Search Results (2,162)

Transmission tower climbing is a critical specialized operation in ultra-high-voltage power maintenance and communication infrastructure servicing. However, existing lower-limb exoskeletons used for tower climbing still suffer from insufficient motion intention recognition accuracy under complex operational environments. To address this issue, this study proposes an inertial measurement unit (IMU)-based bidirectional temporal deep learning method for motion intention recognition. First, a one-dimensional convolutional neural network (1D-CNN) is employed to extract local temporal features from multi-channel IMU signals. Subsequently, a bidirectional long short-term memory network (Bi-LSTM) is introduced to model the forward and backward temporal dependencies of motion sequences. Furthermore, a temporal attention mechanism is incorporated to emphasize discriminative features at critical movement phases, enabling the precise recognition of short-duration and transitional motions. Experimental results demonstrate that the proposed method outperforms traditional machine learning approaches and unidirectional temporal models in terms of accuracy, F1-score, and other evaluation metrics. In particular, this method demonstrates significant advantages in identifying the flexion/extension phases and transitional states. This study provides an offline method for analyzing movement intentions in lower-limb exoskeleton control for power transmission tower climbing scenarios and offers a reference for developing assistive control strategies for assisted climbing tasks in this specific context. Full article

Line spectrum purification is a fundamental task in underwater detection and identification tasks. A dual-input architecture based on Dense U-net is introduced to extract clean line spectra from strong interference. The U-net model features a symmetric encoder–decoder structure that accepts two-dimensional data as both input and output. The DenseBlock, a core component of DenseNets, offers greater parameter efficiency compared to conventional convolutional layers. In this paper, standard convolutional layers inside the original U-net are replaced by DenseBlocks. This model possesses two input channels, thus allowing the time–frequency feature of the interference and that of the interference–target mixture to be fed simultaneously. With supervised learning, the model is capable of eliminating the strong interference components and background noise from the superimposed spectrum, thereby producing a purified target line spectrum. Compared to traditional interference suppression methods, this approach offers higher feature accuracy and greater signal-to-interference-and-noise ratio (SINR) gain. Moreover, the model is trainable using simulation datasets and then deployed to real-world measurements, demonstrating strong generalization capabilities—a valuable property given the limited availability of labeled samples in underwater detection tasks. Being data-driven, this method operates without requiring prior assumptions about the array configuration, and consequently exhibits greater resilience to array imperfections relative to conventional model-based interference suppression techniques. Simulation and experimental results demonstrate that the proposed method achieves an output SINR improvement of more than 8 dB under low SINR conditions and exhibits significantly better robustness to array position errors than conventional methods, verifying its excellent line spectrum purification capability. Full article

In collaborative robotics, efficiency and user experience play a central role. This study looks at how perceived performance differs from measured performance when comparing two ways of controlling industrial robots: traditional teaching pendants and wearable EMG-based gesture control. A Myo Armband was used as an accessible 8-channel EMG platform, and three experiments were carried out on a Universal Robots UR10e to test pick-and-place tasks and precision positioning. Time and accuracy data were gathered together with blind feedback from 13 participants through a multi-criteria analysis framework. Even though the teaching pendant turned out to be more accurate in every scenario, 85% of participants still rated gesture control higher in overall satisfaction. These results point to a notable gap between what users perceive and how they actually perform and suggest that user experience deserves more weight in the design of future robot control interfaces. Full article

