Paper WeBT11.3
Klinger, Julian (University of Applied Sciences FH Kufstein Tirol), Mohebbi Najmabad, Mohammadreza (Josef Ressel Center Vision2Move, University of Applied Sciences ), Döller, Mario (University of Applied Sciences FH Kufstein Tirol)
Real Transportation Data Benchmark: Advancing Efficiency through ML-Based Waiting Time Prediction
Scheduled for presentation during the Regular Session "Intelligent Logistics" (WeBT11), Wednesday, September 25, 2024,
15:10−15:30, Salon 19/20
2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada
This information is tentative and subject to change. Compiled on October 3, 2024
|
|
Keywords Intelligent Logistics, Theory and Models for Optimization and Control, Data Mining and Data Analysis
Abstract
In transport and supply chain management (SCM), accurate prediction of waiting times is pivotal for optimizing resource allocation, minimizing costs, and operational efficiency. However, this task is filled with challenges due to numerous unknown variables, including congestion, weather conditions, and varying operational requirements. This paper addresses these challenges by predicting the waiting times of transporters in transport management and SCM. By analyzing key performance indicators in the planning process of production measures and delivery cycles, we have identified an important research direction for improving the accuracy of forecasting waiting times. Therefore, we introduce a novel dataset based on real data, focusing on delivery cycles, by analyzing GPS-Trajectories and planning data of 165 transporters on 550 production measures in a span of one year and condensing them into a total of 6144 delivery records. To set a performance baseline, we analyze this dataset and apply several Machine Learning models, such as AdaBoost, SVR and MLP, for waiting time prediction by providing different metrics such as MAE, MSE and the R2-Score. We conclude that, with our approach, it is possible to successfully predict waiting time in the form of trends already in the planning phase of transport management.
|
|