Search Results (109)

There are significant scale and morphological differences between fire and smoke features in forest fire detection. This paper proposes a detection method based on dual-branch multi-scale adaptive feature fusion network (DMAFNet). In this method, convolutional neural network (CNN) and transformer are used to form a dual-branch backbone network to extract local texture and global context information, respectively. In order to overcome the difference in feature distribution and response scale between the two branches, a feature correction module (FCM) is designed. Through space and channel correction mechanisms, the adaptive alignment of two branch features is realized. The Fusion Feature Module (FFM) is further introduced to fully integrate dual-branch features based on the two-way cross-attention mechanism and effectively suppress redundant information. Finally, the Multi-Scale Fusion Attention Unit (MSFAU) is designed to enhance the multi-scale detection capability of fire targets. Experimental results show that the proposed DMAFNet has significantly improved in mAP (mean average precision) indicators compared with existing mainstream detection methods. Full article

Geographic object-based image analysis (GEOBIA) has demonstrated substantial utility in remote sensing tasks. However, its integration with deep learning remains largely confined to image-level classification. This is primarily due to the irregular shapes and fragmented boundaries of segmented objects, which limit its applicability in semantic segmentation. While convolutional neural networks (CNNs) excel at local feature extraction, they inherently struggle to capture long-range dependencies. In contrast, Transformer-based models are well suited for global context modeling but often lack fine-grained local detail. To overcome these limitations, we propose GOFENet (Geo-Object Feature Enhanced Network)—a hybrid semantic segmentation architecture that effectively fuses object-level priors into deep feature representations. GOFENet employs a dual-encoder design combining CNN and Swin Transformer architectures, enabling multi-scale feature fusion through skip connections to preserve both local and global semantics. An auxiliary branch incorporating cascaded atrous convolutions is introduced to inject information of segmented objects into the learning process. Furthermore, we develop a cross-channel selection module (CSM) for refined channel-wise attention, a feature enhancement module (FEM) to merge global and local representations, and a shallow–deep feature fusion module (SDFM) to integrate pixel- and object-level cues across scales. Experimental results on the GID and LoveDA datasets demonstrate that GOFENet achieves superior segmentation performance, with 66.02% mIoU and 51.92% mIoU, respectively. The model exhibits strong capability in delineating large-scale land cover features, producing sharper object boundaries and reducing classification noise, while preserving the integrity and discriminability of land cover categories. Full article

This study addresses the challenges of manual measurement bias and low robustness in detecting small, occluded targets in complex marine environments during real-time onboard sorting of Portunus trituberculatus. We propose YOLO-DFAM, an enhanced YOLOv11n-based model that replaces the global average pooling in the Focal Modulation module with a spatial–channel dual-attention mechanism and incorporates the ASF-YOLO cross-scale fusion strategy to improve feature representation across varying target sizes. These enhancements significantly boost detection, achieving an mAP@50 of 98.0% and precision of 94.6%, outperforming RetinaNet-CSL and Rotated Faster R-CNN by up to 6.3% while maintaining real-time inference at 180.3 FPS with only 7.2 GFLOPs. Unlike prior static-scene approaches, our unified framework integrates attention-guided detection, scale-adaptive tracking, and lightweight weight estimation for dynamic marine conditions. A ByteTrack-based tracking module with dynamic scale calibration, EMA filtering, and optical flow compensation ensures stable multi-frame tracking. Additionally, a region-specific allometric weight estimation model (R² = 0.9856) reduces dimensional errors by 85.7% and maintains prediction errors below 4.7% using only 12 spline-interpolated calibration sets. YOLO-DFAM provides an accurate, efficient solution for intelligent onboard fishery monitoring. Full article

With the rising automation and complexity level of industrial systems, the efficiency and accuracy of fault diagnosis have become a critical challenge. The convolutional neural network (CNN) has shown some success in the fault diagnosis field. However, typical convolutional kernels are commonly fixed-sized, which makes it difficult to capture multi-scale features simultaneously. Additionally, the use of numerous fixed-size convolutional filters often results in redundant parameters. During the feature extraction process, the CNN often struggles to take inter-channel dependencies and spatial location information into consideration. There are also limitations in extracting various time-scale features. To address these issues, a fault diagnosis method on the basis of a dual-path mixed convolutional attention-BiGRU network (DMCA-BiGRUN) is proposed for industrial processes. Firstly, a dual-path mixed CNN (DMCNN) is designed to capture features at multiple scales while effectively reducing the parameter count. Secondly, a coordinate attention mechanism (CAM) is designed to help the network to concentrate on main features more effectively during feature extraction by combining the channel relationship and position information. Finally, a bidirectional gated recurrent unit (BiGRU) is introduced to process sequences in both directions, which can effectively learn the long-range temporal dependencies of sequence data. To verify the fault diagnosis performance of the proposed method, simulation experiments are implemented on the Tennessee Eastman (TE) and Continuous Stirred Tank Reactor (CSTR) datasets. Some deep learning methods are compared in the experiments, and the results confirm the feasibility and superiority of DMCA-BiGRUN. Full article

The challenge of accurately diagnosing mechanical failures in high-voltage circuit breakers is exacerbated by the non-stationary characteristics of vibration signals. This study proposes a Dual-Channel Convolutional Neural Network (DC-CNN) framework based on the Gramian Angular Field (GAF) transformation, which effectively captures both global and local information about faults. Specifically, vibration signals from circuit breaker sensors are firstly transformed into Gramian Angular Summation Field (GASF) and Gramian Angular Difference Field (GADF) images. These images are then combined into multi-channel inputs for parallel CNN modules to extract and fuse complementary features. Experimental validation under six operational conditions of a 220 kV high-voltage circuit breaker demonstrates that the GAF-DC-CNN method achieves a fault diagnosis accuracy of 99.02%, confirming the model’s effectiveness. This work provides substantial support for high-precision and reliable fault diagnosis in high-voltage circuit breakers within power systems. Full article

Large turbine generators rely on shaft earthing brushes to safely divert harmful shaft currents to ground, protecting bearings from electrical damage. This paper presents a novel deep learning-based diagnostic framework to detect and classify faults in shaft earthing brushes of large turbine generators. A key innovation lies in the use of FFT-derived spectrograms from both voltage and current waveforms as dual-channel inputs to the CNN, enabling automatic feature extraction of time–frequency patterns associated with different SEB fault types. The proposed framework combines advanced signal processing and convolutional neural networks (CNNs) to automatically recognize fault-related patterns in shaft grounding current and voltage signals. In the approach, raw time-domain signals are converted into informative time–frequency representations, which serve as input to a CNN model trained to distinguish normal and faulty conditions. The framework was evaluated using data from a fleet of large-scale generators under various brush fault scenarios (e.g., increased brush contact resistance, loss of brush contact, worn out brushes, and brush contamination). Experimental results demonstrate high fault detection accuracy (exceeding 98%) and the reliable identification of different fault types, outperforming conventional threshold-based monitoring techniques. The proposed deep learning framework offers a novel intelligent monitoring solution for predictive maintenance of turbine generators. The contributions include the following: (1) the development of a specialized deep learning model for shaft earthing brush fault diagnosis, (2) a systematic methodology for feature extraction from shaft current signals, and (3) the validation of the framework on real-world fault data. This work enables the early detection of brush degradation, thereby reducing unplanned downtime and maintenance costs in power generation facilities. Full article

With the advancement of agricultural automation technologies, apple-harvesting robots have gradually become a focus of research. As their “perceptual core,” machine vision systems directly determine picking success rates and operational efficiency. However, existing vision systems still exhibit significant shortcomings in target detection and positioning accuracy in complex orchard environments (e.g., uneven illumination, foliage occlusion, and fruit overlap), which hinders practical applications. This study proposes a visual system for apple-harvesting robots based on improved Mask R-CNN and binocular vision to achieve more precise fruit positioning. The binocular camera (ZED2i) carried by the robot acquires dual-channel apple images. An improved Mask R-CNN is employed to implement instance segmentation of apple targets in binocular images, followed by a template-matching algorithm with parallel epipolar constraints for stereo matching. Four pairs of feature points from corresponding apples in binocular images are selected to calculate disparity and depth. Experimental results demonstrate average coefficients of variation and positioning accuracy of 5.09% and 99.61%, respectively, in binocular positioning. During harvesting operations with a self-designed apple-picking robot, the single-image processing time was 0.36 s, the average single harvesting cycle duration reached 7.7 s, and the comprehensive harvesting success rate achieved 94.3%. This work presents a novel high-precision visual positioning method for apple-harvesting robots. Full article

