Travel Mode Detection Based on Neural Networks and Particle Swarm Optimization
The collection of massive Global Positioning System (GPS) data from travel surveys has increased exponentially worldwide since the 1990s. A number of methods, which range from rule-based to advanced classification approaches, have been applied to detect travel modes from GPS positioning data collect...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2015-08-01
|
Series: | Information |
Subjects: | |
Online Access: | http://www.mdpi.com/2078-2489/6/3/522 |
id |
doaj-697fa861470e4cb8be16118e70de81dd |
---|---|
record_format |
Article |
spelling |
doaj-697fa861470e4cb8be16118e70de81dd2020-11-24T23:59:34ZengMDPI AGInformation2078-24892015-08-016352253510.3390/info6030522info6030522Travel Mode Detection Based on Neural Networks and Particle Swarm OptimizationGuangnian Xiao0Zhicai Juan1Jingxin Gao2Antai College of Economics & Management, Shanghai Jiao Tong University, Shanghai 200052, ChinaAntai College of Economics & Management, Shanghai Jiao Tong University, Shanghai 200052, ChinaAntai College of Economics & Management, Shanghai Jiao Tong University, Shanghai 200052, ChinaThe collection of massive Global Positioning System (GPS) data from travel surveys has increased exponentially worldwide since the 1990s. A number of methods, which range from rule-based to advanced classification approaches, have been applied to detect travel modes from GPS positioning data collected in travel surveys based on GPS-enabled smartphones or dedicated GPS devices. Among these approaches, neural networks (NNs) are widely adopted because they can extract subtle information from training data that cannot be directly obtained by human or other analysis techniques. However, traditional NNs, which are generally trained by back-propagation algorithms, are likely to be trapped in local optimum. Therefore, particle swarm optimization (PSO) is introduced to train the NNs. The resulting PSO-NNs are employed to distinguish among four travel modes (walk, bike, bus, and car) with GPS positioning data collected through a smartphone-based travel survey. As a result, 95.81% of samples are correctly flagged for the training set, while 94.44% are correctly identified for the test set. Results from this study indicate that smartphone-based travel surveys provide an opportunity to supplement traditional travel surveys.http://www.mdpi.com/2078-2489/6/3/522global positioning systemneural networksparticle swarm optimizationtravel mode |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Guangnian Xiao Zhicai Juan Jingxin Gao |
spellingShingle |
Guangnian Xiao Zhicai Juan Jingxin Gao Travel Mode Detection Based on Neural Networks and Particle Swarm Optimization Information global positioning system neural networks particle swarm optimization travel mode |
author_facet |
Guangnian Xiao Zhicai Juan Jingxin Gao |
author_sort |
Guangnian Xiao |
title |
Travel Mode Detection Based on Neural Networks and Particle Swarm Optimization |
title_short |
Travel Mode Detection Based on Neural Networks and Particle Swarm Optimization |
title_full |
Travel Mode Detection Based on Neural Networks and Particle Swarm Optimization |
title_fullStr |
Travel Mode Detection Based on Neural Networks and Particle Swarm Optimization |
title_full_unstemmed |
Travel Mode Detection Based on Neural Networks and Particle Swarm Optimization |
title_sort |
travel mode detection based on neural networks and particle swarm optimization |
publisher |
MDPI AG |
series |
Information |
issn |
2078-2489 |
publishDate |
2015-08-01 |
description |
The collection of massive Global Positioning System (GPS) data from travel surveys has increased exponentially worldwide since the 1990s. A number of methods, which range from rule-based to advanced classification approaches, have been applied to detect travel modes from GPS positioning data collected in travel surveys based on GPS-enabled smartphones or dedicated GPS devices. Among these approaches, neural networks (NNs) are widely adopted because they can extract subtle information from training data that cannot be directly obtained by human or other analysis techniques. However, traditional NNs, which are generally trained by back-propagation algorithms, are likely to be trapped in local optimum. Therefore, particle swarm optimization (PSO) is introduced to train the NNs. The resulting PSO-NNs are employed to distinguish among four travel modes (walk, bike, bus, and car) with GPS positioning data collected through a smartphone-based travel survey. As a result, 95.81% of samples are correctly flagged for the training set, while 94.44% are correctly identified for the test set. Results from this study indicate that smartphone-based travel surveys provide an opportunity to supplement traditional travel surveys. |
topic |
global positioning system neural networks particle swarm optimization travel mode |
url |
http://www.mdpi.com/2078-2489/6/3/522 |
work_keys_str_mv |
AT guangnianxiao travelmodedetectionbasedonneuralnetworksandparticleswarmoptimization AT zhicaijuan travelmodedetectionbasedonneuralnetworksandparticleswarmoptimization AT jingxingao travelmodedetectionbasedonneuralnetworksandparticleswarmoptimization |
_version_ |
1725447379838042112 |