Search Results (113)

As port operations rapidly evolve toward intelligent and heavy-duty applications, fault diagnosis for core equipment demands higher levels of real-time performance and robustness. Deep learning, with its powerful autonomous feature learning capabilities, demonstrates significant potential in mechanical fault prediction and health management. This paper first provides a systematic review of deep learning research advances in rotating machinery fault diagnosis over the past eight years, focusing on the technical approaches and application cases of four representative models: Deep Belief Networks (DBNs), Convolutional Neural Networks (CNNs), Auto-encoders (AEs), and Recurrent Neural Networks (RNNs). These models, respectively, embody four core paradigms, unsupervised feature generation, spatial pattern extraction, data reconstruction learning, and temporal dependency modeling, forming the technological foundation of contemporary intelligent diagnostics. Building upon this foundation, this paper delves into the unique challenges encountered when transferring these methods from generic laboratory components to specialized port equipment such as shore cranes and yard cranes—including complex operating conditions, harsh environments, and system coupling. It further explores future research directions, including cross-condition transfer, multi-source information fusion, and lightweight deployment, aiming to provide theoretical references and implementation pathways for the technological advancement of intelligent operation and maintenance in port equipment. Full article

Levees are critical for flood defence, but their integrity is threatened by hazards such as piping and seepage, especially during high-water-level periods. Traditional manual inspections for these hazards and associated emergency response elements, such as personnel and assets, are inefficient and often impractical. While UAV-based remote sensing offers a promising alternative, the effective fusion of multi-modal data and the scarcity of labelled data for supervised model training remain significant challenges. To overcome these limitations, this paper reframes levee monitoring as an unsupervised anomaly detection task. We propose a novel, fully automated framework that unifies geophysical hazards and emergency response elements into a single analytical category of “abnormal targets” for comprehensive situational awareness. The framework consists of three key modules: (1) a state-of-the-art registration algorithm to precisely align infrared and visible images; (2) a generative adversarial network to fuse the thermal information from IR images with the textural details from visible images; and (3) an adaptive, unsupervised segmentation module where a mean-shift clustering algorithm, with its hyperparameters automatically tuned by Bayesian optimization, delineates the targets. We validated our framework on a real-world dataset collected from a levee on the Pajiang River, China. The proposed method demonstrates superior performance over all baselines, achieving an Intersection over Union of 0.348 and a macro F1-Score of 0.479. This work provides a practical, training-free solution for comprehensive levee monitoring and demonstrates the synergistic potential of multi-modal fusion and automated machine learning for disaster management. Full article

The increasing complexity of modern food production demands advanced solutions for quality control (QC), safety monitoring, and process optimization. This review systematically explores recent advancements in machine learning (ML) for QC across six domains: Food Quality Applications; Defect Detection and Visual Inspection Systems; Ingredient Optimization and Nutritional Assessment; Packaging—Sensors and Predictive QC; Supply Chain—Traceability and Transparency and Food Industry Efficiency; and Industry 4.0 Models. Following a PRISMA-based methodology, a structured search of the Scopus database using thematic Boolean keywords identified 124 peer-reviewed publications (2005–2025), from which 25 studies were selected based on predefined inclusion and exclusion criteria, methodological rigor, and innovation. Neural networks dominated the reviewed approaches, with ensemble learning as a secondary method, and supervised learning prevailing across tasks. Emerging trends include hyperspectral imaging, sensor fusion, explainable AI, and blockchain-enabled traceability. Limitations in current research include domain coverage biases, data scarcity, and underexplored unsupervised and hybrid methods. Real-world implementation challenges involve integration with legacy systems, regulatory compliance, scalability, and cost–benefit trade-offs. The novelty of this review lies in combining a transparent PRISMA approach, a six-domain thematic framework, and Industry 4.0/5.0 integration, providing cross-domain insights and a roadmap for robust, transparent, and adaptive QC systems in the food industry. Full article

