Selection of Significant On-Road Sensor Data for Short-Term Traffic Flow Forecasting Using the Taguchi Method

Over the past two decades, neural networks have been applied to develop short-term traffic flow predictors. The past traffic flow data, captured by on-road sensors, is used as input patterns of neural networks to forecast future traffic flow conditions. The amount of input patterns captured by the o...

Full description

Bibliographic Details
Main Authors: Chan, Kit, Khadem, Saghar, Dillon, Tharam, Palade, Vasile, Singh, Jaipal, Chang, Elizabeth
Format: Journal Article
Published: IEEE 2012
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/21506
_version_ 1848750609471111168
author Chan, Kit
Khadem, Saghar
Dillon, Tharam
Palade, Vasile
Singh, Jaipal
Chang, Elizabeth
author_facet Chan, Kit
Khadem, Saghar
Dillon, Tharam
Palade, Vasile
Singh, Jaipal
Chang, Elizabeth
author_sort Chan, Kit
building Curtin Institutional Repository
collection Online Access
description Over the past two decades, neural networks have been applied to develop short-term traffic flow predictors. The past traffic flow data, captured by on-road sensors, is used as input patterns of neural networks to forecast future traffic flow conditions. The amount of input patterns captured by the on-road sensors is usually huge, but not all input patterns are useful when trying to predict the future traffic flow. The inclusion of useless input patterns is not effective to developing neural network models. Therefore, the selection of appropriate input patterns, which are significant for short-term traffic flow forecasting, is essential. This can be conducted by setting an appropriate configuration of input nodes of the neural network; however, this is usually conducted by trial and error. In this paper, the Taguchi method, which is a robust and systematic optimization approach for designing reliable and high-quality models, is proposed for the purpose of determining an appropriate neural network configuration, in terms of input nodes, in order to capture useful input patterns for traffic flow forecasting. The effectiveness of the Taguchi method is demonstrated by a case study, which aims to develop a short-term traffic flow predictor based on past traffic flow data captured by on-road sensors located on a Western Australia freeway. Three advantages of using the Taguchi method were demonstrated: 1) short-term traffic flow predictors with high accuracy can be designed; 2) the development time for short-term traffic flow predictors is reasonable; and 3) the accuracy of short-term traffic flow predictors is robust with respect to the initial settings of the neural network parameters during the learning phase.
first_indexed 2025-11-14T07:39:33Z
format Journal Article
id curtin-20.500.11937-21506
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:39:33Z
publishDate 2012
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-215062017-09-13T13:55:04Z Selection of Significant On-Road Sensor Data for Short-Term Traffic Flow Forecasting Using the Taguchi Method Chan, Kit Khadem, Saghar Dillon, Tharam Palade, Vasile Singh, Jaipal Chang, Elizabeth neural network configuration Taguchi method traffic flow forecasting Input patterns neural networks sensor data Over the past two decades, neural networks have been applied to develop short-term traffic flow predictors. The past traffic flow data, captured by on-road sensors, is used as input patterns of neural networks to forecast future traffic flow conditions. The amount of input patterns captured by the on-road sensors is usually huge, but not all input patterns are useful when trying to predict the future traffic flow. The inclusion of useless input patterns is not effective to developing neural network models. Therefore, the selection of appropriate input patterns, which are significant for short-term traffic flow forecasting, is essential. This can be conducted by setting an appropriate configuration of input nodes of the neural network; however, this is usually conducted by trial and error. In this paper, the Taguchi method, which is a robust and systematic optimization approach for designing reliable and high-quality models, is proposed for the purpose of determining an appropriate neural network configuration, in terms of input nodes, in order to capture useful input patterns for traffic flow forecasting. The effectiveness of the Taguchi method is demonstrated by a case study, which aims to develop a short-term traffic flow predictor based on past traffic flow data captured by on-road sensors located on a Western Australia freeway. Three advantages of using the Taguchi method were demonstrated: 1) short-term traffic flow predictors with high accuracy can be designed; 2) the development time for short-term traffic flow predictors is reasonable; and 3) the accuracy of short-term traffic flow predictors is robust with respect to the initial settings of the neural network parameters during the learning phase. 2012 Journal Article http://hdl.handle.net/20.500.11937/21506 10.1109/TII.2011.2179052 IEEE fulltext
spellingShingle neural network configuration
Taguchi method
traffic flow forecasting
Input patterns
neural networks
sensor data
Chan, Kit
Khadem, Saghar
Dillon, Tharam
Palade, Vasile
Singh, Jaipal
Chang, Elizabeth
Selection of Significant On-Road Sensor Data for Short-Term Traffic Flow Forecasting Using the Taguchi Method
title Selection of Significant On-Road Sensor Data for Short-Term Traffic Flow Forecasting Using the Taguchi Method
title_full Selection of Significant On-Road Sensor Data for Short-Term Traffic Flow Forecasting Using the Taguchi Method
title_fullStr Selection of Significant On-Road Sensor Data for Short-Term Traffic Flow Forecasting Using the Taguchi Method
title_full_unstemmed Selection of Significant On-Road Sensor Data for Short-Term Traffic Flow Forecasting Using the Taguchi Method
title_short Selection of Significant On-Road Sensor Data for Short-Term Traffic Flow Forecasting Using the Taguchi Method
title_sort selection of significant on-road sensor data for short-term traffic flow forecasting using the taguchi method
topic neural network configuration
Taguchi method
traffic flow forecasting
Input patterns
neural networks
sensor data
url http://hdl.handle.net/20.500.11937/21506