Search Results (146)

Existing methods for detecting cotton boll diseases frequently exhibit high rates of both false negatives and false positives under complex field conditions (e.g., lighting variations, shadows, and occlusions) and struggle to achieve real-time performance on edge devices. To address these limitations, this study proposes an enhanced YOLOv11n model (YOLOv11n-ECS) for improved detection accuracy. A dataset of cotton boll diseases under different lighting conditions and shooting angles in the field was constructed. To mitigate false negatives and false positives encountered by the original YOLOv11n model during detection, the EMA (efficient multi-scale attention) mechanism is introduced to enhance the weights of important features and suppress irrelevant regions, thereby improving the detection accuracy of the model. Partial Convolution (PConv) is incorporated into the C3k2 module to reduce computational redundancy and lower the model’s computational complexity while maintaining high recognition accuracy. Furthermore, to enhance the localization accuracy of diseased bolls, the original CIoU loss is replaced with Shape-IoU. The improved model achieves floating point operations (FLOPs), parameter count, and model size at 96.8%, 96%, and 96.3% of the original YOLOv11n model, respectively. The improved model achieves an mAP@0.5 of 85.6% and an mAP@0.5:0.95 of 62.7%, representing improvements of 2.3 and 1.9 percentage points, respectively, over the baseline YOLOv11n model. Compared with CenterNet, Faster R-CNN, YOLOv8-LSW, MSA-DETR, DMN-YOLO, and YOLOv11n, the improved model shows mAP@0.5 improvements of 25.7, 21.2, 5.5, 4.0, 4.5, and 2.3 percentage points, respectively, along with corresponding mAP@0.5:0.95 increases of 25.6, 25.3, 8.3, 2.8, 1.8, and 1.9 percentage points. Deployed on a Jetson TX2 development board, the model achieves a recognition speed of 56 frames per second (FPS) and an mAP of 84.2%, confirming its suitability for real-time detection. Furthermore, the improved model effectively reduces instances of both false negatives and false positives for diseased cotton bolls while yielding higher detection confidence, thus providing robust technical support for intelligent cotton boll disease detection. Full article

Sentiment analysis is a sub-field within Natural Language Processing (NLP), concentrating on the extraction and interpretation of user sentiments or opinions from textual data. Despite significant advancements in the analysis of online content, a continuing challenge persists in the handling of sentiment datasets that are high-dimensional and frequently include substantial amounts of irrelevant or redundant features. Existing methods to address this issue typically rely on dimensionality reduction techniques; however, their effectiveness in removing irrelevant features and managing noisy or redundant data has been inconsistent. This research seeks to overcome these challenges by introducing an innovative methodology that integrates ensemble feature selection techniques based on information gain with feature hashing. Our proposed approach aims to enhance the conventional feature selection process by synergistically combining these two strategies to more effectively tackle the issues of irrelevant features, noisy classes, and redundant data. The novel integration of information gain with feature hashing facilitates a more precise and strategic feature selection process, resulting in improved efficiency and effectiveness in sentiment analysis tasks. Through comprehensive experimentation and evaluation, we demonstrate that our proposed method significantly outperforms baseline approaches and existing techniques across a wide range of scenarios. The results indicate that our method offers substantial advancements in managing high-dimensional sentiment data, thereby contributing to more accurate and reliable sentiment analysis outcomes. Full article

Fine-grained recognition tasks face significant challenges in differentiating subtle, class-specific details against cluttered backgrounds. This paper presents an efficient architecture built upon the Res2Net backbone, significantly enhanced by a dynamic Sparse Attention mechanism. The core approach leverages the inherent multi-scale representation power of Res2Net to capture discriminative patterns across different granularities. Crucially, the integrated Sparse Attention module operates dynamically, selectively amplifying the most informative features while attenuating irrelevant background noise and redundant details. This combined strategy substantially improves the model’s ability to focus on pivotal regions critical for accurate classification. Furthermore, strategic architectural optimizations are applied throughout to minimize computational complexity, resulting in a model that demands significantly fewer parameters and exhibits faster inference times. Extensive evaluations on benchmark datasets demonstrate the effectiveness of the proposed method. It achieves a modest but consistent accuracy gain over strong baselines (approximately 2%) while simultaneously reducing model size by around 30% and inference latency by about 20%, proving highly effective for practical fine-grained recognition applications requiring both high accuracy and operational efficiency. Full article

