TDCM: Transport Destination Calibrating Based on Multi-task Learning

Wu, Tao; Zhu, Kaixuan; Mao, Jiali; Yang, Miaomiao; Zhou, Aoying

doi:10.1007/978-3-031-43430-3_17

Cited by 2 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are unsuitable for identifying large-scale places containing several areas where a certain distance lies between areas, e.g., a logistics park having multiple companies, a large steel mill with many warehouses, etc. To address this issue, we put forward a road turn-off location based destination identification strategy in our previous study [10]. But it still cannot ensure precisely identifying locations of the Tshots having multiple entrances such as deserted open spaces.…”

Section: Related Workmentioning

confidence: 99%

“…Here we use this method to cluster stay points to detect Tshots. • TDCM [10] proposes a stay area merging strategy to infer the location of the transport destination. It first clusters stay points to detect stay areas, then infers the road turn-off locations for each stay area by clustering road turn-off points.…”

Section: Datasets and Settingsmentioning

confidence: 99%

“…To address the first challenge, in view of that different Tshots have their respective locations of turning points on the road (as road turn-off locations marked by arrows in Fig. 1(a), we first try to merge the stay areas that obtained by clustering the stay points based on extracted road turn-off locations [10]. But given some Tshots (e.g., ) have more than one entrance, the above strategy may result in low precision of location identifying for Tshots.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-View Context Awareness based Transport Stay Hotspot Recognization

Wu,

Mao,

Zhu

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

During long distance transporting for bulk commodities, the trucks need to stop off at multiple places for resting, refueling, repairing or unloading, which are important in transport route planning, called as transport stay hotspots (or Tshot for short). Massive waybills and their related trajectories accumulated by the freight platforms enable us to recognize Tshots and keep them updated constantly. But due to most of Tshots have varying sizes and are adjacent to each other, it is hard to pinpoint their locations precisely. In addition, to correctly annotate functional tags of Tshots that have fewer visiting trajectories is quite difficult. In this paper, we propose a Multi-view Context awareness based transport Stay hotspot Recognization framework, called MCSR, consisting of location identification, feature extraction and functional tag annotation. To address the mis-detection issue in pinpointing adjacent Tshots having various sizes, we design a multi-view clustering based stay area merging strategy by incorporating distance between road turn-off locations, number of visiting trajectories with similarity of visiting time distribution. Further, aiming at the issue of low annotating precision resulted by data scarcity, based upon extracting behavioral features and attribute features from waybill trajectories, we leverage a time interval-aware self-attention network to extract semantic contextual features to assist in ensemble learning based annotation modeling correctly. Finally, extensive experiments and case studies are conducted on real steel logistics data to demonstrate the effectiveness and practicability of MCSR.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Datasets and Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation