Truck Parking Occupancy Prediction: XGBoost-LSTM Model Fusion
For haul truck drivers it is becoming increasingly difficult to find appropriate parking at the end of a shift. Proper, legal, and safe overnight parking spots are crucial for truck drivers in order for them to be able to comply with Hours of Service regulation, reduce fatigue, and improve road safe...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-07-01
|
| Series: | Frontiers in Future Transportation |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/ffutr.2021.693708/full |
| _version_ | 1818917421587628032 |
|---|---|
| author | Sebastian Gutmann Sebastian Gutmann Christoph Maget Christoph Maget Matthias Spangler Klaus Bogenberger |
| author_facet | Sebastian Gutmann Sebastian Gutmann Christoph Maget Christoph Maget Matthias Spangler Klaus Bogenberger |
| author_sort | Sebastian Gutmann |
| collection | DOAJ |
| description | For haul truck drivers it is becoming increasingly difficult to find appropriate parking at the end of a shift. Proper, legal, and safe overnight parking spots are crucial for truck drivers in order for them to be able to comply with Hours of Service regulation, reduce fatigue, and improve road safety. The lack of parking spaces affects the backbone of the economy because 70% of all United States domestic freight shipments (in terms of value) are transported by trucks. Many research projects provide real-time truck parking occupancy information at a given stop. However, truck drivers ultimately need to know whether parking spots will be available at a downstream stop at their expected arrival time. We propose a machine-learning-based model that is capable of accurately predicting occupancy 30, 60, 90, and 120 min ahead. The model is based on the fusion of Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) with the help of a feed-forward neural network. Our results show that prediction of truck parking occupancy can be achieved with small errors. Root mean square error metrics are 2.1, 2.9, 3.5, and 4.1 trucks for the four different horizons, respectively. The unique feature of our proposed model is that it requires only historic occupancy data. Thus, any truck occupancy detection system could also provide forecasts by implementing our model. |
| first_indexed | 2024-12-20T00:33:48Z |
| format | Article |
| id | doaj.art-10fa72850c0c47b8ac03754890e8c9de |
| institution | Directory Open Access Journal |
| issn | 2673-5210 |
| language | English |
| last_indexed | 2024-12-20T00:33:48Z |
| publishDate | 2021-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Future Transportation |
| spelling | doaj.art-10fa72850c0c47b8ac03754890e8c9de2022-12-21T19:59:50ZengFrontiers Media S.A.Frontiers in Future Transportation2673-52102021-07-01210.3389/ffutr.2021.693708693708Truck Parking Occupancy Prediction: XGBoost-LSTM Model FusionSebastian Gutmann0Sebastian Gutmann1Christoph Maget2Christoph Maget3Matthias Spangler4Klaus Bogenberger5Chair of Traffic Engineering and Control, Technical University of Munich, Munich, GermanyBavarian Centre for Traffic Management, Munich, GermanyChair of Traffic Engineering and Control, Technical University of Munich, Munich, GermanyBavarian Centre for Traffic Management, Munich, GermanyChair of Traffic Engineering and Control, Technical University of Munich, Munich, GermanyChair of Traffic Engineering and Control, Technical University of Munich, Munich, GermanyFor haul truck drivers it is becoming increasingly difficult to find appropriate parking at the end of a shift. Proper, legal, and safe overnight parking spots are crucial for truck drivers in order for them to be able to comply with Hours of Service regulation, reduce fatigue, and improve road safety. The lack of parking spaces affects the backbone of the economy because 70% of all United States domestic freight shipments (in terms of value) are transported by trucks. Many research projects provide real-time truck parking occupancy information at a given stop. However, truck drivers ultimately need to know whether parking spots will be available at a downstream stop at their expected arrival time. We propose a machine-learning-based model that is capable of accurately predicting occupancy 30, 60, 90, and 120 min ahead. The model is based on the fusion of Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) with the help of a feed-forward neural network. Our results show that prediction of truck parking occupancy can be achieved with small errors. Root mean square error metrics are 2.1, 2.9, 3.5, and 4.1 trucks for the four different horizons, respectively. The unique feature of our proposed model is that it requires only historic occupancy data. Thus, any truck occupancy detection system could also provide forecasts by implementing our model.https://www.frontiersin.org/articles/10.3389/ffutr.2021.693708/fulltruck parkingoccupancy predictionmachine learningmodel fusionXGBoostLSTM |
| spellingShingle | Sebastian Gutmann Sebastian Gutmann Christoph Maget Christoph Maget Matthias Spangler Klaus Bogenberger Truck Parking Occupancy Prediction: XGBoost-LSTM Model Fusion Frontiers in Future Transportation truck parking occupancy prediction machine learning model fusion XGBoost LSTM |
| title | Truck Parking Occupancy Prediction: XGBoost-LSTM Model Fusion |
| title_full | Truck Parking Occupancy Prediction: XGBoost-LSTM Model Fusion |
| title_fullStr | Truck Parking Occupancy Prediction: XGBoost-LSTM Model Fusion |
| title_full_unstemmed | Truck Parking Occupancy Prediction: XGBoost-LSTM Model Fusion |
| title_short | Truck Parking Occupancy Prediction: XGBoost-LSTM Model Fusion |
| title_sort | truck parking occupancy prediction xgboost lstm model fusion |
| topic | truck parking occupancy prediction machine learning model fusion XGBoost LSTM |
| url | https://www.frontiersin.org/articles/10.3389/ffutr.2021.693708/full |
| work_keys_str_mv | AT sebastiangutmann truckparkingoccupancypredictionxgboostlstmmodelfusion AT sebastiangutmann truckparkingoccupancypredictionxgboostlstmmodelfusion AT christophmaget truckparkingoccupancypredictionxgboostlstmmodelfusion AT christophmaget truckparkingoccupancypredictionxgboostlstmmodelfusion AT matthiasspangler truckparkingoccupancypredictionxgboostlstmmodelfusion AT klausbogenberger truckparkingoccupancypredictionxgboostlstmmodelfusion |