Situation awareness (SA) involves analyzing sensory data, such as audio signals, to identify anomalies. While acoustic features are widely used in audio analysis, existing methods face critical limitations; they often overlook the relevance of SA audio segments, failing to capture the complex relational patterns in audio data that are essential for SA. In this study, we first propose a graph neural network (GNN) with an attention mechanism that models SA audio features through graph structures, capturing both node attributes and their relationships for richer representations than traditional methods. Our analysis identifies suitable audio feature combinations and graph constructions for SA tasks. Building on this, we introduce a situation awareness gated-attention GNN (SAGA-GNN), which dynamically filters irrelevant nodes through max-relevance neighbor sampling to reduce redundant connections, and a learnable edge gated-attention mechanism that suppresses noise while amplifying critical events. The proposed method employs sigmoid-activated attention weights conditioned on both node features and temporal relationships, enabling adaptive node emphasizing for different acoustic environments. Experiments reveal that the proposed graph-based audio features demonstrate superior representation capacity compared to traditional methods. Additionally, both proposed graph-based methods outperform existing approaches. Specifically, owing to the combination of graph-based audio features and dynamic selection of audio nodes based on gated-attention, SAGA-GNN achieved superior results on two real datasets. This work underscores the importance and potential value of graph-based audio features and attention mechanism-based GNNs, particularly in situational awareness applications. Full article

Deep learning has significantly advanced image classification by leveraging hierarchical feature representations. A key factor in enhancing classification accuracy is feature concatenation, which integrates diverse feature sets to provide a richer representation of input data. However, this fusion strategy has inherent limitations, including increased computational complexity, susceptibility to redundant or irrelevant features, and challenges in optimally weighting different feature contributions. To address these challenges, this paper presents a pseudo-multiview learning method that dynamically combines different views at the evidence level using a belief-based model known as subjective logic. This approach adaptively assigns confidence levels to each view, ensuring more effective integration of complementary information while mitigating the impact of noisy or less relevant features. Experimental evaluations of datasets from various domains demonstrate that the proposed method enhances classification accuracy and robustness compared with conventional classification techniques. Full article

In intelligent building, efficient surface defect detection is crucial for structural safety and maintenance quality. Traditional methods face three challenges in complex scenarios: locating defect features accurately due to multi-scale texture and background interference, missing fine cracks because of their tiny size and low contrast, and the insufficient generalization of irregular defects due to complex geometric deformation. To address these issues, an improved version of the You Only Look Once (YOLOv8) algorithm is proposed for building surface defect detection. The dataset used in this study contains six common building surface defects, and the images are captured in diverse scenarios with different lighting conditions, building structures, and ages of material. Methodologically, the first step involves a normalization-based attention module (NAM). This module minimizes irrelevant features and redundant information and enhances the salient feature expression of cracks, delamination, and other defects, improving feature utilization. Second, for bottlenecks in fine crack detection, an explicit vision center (EVC) feature fusion module is introduced. It focuses on integrating specific details and overall context, improving the model’s effectiveness. Finally, the backbone network integrates deformable convolution net v2 (DCNV2) to capture the contour deformation features of targets like mesh cracks and spalling. Our experimental results indicate that the improved model outperforms YOLOv8, achieving a 3.9% higher mAP50 and a 4.2% better mAP50-95. Its performance reaches 156 FPS, suitable for real-time inspection in smart construction scenarios. Our model significantly improves defect detection accuracy and robustness in complex scenarios. The study offers a reliable solution for accurate multi-type defect detection on building surfaces. Full article