During the interpretation of Borehole Radar (BHR) B-scan profiles, the accurate determination of the azimuth of geological targets in three-dimensional space is a critical issue for achieving precise anomaly localization and spatial structure inversion. However, existing directional BHR anomaly localization methods exhibit limited intelligence, insufficient adaptability to multi-site data, and weak generalization capability, rendering them inadequate for engineering applications under complex geological conditions. To address these challenges, a robust deep learning model, termed BSS-Pose-BHR, is developed based on YOLOv11n-pose for keypoint detection in directional BHR profiles. The model incorporates three key optimizations: Bi-Level Routing Attention (BRA) replaces Multi-Head Self-Attention (MHSA) in the backbone to improve computational efficiency; Conv_SAMWS enhances keypoint-related feature weighting in the backbone and neck; and Spatial and Channel Reconstruction Convolution (SCConv) is integrated into the detection head to reduce redundancy and strengthen local feature extraction, thereby improving suitability for keypoint detection tasks. In addition, a three-dimensional electromagnetic model of limestone containing a certain density of clay particles is established to construct a simulation dataset. On the simulated test set, compared with current mainstream deep learning approaches and conventional directional borehole radar anomaly localization algorithms, BSS-Pose-BHR achieves superior performance, with an mAP50(B) of 0.9686, an mAP50–95(B) of 0.7712, an mAP50(P) of 0.9951, and an mAP50–95(P) of 0.9952. Ablation experiments demonstrate that each proposed module contributes significantly to performance improvement. Compared with the baseline, BSS-Pose-BHR improves mAP50(B) by 5.39% and mAP50(P) by 0.86%, while increasing model weight by only 1.05 MB, thereby achieving a reasonable trade-off between detection accuracy and complexity. Furthermore, indoor physical model experiments validate the effectiveness of the method on measured data. Robustness experiments under different Peak Signal-to-Noise Ratio (PSNR) conditions and varying missing-trace rates indicate that BSS-Pose-BHR maintains high detection accuracy under moderate noise and data loss, demonstrating strong engineering applicability and practical value. Full article

In recent years, image denoising has seen a shift from traditional non-local self-similarity methods like BM3D to deep-learning based approaches that use learnable convolutions and attention mechanisms. While pixel-level attention is effective at capturing long-range relationships similar to non-local self-similarity based methods, it incurs extremely high computational costs that scale quadratically with image resolution. As an alternative, channel-wise attention is resolution-independent and computationally efficient but may miss crucial spatial details. In this paper, an adjustable attention mechanism is introduced that bridges the gap between pixel and channel attentions. In the proposed model, average pooling and variable-size convolutions are added before attention calculation to adjust spatial resolution and, thus, allow dynamical adjustment of computational complexity. This adjustable attention is applied in a transformer-based U-Net architecture and achieves performance comparable to state-of-the-art methods in both real and Gaussian blind denoising tasks. To be more concrete, the proposed method achieves a Peak Signal-to-Noise Ratio of 39.65 dB and a Structural Similarity Index Measure of 0.913 on the Smartphone Image Denoising Dataset. Therefore, the proposed method demonstrates a balance between efficiency and denoising quality. Full article

Autonomous Underwater Vehicles (AUVs) play a crucial role in deep-sea exploration missions. In the complex and highly dynamic marine environment, it is essential for AUVs to possess robust fault diagnosis capabilities to enhance their operational safety. In the context of AUV fault diagnosis, closed-set recognition methods tend to misclassify unknown faults as known ones, which may lead to severe operational consequences. In order to enable AUVs to adapt to new and unknown deep-sea environments and effectively detect new unknown faults, this paper proposes an open-set AUV fault recognition method based on a Convolutional Neural Network (CNN). Firstly, the CNN is employed to extract high-level discriminative features from raw sensor data. Then, a committee consisting of multiple one-class SVMs (OC-SVMs) is constructed to determine whether the input sample belongs to a known category. Finally, the identified known samples are accurately classified via the designed classifier module. This method can effectively distinguish between known faults and unknown faults. To improve the recognition accuracy of the model, an attention mechanism is introduced. By learning to automatically assign weights to different feature channels, the model can focus on more important or relevant feature channels. Experiments based on the “Haizhe” dataset demonstrate that the proposed CNN-OC-SVM model exhibits superior performance in AUV fault diagnosis tasks compared with the state-of-the-art and traditional methods. Full article

