Development of Multilayer-Based Map Matching to Enhance Performance in Large Truck Fleet Dispatching

Abstract

Spatial information technology has been widely used for vehicles in general and for fleet management. Many studies have focused on improving vehicle positioning accuracy, although few studies have focused on efficiency improvements for managing large truck fleets in the context of the current complex network of roads. Therefore, this paper proposes a multilayer-based map matching algorithm with different spatial data structures to deal rapidly with large amounts of coordinate data. Using the dimension reduction technique, the geodesic coordinates can be transformed into plane coordinates. This study provides multiple layer grouping combinations to deal with complex road networks. We integrated these techniques and employed a puncture method to process the geometric computation with spatial data-mining approaches. We constructed a spatial division index and combined this with the puncture method, which improves the efficiency of the system and can enhance data retrieval efficiency for large truck fleet dispatching. This paper also used a multilayer-based map matching algorithm with raster data structures. Comparing the results revealed that the look-up table method offers the best outcome. The proposed multilayer-based map matching algorithm using the look-up table method is suited to obtaining competitive performance in identifying efficiency improvements for large truck fleet dispatching.

Developing Prediction Model of Travel Times of the Logistics Fleets of Large Convenience Store Chains Using Machine Learning

“…For example, if there is a group of data with a sample size of 17, the average travel time obtained by this study model is 3270, and the travel time predicted by the map is 2796, the time difference is (3270 − 2796)/2796 = 16.9, and the reference rate is 17/16.9, which is about 100%. The equation of reference rate is shown in (3).…”

“…For example, if there is a group of data with a sample size of 17, the average travel time obtained by this study model is 3270, and the travel time predicted by the map is 2796, the time difference is (3270 − 2796)/2796 = 16.9, and the reference rate is 17/16.9, which is about 100%. The equation of reference rate is shown in (3). To prevent the lack of historical travel data for some location pairs from undermining the quality of dispatch scheduling, this study filled the missing data by using the established intervallic road networks as training data for machine learning and constructing a nonlinear regression equation.…”

“…Many studies have been conducted on map matching. Mu et al [3] proposed the conversion of vector data into raster data and the use of a look-up table for rapidly finding the location corresponding to a set of destination coordinates from each pixel in the raster data. Their method was more efficient than the conventional puncture method.…”