Pedestrian detection technology refers to identifying pedestrians within the field of view and is widely used in smart cities, public safety surveillance, and other scenarios. However, in real-world complex scenes, challenges such as high pedestrian density, occlusion, and low lighting conditions lead to blurred image boundaries, which significantly impact accuracy of pedestrian detection. To address these challenges, we propose a novel pedestrian detection algorithm, FA-YOLO. First, to address issues of limited effective information extraction in backbone network and insufficient feature map representation, we propose a feature enhancement module (FEM) that integrates both global and local features of the feature map, thereby enhancing the network’s feature representation capability. Then, to reduce redundant information and improve adaptability to complex scenes, an adaptive sparse self-attention (ASSA) module is designed to suppress noise interactions in irrelevant regions and eliminate feature redundancy across both spatial and channel dimensions. Finally, to further enhance the model’s focus on target features, we propose cross stage partial with adaptive sparse self-attention (C3ASSA), which improves overall detection performance by reinforcing the importance of target features during the final detection stage. Additionally, a scalable intersection over union (SIoU) loss function is introduced to address the vector angle differences between predicted and ground-truth bounding boxes. Extensive experiments on the WiderPerson and RTTS datasets demonstrate that FA-YOLO achieves State-of-the-Art performance, with a precision improvement of 3.5% on the WiderPerson and 3.0% on RTTS compared to YOLOv11. Full article

Breast cancer is the most common disease in women, with 287,800 new cases and 43,200 deaths in 2022 across United States. Early mammographic picture analysis and processing reduce mortality and enable efficient treatment. Several deep-learning-based mammography classification methods have been developed. Due to low-contrast images and irrelevant information in publicly available breast cancer datasets, existing models generally perform poorly. Pre-trained convolutional neural network models trained on generic datasets tend to extract irrelevant features when applied to domain-specific classification tasks, highlighting the need for a feature selection mechanism to transform high-dimensional data into a more discriminative feature space. This work introduces an innovative and effective multi-step pathway to overcome these restrictions. In preprocessing, mammographic pictures are haze-reduced using adaptive transformation, normalized using a cropping algorithm, and balanced using rotation, flipping, and noise addition. A 32-layer convolutional neural model inspired by YOLO, U-Net, and ResNet is intended to extract highly discriminative features for breast cancer classification. A modified Grey Wolf Optimization algorithm with three significant adjustments improves feature selection and redundancy removal over the previous approach. The robustness and efficacy of the proposed model in the classification of breast cancer were validated by its consistently high performance across multiple benchmark mammogram datasets. The model’s constant and better performance proves its robust generalization, giving it a powerful solution for binary and multiclass breast cancer classification. Full article

As more IoT devices become connected to the Internet, the attack surface for cybercrimes expands, leading to significant security concerns for these devices. Existing intrusion detection systems (IDSs) designed to address these concerns often suffer from high rates of false positives and missed threats due to the presence of redundant and irrelevant information for the IDSs. Furthermore, recent IDSs that utilize artificial intelligence are often presented as black boxes, offering no explanation of their internal operations. In this study, we develop a solution to the identified challenges by presenting a deep learning-based model that adapts to new attacks by selecting only the relevant information as inputs and providing transparent internal operations for easy understanding and adoption by cybersecurity personnel. Specifically, we employ a hybrid approach using statistical methods and a metaheuristic algorithm for feature selection to identify the most relevant features and limit the overall feature set while building an LSTM-based model for intrusion detection. To this end, we utilize two publicly available datasets, NF-BoT-IoT-v2 and IoTID20, for training and testing. The results demonstrate an accuracy of 98.42% and 89.54% for the NF-BoT-IoT-v2 and IoTID20 datasets, respectively. The performance of the proposed model is compared with that of other machine learning models and existing state-of-the-art models, demonstrating superior accuracy. To explain the proposed model’s predictions and increase trust in its outcomes, we applied two explainable artificial intelligence (XAI) tools: Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), providing valuable insights into the model’s behavior. Full article

