Search Results (186)

Single-image dehazing of high-voltage power transmission lines (HPTLs) using deep learning methods confronts two critical challenges: the non-homogeneous haze distribution in HPTL images and the unavailability of paired clear images for supervised training. To overcome these issues, this paper proposes a novel dehaze neural network, named FIF-RSCT-Net, that employs a hybrid supervised-to-unsupervised iterative learning approach according to the characteristic of HPTL single images. The FIF-RSCT-Net incorporates the Spatial–Channel Feature Intersection modules and Residual Separable Convolution Transformers to enhance the feature representation capability. Crucially, this novel architecture could learn more generalized dehazing knowledge that can be transferred from the original image domain to HPTL scenarios. In the dehazing knowledge transformation, an unsupervised iterative learning mechanism based on the Line Segment Detector is designed to optimize the restoration of power transmission lines. The effectiveness of FIF-RSCT-Net on the original image domain is demonstrated in the comparative experiments of the I-Haze, O-Haze, NH-Haze, and SOTS datasets. Our methodology achieves the best average PSNR of 24.647 dB and SSIM of 0.8512. And the qualitative evaluation of unsupervised iterative learning results shows that the missed line segments are exhibited during progressive training iterations. Full article

This paper presents a modified Orthogonal Frequency Division Multiplexing (OFDM) system that combines Discrete Wavelet Transform (DWT) with Discrete Sine Transform (DST) to enhance data rate capacity over traditional Discrete Fourier Transform (DFT)-based OFDM systems. By applying Inverse Discrete Wavelet Transform (IDWT) to the modulated Binary Phase Shift Keying (BPSK) bits, the constellation diagram reveals that half of the time-domain samples after single-level Haar IDWT are zeros, while the other half are real. The proposed system utilizes these $0.5N$ zero values, modulating them with the DST (IDST) and assigning them as the imaginary part of the signal. Performance comparisons demonstrate that the Bit-Error-Rate (BER) of this hybrid DWT-DST configuration lies between that of BPSK and Quadrature Phase Shift Keying (QPSK) in a DWT-based system, while also achieving data rate improvement of $0.5N$. Additionally, simulation results indicate that the proposed approach demonstrates stable performance even in the presence of estimation errors, with less than 3.4% BER degradation for moderate errors, and consistently better robustness than QPSK-based systems while offering improved data rate efficiency over BPSK. This novel configuration highlights the potential for more efficient and reliable data transmission in OFDM systems, making it a promising alternative to conventional DWT or DFT-based methods. Full article

Fiber-optic sensing systems based on a forward transmission interferometric structure can achieve high sensitivity and a wide frequency response over long distances. However, there are still shortcomings in its ability to position multi-point vibrations and detect low-frequency vibrations, which limits its usefulness. To address these challenges, we study the viability of merging long-range forward-transmission distributed vibration sensing (FTDVS) with high spatial resolution optical frequency-domain reflectometry (OFDR), forming the first reported hybrid distributed sensing method between these two methods. The probe light source is shared between the two sub-systems, which utilizes stable linear optical frequency sweeping facilitated by high-order sideband injection locking. As a result, this is a new approach for the FTDVS method, which conventionally uses fixed-frequency continuous light. The method of nearest neighbor signal replacement (NSR) is proposed to address the issue of discontinuity in phase demodulation under periodic external modulation. The experimental results demonstrate that the hybrid system can determine the position of vibration signals between 0 and 900 Hz within a sensing distance of 21 km. When the sensing distance is extended to 71 km, the FTDVS module can still function adequately for high-frequency vibration signals. This hybrid architecture offers a fresh approach to simultaneously achieving long-distance sensing and wide frequency response, making it suitable for the combined measurement of dynamic (e.g., gas leakage, pipeline excavation warning) and quasi-static (e.g., pipeline displacement) events in long-distance applications. Full article