In this paper, we provide a thorough review of novel machine learning (ML) models for anomalous sound detection (ASD). We focus on deploying models to highly constrained, embedded systems and tiny ML, and using single-channel sound as the data input. The survey includes only the works published in 2020 and later. Researchers address the anomaly detection task in various ways, borrowing models and techniques from such fields as speech processing, audio generation, and even computer vision. However, it is not clear which of these are suitable for embedded systems, meeting their constraints such as memory or compute. To address that, we provide a deep analysis of these models and optimization techniques applied to meet the design criteria for embedded platforms. We consider both deep learning and classical ML methods. We define categories for the anomaly detection methods depending on the approach taken to provide a structure and simplify the comparison of methods. We aim to provide a guideline on how to develop ASD systems and how to efficiently deploy the models on the embedded platforms. Full article

Underwater sonar object detection is challenging because targets are often small, boundaries are blurred, background clutter is strong, and labeled sonar data are limited. To address these issues, we propose T2C-DETR, a detector built on RT-DETR with three task-oriented improvements: (i) a Transformer–Convolution dual-channel backbone (TCDCNet) for complementary global-context and local-detail modeling, (ii) a Noise Filtering Module (NFM) inserted before neck fusion to suppress noise-dominated activations, and (iii) a stage-wise transfer-learning strategy tailored to small sonar datasets. We evaluate the method under three pre-training sources (COCO 2017, DOTA, and an infrared dataset) and then fine-tune on a self-built sonar dataset. Experimental results show that T2C-DETR achieves AP50 of 97.8%, 98.2%, and 98.5% at 72–73 FPS, consistently outperforming the RT-DETR baseline, YOLOv5-Imp, and MLFFNet in the accuracy–speed trade-off. These results indicate that combining global–local representation learning with targeted noise suppression is effective for practical real-time sonar detection. Full article

Brain–computer interfaces (BCIs) are essential in assistive technologies to restore mobility in individuals with motor impairments. Although electroencephalography (EEG)-based brain-controlled wheelchairs have been extensively studied, most tongue-controlled systems rely on physical tongue movements, intraoral devices, or limited offline commands, which reduces the usability and comfort. This study introduces an EEG-based tongue motor imagery (MI) BCI for intuitive and entirely mental wheelchair control. By leveraging preserved motor function and the cortical representation of the tongue, the system enables natural four-directional control through imagined tongue movements. Six imagined tongue actions—touching the left and right mouth corners, the upper and lower lips, and producing left and right cheek bulges—were designed to elicit alpha-band event-related desynchronization (ERD) patterns over the tongue motor cortex. EEG data were collected from 15 healthy participants using a 14-channel consumer-grade EMOTIV EPOC X headset. Alpha-band ERD features were extracted and classified using linear discriminant analysis, support vector machine, naïve Bayes, and artificial neural networks (ANNs). Simpler command sets yielded the highest accuracy: two-class tasks achieved 76.19%, while the performance decreased with increasing task complexity. The ANN achieved superior results in multi-class scenarios. The proposed tongue MI method offers initial support for developing a BCI control strategy for assistive technology; however, further improvements in classification techniques, user training, and real-time validation are needed to improve the robustness and practical usability. Full article

Finite Rate of Innovation (FRI) sampling has been widely used to sampling parametric signals at sub-Nyquist sampling rates. Nevertheless, real-world systems generally handle real-valued signals, posing challenges for acquiring complex domain Fourier coefficients directly. To overcome this limitation, we propose a Chebyshev polynomial-based FRI sampling framework that enables processing entirely in the real domain. Projecting the FRI signal onto the Chebyshev basis and employing a improved annihilating filter reformulates the parameter estimation problem into a classical spectral estimation task. Furthermore, the integration of the discrete Hilbert transform allows for a further reduction in both sampling channels and total sample count. Numerical simulations validate the effectiveness of the proposed approach and the generalizability of FRI theory across different signal bases. Full article

