Deep reinforcement learning (DRL)-based frameworks, featuring Transformer-style policy networks, have demonstrated their efficacy across various vehicle routing problem (VRP) variants. However, the application of these methods to multi-trip time-dependent (MTTDVRP) with maximum working hours constraints—a pivotal element urban logistics—remains largely unexplored. This paper introduces a DRL-based method called Simultaneous Encoder and Dual Decoder Attention Model (SED2AM), tailored for...

Analyzing freight vehicle movements using GPS trajectory data presents challenges due to environmental conditions and hardware limitations impacting accuracy. Map matching, the process of aligning signals with road networks, facilitates accurate route reconstruction. However, existing methods have limitations, particularly low ultra-low sampling rates. They often assume shortest path between points, overlook historical insights neglect diverse driving behaviors, which may not align...

Anomalous urban mobility pattern refers to abnormal human flow in a city. detection is important the study of mobility. In this paper, framework proposed identify anomalous patterns based on taxi GPS trajectories and Point Interest (POI) data. framework, functional regions are first generated distribution POIs by DBSCAN clustering algorithm. A Weighted Term Frequency-Inverse Document Frequency (WTF-IDF) method function values each region. Then, Origin-Destination (OD) trips between extracted...

Outfit recommendation requires the answers of some challenging outfit compatibility questions such as 'Which pair boots and school bag go well with my jeans sweater?'. It is more complicated than conventional similarity search, needs to consider not only visual aesthetics but also intrinsic fine-grained multi-category nature fashion items. Some existing approaches solve problem through sequential models or learning pair-wise distances between However, most them coarse category information in...

Sexual health education is an essential part of quality-oriented for college students. It aims to help these students acquire knowledge sexual physiology, psychology, and social norms that consistent with the maturity Along students’attitudes toward sex, their perceptions regarding behavior have also undergone profound changes. The importance safe behavior, taboos, autonomy are gaining increasing attention as Chinese society becoming more open. For who just reached adulthood full themselves,...

The current study investigated what influences college students’ behavioral intention and behavior towards sports gambling using the theory of planned (TPB) as a theoretical framework. also explored moderation effect problem severity in relationships between TPB determinants, intention, behavior. Data were collected from 334 students four different universities U.S. analyzed through partial least squares structural equation modeling (PLS-SEM) multi-group analysis. results indicated that...

GPS (Global Positioning System) trajectories with low sampling rates are prevalent in many applications. However, current map matching methods do not perform well for low-sampling-rate due to the large uncertainty between consecutive points. In this paper, a collaborative method (CMM) is proposed trajectories. CMM processes batches. First, it groups similar into clusters and then supplements missing information by resampling. A trajectory extracted each cluster matched road network, based on...

Fleet sizing is critical for shared autonomous vehicle(SAV) fleet management to reduce maintenance costs and traffic congestions. As the passenger demands are dynamic, how make demand-aware dynamic ridesharing calculate size an important challenging problem. In this paper, we propose a minimum method called Sizing Dynamic Ridesharing (FSDR) accurately determine enabled SAV system. Specifically, travel first predicted by ensemble that takes account of temporal correlations between regions....

Efficiency is crucial to the online recommender systems, especially for ones which needs deal with tens of millions users and items. Because representing items as binary vectors Collaborative Filtering (CF) can achieve fast user-item affinity computation in Hamming space, recent years, we have witnessed an emerging research effort exploiting hashing techniques CF methods. However, codes naturally suffers from low accuracy due limited representation capability each bit, impedes it modeling...

This article addresses two important issues of causal inference in the high-dimensional situation. One is how to reduce redundant conditional independence (CI) tests, which heavily impact efficiency and accuracy existing constraint-based methods. Another construct true graph from a set Markov equivalence classes returned by these For first issue, we design recursive decomposition approach where original data (a variables) are decomposed into small subsets, each then recursively smaller...

Abstract Labor education in colleges and universities the new era is fundamental task of implementing principle establishing morality educating people, as well an essential hand cultivating college students with all-round development morality, intelligence, physicality, aesthetics, labor. This paper focuses on objective evaluation method students’ labor to conduct research. Using improved binary tree support vector machine multi-class classification algorithm, model for based a has been...

Recent advances in satellite technology have brought enormous potential to ecosystem mapping, which is one of the fundamental components environmental studies. In this paper, a Random Forest classifier applied for strict assessment efficiency mapping through detailed comparative analysis between combined Sentinel-1 and Sentinel-2 data stand-alone imagery over three priority ecosystems, including wetlands, riverine areas, mangroves Bangladesh. The collocated images, based on integration with...

Land use and transportation planning have a significant impact on the performance of cities’ traffic conditions quality people’s lives. The changing characteristics land will affect challenge how city is able to manage, organize, plan for new developments transportation. These challenges can be better addressed with effective methods monitoring predicting, which enable optimal efficiency in growing like Calgary, Canada, perform. Using ontology initiative currently being researched explored....

Abstract Trailer allocation and truck routing are critical components of transportation management. However, in real‐world applications, inter‐influence between selecting the best trailers trucks, strict fulfillment Pickup or Delivery (PD) orders, size fleet some challenges that need to be dealt with a large company. In addition, trailer problems considered NP‐hard combinatorial optimization (CO) problems. Therefore, we use deep reinforcement learning (DRL), which has capability solving...

In the matching pursuit algorithm of compressed sensing, traditional reconstruction needs to know signal sparsity. The sparsity adaptive (SAMP) can adaptively approach when is unknown. However, SAMP starts from zero and iterates several times with a fixed step size approximate true sparsity, which increases runtime. To increase run speed, preestimated (SPAMP) proposed in this paper. Firstly, strategy used estimate then reconstructed by as iterative initial value. method reconstructs reduces...