Neural Network Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm
This paper proposes a novel neural network (NN) training method that employs the hybrid exponential smoothing method and the Levenberg–Marquardt (LM) algorithm, which aims to improve the generalization capabilities of previously used methods for training NNs for short-term traffic flow forecasting....
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Published: |
IEEE Intelligent Transportation Systems Society
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/28800 |
| _version_ | 1848752633141002240 |
|---|---|
| author | Chan, Kit Yan Dillon, Tharam Singh, Jaipal Chang, Elizabeth |
| author_facet | Chan, Kit Yan Dillon, Tharam Singh, Jaipal Chang, Elizabeth |
| author_sort | Chan, Kit Yan |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This paper proposes a novel neural network (NN) training method that employs the hybrid exponential smoothing method and the Levenberg–Marquardt (LM) algorithm, which aims to improve the generalization capabilities of previously used methods for training NNs for short-term traffic flow forecasting. The approach uses exponential smoothing to preprocess traffic flow data by removing the lumpiness from collected traffic flow data, before employing a variant of the LM algorithm to train the NN weights of an NN model. This approach aids NN training, as the preprocessed traffic flow data are more smooth and continuous than the original unprocessed traffic flow data. The proposed method was evaluated by forecasting short-term traffic flow conditions on the Mitchell freeway in Western Australia. With regard to the generalization capabilities for short-term traffic flow forecasting, the NN models developed using the proposed approach outperform those that are developed based on the alternative tested algorithms, which are particularly designed either for short-term traffic flow forecasting or for enhancing generalization capabilities of NNs. |
| first_indexed | 2025-11-14T08:11:43Z |
| format | Journal Article |
| id | curtin-20.500.11937-28800 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:11:43Z |
| publishDate | 2011 |
| publisher | IEEE Intelligent Transportation Systems Society |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-288002017-09-13T15:56:19Z Neural Network Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm Chan, Kit Yan Dillon, Tharam Singh, Jaipal Chang, Elizabeth neural networks (NNs) Exponential smoothing method short-term - traffic flow forecasting Levenberg-Marquardt (LM) algorithm This paper proposes a novel neural network (NN) training method that employs the hybrid exponential smoothing method and the Levenberg–Marquardt (LM) algorithm, which aims to improve the generalization capabilities of previously used methods for training NNs for short-term traffic flow forecasting. The approach uses exponential smoothing to preprocess traffic flow data by removing the lumpiness from collected traffic flow data, before employing a variant of the LM algorithm to train the NN weights of an NN model. This approach aids NN training, as the preprocessed traffic flow data are more smooth and continuous than the original unprocessed traffic flow data. The proposed method was evaluated by forecasting short-term traffic flow conditions on the Mitchell freeway in Western Australia. With regard to the generalization capabilities for short-term traffic flow forecasting, the NN models developed using the proposed approach outperform those that are developed based on the alternative tested algorithms, which are particularly designed either for short-term traffic flow forecasting or for enhancing generalization capabilities of NNs. 2011 Journal Article http://hdl.handle.net/20.500.11937/28800 10.1109/TITS.2011.2174051 IEEE Intelligent Transportation Systems Society fulltext |
| spellingShingle | neural networks (NNs) Exponential smoothing method short-term - traffic flow forecasting Levenberg-Marquardt (LM) algorithm Chan, Kit Yan Dillon, Tharam Singh, Jaipal Chang, Elizabeth Neural Network Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm |
| title | Neural Network Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm |
| title_full | Neural Network Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm |
| title_fullStr | Neural Network Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm |
| title_full_unstemmed | Neural Network Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm |
| title_short | Neural Network Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm |
| title_sort | neural network based models for short-term traffic flow forecasting using a hybrid exponential smoothing and levenberg–marquardt algorithm |
| topic | neural networks (NNs) Exponential smoothing method short-term - traffic flow forecasting Levenberg-Marquardt (LM) algorithm |
| url | http://hdl.handle.net/20.500.11937/28800 |