasting 10 to 60 minutes.

Abstract

Predicting a trip's travel time is essential for route planning and navigation applications. The majority of research is based on international data that does not apply to Pakistan's road conditions. We designed a complete pipeline for mining trajectories from sensors data. On this data, we employed state-of-the-art approaches, including a shallow artificial neural network, a deep multi-layered perceptron, and a long-short-term memory, to explore the issue of travel time prediction on frequent routes. The experimental results demonstrate an average prediction error ranging from 30 seconds to 1.2 minutes on trips lasting 10 minutes to 60 minutes on six most frequent routes in regions of Islamabad, Pakistan.