While synthetic biology has traditionally focused on creating biological systems often through genetic engineering, emerging technologies, for example, implantable pacemakers with integrated piezo-electric and tribo-electric materials are beginning to enlarge the classical domain into what we call symbiotic synthetic biology. These devices are permanently attached to a body, although non-living or genetically unaltered, and closely mimic biological behavior by harvesting biomechanical energy and providing functions, such as autonomous heart pacing. They form active interfaces with human tissues and operate as hybrid systems, similar to synthetic organs. In this context, the present paper first presents a short summary of previous in vivo studies on piezo-electric composites in relation to their deployment as battery-less pacemakers. This is then followed by a summary of a recent theoretical work using a damped harmonic resonance model, which is being extended to mimic the functioning of such devices. We then extend the theoretical study further to include new solutions and obtain a sum rule for the power output per cycle in such systems. In closing, we present our quantitative understanding to explore the modulation of the quantum vacuum energy (Casimir effect) by periodic body movements to power pacemakers. Taken together, the present work provides the scientific foundation of the next generation bio-integrated intelligent implementation. Full article

Transformer-based 2D-to-3D lifting methods have demonstrated outstanding performance in 3D human pose estimation from 2D pose sequences. However, they still encounter challenges with the relatively poor quality of 2D joints and substantial computational costs. In this paper, we propose a CGFusionFormer to address these problems. We propose a compact spatial representation (CSR) to robustly generate local spatial multihypothesis features from part of the 2D pose sequence. Specifically, CSR models spatial constraints based on body parts and incorporates 2D Gaussian filters and nonparametric reduction to improve spatial features against low-quality 2D poses and reduce the computational cost of subsequent temporal encoding. We design a residual-based Hybrid Adaptive Fusion module that combines multihypothesis features with global frequency domain features to accurately estimate the 3D human pose with minimal computational cost. We realize CGFusionFormer with a PoseFormer-like transformer backbone. Extensive experiments on the challenging Human3.6M and MPI-INF-3DHP benchmarks show that our method outperforms prior transformer-based variants in short receptive fields and achieves a superior accuracy–efficiency trade-off. On Human3.6M (sequence length 27, 3 input frames), it achieves 47.6 mm Mean Per Joint Position Error (MPJPE) at only 71.3 MFLOPs, representing about a 40 percent reduction in computation compared with PoseFormerV2 while attaining better accuracy. On MPI-INF-3DHP (81-frame sequences), it reaches 97.9 Percentage of Correct Keypoints (PCK), 78.5 Area Under the Curve (AUC), and 27.2 mm MPJPE, matching the best PCK and achieving the lowest MPJPE among the compared methods under the same setting. Full article

With the widespread deployment of deep neural networks in real-world physical environments, assessing their robustness against adversarial attacks has become a central issue in AI safety. However, the existing two-dimensional adversarial methods often lack robustness in the physical world, while three-dimensional adversarial camouflage generation typically relies on high-fidelity 3D models, limiting practicality. To address these limitations, we propose CAM3D, a cross-domain 3D adversarial camouflage generation framework based on single-view image input. The framework establishes an inverse graphics network based on the Mamba architecture, integrating a hybrid non-causal state-space-duality module and a wavelet-enhanced dual-branch local perception module. This design preserves global dependency modeling while strengthening high-frequency detail representation, enabling high-precision recovery of 3D geometry and texture from a single image and providing a high-quality structural prior for subsequent adversarial camouflage optimization. On this basis, CAM3D employs a progressive three-stage optimization strategy that sequentially performs multi-view pseudo-supervised reconstruction, real-image detail refinement, and cross-domain adversarial camouflage generation, thereby systematically improving the attack effectiveness of adversarial camouflage in both the digital and physical domains. The experimental results demonstrate that CAM3D substantially reduces the detection performance of mainstream object detectors, and comparative as well as ablation studies further confirm its advantages in geometric consistency, texture fidelity, and physical transferability. Overall, CAM3D offers an effective paradigm for adversarial attack research in real-world physical settings, characterized by low data dependency and strong physical generalization. Full article

