Explore the vast range of titles available.

Chaotic time series prediction is a prediction method based on chaos theory, and has important theoretical and application value. At present, most prediction methods only pursue digital fitting and do not consider the directional trend. In addition, using the single model will not achieve better prediction results. Therefore, a chaotic time series combined prediction model for improving trend lagging (ITL) is proposed. An improved dual‐stage attention‐based long short‐term memory model with the improved training objective fuction is designed to solve the trend lagging problem. Then, an auto regressive moving average model with the sliding window is established to mine other characteristics of the time series except nonlinear characteristic. Finally, the idea of optimization algorithm is introduced to construct a time series combined prediction model with high accuracy based on the above two models, so as to perform the chaotic time series prediction from multiple perspectives. Multiple datasets are selected as experimental datasets, and the proposed method is compared with common prediction methods. The results show that the proposed method can achieve single‐step prediction with high accuracy and effectively improve the lagging of chaotic time series prediction. This research can provide theoretical support for the complex chaotic time series prediction. In this paper, a time series combined prediction model for improving trend lagging is proposed. The improved dual‐stage attention‐based long short‐term memory model is designed. And the optimized training objective function is constructed to solve the problem that the prediction methods do not consider the directional trend. The idea of optimization algorithm is introduced to construct a time series combined prediction model with high accuracy, and the time series prediction is performed from multiple perspectives, so as to improve the generalization ability of the model.

Unmanned aerial vehicle (UAV) vision systems have been widely deployed for aerial monitoring applications, yet small-target detection in UAV imagery remains a significant challenge due to minimal pixel representation, substantial scale variations, complex background interference, and varying illumination conditions. Existing object detection algorithms struggle to maintain high accuracy when processing small targets with fewer than 32 × 32 pixels in UAV-captured scenes, particularly in complex environments where target-background confusion is prevalent. To address these limitations, this study proposes RMH-YOLO, a refined multi-scale architecture. The model incorporates four key innovations: a Refined Feature Module (RFM) that fuses channel and spatial attention mechanisms to enhance weak feature representation of small targets while maintaining contextual integrity; a Multi-scale Focus-and-Diffuse (MFFD) network that employs a focus-diffuse transmission pathway to preserve fine-grained spatial details from high-resolution layers and propagate them to semantic features; an efficient CS-Head detection architecture that utilizes parameter-sharing convolution to enable efficient processing on embedded platforms; and an optimized loss function combining Normalized Wasserstein Distance (NWD) with InnerCIoU to improve localization accuracy for small targets. Experimental validation on the VisDrone2019 dataset demonstrates that RMH-YOLO achieves a precision and recall of 53.0% and 40.4%, representing improvements of 8.8% and 7.4% over the YOLOv8n baseline. The proposed method attains mAP50 and mAP50:95 of 42.4% and 25.7%, corresponding to enhancements of 9.2% and 6.4%, respectively, while maintaining computational efficiency with only 1.3 M parameters and 16.7 G FLOPs. Experimental results confirm that RMH-YOLO effectively improves small-target detection accuracy while maintaining computational efficiency, demonstrating its broad application potential in diverse UAV aerial monitoring scenarios.

Bui, N.A.; Oh, Y.G., and Lee, I.P., 2023. Oil spill detection and classification from airborne EOIR images using a deep learning model. In: Lee, J.L.; Lee, H.; Min, B.I.; Chang, J.-I.; Cho, G.T.; Yoon, J.-S., and Lee, J. (eds.), Multidisciplinary Approaches to Coastal and Marine Management. Journal of Coastal Research, Special Issue No. 116, pp. 279-283. Charlotte (North Carolina), ISSN 0749-0208. The marine ecological environment is adversely affected by oil spills, which necessitates effective and rapid treatment options. While current research mainly focuses on detecting oil spills, detection alone is insufficient. It is necessary to provide information regarding the types of oil involved in the accident, the mass of each oil type, and other relevant data. In this research, a dataset consisting of patrol videos captured by EOIR cameras mounted on Korean Coast Guard helicopters, along with internet-collected data, was utilized to train a DaNet deep learning model for the purpose of oil spill detection and classification. The results indicate that the DaNet model can detect oil with a mean accuracy of 83.48% and a mean Intersection over Union (mIoU) of 72.54%. Moreover, the model can classify four types of oil with a macro-average F1-score of 83.91%. This study also demonstrates that using the DaNet decoder results in 6.14% higher accuracy than PsPnet.