As a critical component of rail travel, the train communication network (TCN) is an integrated central platform that is used to realize the train control, condition monitoring, and data transmission, whose failure will disrupt the symmetry of TCN topology and endanger the security of rail trains. To enhance the reliability of TCN, an intelligent fault diagnosis method is proposed based on active learning (AL) and a stacked consistent autoencoder (SCAE), which is capable of building a competitive classifier with a limited amount of labeled training samples. SCAE can learn better feature presentations from electrical multifunction vehicle bus (MVB) signals by reconstructing the same raw input data layer by layer in the unsupervised feature learning phase. In the supervised fine-tuning phase, a deep AL-based fault diagnosis framework is proposed, and a dynamic fusion AL method is presented. The most valuable unlabeled samples are selected for labeling and training by considering uncertainty and similarity simultaneously, and the fusion weight is dynamically adjusted at the different training stages. A TCN experimental platform is constructed, and experimental results show that the proposed method achieves better performance under three different metrics with fewer labeled samples compared to the state-of-the-art methods; it is also symmetrically valid in class-imbalanced data. Full article

The performance of unsupervised stereo matching in complex regions such as weak textures and occlusions is constrained by the inherently local receptive fields of convolutional neural networks (CNNs), the absence of geometric priors, and the limited expressiveness of MLP in conventional ViTs. To address these problems, we propose an Adaptive Geometry-aware Stereo-KANformer Network (AGSK-Net) for unsupervised stereo matching. Firstly, to resolve the conflict between the isotropic nature of traditional ViT and the epipolar geometry priors in stereo matching, we propose Adaptive Geometry-aware Multi-head Self-Attention (AG-MSA), which embeds epipolar priors via an adaptive hybrid structure of geometric modulation and penalty, enabling geometry-aware global context modeling. Secondly, we design Spatial Group-Rational KAN (SGR-KAN), which integrates the nonlinear capability of rational functions with the spatial awareness of deep convolutions, replacing the MLP with flexible, learnable rational functions to enhance the nonlinear expression ability of complex regions. Finally, we propose a Dynamic Candidate Gated Fusion (DCGF) module that employs dynamic dual-candidate states and spatially aware pre-enhancement to adaptively fuse global and local features across scales. Experiments demonstrate that AGSK-Net achieves state-of-the-art accuracy and generalizability on Scene Flow, KITTI 2012/2015, and Middlebury 2021. Full article

Micro-X-ray fluorescence spectroscopy (micro-XRF) integrates spatial and spectral information and is widely employed for multi-elemental analyses of rock-forming minerals. However, its inherent limitation in spatial resolution gives rise to significant pixel mixing, thereby hindering the accurate identification of fine-scale or anomalous mineral phases. Furthermore, most existing methods heavily rely on manually labeled data or predefined spectral libraries, rendering them poorly adaptable to complex and variable mineral systems. To address these challenges, this paper presents an unsupervised deep aggregation network (MSFA-Net) for micro-XRF imagery, aiming to eliminate the reliance of traditional methods on prior knowledge and enhance the recognition capability of rare mineral anomalies. Built on an autoencoder architecture, MSFA-Net incorporates a multi-scale orthogonal attention module to strengthen spectral–spatial feature fusion and employs density-based adaptive clustering to guide semantically aware reconstruction, thus achieving high-precision responses to potential anomalous regions. Experiments on real-world micro-XRF datasets demonstrate that MSFA-Net not only outperforms mainstream anomaly detection methods but also transcends the physical resolution limits of the instrument, successfully identifying subtle mineral anomalies that traditional approaches fail to detect. This method presents a novel paradigm for high-throughput and weakly supervised interpretation of complex geological images. Full article