Background: Electroencephalography (EEG) signals play a crucial role in diagnosing epilepsy by reflecting distinct patterns associated with normal brain activity, ictal (seizure) states, and interictal (between-seizure) periods. However, the manual classification of these patterns is labor-intensive, time-consuming, and depends heavily on specialized expertise. While deep learning methods have shown promise, many current models suffer from limitations such as excessive complexity, high computational demands, and insufficient generalizability. Developing lightweight and accurate models for real-time epilepsy detection remains a key challenge. Methods: This study proposes a novel dual-channel deep learning model to classify epileptic EEG signals into three categories: normal, ictal, and interictal states. Channel 1 integrates a bidirectional long short-term memory (BiLSTM) network with a Squeeze-and-Excitation (SE) ResNet attention module to dynamically emphasize critical feature channels. Channel 2 employs a dual-branch convolutional neural network (CNN) to extract deeper and distinct features. The model’s performance was evaluated on the publicly available Bonn EEG dataset. Results: The proposed model achieved an outstanding accuracy of 98.57%. The dual-channel structure improved specificity to 99.43%, while the dual-branch CNN boosted sensitivity by 5.12%. Components such as SE-ResNet attention modules contributed 4.29% to the accuracy improvement, and BiLSTM further enhanced specificity by 1.62%. Ablation studies validated the significance of each module. Conclusions: By leveraging a lightweight design and attention-based mechanisms, the dual-channel model offers high diagnostic precision while maintaining computational efficiency. Its applicability to real-time automated diagnosis positions it as a promising tool for clinical deployment across diverse patient populations. Full article

Advanced persistent threat (APT) attacks present significant challenges to cybersecurity due to their covert nature, high complexity, and ability to operate across multiple temporal and spatial scales. Existing detection techniques often struggle with issues like class imbalance, insufficient feature extraction, and the inability to capture complex attack dependencies. To address these limitations, we propose a dual-phase framework for APT detection, combining multi-feature-conditioned generative adversarial networks (MF-CGANs) for data reconstruction and a multi-scale convolution and channel attention-enhanced graph convolutional network (MC-GCN) for improved attack detection. The MF-CGAN model generates minority-class samples to resolve the class imbalance problem, while MC-GCN leverages advanced feature extraction and graph convolution to better model the intricate relationships within network traffic data. Experimental results show that the proposed framework achieves significant improvements over baseline models. Specifically, MC-GCN outperforms traditional CNN-based IDS models, with accuracy, precision, recall, and F1-score improvements ranging from 0.47% to 13.41%. The MC-GCN model achieves an accuracy of 99.87%, surpassing CNN (86.46%) and GCN (99.24%), while also exhibiting high precision (99.87%) and recall (99.88%). These results highlight the proposed model’s superior ability to handle class imbalance and capture complex attack behaviors, establishing it as a leading approach for APT detection. Full article

Traditional underwater acoustic reconnaissance technologies are limited in directly detecting underwater acoustic communication signals. This paper proposes a dual-feature ResNet–Transformer model with two innovative breakthroughs: (1) A dual-modal fusion architecture of ResNet and Transformer is constructed using residual connections to alleviate gradient degradation in deep networks and combining multi-head self-attention to enhance long-distance dependency modeling. (2) The time–frequency representation obtained from the smooth pseudo-Wigner–Ville distribution is used as the first input branch, and higher-order statistics are introduced as the second input branch to enhance phase feature extraction and cope with channel interference. Experiments on the Danjiangkou measured dataset show that the model improves the accuracy by 6.67% compared with the existing Convolutional Neural Network (CNN)–Transformer model in long-distance ranges, providing an efficient solution for modulation recognition in complex underwater acoustic environments. Full article

Ground Penetrating Radar (GPR) is widely used for assessing the deterioration of concrete bridge decks. GPR surveys generate large amounts of data in the form of B-scan images, which display rebar traces as hyperbolas. Accurate analysis of the GPR scans relies on the effective extraction of rebar locations and amplitudes. This paper presents two automated rebar detection algorithms based on Convolutional Neural Network (CNN) machine learning techniques. Two models are proposed: CNN-1 and CNN-2. CNN-1 was trained on raw GPR images to identify hyperbolas, while CNN-2 model used both raw and migrated GPR images for enhanced analysis. The models were evaluated using GPR data collected from three bridges with different overlay types. Performance was assessed through the visual comparison of the generated bridge amplitude maps against ground-truth data, as well as precision, recall, and F1-score metrics. The results demonstrate that CNN-2 outperforms CNN-1 in terms of accuracy and efficiency for rebar detection. Full article

Medical image classification often relies on CNNs to capture local details (e.g., lesions, nodules) or on transformers to model long-range dependencies. However, each paradigm alone is limited in addressing both fine-grained structures and broader anatomical context. We propose ConvTransGFusion, a hybrid model that fuses ConvNeXt (for refined convolutional features) and Swin Transformer (for hierarchical global attention) using a learnable dual-attention gating mechanism. By aligning spatial dimensions, scaling each branch adaptively, and applying both channel and spatial attention, the proposed architecture bridges local and global representations, melding fine-grained lesion details with the broader anatomical context essential for accurate diagnosis. Tested on four diverse medical imaging datasets—including X-ray, ultrasound, and MRI scans—the proposed model consistently achieves superior accuracy, precision, recall, F1, and AUC over state-of-the-art CNNs and transformers. Our findings highlight the benefits of combining convolutional inductive biases and transformer-based global context in a single learnable framework, positioning ConvTransGFusion as a robust and versatile solution for real-world clinical applications. Full article