Failures of rotating machinery, such as bearings and gears, are a critical concern in industrial systems, leading to significant operational downtime and economic losses. A primary research challenge is achieving accurate fault diagnosis under complex industrial noise, where weak fault signatures are often masked by interference signals. This problem is particularly acute in demanding applications like offshore wind turbines, where harsh operating conditions and high maintenance costs necessitate highly robust and reliable diagnostic methods. To address this challenge, this paper proposes a novel Multi-Scale Domain Convolutional Attention Network (MSDCAN). The method integrates enhanced adaptive multi-domain feature extraction with a hybrid attention mechanism, combining information from the time, frequency, wavelet, and cyclic spectral domains with domain-specific attention weighting. A core innovation is the hybrid attention fusion mechanism, which enables cross-modal interaction between deep convolutional features and domain-specific features, enhanced by channel attention modules. The model’s effectiveness is validated on two public benchmark datasets for key rotating components. On the Case Western Reserve University (CWRU) bearing dataset, the MSDCAN achieves accuracies of 97.3% under clean conditions, 96.6% at 15 dB signal-to-noise ratio (SNR), 94.4% at 10 dB SNR, and a robust 85.5% under severe 5 dB SNR. To further validate its generalization, on the Xi’an Jiaotong University (XJTU) gear dataset, the model attains accuracies of 94.8% under clean conditions, 95.0% at 15 dB SNR, 83.6% at 10 dB SNR, and 63.8% at 5 dB SNR. These comprehensive results quantitatively validate the model’s superior diagnostic accuracy and exceptional noise robustness for rotating machinery, establishing a strong foundation for its application in reliable condition monitoring for complex systems, including wind turbines. Full article

Clinical notes often contain unstructured text filled with abbreviations, non-standard terminology, and inconsistent phrasing, which pose significant challenges for automated medical information extraction. Named Entity Recognition (NER) plays a crucial role in structuring this data by identifying and categorizing key clinical entities such as symptoms, medications, and diagnoses. However, traditional and even transformer-based NER models often struggle with ambiguity and fail to produce clinically interpretable outputs. In this study, we present a hybrid two-stage framework that enhances medical NER by integrating a fine-tuned BERT model for initial entity extraction with a Dictionary-Infused Retrieval-Augmented Generation (DiRAG) module for terminology normalization. Our approach addresses two critical limitations in current clinical NER systems: lack of contextual clarity and inconsistent standardization of medical terms. The DiRAG module combines semantic retrieval from a UMLS-based vector database with lexical matching and prompt-based generation using a large language model, ensuring precise and explainable normalization of ambiguous entities. The fine-tuned BERT model achieved an F1 score of 0.708 on the MACCROBAT dataset, outperforming several domain-specific baselines, including BioBERT and ClinicalBERT. The integration of the DiRAG module further improved the interpretability and clinical relevance of the extracted entities. Through qualitative case studies, we demonstrate that our framework not only enhances clarity but also mitigates common issues such as abbreviation ambiguity and terminology inconsistency. Full article

Information retrieval serves as a critical methodology for accurately and efficiently obtaining the required information from massive amounts of data. In this paper, we propose an information retrieval framework (SE-MSLC) that utilizes information theory to improve the retrieval effectiveness of inverted index retrieval, thus achieving higher-quality retrieval results in intelligent vertical domain search engines. First, we propose a semantic entropy-driven keyword importance analysis method (SE-KIA) in the query understanding module. This method combines search query logs, the corpus of the search engine, and the theory of semantic entropy, enabling the search engine to dynamically adjust the weights of query keywords, thereby improving its ability to recognize user intent. Then, we propose a hybrid recall strategy that combines a multi-stage strategy and a logical combination strategy (HRS-MSLC) in the recall module. It separately recalls the keywords obtained from the multi-granularity word segmentation of the query in the form of multi-queue recall and simultaneously considers the “AND” and “OR” logical relationships between the keywords. By systematically managing retrieval uncertainty and giving priority to the keywords with high information content, it achieves the best balance between the quantity of the retrieval results and the relevance of the retrieval results to the query. Finally, we experimentally evaluate our methods using the Hit Rate@K and case analysis. Our results demonstrate that the proposed method improves the Hit Rate@1 by 7.3% and the Hit Rate@3 by 6.6% while effectively solving the bad cases in our vertical domain search engine. Full article

