Search Results (89)

High-resolution range profile (HRRP) target recognition has garnered significant attention in radar automatic target recognition (RATR) research for its rich structural information and low computational costs. With the rapid advancements in deep learning, methods for HRRP target recognition that leverage deep neural networks have emerged as the dominant approaches. Nevertheless, these traditional closed-set recognition methods require labeled data for every class in training, while in reality, seen classes and unseen classes coexist. Therefore, it is necessary to explore methods that can identify both seen and unseen classes simultaneously. To this end, a semantic- and physical-guided generative network (SPGGN) was innovatively proposed for HRRP generalized zero-shot recognition; it combines a constructed knowledge graph with attribute vectors to comprehensively represent semantics and reconstructs strong scattering points to introduce physical constraints. Specifically, to boost the robustness, we reconstructed the strong scattering points from deep features of HRRPs, where class-aware contrastive learning in the middle layer effectively mitigates the influence of target-aspect variations. In the classification stage, discriminative features are produced through attention-based feature fusion to capture multi-faceted information, while the design of balancing loss abates the bias towards seen classes. Experiments on two measured aircraft HRRP datasets validated the superior recognition performance of our method. Full article

This paper investigates Electrocardiogram (ECG) rhythm classification using a progressive deep learning framework that combines time–frequency representations with complementary hand-crafted features. In the first stage, ECG signals from the PhysioNet Challenge 2017 dataset are transformed into scalograms and input to diverse architectures, including Simple Convolutional Neural Network (SimpleCNN), Residual Network with 18 Layers (ResNet-18), Convolutional Neural Network-Transformer (CNNTransformer), and Vision Transformer (ViT). ViT achieved the highest accuracy (0.8590) and F1-score (0.8524), demonstrating the feasibility of pure image-based ECG analysis, although scalograms alone showed variability across folds. In the second stage, scalograms were fused with scattering and statistical features, enhancing robustness and interpretability. FusionViT without dimensionality reduction achieved the best performance (accuracy = 0.8623, F1-score = 0.8528), while Fusion ResNet-18 offered a favorable trade-off between accuracy (0.8321) and inference efficiency (0.016 s per sample). The application of Principal Component Analysis (PCA) reduced the dimensionality of the feature from 509 to 27, reducing the computational cost while maintaining competitive performance (FusionViT precision = 0.8590). The results highlight a trade-off between efficiency and fine-grained temporal resolution. Training-time augmentations mitigated class imbalance, enabling lightweight inference (0.006–0.043 s per sample). For real-world use, the framework can run on wearable ECG devices or mobile health apps. Scalogram transformation and feature extraction occur on-device or at the edge, with efficient models like ResNet-18 enabling near real-time monitoring. Abnormal rhythm alerts can be sent instantly to users or clinicians. By combining visual and statistical signal features, optionally reduced with PCA, the framework achieves high accuracy, robustness, and efficiency for practical deployment. Full article

The slender snipe eel Nemichthys scolopaceus Richardson, 1848 is cosmopolitan in tropical and temperate seas, inhabiting the mesopelagic and bathypelagic zone between 200 and 1000 m depth. It is known to be an active predator in the DSL (Deep Scattering Layer) and the NBA (Near Bottom Aggregation), feeding mostly on decapod and euphausiid crustaceans, and playing a central role in carbon fluxes through meso- and bathypelagic ecosystems. Despite its potential importance in the deep trophic web ecosystem, the trophic ecology of Nemichthys scolopaceus is not well known. The aim of this study was to start to fill this knowledge gap. A total of 35 specimens of N. scolopaceus caught through bottom trawling in the Mediterranean Sea were analyzed in the laboratory for stomach content composition. As expected, mainly decapod crustaceans were found, in particular Plesionika martia, Pasiphaea multidentata, Funchalia woodwardi, and Robustosergia robusta species. The degree of digestion of prey in the stomachs was high in all cases. Our findings seem to confirm the specialist diet of Nemichthys scolopaceus based on shrimp-like crustaceans. Full article

