It is critical to properly plan charging station locations for wider acceptance and penetration of electric vehicles. While, siting and optimizing charging stations in large cities is a massive combinatorial optimization problem involving various factors, and finding a satisfactory solution remains challenging. To solve this problem, this study analyzes the multi-source heterogeneous data related to charging station planning and predicts potential charging demands, thus paving the road for siting location optimization. A multi-objective siting optimization model of charging stations is established with the consideration of minimal investment, maintenance, and user access costs. An improved genetic algorithm (GA) is developed to seek the optimization solution by merging the simulated annealing algorithm, adaptive intersection crossover operator, and elite retention strategy. A case study validation in Chongqing, China shows that the latent charging demand and other factors can provide data to support siting optimization, making charging stations with different grades more evenly distributed and more convenient for users to access. More broadly, the proposed GA enables the avoidance of prematurity and achieves a better solution than the state-of-the-art bionic intelligent algorithms, with a cost decrease of at least 3.22%.

Examining how travel distance is associated with travel mode choice is essential for understanding traveler travel patterns and the potential mechanisms of behavioral changes. Although existing studies have explored the effect of travel distance on travel mode choice, most overlook their non-linear relationship and the heterogeneity between groups. In this study, the correlation between travel distance and travel mode choice is explored by applying the random forest model based on resident travel survey data in Guiyang, China. The results show that travel distance is far more important than other determinants for understanding the mechanism of travel mode choice. Travel distance contributes to 42.28% of explanation power for predicting travel mode choice and even 63.24% for walking. Significant nonlinear associations and threshold effects are found between travel distance and travel mode choice, and such nonlinear associations vary significantly across different socioeconomic groups. Policymakers are recommended to understand the group heterogeneity of travel mode choice behavior and to make targeted interventions for different groups with different travel distances. These results can provide beneficial guidance for optimizing the spatial layout of transportation infrastructure and improving the operational efficiency of low-carbon transportation systems.

The widespread penetration of electric bicycles (E-bicycles) raises numerous charging safety concerns. However, online diagnosis of charging safety for E-bicycles remains challenging due to the limited data and involvement of multiple factors, such as battery, charger, charging mode, and user behavior. To overcome this difficulty and promote charging safety, this article proposes a nonintrusive charging safety intelligent diagnosis scheme on the inputted power grid side. First, more than 150 000 charging records are collected from the grid side, and various charging current patterns are formally identified according to the working principles of different batteries, charging modes, and user behaviors. Then, on the basis of longest similar substring (LSS), an improved dynamic time warping (DTW) model, referred to as LSS-DTW, is established to efficiently identify the charging current profile similarities and meanwhile restrict the overregularization of DTW. By this manner, the abnormal charging processes can be accurately identified. Experimental results reveal that the built LSS-DTW model can distinguish the unsafe charging processes online, and achieve the average identification precision, recall, and F1-score of 94%. Furthermore, the proposed algorithm can be extended to similar charging safety identifications in electric vehicles and other battery-powered systems and provides early warnings to avoid catastrophic consequences.

Real-time and accurate short-term traffic flow prediction is important for the operation and management of expressways. This paper presents a hybrid model that can be used to discover the spatiotemporal dependencies of traffic flows and, thus, achieve a more accurate traffic flow forecast. This model stacks a full connection (FC) layer, two-layer long short-term memory (LSTM), and a middle mean pooling layer, denoted by FC-LSTM, to expand the ability of LSTM to capture spatial correlations and too long-term temporal dependencies of traffic flows. Traffic data of 51 toll stations (accounting for 15% of all stations) in the Guizhou expressway network in China in January 2016 were used to evaluate the validation of FC-LSTM. The results showed that the traffic flows at adjacent tollgates were interactional and correlated, that FC-LSTM could capture this spatial dependency and the temporal correlations of traffic flows, and, thus, that it was superior to other baselines with a low prediction error, high precision, and high fitting degree. Moreover, FC-LSTM is interpretable and robust owing to its explicit input and is suitable for traffic flow prediction for most tollgates under the same parameters.