This study proposes an integrated fatigue life assessment methodology to accurately evaluate the time-domain evolution in tubular joint fatigue damage in offshore wind turbine (OWT) jacket structures under long-term combined wind and wave actions. A customized post-processing module was developed via secondary development on the MLife platform, employing a conditional probability distribution model to perform joint probabilistic modeling of measured marine environmental data, thereby establishing a long-term joint wind–wave distribution database. The reconstruction of hotspot stress time histories at the tubular joints was achieved through a hybrid analytical–numerical approach, integrating analytical formulations of nominal stress with a multi-axial stress concentration factor (SCF) matrix. Long-term fatigue damage assessment was implemented using the Palmgren–Miner linear cumulative damage hypothesis, where a weighted summation methodology based on joint wind–wave probability distributions rigorously accounted for the statistical contributions of individual design load cases. An ultimate bearing capacity analysis was also conducted based on S-N fatigue endurance characteristic curves. This research specifically investigates the influence mechanisms of tuned mass dampers (TMDs) on the time-domain-coupled fatigue performance of tubular joints subjected to long-term combined wind and wave loads. Numerical simulations demonstrate that parametrically optimized TMD systems significantly enhance the fatigue life metrics of critical joints in jacket structures. Full article

Acetylcholinesterase (AChE) has emerged not only as a cholinergic enzyme but also as a modulator of β-amyloid (Aβ) aggregation via its peripheral anionic site (PAS), making it a dual-purpose target in Alzheimer’s disease. While classical AChE inhibitors provide symptomatic relief, they lack efficacy against the amyloidogenic cascade. This review highlights recent advances in multifunctional AChE pharmacophores that inhibit enzymatic activity while simultaneously interfering with Aβ aggregation, oxidative stress, metal dyshomeostasis, and neuroinflammation. Particular emphasis is placed on dual-site inhibitors targeting both catalytic and peripheral domains, multi-target-directed ligands (MTDLs) acting on multiple neurodegenerative pathways, and metal-chelating hybrids that address redox-active metal ions promoting Aβ fibrillization. We also discuss enabling technologies such as AI-assisted drug design, high-resolution structural tools, and human induced pluripotent stem cell (iPSC)-derived neuronal models that support physiologically relevant validation. These insights reflect a paradigm shift towards disease-modifying therapies that bridge molecular pharmacology and pathophysiological relevance. Full article

Modern wireless communication systems increasingly rely on Automatic Modulation Classification (AMC) to enhance reliability and adaptability, especially in the presence of severe signal degradation. However, despite significant progress driven by deep learning, many AMC models still struggle with high computational overhead, suboptimal performance under low-signal-to-noise conditions, and limited interpretability, factors that hinder their deployment in real-time, resource-constrained environments. To address these challenges, we propose the Convolutional Random Fourier Features with Denoising Thresholding Network (CRFFDT-Net), a compact and interpretable deep kernel architecture that integrates Convolutional Random Fourier Features (CRFFSinCos), an automatic threshold-based denoising module, and a hybrid time-domain feature extractor composed of CNN and GRU layers. Our approach is validated on the RadioML 2016.10A benchmark dataset, encompassing eleven modulation types across a wide signal-to-noise ratio (SNR) spectrum. Experimental results demonstrate that CRFFDT-Net achieves an average classification accuracy that is statistically comparable to state-of-the-art models, while requiring significantly fewer parameters and offering lower inference latency. This highlights an exceptional accuracy–complexity trade-off. Moreover, interpretability analysis using GradCAM++ highlights the pivotal role of the Convolutional Random Fourier Features in the representation learning process, providing valuable insight into the model’s decision-making. These results underscore the promise of CRFFDT-Net as a lightweight and explainable solution for AMC in real-world, low-power communication systems. Full article