In recent years, deep learning methods have made breakthroughs in the field of rotating equipment fault diagnosis, thanks to their powerful data analysis capabilities. However, the vibration signals usually incorporate fault features and background noise, and these features may be scattered over multiple frequency levels, which increases the complexity of extracting important information from them. To address this problem, this paper proposes a Masked and Cascaded Multi-Branch Attention Network (MCMBAN), which combines the Noise Mask Filter Block (NMFB) with the Multi-Branch Cascade Attention Block (MBCAB), and significantly improves the noise immunity of the fault diagnostic model and the efficiency of fault feature extraction. NMFB novelly combines a wide convolutional layer and a top k neighbor self-attention masking mechanism, so as to efficiently filter unnecessary high-frequency noise in the vibration signal. On the other hand, MBCAB strengthens the interaction between different layers by cascading the convolutional layers of different scales, thus improving the recognition of periodic fault signals and greatly enhancing the diagnosis accuracy of the model when processing complex signals. Finally, the time–frequency analysis technique is employed to explore the internal mechanisms of the model in depth, aiming to validate the effectiveness of NMFB and MBCAB in fault feature recognition and to improve the feature interpretability of the proposed modes in fault diagnosis applications. We validate the superior performance of the network model in dealing with high-noise backgrounds by testing it on a standard bearing dataset from Case Western Reserve University and a self-constructed composite bearing fault dataset, and the experimental results show that its performance exceeded six of the top current fault diagnosis techniques. Full article

In recent years, the classification of underwater images has become one of the most remarkable areas of research in computer vision due to its useful applications in marine sciences, aquatic robotics, and sea exploration. Underwater imaging is pivotal for the evaluation of marine eco-systems, analysis of biological habitats, and monitoring underwater infrastructure. Extracting useful information from underwater images is highly challenging due to factors such as light distortion, scattering, poor contrast, and complex foreground patterns. These difficulties make traditional image processing and machine learning techniques struggle to analyze images accurately. As a result, these challenges and complexities make the classification difficult or poor to perform. Recently, deep learning techniques, especially convolutional neural network (CNN), have emerged as influential tools for underwater image classification, contributing noteworthy improvements in accuracy and performance in the presence of all these challenges. In this paper, we have proposed a modified ResNet-18 model for the binary classification of underwater images into raw and enhanced images. In the proposed modified ResNet-18 model, we have added new layers such as Linear, rectified linear unit (ReLU) and dropout layers, arranged in a block that was repeated three times to enhance feature extraction and improve learning. This enables our model to learn the complex patterns present in the image in more detail, which helps the model to perform the classification very well. Due to these newly added layers, our proposed model addresses various complexities such as noise, distortion, varying illumination conditions, and complex patterns by learning vigorous features from underwater image datasets. To handle the issue of class imbalance present in the dataset, we applied a data augmentation technique. The proposed model achieved outstanding performance, with 96% accuracy, 99% precision, 92% sensitivity, 99% specificity, 95% F1-score, and a 96% Area under the Receiver Operating Characteristic Curve (AUC-ROC) score. These results demonstrate the strength and reliability of our proposed model in handling the challenges posed by the underwater imagery and making it a favorable solution for advancing underwater image classification tasks. Full article

Time-domain (TD) diffuse reflectance can be modeled using diffusion theory (DT) to non-invasively estimate optical transport coefficients of biological media, which serve as markers of tissue physiology. We employ an optimized N-layer DT solver in cylindrical geometry to reconstruct optical coefficients of bilayered media from TD reflectance generated via Monte Carlo (MC) simulations. Optical properties for 384 bilayered tissue models representing human head or limb tissues were obtained from the literature at three near-infrared wavelengths. MC data were fit using the layered DT model to simultaneously recover transport coefficients in both layers. Bottom-layer absorption was recovered with errors under 0.02 cm⁻¹, and top-layer scattering was retrieved within 3 cm⁻¹ of input values. In contrast, recovered bottom-layer scattering had mean errors exceeding 50%. Total hemoglobin concentration and oxygen saturation were reconstructed for the bottom layer to within 10 μM and 5%, respectively. Extracted transport coefficients were significantly more accurate when obtained using layered DT compared to the conventional, semi-infinite DT model. Our results suggest using improved theoretical modeling to analyze TD reflectance analysis significantly improves recovery of deep-layer absorption. Full article

