Owing to the strength in learning representation of the high-order connectivity of graph neural networks (GNN), GNN-based collaborative filtering has been widely adopted in recommender systems. Furthermore, to overcome the data sparsity problem, some recent GNN-based models attempt to incorporate social information and to design contrastive learning as an auxiliary task to assist the primary recommendation task. Existing GNN and contrastive-learning-based recommendation models learn user and item representations in a symmetrical way and utilize social information and contrastive learning in a complex manner. The above two strategies lead to these models being either ineffective for datasets with a serious imbalance between users and items or inefficient for datasets with too many users and items. In this work, we propose a contrastive graph learning (CGL) model, which combines social information and contrastive learning in a simple and powerful way. CGL consists of three modules: diffusion, readout, and prediction. The diffusion module recursively aggregates and integrates social information and interest information to learn representations of users and items. The readout module takes the average value of user embeddings from all diffusion layers and item embeddings at the last diffusion layer as readouts of users and items, respectively. The prediction module calculates prediction rating scores with an interest graph to emphasize interest information. Three different losses are designed to ensure the function of each module. Extensive experiments on three benchmark datasets are implemented to validate the effectiveness of our model.
Traffic surveillance can be used to monitor and collect the traffic condition data of road networks, which plays an important role in a wide range of applications in intelligent transportation systems (ITSs). Accurately and rapidly detecting and counting vehicles in traffic videos is one of the main problems of traffic surveillance. Traditional video-based vehicle detection methods, such as background subtraction, frame difference, and optical flow have some limitations in accuracy or efficiency. In this paper, deep learning is applied for vehicle counting in traffic videos. First, to solve the problem of the lack of annotated data, a method for vehicle detection based on transfer learning is proposed. Then, based on vehicle detection, a vehicle counting method based on fusing the virtual detection area and vehicle tracking is proposed. Finally, due to possible situations of missing detection and false detection, a missing alarm suppression module and a false alarm suppression module are designed to improve the accuracy of vehicle counting. The results show that the proposed deep learning vehicle counting framework can achieve lane-level vehicle counting without enough annotated data, and the accuracy of vehicle counting can reach up to 99%. In terms of computational efficiency, this method has high real-time performance and can be used for real-time vehicle counting.
African swine fever first broke out in mainland China in August 2018 and has caused a substantial loss to China’s pig industry. Numerous investigations have confirmed that trades and movements of infected pigs and pork products, feeding pigs with contaminative swills, employees, and vehicles carrying the virus are the main transmission routes of the African swine fever virus (ASFV) in mainland China. However, which transmission route is more risky and what is the specific transmission map are still not clear enough. In this study, we crawl the data related to pig farms and slaughterhouses from Baidu Map by writing the Python language and then construct the pig transport network. Following this, we establish an ASFV transmission model over the network based on probabilistic discrete-time Markov chains. Furthermore, we propose spatiotemporal backward detection and forward transmission algorithms in semi-directed weighted networks. Through the simulation and calculation, the risk of transmission routes is analyzed, and the results reveal that the infection risk for employees and vehicles with the virus is the highest, followed by contaminative swills, and the transportation of pigs and pork products is the lowest; the most likely transmission map is deduced, and it is found that ASFV spreads from northeast China to southwest China and then to west; in addition, the infection risk in each province at different times is assessed, which can provide effective suggestions for the prevention and control of ASFV.
This study collects data on electric vehicle (EV) charging piles for various provinces in China and analyzes the development of the network of EV chargers from the perspective of a complex network. Features of the distribution of EV charging piles for the period from May 2016 to April 2019 and the spatio-temporal variations across provinces are thus analyzed. The study then transforms time-series data of the EV charging piles into a complex network by applying a visibility graph, uses several clustering methods to categorize different provinces, and predicts the future development of the network of EV charging piles in China. Additionally, the distribution of EV charging piles across time is analyzed for a combination of national policies and new-energy vehicles. The results of the study will guide provincial governments in creating policies that develop relevant industries progressively and promote the sustainable development of EVs and green-energy industry.