Hyperspectral image (HSI) denoising is challenged by complex spatial-spectral noise coupling. Existing deep learning methods, primarily designed for RGB images, fail to address HSI-specific noise distributions and spectral correlations. This paper proposes a Hybrid-Domain Synergistic Transformer (HDST) integrating frequency-domain enhancement and multiscale modeling. Key contributions include (1) a Fourier-based preprocessing module decoupling spectral noise; (2) a dynamic cross-domain attention mechanism adaptively fusing spatial-frequency features; and (3) a hierarchical architecture combining global noise modeling and detail recovery. Experiments on realistic and synthetic datasets show HDST outperforms state-of-the-art methods in PSNR, with fewer parameters. Visual results confirm effective noise suppression without spectral distortion. The framework provides a robust solution for HSI denoising, demonstrating potential for high-dimensional visual data processing. Full article

Driven by real-world demands of processing massive high-frequency data and achieving longer forecasting horizons in time series forecasting scenarios, a variety of deep learning architectures designed for time series forecasting have emerged at a rapid pace. However, this rapid development actually leads to a sharp increase in parameter size, and the introduction of numerous redundant modules typically offers only limited contribution to improving prediction performance. Although prediction models have shown a trend towards simplification over a period, significantly improving prediction performance, they remain weak in capturing dynamic relationships. Moreover, the predictive accuracy depends on the quality and extent of data preprocessing, making them unsuitable for handling complex real-world data. To address these challenges, we introduced Treeformer, an innovative model that treats the traditional tree-based machine learning model as an encoder and integrates it with a Transformer-based forecasting model, while also adopting the idea of time–feature two-dimensional information extraction by channel independence and cross-channel modeling strategy. It fully utilizes the rich information across variables to improve the ability of time series forecasting. It improves the accuracy of prediction on the basis of the original deep model while maintaining a low computational cost and exhibits better applicability to real-world datasets. We conducted experiments on multiple publicly available datasets across five domains—electricity, weather, traffic, the forex market, healthcare. The results demonstrate improved accuracy, and provide a better hybrid approach for enhancing predictive performance in Long-term Sequence Forecasting (LSTF) problems. Full article

Aiming at the problems of detail blurring and structural distortion caused by speckle noise, additive white noise and hybrid noise interference in synthetic aperture radar (SAR) images, this paper proposes a Dynamic Adaptive Transformer Network (DAT-Net) integrating a dynamic gated attention module and a frequency-domain multi-expert enhancement module for SAR image denoising. The proposed model leverages a multi-scale encoder–decoder framework, combining local convolutional feature extraction with global self-attention mechanisms to transcend the limitations of conventional approaches restricted to single noise types, thereby achieving adaptive suppression of multi-source noise contamination. Key innovations comprise the following: (1) A Dynamic Gated Attention Module (DGAM) employing dual-path feature embedding and dynamic thresholding mechanisms to precisely characterize noise spatial heterogeneity; (2) A Frequency-domain Multi-Expert Enhancement (FMEE) Module utilizing Fourier decomposition and expert network ensembles for collaborative optimization of high-frequency and low-frequency components; (3) Lightweight Multi-scale Convolution Blocks (MCB) enhancing cross-scale feature fusion capabilities. Experimental results demonstrate that DAT-Net achieves quantifiable performance enhancement in both simulated and real SAR environments. Compared with other denoising algorithms, the proposed methodology exhibits superior noise suppression across diverse noise scenarios while preserving intrinsic textural features. Full article