The SPICAV IR spectrometer aboard the Venus Express orbiter measured spectra of the 1.1 and 1.18 μm atmospheric transparency windows at the Venus night side in 2006–2014. The long-term measurements encompassed the major part of the Venus globe, including polar latitudes. For the first time, the H₂O volume mixing ratio in the deep Venus atmosphere at about 10–16 km has been retrieved for the entire SPICAV IR dataset using a radiative transfer model with multiple scattering. The retrieved H₂O volume mixing ratio is found to be sensitive to different approximations of the H₂O and CO₂ absorption lines’ far wings and assumed surface emissivity. The global average of the H₂O abundance retrieved for different parameters ranges from 23.6 ± 1.0 ppmv to 27.7 ± 1.2 ppmv. The obtained values are consistent with recent studies of water vapor below the cloud layer, showing the H₂O mixing ratio below 30 ppmv. Within the considered dataset, the zonal mean of the H₂O mixing ratio does not vary significantly from 60° S to 75° N, except for a 2 ppmv decrease noted at high latitudes. The H₂O local time distribution is also uniform. The 8-year observation period revealed no significant long-term trends or periodicities. Full article

Deep-sea biological detection is a pivotal technology for the exploration and conservation of marine resources. Nonetheless, the inherent complexities of the deep-sea environment, the scarcity of available deep-sea organism samples, and the significant refraction and scattering effects of underwater light collectively impose formidable challenges on the current detection algorithms. To address these issues, we propose an advanced deep-sea biometric identification framework based on an enhanced YOLOv8n architecture, termed PSVG-YOLOv8n. Specifically, our model integrates a highly efficient Partial Spatial Attention module immediately preceding the SPPF layer in the backbone, thereby facilitating the refined, localized feature extraction of deep-sea organisms. In the neck network, a Slim-Neck module (GSconv + VoVGSCSP) is incorporated to reduce the parameter count and model size while simultaneously augmenting the detection performance. Moreover, the introduction of a squeeze–excitation residual module (C2f_SENetV2), which leverages a multi-branch fully connected layer, further bolsters the network’s global representational capacity. Finally, an improved detection head synergistically fuses all the modules, yielding substantial enhancements in the overall accuracy. Experiments conducted on a dataset of deep-sea images acquired by the Jiaolong manned submersible indicate that the proposed PSVG-YOLOv8n model achieved a precision of 79.9%, an mAP50 of 67.2%, and an mAP50-95 of 50.9%. These performance metrics represent improvements of 1.2%, 2.3%, and 1.1%, respectively, over the baseline YOLOv8n model. The observed enhancements underscore the effectiveness of the proposed modifications in addressing the challenges associated with deep-sea organism detection, thereby providing a robust framework for accurate deep-sea biological identification. Full article

Numerical simulation of ground-penetrating radar (GPR) has been widely used to enhance the interpretation of GPR data and serves as a key component in Full Waveform Inversion (FWI). In response to the time-consuming numerical computation of layered medium and buried targets, which leads to inefficiency in full-wave inversion, this paper proposes a machine learning-based forward scattering rapid solution method. Using the detection of rebar buried in concrete under sand as the GPR application scenario, with scene parameters such as concrete moisture content, rebar radius, and burial depth, scattering echo signals are obtained via Finite Difference Time Domain (FDTD) simulation. Principal component analysis (PCA) is applied to reduce the dimensionality of the echo data, and the first 40 principal component weight coefficients are selected as the output of the deep learning network. An innovative cyclic nested deep learning network architecture is designed, which not only fully explores the intrinsic causal relationship between the scene parameters and the principal component weight coefficients, but also refines and corrects each predicted principal component. The numerical results demonstrate that, compared with traditional machine learning methods, the cyclic nested machine learning network architecture offers higher prediction accuracy and learning efficiency, validating the effectiveness of the proposed method. Full article