Accurate fault diagnosis in analog circuits faces significant challenges owing to the inherent complexity of fault data patterns and the limited feature representation capabilities of conventional methodologies. Addressing the limitations of current convolutional neural networks (CNN) in handling heterogeneous fault characteristics, this study presents an efficient channel attention-enhanced multi-input CNN framework (ECA-MI-CNN) with dual-domain feature fusion, demonstrating three key innovations. First, the proposed framework addresses multi-domain feature extraction through parallel CNN branches specifically designed for processing time-domain and frequency-domain features, effectively preserving their distinct characteristic information. Second, the incorporation of an efficient channel attention (ECA) module between convolutional layers enables adaptive feature response recalibration, significantly enhancing discriminative feature learning while maintaining computational efficiency. Third, a hierarchical fusion strategy systematically integrates time-frequency domain features through concatenation and fully connected layer transformations prior to classification. Comprehensive simulation experiments conducted on Butterworth low-pass filters and two-stage quad op-amp dual second-order low-pass filters demonstrate the framework’s superior diagnostic capabilities. Real-world validation on Butterworth low-pass filters further reveals substantial performance advantages over existing methods, establishing an effective solution for complex fault pattern recognition in electronic systems. Full article

Lithology identification provides a crucial foundation for various geological tasks, such as mineral exploration and geological mapping. Traditionally, lithology identification requires geologists to interpret geological data collected from the field. However, the acquisition of geological data requires a substantial amount of time and becomes more challenging under harsh natural conditions. The development of remote sensing technology has effectively mitigated the limitations of traditional lithology identification. In this study, an interpretable dual-channel convolutional neural network (DC-CNN) with the Shapley additive explanations (SHAP) interpretability method is proposed for lithology identification; this approach combines the spectral and spatial features of the remote sensing data. The model adopts a parallel dual-channel structure to extract spectral and spatial features simultaneously, thus implementing lithology identification in remote sensing images. A case study from the Tuolugou mining area of East Kunlun (China) demonstrates the performance of the DC-CNN model in lithology identification on the basis of GF5B hyperspectral data and Landsat-8 multispectral data. The results show that the overall accuracy (OA) of the DC-CNN model is 93.51%, with an average accuracy (AA) of 89.77% and a kappa coefficient of 0.8988; these metrics exceed those of the traditional machine learning models (i.e., Random Forest and CNN), demonstrating its efficacy and potential utility in geological surveys. SHAP, as an interpretable method, was subsequently used to visualize the value and tendency of feature contribution. By utilizing SHAP feature-importance bar charts and SHAP force plots, the significance and direction of each feature’s contribution can be understood, which highlights the necessity and advantage of the new features introduced in the dataset. Full article

The marine environment’s complexity poses considerable difficulties for the stability and reliability of communication links. The restricted coverage of onshore base stations in marine areas makes relay technology a critical solution for extending the communication coverage. Here, connectivity analyses help nodes select the optimal forwarding links, reducing transmission failures and improving the network performance. However, the rapid changes in marine wireless channels and the complexity of hydrological conditions make it challenging to acquire precise channel state information (CSI). In particular, dynamic environmental factors like tides, waves, and wind speed lead to substantial variations in the channel parameters over time. In response to these challenges, this paper puts forward a ship-to-shore communication system using relay ships to extend the coverage of terrestrial base stations. A novel channel modeling method is designed to capture the characteristics of marine wireless channels accurately. Additionally, a machine learning (ML)-based approach is introduced to predict the dual-hop link connection probability at future time points by analyzing historical time-series data on oceanic environmental and ship movement parameters. The proposed model consists of a convolutional-layer-based feature extractor and a bidirectional long short-term memory (BiLSTM) estimator. The CNN module extracts effective high-level features from the input data, while the BiLSTM module further explores the dependencies and dynamic patterns along the temporal dimension. The attention mechanism is introduced to distinguish the importance of the information through a weighted approach. The experimental results show that compared to traditional methods and other deep learning approaches, the proposed CNN-BiLSTM-AM model performs better in terms of its prediction accuracy and fitting ability. The model’s mean squared error (MSE) is as low as 0.0126. Full article