A Deep Learning Model for Traffic Flow State Classification Based on Smart Phone Sensor Data

TL;DR

This paper presents a deep learning approach using a Deep Belief Network to classify traffic flow states from smartphone sensor data, demonstrating improved accuracy and efficiency over traditional methods.

Contribution

It introduces a novel application of Deep Belief Networks for traffic classification using high-density smartphone sensor data, with extensive experimental validation.

Findings

Deep Belief Network outperforms traditional machine learning methods in accuracy.

The model effectively processes noisy, high-density sensor data.

Experimental results confirm the model's computational efficiency.

Abstract

This study proposes a Deep Belief Network model to classify traffic flow states. The model is capable of processing massive, high-density, and noise-contaminated data sets generated from smartphone sensors. The statistical features of Vehicle acceleration, angular acceleration, and GPS speed data, recorded by smartphone software, are analyzed, and then used as input for traffic flow state classification. Data from a five-day experiment is used to train and test the proposed model. A total of 747,856 sets of data are generated and used for both traffic flow states classification and sensitivity analysis of input variables. The result shows that the proposed Deep Belief Network model is superior to traditional machine learning methods in both classification performance and computational efficiency.