This paper presents the development and evaluation of a distributed system employing low-latency embedded field-programmable gate arrays (FPGAs) to optimize scheduling for deep learning (DL) workloads and to configure multiple deep learning accelerator (DLA) architectures. Aimed at advancing FPGA applications in real-time edge computing, this study focuses on achieving optimal latency for a distributed computing system. A novel methodology was adopted, using configurable hardware to examine clusters of DLAs, varying in architecture and scheduling techniques. The system demonstrated its capability to parallel-process diverse neural network (NN) models, manage compute graphs in a pipelined sequence, and allocate computational resources efficiently to intensive NN layers. We examined five configurable DLAs—Versatile Tensor Accelerator (VTA), Nvidia DLA (NVDLA), Xilinx Deep Processing Unit (DPU), Tensil Compute Unit (CU), and Pipelined Convolutional Neural Network (PipeCNN)—across two FPGA cluster types consisting of Zynq-7000 and Zynq UltraScale+ System-on-Chip (SoC) processors, respectively. Four deep neural network (DNN) workloads were tested: Scatter-Gather, AI Core Assignment, Pipeline Scheduling, and Fused Scheduling. These methods revealed an exponential decay in processing time up to 90% speedup, although deviations were noted depending on the workload and cluster configuration. This research substantiates FPGAs’ utility in adaptable, efficient DL deployment, setting a precedent for future experimental configurations and performance benchmarks. Full article

To address the challenge posed by the abundance of small objects with weak object features and little information in the images of underwater biomonitoring scenarios, and the added difficulty of recognizing these objects due to light absorption and scattering in the underwater environment, this study proposes an improved RHS-YOLOv8 (Ref-Dilated-HBFPN-SOB-YOLOv8). Firstly, a combination of hybrid inflated convolution and RefConv is used to redesign the lightweight Ref-Dilated convolution block, which reduces the model computation. Second, a new feature pyramid network fusion module, the Hybrid Bridge Feature Pyramid Network (HBFPN), is designed to fuse the deep features with the high-level features, as well as the features of the current layer, to improve the feature extraction capability for fuzzy objects. Third, Efficient Localization Attention (ELA) is added to reduce the interference of irrelevant factors on prediction. Fourth, an Involution module is introduced to effectively capture spatial long-range relationships and improve recognition accuracy. Finally, a small object detection branch is incorporated into the original architecture to enhance the model’s performance in detecting small objects. Experiments based on the DUO dataset show that RHS-YOLOv8 reduces 9.95% of computing power, while mAP@0.5 and mAP@0.50:0.95 are improved by 2.54% and 4.31%, respectively. Compared with other cutting-edge underwater object detection algorithms, the present algorithm improves the detection accuracy while lightweighting the improvement, which effectively enhances the capability to detect small underwater objects. Full article

High pressure and temperature (PT) experimental charges are valuable systems composed of minerals, often with quenched melt and/or fluid, synthesized to inform petrological processes deep within Earth. We explored the utility of phase mapping for the analysis of 5 GPa partial melting experiments of peridotite. We further developed an open-source software workflow to generate phase maps, which is scanning electron microscope (SEM) instrument agnostic. Phase maps were constructed offline, combining high-quality back-scattered electron images and selected element maps, and compared and verified with maps obtained with commercial automated mineralogy software. One sub-solidus assemblage, one charge containing a small percentage of melt, and a melting experiment that displayed reactions (caused by a strong thermal gradient) were analyzed. For the sub-solidus experiment, the phase map returned an accurate modal mineralogy. For the quenched melt experiments, the phase map located low-abundance phases and identified the best-suited targets for chemical analysis. Using modal mineralogy of sub-regions on maps and mutual neighboring relationships, the phase maps helped to establish equilibrium conditions and verify melting reactions inferred from mass balance. We propose phase maps as valuable tools for documenting high PT charges, particularly for layered reaction experiments. We conclude with a set of recommended instrument settings for high-quality phase maps on small experimental charges. Full article