Background: Mindfulness and mind wandering are cognitive traits central to attentional control and psychological well-being, yet their neural underpinnings are yet to be elucidated. This study aimed to identify structural brain networks comprising gray matter (GM) and white matter (WM) that predict individual differences in mindfulness and distinct mind wandering tendencies (deliberate and spontaneous). Methods: Using structural MRI data and self-report measures from 76 participants, we applied an unsupervised data-fusion machine learning technique (parallel independent component analysis) to identify GM and WM networks associated with mindfulness and mind wandering traits. Results: Our analysis revealed several distinct brain networks linked to these cognitive constructs. Specifically, one GM network involving subcortical regions, including the caudate and thalamus, positively predicted mindfulness and deliberate mind wandering, while negatively influencing spontaneous mind wandering through the mediating role of the mindfulness facet “acting with awareness.” In addition, two separate WM networks, predominantly involving frontoparietal and temporal regions, were directly associated with reduced spontaneous mind wandering. Conclusions: These findings advance our current knowledge by demonstrating that specific GM and WM structures are involved in mindfulness and different forms of mind wandering. Our results also show that the “acting with awareness” facet has a mediating effect on spontaneous mind wandering, which provides supporting evidence for attentional and executive control models. These new insights into the neuroanatomical correlates of mindfulness and mind wandering have implications for ongoing research in the growing topic of mindfulness and mind wandering, mindfulness-based interventions, and other clinical applications. Full article

Reconstruction-based unsupervised detection methods have demonstrated strong generalization capabilities in the field of tablet anomaly detection, but there are still problems such as poor reconstruction effect and inaccurate positioning of abnormal areas. To address these problems, this paper proposes an unsupervised Diffusion-based Tablet Defect Detection (DTDD) method. This method uses an Assisted Reconstruction (AR) network to introduce original image information to assist in the reconstruction of abnormal areas, thereby improving the reconstruction effect of the diffusion model. It also uses a Scale Fusion (SF) network and an improved anomaly measurement method to improve the accuracy of abnormal area positioning. Finally, the effectiveness of the algorithm is verified on the tablet dataset. The experimental results show that the algorithm in this paper is superior to the algorithms in the same field, effectively improving the detection accuracy and abnormal positioning accuracy, and performing well in the tablet defect detection task. Full article

Cancer metabolic reprogramming plays a critical role in tumor progression and therapeutic resistance, underscoring the need for advanced analytical strategies. Metabolomics, leveraging mass spectrometry and nuclear magnetic resonance (NMR) spectroscopy, offers a comprehensive and functional readout of tumor biochemistry. By enabling both targeted metabolite quantification and untargeted profiling, metabolomics captures the dynamic metabolic alterations associated with cancer. The integration of metabolomics with machine learning (ML) approaches further enhances the interpretation of these complex, high-dimensional datasets, providing powerful insights into cancer biology from biomarker discovery to therapeutic targeting. This review systematically examines the transformative role of ML in cancer metabolomics. We discuss how various ML methodologies—including supervised algorithms (e.g., Support Vector Machine, Random Forest), unsupervised techniques (e.g., Principal Component Analysis, t-SNE), and deep learning frameworks—are advancing cancer research. Specifically, we highlight three major applications of ML–metabolomics integration: (1) cancer subtyping, exemplified by the use of Similarity Network Fusion (SNF) and LASSO regression to classify triple-negative breast cancer into subtypes with distinct survival outcomes; (2) biomarker discovery, where Random Forest and Partial Least Squares Discriminant Analysis (PLS-DA) models have achieved >90% accuracy in detecting breast and colorectal cancers through biofluid metabolomics; and (3) prognostic modeling, demonstrated by the identification of race-specific metabolic signatures in breast cancer and the prediction of clinical outcomes in lung and ovarian cancers. Beyond these areas, we explore applications across prostate, thyroid, and pancreatic cancers, where ML-driven metabolomics is contributing to earlier detection, improved risk stratification, and personalized treatment planning. We also address critical challenges, including issues of data quality (e.g., batch effects, missing values), model interpretability, and barriers to clinical translation. Emerging solutions, such as explainable artificial intelligence (XAI) approaches and standardized multi-omics integration pipelines, are discussed as pathways to overcome these hurdles. By synthesizing recent advances, this review illustrates how ML-enhanced metabolomics bridges the gap between fundamental cancer metabolism research and clinical application, offering new avenues for precision oncology through improved diagnosis, prognosis, and tailored therapeutic strategies. Full article

