As a key factor of logistics distribution, vehicle routing problem (VRP) is a hot research topic in management and computation science. In this paper the principle and algorithm process of firefly algorithm are introduced in detail. Then the algorithm process and solving steps are designed for vehicle routing problem with time windows (VRPTW), including the coding and design of disturbance mechanism of elicit fireflies. In the end, the testing examples from benchmark and other literatures are conducted with good outputs, which prove the validity of the firefly algorithm for VRP.
Accurately predicting the spatiotemporal distribution of traffic accident risk is crucial for proactive safety management and intelligent transportation systems. However, the inherent complex spatial dependencies and dynamic temporal patterns in traffic data, coupled with severe class imbalance in accident severity categories, pose significant challenges to conventional prediction models. This study proposes a novel deep learning framework that integrates Graph Neural Networks (GNN) and Long Short-Term Memory (LSTM) networks to address these challenges. The GNN module effectively captures complex spatial dependencies between geographical regions by modeling the traffic network as a graph structure, while the LSTM module learns the temporal dynamics of accident occurrences. To tackle the critical issue of data imbalance caused by scarce severe accident samples, this study employs the Adaptive Synthetic Sampling (ADASYN) technique at the data level to balance sample distributions, and at the model level, utilizes the Focal Loss function to focus the training process on hard-to-classify minority class instances. Furthermore, the model architecture incorporates TransformerConv layers, bidirectional LSTM, and multi-head attention mechanisms to capture more nuanced spatiotemporal features. Experimental evaluation on the large-scale US-Accidents dataset (2016–2021) demonstrates that the proposed GNN-LSTM fusion model significantly outperforms existing methods across multiple key metrics. On the test set, the model achieved a weighted F1-score of 0.7923 ± 0.0123 and a macro-average F1-score of 0.6587 ± 0.0156, representing improvements of 1.12 and 3.53 percentage points, respectively, over the strongest baseline model Graph WaveNet. In addressing class imbalance, the model attained an AUC-PR of 0.7124 ± 0.0098 and a Cohen’s Kappa of 0.6012 ± 0.0134, both significantly superior to conventional approaches. Ablation studies further validated the effectiveness of key components, with the GNN module contributing 13.8% to the performance gain, while ADASYN and Focal Loss contributed 8.7 and 6.5%, respectively. This study provides a robust and efficient solution for traffic risk prediction, offering a scientific foundation for traffic management authorities to develop precise early-warning systems and targeted intervention strategies.
1 July 2021 in Journal of Physics: Conference Series
With the rapid development of traffic, urban expressways are becoming more and more popular. However, the problem of overload and overrun on expressways that followed has been repeatedly banned, seriously affecting transportation safety. This article takes the urban expressway in Huai’an as an example, collects big data, analyzes the data with SPSS software, and combines the real case of the viaduct collapse in Wuxi to provide governance strategies for expressway overload and over-run control and improve transportation safety.
1 November 2019 in IOP Conference Series: Materials Science and Engineering
This paper studies the problem of urban express joint distribution. Considering the problem of distribution complexity of city express delivery due to multiple frequency and small quantity and difficult to form economies of scale, we proposed the joint distribution mode and a mathematical model of split delivery vehicle routing problem based on the mode with the goal of minimum total distribution cost. Then an improved competition decision algorithm based on the characteristics of the model was designed. Finally, the effectiveness and practicability of the model and algorithm were illustrated by calculations.
In order to explore the location problem of emergency logistics center in Central China under public health emergencies, this study selected 30 cities in Central China as the research object and realized the location of emergency logistics center in Central China by constructing the location model of emergency logistics center. Firstly, the model uses a two-stage iterative method to extract the structure of large network communities, and divides the Central China into 5 communities with close internal road networks. Then, the Floyd algorithm was used to select 5 potential emergency logistics center cities from these communities. Further, starting from four key dimensions such as social economy and infrastructure development level, this study constructs an evaluation system including 14 comprehensive evaluation indicators. By applying D-CRITIC (Distance Correlation-based CRITIC)-GRA (Grey Relational Analysis), the paper conducts an in-depth analysis of 5 candidate cities within each community, and obtains the grey weighted Correlation degree of 5 candidate cities within each community. Finally, the study identified the city with the highest gray weighted correlation degree in each community as the first-level emergency logistics center, and selected the candidate city of second-level emergency logistics center. Through the model constructed in this paper, the hub-and-spoke network structure of emergency logistics in Central China under public health emergencies is constructed.
In recent years, urban road traffic is frequently affected by various abnormal events, which not only damage the traffic facilities, but also have an impact on the operation of social economy. Therefore, it has become an important research direction to explore the resilience of urban road traffic, identify its influencing factors, and analyze the advantages and disadvantages of urban traffic resilience. This paper takes Beijing and Shanghai as the research objects, uses analytic hierarchy process (AHP) to construct the urban road traffic resilience evaluation index system, obtains the index data from 2017 to 2021, and evaluates the urban road traffic resilience according to the index weights by using the grey relational degree model. The main research content is the evaluation of urban road traffic resilience, the exploration of influencing factors and the optimization strategy. The results show that road traffic resilience in Beijing and Shanghai is closely related to each index.