Automated crack detection is vital for structural maintenance in areas such as construction, roads, and bridges. Accurate crack detection allows for the timely identification and repair of cracks, reducing safety risks and extending the service life of structures. However, traditional methods struggle with fine cracks, complex backgrounds, and image noise. In recent years, although deep learning techniques excel in pixel-level crack segmentation, challenges like inadequate local feature processing, information loss, and class imbalance persist. To address these challenges, we propose an encoder–decoder network based on multiple selective fusion mechanisms. Initially, a star feature enhancement module is designed to resolve the issues of insufficient local feature processing and feature redundancy during the feature extraction process. Then, a multi-scale adaptive fusion module is developed to selective capture both global and local contextual information, mitigating the information loss. Finally, to tackle class imbalance, a multi-scale monitoring and selective output module is introduced to enhance the model’s focus on crack features and suppress the interference from background and irrelevant information. Extensive experiments are conducted on three publicly available crack datasets: SCD, CFD, and DeepCrack. The results demonstrate that the proposed segmentation network achieves superior performance in pixel-level crack segmentation, with Dice scores of 66.2%, 54.2%, and 86.8% and mIoU values of 74.4%, 67.5%, and 87.9% on the SCD, CFD, and DeepCrack datasets, respectively. These results outperform those of existing models, such as U-Net, DeepLabv3+, and Attention UNet, particularly in handling complex backgrounds, fine cracks, and low-contrast images. Furthermore, the proposed MSF-CrackNet also significantly reduces computational complexity, with only 2.39 million parameters and 8.58 GFLOPs, making it a practical and efficient solution for real-world crack detection tasks, especially in scenarios with limited computational resources. Full article

To achieve the rapid and accurate classification and identification of soybean components, this study selected soybeans harvested by the 4LZ-1.5 soybean combine harvester as the research subject. Hyperspectral images of soybean samples were collected using the Pika L spectrometer, and spectral information was extracted from the regions of interest (ROI) in the images. Eight preprocessing methods, including baseline correction (BC), moving average (MA), Savitzky–Golay derivative (SGD), normalization, standard normal variate transformation (SNV), multiplicative scatter correction (MSC), first derivative (DS), and Savitzky–Golay smoothing (SGS), were applied to the raw spectral data to eliminate irrelevant information. Feature wavelengths were selected using the successive projections algorithm (SPA) and the competitive adaptive reweighted sampling (CARS) algorithm to reduce spectral redundancy and enhance model detection performance, retaining eight and ten feature wavelengths, respectively. Subsequently, a random forest (RF) model was developed for soybean component classification. The model parameters were optimized using particle swarm optimization (PSO) and differential evolution (DE) algorithms to improve performance. Experimental results showed that the RF classification model based on SPA-BC preprocessed spectra and DE-tuned parameters achieved an optimal prediction accuracy of 1.0000 during training. This study demonstrates the feasibility of using hyperspectral imaging technology for the rapid and accurate detection of soybean components, providing technical support for the assessment of breakage and impurity levels during soybean harvesting and storage processes. It also offers a reference for the development of future machine-harvested soybean breakage and impurity detection systems. Full article

Ship orientation detection is essential for maritime navigation, traffic monitoring, and defense, yet existing methods face challenges with rotational invariance in large-angle scenarios, difficulties in multi-scale feature fusion, and the limitations of traditional IoU when detecting oriented objects and predicting objects’ orientation. In this article, we propose a novel ship orientation detection (RACR-ShipDet) network based on rotation-adaptive ConvNeXt and Enhanced RepBiFPAN in remote sensing images. To equip the model with rotational invariance, ConvNeXt is first improved so that it can dynamically adjust the rotation angle and convolution kernel through adaptive rotation convolution, namely, ARRConv, forming a new architecture called RotConvNeXt. Subsequently, the RepBiFPAN, enhanced with the Weighted Feature Aggregation module, is employed to prioritize informative features by dynamically assigning adaptive weights, effectively reducing the influence of redundant or irrelevant features and improving feature representation. Moreover, a more stable version of KFIoU is proposed, named SCKFIoU, which improves the accuracy and stability of overlap calculation by introducing a small perturbation term and utilizing Cholesky decomposition for efficient matrix inversion and determinant calculation. Evaluations using the DOTA-ORShip dataset demonstrate that RACR-ShipDet outperforms current state-of-the-art models, achieving an mAP of 95.3%, representing an improvement of 5.3% over PSC (90.0%) and of 1.9% over HDDet (93.4%). Furthermore, it demonstrates a superior orientation accuracy of 96.9%, exceeding HDDet by a margin of 5.0%, establishing itself as a robust solution for ship orientation detection in complex environments. Full article