Recent advancements in Earth observation technologies have accelerated remote sensing (RS) data acquisition, yet cross-domain semantic segmentation remains challenged by domain shifts. Traditional unsupervised domain adaptation (UDA) methods often rely on computationally intensive and unstable generative adversarial networks (GANs). This study introduces elevation-aware domain adaptation (EADA), a multi-task framework that integrates elevation estimation (via digital surface models) with semantic segmentation to address distribution discrepancies. EADA employs a shared encoder and task-specific decoders, enhanced by a spatial attention-based feature fusion module. Experiments on Potsdam and Vaihingen datasets under cross-domain settings (e.g., Potsdam IRRG → Vaihingen IRRG) show that EADA achieves state-of-the-art performance, with a mean IoU of 54.62% and an F1-score of 65.47%, outperforming single-stage baselines. Elevation awareness significantly improves the segmentation of height-sensitive classes, such as buildings, while maintaining computational efficiency. Compared to multi-stage approaches, EADA’s end-to-end design reduces training complexity without sacrificing accuracy. These results demonstrate that incorporating elevation data effectively mitigates domain shifts in RS imagery. However, lower accuracy for elevation-insensitive classes suggests the need for further refinement to enhance overall generalizability. Full article

Ground penetrating radar (GPR) is widely used for subsurface object detection, but manual interpretation of hyperbolic features in B-scan images remains inefficient and error-prone. In addition, traditional forward modeling methods suffer from low computational efficiency and strong dependence on field measurements. To address these challenges, we propose an unsupervised data augmentation framework that utilizes CycleGAN-based model to generate diverse synthetic B-scan images by simulating varying geological parameters and scanning configurations. This approach achieves GPR data forward modeling and enhances the scenario coverage of training data. We then apply the EfficientDet architecture, which incorporates a bidirectional feature pyramid network (BiFPN) for multi-scale feature fusion, to enhance the detection capability of hyperbolic signatures in B-scan images under challenging conditions such as partial occlusions and background noise. The proposed method achieves a mean average precision (mAP) of 0.579 on synthetic datasets, outperforming YOLOv3 and RetinaNet by 16.0% and 23.5%, respectively, while maintaining robust multi-object detection in complex field conditions. Full article

The underwater environment severely degrades image quality by absorbing and scattering light. This causes significant challenges, including non-uniform illumination, low contrast, color distortion, and blurring. These degradations compromise the performance of critical underwater applications, including water quality monitoring, object detection, and identification. To address these issues, this study proposes a detail-oriented hybrid framework for underwater image enhancement that synergizes the strengths of traditional image processing with the powerful feature extraction capabilities of unsupervised deep learning. Our framework introduces a novel multi-scale detail enhancement unit to accentuate structural information, followed by a Latent Low-Rank Representation (LatLRR)-based simplification step. This unique combination effectively suppresses common artifacts like oversharpening, spurious edges, and noise by decomposing the image into meaningful subspaces. The principal structural features are then optimally combined with a gamma-corrected luminance channel using an unsupervised MU-Fusion network, achieving a balanced optimization of both global contrast and local details. The experimental results on the challenging Test-C60 and OceanDark datasets demonstrate that our method consistently outperforms state-of-the-art fusion-based approaches, achieving average improvements of 7.5% in UIQM, 6% in IL-NIQE, and 3% in AG. Wilcoxon signed-rank tests confirm that these performance gains are statistically significant (p < 0.01). Consequently, the proposed method significantly mitigates prevalent issues such as color aberration, detail loss, and artificial haze, which are frequently encountered in existing techniques. Full article

