ABSTRACT Traffic violations constitute one of the principal contributors to serious road accidents and remain a persistent threat to public safety and property worldwide. For this reason, accurate identification and prediction of traffic violations are of considerable importance for improving traffic governance and supporting early intervention. To address the challenges posed by traffic violation data with complex structures and heterogeneous feature distributions, this paper proposes a new classification framework: TrafficViolationNet. The proposed model integrates an enhanced residual architecture with a lightweight attention mechanism to improve feature learning from structured traffic data. At the architectural level, TrafficViolationNet is built upon ResNet Plus, in which auxiliary residual branches and dense shortcut connections are introduced to facilitate information propagation, improve gradient flow, and strengthen feature representation. In addition, an attention module is incorporated into each residual block to adaptively emphasize informative features and capture complex dependencies among variables. Experimental results on traffic violation datasets from the United States and Qatar show that the proposed method consistently outperforms mainstream machine learning baselines and achieves state‐of‐the‐art classification performance.

Prostate cancer is the most common malignancy among Australian men, with over 20 000 new diagnoses each year. Accurate forecasts of its incidence and mortality inform stakeholder decision-making and help mitigate its public health impact. In this context, we introduce cutting-edge lightweight neural networks into the domain of prostate cancer data forecasting with edge intelligence for the first time. To address the issue of overfitting in coarse-grained and small-scale prostate cancer datasets, we employ structurally streamlined models: the Gated Recurrent Unit (GRU) and Temporal Convolutional Network (TCN), representing two predominant branches of neural networks. The GRU’s simplified gating mechanism maintains excellent long-term dependencies capturing capability while drastically reducing parameter count, and the TCN combines sparse connections, parameter sharing, and causal dilated convolutions for efficient temporal modeling. To further bolster generalization, we integrate multiple regularization strategies, including the snapshot ensemble method. Comparative experiments on three real-world prostate cancer datasets demonstrate that our improved lightweight, high-performance neural networks achieve over 40% higher accuracy than linear time series forecasting suitable for small-scale datasets.

As a pivotal subfield within the domain of time series forecasting, runoff forecasting plays a crucial role in water resource management and scheduling. Recent advancements in the application of artificial neural networks (ANNs) and attention mechanisms have markedly enhanced the accuracy of runoff forecasting models. This article introduces an innovative hybrid model, ResTCN-DAM, which synergizes the strengths of deep residual network (ResNet), temporal convolutional networks (TCNs), and dual attention mechanisms (DAMs). The proposed ResTCN-DAM is designed to leverage the unique attributes of these three modules: TCN has outstanding capability to process time series data in parallel. By combining with modified ResNet, multiple TCN layers can be densely stacked to capture more hidden information in the temporal dimension. DAM module adeptly captures the interdependencies within both temporal and feature dimensions, adeptly accentuating relevant time steps/features while diminishing less significant ones with minimal computational cost. Furthermore, the snapshot ensemble method is able to obtain the effect of training multiple models through one single training process, which ensures the accuracy and robustness of the forecasts. The deep integration and collaborative cooperation of these modules comprehensively enhance the model's forecasting capability from various perspectives. Ablation studies conducted validate the efficacy of each module, and through multiple sets of comparative experiments, it is shown that the proposed ResTCN-DAM has exceptional and consistent performance across varying lead times. We also employ visualization techniques to display heatmaps of the model's weights, thereby enhancing the interpretability of the model. When compared with the prevailing neural network-based runoff forecasting models, ResTCN-DAM exhibits state-of-the-art accuracy, temporal robustness, and interpretability, positioning it at the forefront of contemporary research.

Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision Transformer can learn instance-level attention without labels, extracting high-quality instance-level representations for boosting downstream tasks. In this paper, we achieve unsupervised part-specific attention learning using a novel paradigm and further employ the part representations to improve part discovery performance. Specifically, paired images are generated from the same image with different geometric transformations, and multiple part representations are extracted from these paired images using a novel module, named PartFormer. These part representations from the paired images are then exchanged to improve geometric transformation invariance. Subsequently, the part representations are aligned with the feature map extracted by a feature map encoder, achieving high similarity with the pixel representations of the corresponding part regions and low similarity in irrelevant regions. Finally, the geometric and semantic constraints are applied to the part representations through the intermediate results in alignment for part-specific attention learning, encouraging the PartFormer to focus locally and the part representations to explicitly include the information of the corresponding parts. Moreover, the aligned part representations can further serve as a series of reliable detectors in the testing phase, predicting pixel masks for part discovery. Extensive experiments are carried out on four widely used datasets, and our results demonstrate that the proposed method achieves competitive performance and robustness due to its part-specific attention.

Runoff forecasting is the key to the rational use and protection of water resources by mankind. The large-scale application of machine learning and neural networks in hydrological models has made accurate and reliable short-term runoff forecasting possible. In this article, a novel short-term runoff forecasting framework called ResGRU Plus is proposed with gated recurrent unit (GRU) as the backbone. GRU has the characteristics of long short-term memory (LSTM) that can selectively memorize and forget information while merging gating units to reduce the amount of parameters. Residual network (ResNet) is also deeply integrated with GRU, and its unique shortcut connection effectively solves the degradation problem of traditional neural networks, making it possible to train deep neural networks based on the recurrent architecture. Moreover, a lightweight attention mechanism module: squeeze-and-excitation network (SENet) is embedded in the framework. SENet explicitly models the interdependence between feature dimensions through one global average pooling layer (GAP) and two fully connected (FC) layers, and rescales the original features through the learned weights to adaptively amplify or suppress features. Snapshot ensemble method is also used to train ResGRU Plus, which can integrate multiple homogeneous weak learners through one training process to improve the performance of the model at a small cost. In this article, the hourly runoff of the Columbia River is used as the data set. The Nash–Sutcliffe coefficient (NSE) of Efficiency and coefficient of determination$(R^{2})$, which are two common evaluation metrics for hydrological models, are used to measure the performance of the models. Multiple sets of ablation experiments show that the proposed ResGRU Plus, which combines ResNet and the attention mechanism, is able to improve depth by a factor of over 4 and accuracy by nearly 18% compared to the vanilla GRU, which further fully validates the effectiveness of combining the residual structure and attention mechanism with the recurrent architecture-based neural network and the feasibility of applying it to runoff forecasting. In addition, several sets of comparative experiments have also demonstrated the state-of-the-art performance of ResGRU Plus with significant improvement in accuracy compared to mainstream time-series forecasting models.