(1) Objective: As light propagates through water, it undergoes significant attenuation and scattering, causing underwater images to experience color distortion and exhibit a bluish or greenish tint. Additionally, suspended particles in the water further degrade image quality. This paper proposes an improved U-Net network model for underwater image enhancement to generate high-quality images. (2) Method: Instead of incorporating additional complex modules into enhancement networks, we opted to simplify the classic U-Net architecture. Specifically, we replaced the standard convolutions in U-Net with our self-designed efficient basic block, which integrates a simplified channel attention mechanism. Moreover, we employed Layer Normalization to enhance the capability of training with a small number of samples and used the GELU activation function to achieve additional benefits in image denoising. Furthermore, we introduced the SK fusion module into the network to aggregate feature information, replacing traditional concatenation operations. In the experimental section, we used the “Underwater ImageNet” dataset from “Enhancing Underwater Visual Perception (EUVP)” for training and testing. EUVP, established by Islam et al., is a large-scale dataset comprising paired images (high-quality clear images and low-quality blurry images) as well as unpaired underwater images. (3) Results: We compared our proposed method with several high-performing traditional algorithms and deep learning-based methods. The traditional algorithms include He, UDCP, ICM, and ULAP, while the deep learning-based methods include CycleGAN, UGAN, UGAN-P, and FUnIEGAN. The results demonstrate that our algorithm exhibits outstanding competitiveness on the underwater imagenet-dataset. Compared to the currently optimal lightweight model, FUnIE-GAN, our method reduces the number of parameters by 0.969 times and decreases Floating-Point Operations Per Second (FLOPS) by more than half. In terms of image quality, our approach achieves a minimal UCIQE reduction of only 0.008 while improving the NIQE by 0.019 compared to state-of-the-art (SOTA) methods. Finally, extensive ablation experiments validate the feasibility of our designed network. (4) Conclusions: The underwater image enhancement algorithm proposed in this paper significantly reduces model size and accelerates inference speed while maintaining high processing performance, demonstrating strong potential for practical applications. Full article

The quality of ISAR (Inverse Synthetic Aperture Radar) images has a significant impact on the detection and recognition of targets. Therefore, ISAR image quality assessment is a fundamental prerequisite and primary link in the utilization of ISAR images. Previous ISAR image quality assessment methods typically extract hand-crafted features or use simple multi-layer networks to extract local features. Hand-crafted features and local features from networks usually lack the global information of ISAR images. Furthermore, most deep neural networks obtain feature representations by abridging the prediction quality score and the ground truth, neglecting to explore the strong correlations between features and quality scores in the stage of feature extraction. This study proposes a Gramin Transformer to explore the similarity and diversity of features extracted from different images, thus obtaining features containing quality-related information. The Gramin matrix of features is computed to obtain the score token through the self-attention layer. It prompts the network to learn more discriminative features, which are closely associated with quality scores. Despite the Transformer architecture’s ability to extract global information, the Channel Attention Block (CAB) can capture complementary information from different channels in an image, aggregating and mining information from these channels to provide a more comprehensive evaluation of ISAR images. ISAR images are formed from target scattering points with a background containing substantial silent noise, and the Inter-Region Attention Block (IRAB) is utilized to extract local scattering point features, which decide the clarity of target. In addition, extensive experiments are conducted on the ISAR image dataset (including space stations, ships, aircraft, etc.). The evaluation results of our method on the dataset are significantly superior to those of traditional feature extraction methods and existing image quality assessment methods. Full article

Tree roots are vital for tree ecosystems; accurate root detection helps analyze the health of trees and supports the effective management of resources such as fertilizers, water and pesticides. In this paper, a deep learning-based ground-penetrating radar (GPR) inversion method is proposed to simultaneously image the spatial distribution of permittivity for subsurface tree roots and layered heterogeneous soils in real time. Additionally, a GPR simulation data set and a measured data set are built in this study, which were used to train inversion models and validate the effectiveness of GPR inversion methods.The introduced GPR inversion model is a pyramid convolutional network with vision transformer and edge inversion auxiliary task (PyViTENet), which combines pyramidal convolution and vision transformer to improve the diversity and accuracy of data feature extraction. Furthermore, by adding the task of edge inversion of the permittivity distribution of underground materials, the model focuses more on the details of heterogeneous structures. The experimental results show that, for the case of buried scatterers in layered heterogeneous soil, the PyViTENet performs better than other deep learning methods on the simulation data set. It can more accurately invert the permittivity of scatterers and the soil stratification. The most notable advantage of PyViTENet is that it can accurately capture the heterogeneous structural details of the soil within the layer since the soil around the tree roots in the real scene is layered soil and each layer of soil is also heterogeneous due to factors such as humidity, proportion of different soil particles, etc.In order to further verify the effectiveness of the proposed inversion method, this study applied the PyViTENet to GPR measured data through transfer learning for reconstructing the permittivity, shape, and position information of scatterers in the actual scene. The proposed model shows good generalization ability and accuracy, and provides a basis for non-destructive detection of underground scatterers and their surrounding medium. Full article