Abstract Traffic flow prediction plays a crucial role in intelligent transportation systems as it enables effective control and management of urban traffic. However, existing methods that based on Graph Convolutional Networks (GCNs) primarily utilize local neighborhood information for message passing, resulting in limited perception of global structures. Additionally, it is also a challenge to extract spatial-temporal similarity features due to the constraints of graph structures. To address these issues, we propose a novel traffic flow prediction model based on Dynamic Spatial-Temporal Similarity Pyramid Network (DSTSPYN). Our model employs a spatial-temporal pyramid architecture, which dynamically adjusts the weights of central, edge, and global spatial-temporal features using an enhanced attention mechanism. Furthermore, it captures dynamic temporal dependencies at different scales through pyramid gated convolution. Meanwhile, the spatial similarity features of different time steps can be extracted through the spatial-temporal global similarity (STGS) module. We evaluate our model on four public transportation datasets and demonstrate that the DSTSPYN model outperforms several baseline methods in terms of prediction accuracy. It effectively captures the dynamic spatial-temporal correlations of the road network and edge node features, making it well-suited for long-term traffic flow prediction.

ABSTRACT The reliable operation of on‐board unit (OBU) in electronic toll collection (ETC) systems is critical for maintaining transaction accuracy and preventing revenue loss. However, real‐time monitoring of OBU status faces challenges such as technological obsolescence, environmental vulnerabilities, and data inconsistencies. This study proposes a novel GraphSAGE‐based approach for real‐time OBU status monitoring. First, we establish a classification standard for OBU operating status based on missing data patterns, enabling precise identification of abnormal states. Second, we design a real‐time data warehouse architecture tailored to the characteristics of ETC transaction data, ensuring efficient data processing and storage. Third, we use the GraphSAGE model to monitor OBU status in real‐time, leveraging heterogeneous graph learning to capture both temporal and structural dependencies in the data. The experimental results demonstrate the effectiveness of the proposed approach, achieving a true positive rate of 99.8% and a false positive rate of 0.2% across various performance metrics, including accuracy, precision, recall, and F1‐score. The proposed method outperforms existing models, such as graph convolutional network, GAT, and XGBoost, in real‐time monitoring tasks, showcasing its stability and generalization ability under different data volumes. This study provides a comprehensive framework for improving OBU condition monitoring, contributing to enhanced maintenance strategies and more effective detection of fee evasion by regulatory authorities.

Traffic flow prediction forms a critical foundation for the management and planning of urban transportation systems. However, the complex spatial interactions among road segments and the dynamic patterns of traffic flow variations across multiple time scales pose significant challenges to improving forecasting accuracy. To address these complexities, this paper introduces a Diversified Spatio-Temporal Feature Extraction (DSTF) Model, designed to effectively mine temporal, spatial, and spatio-temporal cross-correlations. Specifically, in the temporal dimension, a gated convolution-enhanced Res2Net architecture is employed to capture diverse traffic flow patterns across varying time scales. In the spatial dimension, the model integrates global and local perspectives by employing spatial attention mechanisms and a dual-view Geom-GCN, enabling it to capture global spatial dependencies, local geographic neighborhood relationships, and semantic similarity-driven spatial correlations among nodes within the urban road network. For spatio-temporal cross-correlations, a dynamic synchronization aggregation module is developed using spatio-temporal attention, effectively capturing the evolving interactions between nodes or regions across different time slices. Experimental evaluations conducted on four real-world highway traffic datasets demonstrate that DSTF outperforms PDFormer, achieving average improvements of 1.35%, 1.61% and 0.81% in MAE, MAPE and RMSE metrics, respectively. These results highlight the model’s superior capability in extracting and leveraging temporal and spatial features for traffic flow prediction. • Addresses issues related to dynamic traffic flow data. • Captures multi-scale time features of traffic flow temporally. • Models the dynamism of traffic flow in both temporal and spatial dimensions. • Surpasses state-of-the-art methods.

The rapid advancement of autonomous driving systems has created a pressing need for accurate and robust lane detection to ensure driving safety and reliability. However, lane detection still faces several critical challenges in real-world scenarios: 1) severe occlusions caused by urban traffic and complex road layouts; 2) the difficulty of handling sharp curves and large curvature variations; and 3) varying lighting conditions that blur or degrade lane markings. To address these challenges, we propose DLNet, a novel direction-aware feature integration framework that integrates both low-level geometric details and high-level semantic cues. In particular, the approach includes: (i) a Multi-Skip Feature Attention Block (MSFAB) to refine local lane features by adaptively fusing multi-scale representations, (ii) a Context-Aware Feature Pyramid Network (CAFPN) to enhance global context modeling under adverse conditions, and (iii) a Directional Lane IoU (DLIoU) loss function that explicitly encodes lane directionality and curvature, providing more accurate lane overlap estimation. Extensive experiments conducted on two benchmark datasets, CULane and CurveLanes, show DLNet achieves new state-of-the-art results, with${\mathrm {F}}{1_{50}}$and${\mathrm {F}}{1_{75}}$scores of 81.23% and 64.75% on CULane, an${\mathrm {F}}{1_{50}}$score of 86.51% on CurveLanes and a high F1 score of 97.62% on the TUSimple dataset. Moreover, the model maintains competitive computational efficiency at 18.8 GFLOPs while running at 74FPS, satisfying real-time requirements. The source code has been publicly released athttps://github.com/RDXiaoLu/DLNet.git