This paper presents FWStab, a specialized video stabilization dataset tailored for flapping-wing platforms. The dataset encompasses five typical flight scenarios, featuring 48 video clips with intense dynamic jitter. The corresponding Inertial Measurement Unit (IMU) sensor data are synchronously collected, which jointly provide reliable support for multimodal modeling. Based on this, to address the issue of poor image acquisition quality due to severe vibrations in aerial vehicles, this paper proposes a multi-modal signal fusion video stabilization framework. This framework effectively integrates image features and inertial sensor features to predict smooth and stable camera poses. During the video stabilization process, the true camera motion originally estimated based on sensors is warped to the smooth trajectory predicted by the network, thereby optimizing the inter-frame stability. This approach maintains the global rigidity of scene motion, avoids visual artifacts caused by traditional dense optical flow-based spatiotemporal warping, and rectifies rolling shutter-induced distortions. Furthermore, the network is trained in an unsupervised manner by leveraging a joint loss function that integrates camera pose smoothness and optical flow residuals. When coupled with a multi-stage training strategy, this framework demonstrates remarkable stabilization adaptability across a wide range of scenarios. The entire framework employs Long Short-Term Memory (LSTM) to model the temporal characteristics of camera trajectories, enabling high-precision prediction of smooth trajectories. Full article

As a fundamental technology in environmental perception, sound source localization (SSL) plays a critical role in public safety, marine exploration, and smart home systems. However, traditional methods such as beamforming and time-delay estimation rely on manually designed physical models and idealized assumptions, which struggle to meet practical demands in dynamic and complex scenarios. Recent advancements in deep learning have revolutionized SSL by leveraging its end-to-end feature adaptability, cross-scenario generalization capabilities, and data-driven modeling, significantly enhancing localization robustness and accuracy in challenging environments. This review systematically examines the progress of deep learning-based SSL across three critical domains: marine environments, indoor reverberant spaces, and unmanned aerial vehicle (UAV) monitoring. In marine scenarios, complex-valued convolutional networks combined with adversarial transfer learning mitigate environmental mismatch and multipath interference through phase information fusion and domain adaptation strategies. For indoor high-reverberation conditions, attention mechanisms and multimodal fusion architectures achieve precise localization under low signal-to-noise ratios by adaptively weighting critical acoustic features. In UAV surveillance, lightweight models integrated with spatiotemporal Transformers address dynamic modeling of non-stationary noise spectra and edge computing efficiency constraints. Despite these advancements, current approaches face three core challenges: the insufficient integration of physical principles, prohibitive data annotation costs, and the trade-off between real-time performance and accuracy. Future research should prioritize physics-informed modeling to embed acoustic propagation mechanisms, unsupervised domain adaptation to reduce reliance on labeled data, and sensor-algorithm co-design to optimize hardware-software synergy. These directions aim to propel SSL toward intelligent systems characterized by high precision, strong robustness, and low power consumption. This work provides both theoretical foundations and technical references for algorithm selection and practical implementation in complex real-world scenarios. Full article

Keeping drinking water safe is a critical aspect of protecting public health. Traditional laboratory-based methods for evaluating water potability are often time-consuming, costly, and labour-intensive. This paper presents a comparative analysis of four transformer-based deep learning models in the development of automatic classification systems for water potability based on physicochemical attributes. The models examined include the enhanced tabular transformer (ETT), feature tokenizer transformer (FTTransformer), self-attention and inter-sample network (SAINT), and tabular autoencoder pretraining enhancement (TAPE). The study utilized an open-access water quality dataset that includes nine key attributes such as pH, hardness, total dissolved solids (TDS), chloramines, sulphate, conductivity, organic carbon, trihalomethanes, and turbidity. The models were evaluated under a unified protocol involving 70–15–15 data partitioning, five-fold cross-validation, fixed random seed, and consistent hyperparameter settings. Among the evaluated models, the enhanced tabular transformer outperforms other models with an accuracy of 95.04% and an F1 score of 0.94. ETT is an advanced model because it can efficiently model high-order feature interactions through multi-head attention and deep hierarchical encoding. Feature importance analysis consistently highlighted chloramines, conductivity, and trihalomethanes as key predictive features across all models. SAINT demonstrated robust generalization through its dual-attention mechanism, while TAPE provided competitive results with reduced computational overhead due to unsupervised pretraining. Conversely, FTTransformer showed limitations, likely due to sensitivity to class imbalance and hyperparameter tuning. The results underscore the potential of transformer-based models, especially ETT, in enabling efficient, accurate, and scalable water quality monitoring. These findings support their integration into real-time environmental health systems and suggest approaches for future research in explainability, domain adaptation, and multimodal fusion. Full article