Multi-object tracking is a challenging computer vision task that is a research hotspot in the literature. Although current one-stage methods can jointly optimize detection and appearance embedding models through an end-to-end approach, they still face major challenges. These include high computational demands, difficulty in distinguishing similar objects and poor performance in reidentifying lost objects. To overcome these challenges, we propose a lightweight multi-object tracking method to enhance tracking efficiency through the dual attention mechanism. This mechanism, on the one hand, adopts an intra-sample local attention, enabling the model to focus on discriminative regions to extract instance context, thereby effectively distinguishing similar objects. On the other hand, it employs inter-sample global attention, which captures instance-level semantic information across samples, facilitating feature interaction between objects in different frames, thus enhancing the re-identification performance for lost objects. We validated the effectiveness of the proposed method with extensive experiments on publicly available MOT and our proposed STATION datasets, achieving comparable performance.

As a core component of hydraulic systems, hydraulic pumps generate vibration signals that contain abundant key features reflecting the operational state of internal machinery. However, most existing fault diagnosis methods rely solely on single-channel vibration data, neglecting the correlations and complementarities among multi-channel signals, which results in unstable and less accurate diagnostic outcomes. To address this limitation, this study proposes an intelligent fault diagnosis approach for hydraulic pumps based on multi-source signal fusion and a dual attention mechanism. First, vibration, pressure, and acoustic signals are transformed into time-frequency feature images, and an RGB image fusion strategy is applied to map the time-frequency representations of different signals into the individual channels of a color image. Subsequently, a convolutional neural network incorporating enhanced channel and spatial attention mechanisms is constructed to extract features from the fused images and perform classification. Experimental results demonstrate that the proposed method significantly improves fault diagnosis performance and outperforms other deep learning-based approaches, offering a novel strategy for intelligent hydraulic pump diagnostics with promising engineering applications.

Deep learning-based fault diagnosis models achieve great success with sufficient balanced data, but the imbalanced dataset in real industrial scenarios will seriously affect the performance of various popular deep learning models. Data generation-based strategy provides a solution by expanding the number of minority samples. However, many data-generation methods cannot generate high-quality samples when the imbalanced ratio is high. To address these problems, a dual-attention feature fusion network (DAFFN) with two-stream hybrid-generated data is proposed. First, the two-stream hybrid generator including a generative model and an oversampling technique is adopted to generate minority fault data. Then, the convolutional neural network is used to extract features from hybrid-generated data. In particular, a feature fusion network with a dual-attention mechanism, i.e., a channel attention mechanism and a layer attention mechanism are designed to learn channel-level and layer-level weights of the features. Extensive results on two bearing datasets indicate that the proposed framework achieves outstanding performance in various high imbalanced-ratio cases.

Recently, facial-expression recognition (FER) has primarily focused on images in the wild, including factors such as face occlusion and image blurring, rather than laboratory images. Complex field environments have introduced new challenges to FER. To address these challenges, this study proposes a cross-fusion dual-attention network. The network comprises three parts: (1) a cross-fusion grouped dual-attention mechanism to refine local features and obtain global information; (2) a proposed C 2 activation function construction method, which is a piecewise cubic polynomial with three degrees of freedom, requiring less computation with improved flexibility and recognition abilities, which can better address slow running speeds and neuron inactivation problems; and (3) a closed-loop operation between the self-attention distillation process and residual connections to suppress redundant information and improve the generalization ability of the model. The recognition accuracies on the RAF-DB, FERPlus, and AffectNet datasets were 92.78%, 92.02%, and 63.58%, respectively. Experiments show that this model can provide more effective solutions for FER tasks.