Accident severity prediction is a hot topic of research aimed at ensuring road safety as well as taking precautionary measures for anticipated future road crashes. In the past decades, both classical statistical methods and machine learning algorithms have been used to predict traffic crash severity. However, most of these models suffer from several drawbacks including low accuracy, and lack of interpretability for people. To address these issues, this paper proposed a hybrid of Balanced Bagging Classification (BBC) and Light Gradient Boosting Machine (LGBM) to improve the accuracy of crash severity prediction and eliminate the issues of bias and variance. To the best of the author’s knowledge, this is one of the pioneer studies which explores the application of BBC-LGBM to predict traffic crash severity. On the accident dataset of Great Britain (UK) from 2013 to 2019, the proposed model has demonstrated better performance when compared with other models such as Gaussian Naïve Bayes (GNB), Support vector machines (SVM), and Random Forest (RF). More specifically, the proposed model managed to achieve better performance among all metrics for the testing dataset (accuracy = 77.7%, precision = 75%, recall = 73%, F1-Score = 68%). Moreover, permutation importance is used to interpret the results and analyze the importance of each factor influencing crash severity. The accuracy-enhanced model is significant to several stakeholders including drivers for early alarm and government departments, insurance companies, and even hospitals for the services concerned about human lives and property damage in road crashes.

Reversible data hiding with contrast enhancement (RDH-CE) is proposed to aim at improving the contrast of images while embedding data. After deeply analyzing and studying the RDH-CE method proposed by Jafaret al., it is found that there are three main problems in their method. Firstly, their method ignores the fact that the left-bottom neighbors of a pixel contribute to increasing the accuracy of the local-complexity evaluation. Secondly, Jafaret al.’s method employs K-means clustering in combination with one single feature to split pixels into five classes, leading to a weak clustering performance. Finally, Jafaret al.’s method uniformly embedded 1 bit into each pixel irrespective of the local complexity, and thus, the embedding capacity is limited. To this end, an improved RDH-CE method is proposed in this paper. Considering that the complexity evaluation plays a vital role in both contrast enhancement and payload increase, we improve embedding performance by including left-bottom neighbors of a pixel into complexity evaluation. Compared with one single feature in Jafaret al.’s method, we extract multiple features to assist K-means clustering such that a better cluster performance is obtained. In addition, our method provides an adaptive pixel modification strategy based on the local complexity, in which we can adaptively embed 1 or 2 bits into a pixel according to the corresponding complexity. By these three improvements, our method is capable of achieving high capacity while enhancing contrast. The experimental results also show that our method achieves higher accuracy of the complexity evaluation, larger payload, and better local contrast enhancement than those existing RDH-CE related methods.

The similarity measurement of time series is a significant approach to mine the rich and valuable law information hidden in the massive time series data. As the most advantageous approach in measuring similarities of time series, Dynamic Time Warping (DTW) has become one of the hottest researches in the field of data mining. However, the DTW algorithm does not satisfy the trigonometric inequality, its time and space complexity are extremely high, how to efficiently realize the retrieval of similar sequences in large-scale sequential sequences remains a challenge. This paper first introduces a novel extensible lower bound function (LB_ex), then validates the effeteness of its lower bound tightness theoretically, finally uses a bidirectional processing strategy (BPS) to reduce computation complexity and time consumption during the massive sequential data retrieval, and significantly improves the operation efficiency. Extensive experiments were conducted with public dataset to evaluate feasibility and efficiency of the proposed approaches. The results show that LB_ex and BPS performs a more robust and efficient processing of similarity of time series than does traditional approaches, reducing by about 43% of time-consuming.

Summary In this paper, we consider an online learning scenario where the instances arrive sequentially with partly revealed labels. We assume that the labels of instances are revealed randomly according to some distribution, eg, Bernoulli distribution. Three specific algorithms based on different inspirations are developed. The first one performs the idea of Estimated gradient for which a strict high‐probability regret guarantee in scale of can be derived, when the distributing parameter p is revealed. An empirical version is also developed for cases where the learner has to learn the parameter p when it is not revealed. Experiments on several benchmark data sets show the feasibility of the proposed method. To further improve the performance, two kinds of aggressive algorithms are presented. The first one is based on the idea of instances recalling, which tries to get the full use of the labeled instances. The second one is based on the idea of labels learning, and it tries to learn the labels for unlabeled instances. In particular, it includes the step of online co‐learning, which aims to learn the labels, and the step of weighted voting, which aims to make the final decision. Empirical results confirm the positive effects of the two aggressive algorithms.

According to the characteristic of pepper‐and‐salt noise, the authors first classify pixels in a polluted image into two classes: suspected noise and noise‐free pixels. For a suspected noisy pixel, by counting the number of closed grey‐level and noise‐free pixels in a neighbourhood, one can correctly determine a noise or a noise‐free pixel. Noise filtering does not process noise‐free pixels. For the noisy pixels, an adaptive filtering algorithm with weighting mean based on Euler distance achieves excellent noise removal and good detail preservation. The algorithm can handle different noise levels, and the authors do not need to manually adjust the parameters and thresholds. The experimental results indicate that the authors’ proposed method effectively filters pepper‐and‐salt noise. The authors note that when noise‐free and noisy pixels with the same grey level appear in the polluted images, the noise‐removal performance by the proposed method is much more excellent than those of the other existing methods.