Structural health monitoring (SHM) is critical for ensuring the safety and longevity of structures, yet existing methodologies often face challenges such as high data dimensionality, lack of interpretability, and reliance on extensive label datasets. Current research in SHM has primarily focused on supervised approaches, which require significant manual effort for data labeling and are less adaptable to new environments. Additionally, the large volume of data generated from dynamic structural monitoring campaigns often includes irrelevant or redundant features, further complicating the analysis and reducing computational efficiency. This study addresses these issues by introducing an unsupervised learning approach for SHM, employing an agglomerative clustering model alongside an unsupervised feature selection technique utilizing box-plot statistics. The proposed method is assessed through raw acceleration signals obtained from four dynamic structural monitoring campaigns, including 44 features with temporal, statistical, and spectral information. In addition, these features are also evaluated in terms of their relevance, and the most important ones are selected for a new execution of the computational procedure. The proposed feature selection not only reduces data dimensionality but also enhances model interpretability, improving the clustering performance in terms of homogeneity, completeness, V-measure, and adjusted Rand score. The results obtained for the four analyzed cases provide clear insights into the patterns of behavior and structural anomalies. Full article

To address challenges such as the frequent misdetection of targets, missed detections of multiple targets, high computational demands, and poor real-time detection performance in the video surveillance of external breakage obstacles on transmission lines, we propose a lightweight target detection algorithm incorporating the ACmix mechanism. First, the ShuffleNetv2 backbone network is used to reduce the model parameters and improve the detection speed. Next, the ACmix attention mechanism is integrated into the Neck layer to suppress irrelevant information, mitigate the impact of complex backgrounds on feature extraction, and enhance the network’s ability to detect small external breakage targets. Additionally, we introduce the PC-ELAN module to replace the ELAN-W module, reducing redundant feature extraction in the Neck network, lowering the model parameters, and boosting the detection efficiency. Finally, we adopt the SIoU loss function for bounding box regression, which enhances the model stability and convergence speed due to its smoothing characteristics. The experimental results show that the proposed algorithm achieves an mAP of 92.7%, which is 3% higher than the baseline network. The number of model parameters and the computational complexity are reduced by 32.3% and 44.9%, respectively, while the detection speed is improved by 3.5%. These results demonstrate that the proposed method significantly enhances the detection performance. Full article

The advancement of Transformer models in computer vision has rapidly spurred numerous Transformer-based object detection approaches, such as DEtection TRansformer. Although DETR’s self-attention mechanism effectively captures the global context, it struggles with fine-grained detail detection, limiting its efficacy in small object detection where noise can easily obscure or confuse small targets. To address these issues, we propose Fuzzy System DNN-DETR involving two key modules: Fuzzy Adapter Transformer Encoder and Fuzzy Denoising Transformer Decoder. The fuzzy Adapter Transformer Encoder utilizes adaptive fuzzy membership functions and rule-based smoothing to preserve critical details, such as edges and textures, while mitigating the loss of fine details in global feature processing. Meanwhile, the Fuzzy Denoising Transformer Decoder effectively reduces noise interference and enhances fine-grained feature capture, eliminating redundant computations in irrelevant regions. This approach achieves a balance between computational efficiency for medium-resolution images and the accuracy required for small object detection. Our architecture also employs adapter modules to reduce re-training costs, and a two-stage fine-tuning strategy adapts fuzzy modules to specific domains before harmonizing the model with task-specific adjustments. Experiments on the COCO and AI-TOD-V2 datasets show that FSDN-DETR achieves an approximately 20% improvement in average precision for very small objects, surpassing state-of-the-art models and demonstrating robustness and reliability for small object detection in complex environments. Full article