Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms
Accurate travel time prediction is of high value for freight transports, as it allows supply chain participants to increase their logistics quality and efficiency. It requires both sufficient input data, which can be generated, e.g., by mobile sensors, and adequate prediction methods. Machine Learni...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-12-01
|
| Series: | Logistics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2305-6290/4/1/1 |
| _version_ | 1818023822063828992 |
|---|---|
| author | Nikolaos Servos Xiaodi Liu Michael Teucke Michael Freitag |
| author_facet | Nikolaos Servos Xiaodi Liu Michael Teucke Michael Freitag |
| author_sort | Nikolaos Servos |
| collection | DOAJ |
| description | Accurate travel time prediction is of high value for freight transports, as it allows supply chain participants to increase their logistics quality and efficiency. It requires both sufficient input data, which can be generated, e.g., by mobile sensors, and adequate prediction methods. Machine Learning (ML) algorithms are well suited to solve non-linear and complex relationships in the collected tracking data. Despite that, only a minority of recent publications use ML for travel time prediction in multimodal transports. We apply the ML algorithms extremely randomized trees (ExtraTrees), adaptive boosting (AdaBoost), and support vector regression (SVR) to this problem because of their ability to deal with low data volumes and their low processing times. Using different combinations of features derived from the data, we have built several models for travel time prediction. Tracking data from a real-world multimodal container transport relation from Germany to the USA are used for evaluation of the established models. We show that SVR provides the best prediction accuracy, with a mean absolute error of 17 h for a transport time of up to 30 days. We also show that our model performs better than average-based approaches. |
| first_indexed | 2024-12-10T03:50:25Z |
| format | Article |
| id | doaj.art-a08ccefd897d41c495ea994afde8ac4d |
| institution | Directory Open Access Journal |
| issn | 2305-6290 |
| language | English |
| last_indexed | 2024-12-10T03:50:25Z |
| publishDate | 2019-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Logistics |
| spelling | doaj.art-a08ccefd897d41c495ea994afde8ac4d2022-12-22T02:03:16ZengMDPI AGLogistics2305-62902019-12-0141110.3390/logistics4010001logistics4010001Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning AlgorithmsNikolaos Servos0Xiaodi Liu1Michael Teucke2Michael Freitag3Bosch Connected Industry, Robert Bosch Manufacturing Solutions GmbH, Leitzstrasse 47, 70469 Stuttgart, GermanyBosch Connected Industry, Robert Bosch Manufacturing Solutions GmbH, Leitzstrasse 47, 70469 Stuttgart, GermanyBIBA—Bremer Institut für Produktion und Logistik GmbH, University of Bremen, Hochschulring 20, 28359 Bremen, GermanyBIBA—Bremer Institut für Produktion und Logistik GmbH, University of Bremen, Hochschulring 20, 28359 Bremen, GermanyAccurate travel time prediction is of high value for freight transports, as it allows supply chain participants to increase their logistics quality and efficiency. It requires both sufficient input data, which can be generated, e.g., by mobile sensors, and adequate prediction methods. Machine Learning (ML) algorithms are well suited to solve non-linear and complex relationships in the collected tracking data. Despite that, only a minority of recent publications use ML for travel time prediction in multimodal transports. We apply the ML algorithms extremely randomized trees (ExtraTrees), adaptive boosting (AdaBoost), and support vector regression (SVR) to this problem because of their ability to deal with low data volumes and their low processing times. Using different combinations of features derived from the data, we have built several models for travel time prediction. Tracking data from a real-world multimodal container transport relation from Germany to the USA are used for evaluation of the established models. We show that SVR provides the best prediction accuracy, with a mean absolute error of 17 h for a transport time of up to 30 days. We also show that our model performs better than average-based approaches.https://www.mdpi.com/2305-6290/4/1/1logisticssupply chain managementmultimodal freight transportstravel time predictionmachine learning |
| spellingShingle | Nikolaos Servos Xiaodi Liu Michael Teucke Michael Freitag Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms Logistics logistics supply chain management multimodal freight transports travel time prediction machine learning |
| title | Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms |
| title_full | Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms |
| title_fullStr | Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms |
| title_full_unstemmed | Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms |
| title_short | Travel Time Prediction in a Multimodal Freight Transport Relation Using Machine Learning Algorithms |
| title_sort | travel time prediction in a multimodal freight transport relation using machine learning algorithms |
| topic | logistics supply chain management multimodal freight transports travel time prediction machine learning |
| url | https://www.mdpi.com/2305-6290/4/1/1 |
| work_keys_str_mv | AT nikolaosservos traveltimepredictioninamultimodalfreighttransportrelationusingmachinelearningalgorithms AT xiaodiliu traveltimepredictioninamultimodalfreighttransportrelationusingmachinelearningalgorithms AT michaelteucke traveltimepredictioninamultimodalfreighttransportrelationusingmachinelearningalgorithms AT michaelfreitag traveltimepredictioninamultimodalfreighttransportrelationusingmachinelearningalgorithms |