Hyperspectral image (HSI) classification is a core task in remote sensing data interpretation. Although recently introduced state space models (SSMs), such as Mamba, have demonstrated promising performance in hyperspectral analysis due to their linear computational complexity and strong long-sequence modeling capability, existing single-stream scanning mechanisms struggle to effectively balance the intrinsic spectral continuity dependency and the high-dimensional redundancy inherent in HSI data. Moreover, they often suffer from representation discrepancies when fusing features from heterogeneous representation spaces. To address these challenges, we propose a continuous–discrete collaborative framework, termed Confluence Mamba (CF-Mamba). Specifically, the continuous modeling path (AHSE) introduces a multi-view adaptive routing mechanism to accurately capture anisotropic spectral–spatial continuous evolution patterns. Simultaneously, the discrete interaction path (IISE) employs interval sampling and channel shuffling strategies to efficiently decouple high-dimensional redundancy while maintaining fine-grained feature interactions. Furthermore, the confluence gating unit (CGU) leverages a bidirectional cross-modulation mechanism to constrain discrete feature distributions using continuous contextual information, effectively alleviating representation discrepancies during multi-scale feature fusion. Extensive experiments conducted on four benchmark datasets, namely, Indian Pines, Pavia University, Houston, and WHU-Hi-Longkou, demonstrate that CF-Mamba achieves overall accuracies of 97.77%, 99.68%, 99.06%, and 99.59%, respectively. The proposed method consistently outperforms existing CNN-, Transformer-, and Mamba-based approaches in terms of both classification performance and computational efficiency. Full article

The deep image prior (DIP) suggests that it is possible to train a randomly initialized network with a suitable architecture to solve inverse imaging problems by simply optimizing its parameters to reconstruct a single degraded image. However, the prior knowledge exploited by vanilla DIP relies on basic local convolutions, which inevitably limits the performance of inverse imaging tasks to the generative capacity of the model. Furthermore, image information is often not only related to neighboring pixels but also dependent on global color features and spatial distribution. Simple local convolutions used in inverse imaging cannot capture precise fine-grained details. Moreover, DIP is an unsupervised process but requires iterations to learn inverse imaging, consuming computational power and limiting the adaptation of global attention. To solve these problems, this article explores an efficient global prior module—a tri-directional multi-head self-attention mechanism—aiming to learn pixel-wise correlations along three directions: horizontal, vertical, and channel-wise. Our observations found that global learning can effectively enhance the detail information of edge pixels, making images more vivid and textures clearer. In addition, tri-directional multi-head self-attention can efficiently replace the global perception ability of pixel-level self-attention. Finally, we demonstrate that global learning can effectively improve the imaging effect of inverse imaging problems and enhance the information of texture edge pixels. Moreover, tri-directional multi-head self-attention can effectively alleviate the computation redundancy of pixel-level self-attention, thus achieving efficient and high-quality inverse imaging tasks. The principle of this method lies in global feature capture and efficient attention modeling, striking a balance between detail fidelity and computational practicality. Full article

The methods employed for image demosaicing and denoising play a pivotal role in image acquisition and restoration, and have been extensively studied over the past few decades. Traditionally, these tasks are performed sequentially, with demosaicing followed by denoising, or vice versa, treating each process independently. While this approach can enhance image quality, it often leads to issues such as color inaccuracies and information loss, as the outcome of the first task influences the second. Consequently, the integration of joint demosaicing and denoising (JDD) has become a focal point in recent research. Deep convolutional neural networks have shown promising results in addressing JDD challenges. This study introduces an end-to-end network, termed the Frequency-domain Features learning Network (FFNet), designed to tackle the JDD problem. Unlike conventional methods that focus on spatial domain features, FFNet utilizes frequency-domain (FD) characteristics to capture both global and local image details. Based on the vision Transformer architecture, FFNet consists of two key components: a global Fourier block (GFB), which uses global attention to determine the weights of FD parameters, and an MLP-based local Fourier block (LFB), which improves local feature extraction. These blocks are integrated with a channel attention mechanism to form the frequency-domain attention block (FAB), the core element of FFNet. Extensive experimental results on benchmark datasets demonstrate that FFNet achieves superior performance in terms of both quantitative metrics (PSNR/SSIM) and visual quality compared to existing state-of-the-art JDD methods. Furthermore, we provide a comprehensive analysis of its computational efficiency, including parameter count, FLOPs, and inference time, showing a competitive trade-off between performance and complexity. Full article

