Short-Term Urban Link Travel Time Prediction Using Dynamic Time Warping With Disaggregate Probe Data
There is increasing demand for short-term urban link travel time prediction to build an advanced intelligent transportation system (ITS). With the development of data collection technology, probe data are receiving more attention but the penetration rate of probe vehicles capable of sending probe da...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8766086/ |
| _version_ | 1818642817645281280 |
|---|---|
| author | Ruotian Tang Ryo Kanamori Toshiyuki Yamamoto |
| author_facet | Ruotian Tang Ryo Kanamori Toshiyuki Yamamoto |
| author_sort | Ruotian Tang |
| collection | DOAJ |
| description | There is increasing demand for short-term urban link travel time prediction to build an advanced intelligent transportation system (ITS). With the development of data collection technology, probe data are receiving more attention but the penetration rate of probe vehicles capable of sending probe data is still limited. Most research pertaining to short-term travel time prediction tends to aggregate probe data to obtain useful samples when the penetration rate is low. However, as a result, the prediction can only provide a general description of the travel time and changes in travel time during a short time interval are neglected. To overcome this limitation, a non-parametric model using disaggregate probe data based on dynamic time warping (DTW) was developed in this study. Data from the crossing direction are introduced to separate the data into different signal phases instead of identifying the exact signal pattern. A classical k-nearest neighbor (KNN) model and a naïve model were compared with the proposed model. The models were tested in three scenarios: a computer simulation and two real cases from Nagoya, Japan. The results showed that the proposed model outperforms the other two models under different data penetration rates because it can reflect changes in travel time during a traffic signal cycle. Moreover, the proposed model has wider applicability than the KNN model because it is free from the equal time interval constraint. |
| first_indexed | 2024-12-16T23:49:05Z |
| format | Article |
| id | doaj.art-25616ca7f7c6420abecb18b8d97d3980 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T23:49:05Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-25616ca7f7c6420abecb18b8d97d39802022-12-21T22:11:23ZengIEEEIEEE Access2169-35362019-01-017989599897010.1109/ACCESS.2019.29297918766086Short-Term Urban Link Travel Time Prediction Using Dynamic Time Warping With Disaggregate Probe DataRuotian Tang0https://orcid.org/0000-0001-6256-6606Ryo Kanamori1Toshiyuki Yamamoto2Department of Civil Engineering, Nagoya University, Nagoya, JapanInstitute of Innovation for Future Society, Nagoya University, Nagoya, JapanInstitute of Materials and Systems for Sustainability, Nagoya University, Nagoya, JapanThere is increasing demand for short-term urban link travel time prediction to build an advanced intelligent transportation system (ITS). With the development of data collection technology, probe data are receiving more attention but the penetration rate of probe vehicles capable of sending probe data is still limited. Most research pertaining to short-term travel time prediction tends to aggregate probe data to obtain useful samples when the penetration rate is low. However, as a result, the prediction can only provide a general description of the travel time and changes in travel time during a short time interval are neglected. To overcome this limitation, a non-parametric model using disaggregate probe data based on dynamic time warping (DTW) was developed in this study. Data from the crossing direction are introduced to separate the data into different signal phases instead of identifying the exact signal pattern. A classical k-nearest neighbor (KNN) model and a naïve model were compared with the proposed model. The models were tested in three scenarios: a computer simulation and two real cases from Nagoya, Japan. The results showed that the proposed model outperforms the other two models under different data penetration rates because it can reflect changes in travel time during a traffic signal cycle. Moreover, the proposed model has wider applicability than the KNN model because it is free from the equal time interval constraint.https://ieeexplore.ieee.org/document/8766086/Travel time predictiondisaggregate probe datashort termdynamic time warpingtraffic signal cyclepenetration rate |
| spellingShingle | Ruotian Tang Ryo Kanamori Toshiyuki Yamamoto Short-Term Urban Link Travel Time Prediction Using Dynamic Time Warping With Disaggregate Probe Data IEEE Access Travel time prediction disaggregate probe data short term dynamic time warping traffic signal cycle penetration rate |
| title | Short-Term Urban Link Travel Time Prediction Using Dynamic Time Warping With Disaggregate Probe Data |
| title_full | Short-Term Urban Link Travel Time Prediction Using Dynamic Time Warping With Disaggregate Probe Data |
| title_fullStr | Short-Term Urban Link Travel Time Prediction Using Dynamic Time Warping With Disaggregate Probe Data |
| title_full_unstemmed | Short-Term Urban Link Travel Time Prediction Using Dynamic Time Warping With Disaggregate Probe Data |
| title_short | Short-Term Urban Link Travel Time Prediction Using Dynamic Time Warping With Disaggregate Probe Data |
| title_sort | short term urban link travel time prediction using dynamic time warping with disaggregate probe data |
| topic | Travel time prediction disaggregate probe data short term dynamic time warping traffic signal cycle penetration rate |
| url | https://ieeexplore.ieee.org/document/8766086/ |
| work_keys_str_mv | AT ruotiantang shorttermurbanlinktraveltimepredictionusingdynamictimewarpingwithdisaggregateprobedata AT ryokanamori shorttermurbanlinktraveltimepredictionusingdynamictimewarpingwithdisaggregateprobedata AT toshiyukiyamamoto shorttermurbanlinktraveltimepredictionusingdynamictimewarpingwithdisaggregateprobedata |