In the field of clinical neurology, automated detection of epileptic seizures based on electroencephalogram (EEG) signals has the potential to significantly accelerate the diagnosis of epilepsy. This rapid and accurate diagnosis enables doctors to provide timely and effective treatment for patients, significantly reducing the frequency of future epileptic seizures and the risk of related complications, which is crucial for safeguarding patients’ long-term health and quality of life. Presently, deep learning techniques, particularly Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs), have demonstrated remarkable accuracy improvements across various domains. Consequently, researchers have utilized these methodologies in studies focused on recognizing epileptic signals through EEG analysis. However, current models based on CNN and LSTM still heavily rely on data preprocessing and feature extraction steps. Additionally, CNNs exhibit limitations in perceiving global dependencies, while LSTMs encounter challenges such as gradient vanishing in long sequences. This paper introduced an innovative EEG recognition model, that is the Spatio-temporal feature fusion epilepsy EEG recognition model with dual attention mechanism (STFFDA). STFFDA is comprised of a multi-channel framework that directly interprets epileptic states from raw EEG signals, thereby eliminating the need for extensive data preprocessing and feature extraction. Notably, our method demonstrates impressive accuracy results, achieving 95.18% and 77.65% on single-validation tests conducted on the datasets of CHB-MIT and Bonn University, respectively. Additionally, in the 10-fold cross-validation tests, their accuracy rates were 92.42% and 67.24%, respectively. In summary, it is demonstrated that the seizure detection method STFFD based on EEG signals has significant potential in accelerating diagnosis and improving patient prognosis, especially since it can achieve high accuracy rates without extensive data preprocessing or feature extraction.

To address the over-reliance on sociological and structural balance theories in analysing directed signed networks, which inadequately describe the true relationships between nodes, this paper proposes the DADSGNN model. DADSGNN is a decoupled signed graph neural network that employs a dual attention mechanism to enhance the quality of node embedding representations. Firstly, DADSGNN decouples node features into multiple potential factors within its encoder, employing the concept of decoupled representation learning. This allows for a deeper exploration of potential factors influencing internodal relationships. Secondly, a dual attention mechanism, comprising local and structural attention, is applied. This enables the model to classify and aggregate diverse types of neighbour information and subsequently calculate the characteristics of each potential influence factor. Such an approach effectively improves the accuracy and interpretability of the model’s representation of complex internodal relationships. Thirdly, the decoder component of DADSGNN incorporates a novel decoder for the link sign prediction task. This decoder fully considers the correlation between different potential factors, thereby significantly improving prediction accuracy. Finally, the predictive capability and validity of DADSGNN are evaluated using directed network datasets of varying scales, thereby verifying the model’s performance on real-world signed network data.

Rockfill particle gradation significantly influences mechanical performance in earth–rockfill dam construction, yet on-site screening is often time-consuming, labor-intensive, and structurally invasive. This study proposes a rapid and non-destructive detection method using mobile-based photography and an end-to-end image segmentation approach. An enhanced YOLOv8-seg model with an integrated dual-attention mechanism was pre-trained on laboratory images to accurately segment densely stacked particles. Transfer learning was then employed to retrain the model using a limited number of on-site images, achieving high segmentation accuracy. The proposed model attains a mAP50 of 97.8% (base dataset) and 96.1% (on-site dataset), enabling precise segmentation of adhered and overlapped particles with various sizes. A Minimum Area Rectangle algorithm was introduced to compute the gradation, closely matching the results from manual screening. This method significantly contributes to the automation of construction workflows, cutting labor costs, minimizing structural disruption, and ensuring reliable measurement quality in earth–rockfill dam projects.