As travel demand becomes more diversified and personalized, traditional bus operation struggles to meet the requirements of high-quality service. The customized bus, with its flexibility, has garnered significant attention. However, optimizing customized bus lines involves multiple decision variables. As the scale of transportation networks continues to expand, traditional methods struggle to find the optimal solution within a limited time. In this paper, we propose an innovative customized bus line optimization model and an efficient solving algorithm. In terms of modeling, we aim to maximize the number of passengers served by jointly optimizing bus routes, stop locations, departure time, and service capacity, while considering various constraints such as tolerance time to ensure the service efficiency of customized buses. Since the problem is intractable by exhaustive search, we design a column generation-based algorithm to acquire the optimal solution efficiently. We compare the proposed algorithm with direct solving using the Gurobi solver in small-scale, medium-scale, and large-scale scenarios. The experimental results show that the proposed algorithm can effectively find the optimal solution, even in the large-scale scenario where the Gurobi solver fails to deliver a solution.

The cross-view image geo-localization (CVGL) refers to determining the geographic location of a given query image using an image database with the known location information. Existing methods mainly focus on learning discriminative image representations to optimize the distance of image feature representations in feature space without fully considering the positional relation information of the features and the information redundancy in the features themselves. Therefore, we proposed a cross-view image localization method that combines the global spatial relation attention (GSRA) with feature aggregation. First, we utilize the lightweight GSRA to learn the spatial location structure information of features, which fully enhances the perceptual and discriminative capabilities of the model. The proposed attention has a little effect on the complexity and memory occupancy of the model and can be generalized to other image-processing tasks. In addition, we introduce the sinkhorn algorithm for locally aggregated descriptors (SALADs), which represents the aggregation of local features as an optimal transport problem and selectively discards useless information during the clustering and assignment of features, thus enhancing the generalization and robustness of the descriptors. Experimental results on the public University-1652, CVACT, and CVUSA datasets validate the effectiveness and superiority of the proposed method. Our code is available at:https://github.com/WenjianGan/LRFR.

In the age of big data, the massive online user activity across desktop and mobile platforms generates an immense volume of web traffic logs. Analyzing and forecasting user behaviors, particularly page views, are vital for organizations aiming to enhance personalization, recommendation systems, and search engine optimization efforts. While traditional statistical methods have long been employed for web traffic forecasting, recent advancements in deep learning offer new opportunities for more accurate and insightful predictions. This paper presents a comprehensive comparative study of traditional statistical forecasting techniques and state-of-the-art deep learning methods applied to publicly available Wikipedia web traffic data, which includes hundreds of thousands of pages with over two years of historical page views. We evaluate various deep learning architectures encompassing different model structures, including recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), multilayer perceptrons (MLPs), transformer-based models without pre-training, and pre-trained foundational models. Our findings reveal that deep learning approaches, particularly those leveraging cross-learning and transfer-learning capabilities, significantly outperform conventional methods in forecasting accuracy. These advanced models provide a powerful means to better understand online users’ browsing activities. The enhanced predictive performance of deep learning frameworks equips data scientists and researchers with more effective tools, ultimately improving productivity and efficiency in the analysis of web traffic patterns.

Geolocating a street-view image by matching it with geotagged satellite images is crucial for location assessment. However, the perspective disparity between satellite and street-view images presents significant challenges. To address the issue, the mainstream approach is to convert satellite images to ground-level perspective. So the reference satellite images are not only required the center but also required the coverage to be consistent with the street view images and sometimes even required consistency in the north direction, which is difficult to achieve in the practical applications. This paper introduces a ground-breaking method for converting ground-level images to satellite images. We effectively couple ground images and satellite images by establishing a hemispheric projection relationship to achieve conversion from ground images to satellite perspectives, thus solving the problem of huge perspective differences in cross-view geolocation(CVG). Additionally, we propose the multi-scale fusion of a spatial features mechanism to enhance deep feature representations, improve recall and geolocation accuracy.Our proposed methodology markedly enhances its practical utility and performance, attaining remarkable Top-1 accuracy rates of 75.08% on the CVACT_val dataset and 39.92% on the CVACT_test dataset, respectively, following a stringent quantitative appraisal. This advancement constitutes a substantial contribution to the progression of research in the field of CVG.