In disease control and precision management in aquaculture, rapid and accurate identification of common fish diseases is pivotal to mitigating economic losses and ensuring aquaculture profitability. However, fish diseases are characterized by subtle symptoms, polymorphic lesions, and high susceptibility to environmental perturbations such as water turbidity and illumination fluctuations. Existing detection models generally suffer from inadequate lightweight design, poor fine-grained lesion feature extraction, and deficient adaptability to class imbalance, failing to meet the stringent requirements of precise diagnosis in real-world aquaculture scenarios. To address these challenges, this study proposes FDR-Net: a fine-grained lesion detection model for tilapia via multi-scale feature enhancement and spatial attention fusion. Using image data of Nile tilapia (Oreochromis niloticus) covering 6 common diseases and healthy individuals (from the NTD-1 dataset), the model incorporates symmetry-aware design logic, leveraging the morphological and textural symmetry of healthy tilapia tissues to capture lesion-induced symmetry-breaking features, thereby improving fine-grained lesion detection accuracy. Through depth-width scaling coefficients, FDR-Net achieves lightweight optimization while integrating three core modules and a task-specific loss function for full-chain optimization: specifically, a Micro-lesion Feature Enhancement Module (MLFEM) is embedded in key feature layers of the backbone network to accurately extract edge and texture features of incipient fine-grained lesions via multi-scale frequency decomposition and residual fusion; subsequently, a Lightweight Multi-scale Position Attention Module (MS_PSA) and a Single-modal Intra-feature Contrastive Fusion Module (SMICFM) are collaboratively deployed—the former focusing on spatial localization of lesion features, and the latter enhancing lesion-background discriminability through channel-spatial feature recalibration and contrastive fusion; finally, a Class-Aware Weighted Hybrid Loss (CAWHL) function is combined with customized small-target anchor boxes to alleviate class imbalance and further improve localization and classification accuracy of fine-grained lesions. Empirical evaluations on the NTD-1 dataset demonstrate that compared with mainstream state-of-the-art baseline models, FDR-Net achieves a peak recognition accuracy of 90.1% with substantially enhanced mAP_50-95 performance. Retaining lightweight characteristics, it exhibits superior performance in identifying incipient fine-grained lesions and strong adaptability to simulated complex aquaculture scenarios. Collectively, this study provides an efficient technical backbone for the rapid and precise detection of tilapia fine-grained lesions, offering a potential solution for precise disease management in tilapia farming. Full article

Early and accurate identification of tomato leaf diseases constitutes a key safeguard for mitigating economic losses in tomato production. Conventional tomato leaf disease detection methodologies are constrained by inherent limitations, such as low operational efficiency, inadequate detection precision, and limited adaptability to environmental fluctuations. In contrast, the integration of deep learning techniques has yielded improvements in this research domain. Consequently, the development of deep learning-based approaches for the rapid and precise detection of tomato leaf diseases holds considerable theoretical significance and practical application value. To improve the detection accuracy of tomato leaf diseases, this study proposes a transfer learning-based DenseNet disease recognition model named DenseNet-BiFPN-ECA Fusion Network. The bidirectional feature pyramid network (BiFPN) is introduced at the terminal of DenseNet121 to achieve multi-scale feature fusion, while the efficient channel attention (ECA) mechanism is applied to enhance the discriminative capacity of fused features. Classification is ultimately completed via a global average pooling layer and a fully connected layer. The experimental results demonstrate that the improved model achieves an accuracy of 90.63% on the small-sample tomato leaf dataset collected from complex greenhouse environments, representing an improvement of 20.32 percentage points over the original DenseNet121 model. On the large-scale open-source Plant Village dataset, the model attains an accuracy of 98.47%, significantly outperforming the baseline models. Furthermore, a comparative analysis shows that the highest accuracy achieved by DenseNet, ResNet101, and VGG16 models on the same dataset is only 83.59% (within ±0.5%). This result validates the effectiveness of DenseNet-BiFPN-ECA Fusion Network in disease recognition tasks. The model provides a reliable technical reference for the intelligent diagnosis of tomato leaf diseases. Full article