The directed brain functional network construction gives us the new insights into the relationships between brain regions from the causality point of view. The Granger causality analysis is one of the powerful methods to model the directed network. The complex brain network is also hierarchically constructed, which is particularly suited to facilitate segregated functions and the global integration of the segregated functions. Therefore, it is of great interest to explore new approach to model the hierarchical architecture of the directed network. In the present study, we proposed a new approach, namely, stepwise multivariate Granger causality (SMGC), considering both the directed and hierarchical features of brain functional network to explore the stepwise causal relationship in the network. The simulation study demonstrated that the diverse and complex hierarchical organization could be embedded in the apparently simple directed network. The proposed SMGC method could capture the multiple hierarchy of the directed network. When applying to the real functional magnetic resonance imaging (fMRI) datasets, the core triple resting-state networks in human brain showed within-network directed connections in the first-level directed network and rich and diverse between-network pathways in the second-level hierarchical network. The default mode network (DMN) had a prominent role in the resting-state acting as both the causal source and the important relay station. Further exploratory research on the adaption of directed hierarchical network in athletes suggested the enhanced bidirectional communication between the DMN and the central executive network (CEN) and the enhanced directed connections from the salience network (SN) to the CEN in the athlete group. The SMGC approach is capable of capturing the hierarchical architecture of the brain directed functional network, which refreshes the new stepwise causal relationship in the directed network. This might shed light on the potential application for exploring the altered hierarchical organization of brain directed network in neuropsychiatric disorders.

Response Time Analysis ( RTA ) is an important and promising technique for analyzing the schedulability of real-time tasks under both Global Fixed-Priority ( G-FP ) scheduling and Global Earliest Deadline First ( G-EDF ) scheduling. Most existing RTA methods for tasks under global scheduling are dominated by partitioned scheduling, due to the pessimism of the -based interference calculation where is the number of processors. Two-part execution scenario is an effective technique that addresses this pessimism at the cost of efficiency. The major idea of two-part execution scenario is to calculate a more accurate upper bound of the interference by dividing the execution of the target job into two parts and calculating the interference on the target job in each part. This article proposes a novel RTA execution framework that improves two-part execution scenario by reducing some unnecessary calculation, without sacrificing accuracy of the schedulability test. The key observation is that, after the division of the execution of the target job, two-part execution scenario enumerates all possible execution time of the target job in the first part for calculating the final Worst-Case Response Time ( WCRT ). However, only some special execution time can cause the final result. A set of experiments is conducted to test the performance of the proposed execution framework and the result shows that the proposed execution framework can improve the efficiency of two-part execution scenario analysis by up to in terms of the execution time.

With the rapid development of bulk power grid under extra-high voltage (EHV) AC/DC hybrid power system and extensive access of distributed energy resources (DER), operation characteristics of power grid have become increasingly complicated. To cope with new severe challenges faced by safe operation of interconnected bulk power grids, an in-depth analysis of bulk power grid security defense system under the background of EHV and new energy resources was implemented from aspects of management and technology in this paper. Supported by big data and cloud computing, bulk power grid security defense system was divided into two parts: one is the prevention and control of operation risks. Power grid risks are eliminated and influence of random faults is reduced through measures such as network planning, power-cut scheme, risk pre-warning, equipment status monitoring, voltage control, frequency control and adjustment of operating mode. The other is the fault recovery control. By updating “three defense lines”, intelligent relay protection is used to deal with the challenges brought by EHV AC/DC hybrid grid and new energy resources. And then security defense system featured by passive defense is promoted to active type power grid security defense system.