Search Results (323)

Anomaly detection models trained exclusively on healthy data are widely used in wind turbine condition monitoring because failure data are scarce, heterogeneous, and often unavailable. However, these models produce anomaly indicators that are sensitive not only to fault-related degradation but also to normal operational variability, transient disturbances, and changes in loading conditions. As a result, the practical behavior of an alarm system depends not only on the anomaly detection model but also on the decision rule used to activate and maintain alarm states. This study presents a decision-oriented evaluation of persistence-based alarm confirmation in wind turbine anomaly detection. Four representative techniques are analyzed within a unified framework: Isolation Forest, One-Class Support Vector Machine, Referenced Moving Window Principal Component Analysis using Q-statistic and percentage component weight indicators, and Autoencoder-based reconstruction error. The evaluation combines controlled OpenFAST simulations of rotor unbalance under different severity and noise conditions with an industrial SCADA case study involving a documented main bearing fault. Results show that temporal persistence strongly shapes alarm outcomes across methods and datasets. Low persistence values favor early detection but promote alarms from isolated threshold exceedances, whereas moderate persistence substantially reduces false positives while preserving detection capability in severe and well-observable faults. Excessive persistence increases detection latency and missed detections, particularly for weak, intermittent, or slowly evolving fault signatures. These findings indicate that persistence-based alarm confirmation should be treated as an explicit decision-level configuration variable, rather than as a fixed post-processing or alarm-state heuristic, when designing anomaly detection systems for wind turbine condition monitoring. Full article

Autoencoders (AEs) have been widely used for industrial process fault detection owing to their ability to learn nonlinear representations from normal operating data. However, conventional AE methods rely heavily on reconstruction errors and may miss weak faults due to overgeneralization. In addition, insufficient modeling of temporal evolution and operating condition variations may reduce their sensitivity to dynamic faults. To address these issues, this study proposes a memory-enhanced and prediction-assisted conditional variational autoencoder named MI-CVAE for unsupervised fault detection. In the proposed framework, statistical features extracted from sliding windows are used as condition information to describe variable operating states. A memory module stores representative normal prototypes to constrain reconstruction and reduce overgeneralization to faulty samples. Meanwhile, an Informer branch captures temporal dependencies and provides complementary prediction residuals. Reconstruction and prediction residuals are fused to construct squared prediction error and squared Mahalanobis distance statistics, with control limits determined by kernel density estimation. The proposed method is validated on the Benchmark Simulation Model No. 1 wastewater treatment benchmark and a real papermaking process dataset. The results show that MI-CVAE outperforms the evaluated comparison methods, particularly in detecting weak and dynamic faults, while maintaining a low false alarm rate. Full article

The following narrative review discusses the use of deep learning and 3D modeling in facial reconstruction from skeletal remains, focusing on accuracy, algorithmic bias, and evidential reliability. Forensic facial reconstruction (FFR) is a multidisciplinary field combining anthropology, medicine, and visual sciences to approximate the facial appearance of unidentified individuals from skeletal remains. Traditional manual methods, based on anatomical knowledge and facial soft tissue thickness (FSTT) measurements, are limited by subjectivity, labor intensity, and inter-expert variability. This narrative review summarizes contemporary AI-assisted approaches, with emphasis on convolutional neural networks (CNNs), generative adversarial networks (GANs), variational autoencoders (VAEs), and diffusion models, which enable probabilistic prediction of facial morphology while accounting for demographic variables such as sex, age, and population ancestry. Key challenges affecting reconstruction accuracy—including dataset limitations, population-specific variability, and algorithmic bias—are discussed, alongside quantitative validation methods and concerns regarding model transparency. Legal and ethical considerations, such as privacy, biometric data protection, and the need for explainable AI (XAI) frameworks, are highlighted. Future perspectives include hybrid expert–AI workflows, the development of globally representative datasets, and the integration of multimodal data sources, including DNA phenotyping, 3D morphometrics, and biomechanical modeling. These advances aim to create standardized, interpretable, and biologically informed frameworks that enable AI to support expert judgment and enhance the reliability of forensic facial reconstructions. Full article

This paper presents a hybrid algorithmic framework for fault detection and isolation (FDI) in nonlinear quadrotor unmanned aerial vehicle (UAV) systems operating under closed-loop conditions. The proposed method integrates a Linear Quadratic Control (LQC) strategy, synthesized through Linear Matrix Inequalities (LMIs), with a Conditional Long Short-Term Memory Autoencoder (CLSTM-AE) and an adaptive residual-based decision mechanism. The LQC scheme provides robust trajectory tracking through regional pole-placement constraints, while the CLSTM-AE learns the nominal closed-loop input–output temporal behavior of the UAV using only fault-free data. In contrast to conventional symmetric autoencoder-based detectors, the proposed CLSTM-AE uses the control inputs together with the available attitude estimates, represented by the Euler angles yaw, pitch, and roll, as conditioning information, while reconstructing only the monitored attitude outputs. This asymmetric structure allows the residuals to capture inconsistencies between the commanded control effort and the observed attitude response, which is particularly relevant in closed-loop nonlinear systems where feedback compensation may attenuate fault signatures. Deviations from nominal behavior are detected through reconstruction residuals computed using a smoothed Mean Squared Error (MSE) criterion and evaluated against an adaptive $3\sigma$ threshold. The framework is validated in three-dimensional flight simulations considering abrupt, transient, and incipient actuator fault scenarios. The obtained results show that the proposed approach outperforms representative conventional machine-learning methods, achieving an average accuracy of 98.2%, an average recall of 97.8%, and an average false positive rate of 1.4%. These results suggest that the proposed hybrid algorithm provides an effective and interpretable solution for closed-loop fault diagnosis in nonlinear UAV systems under measurement noise and system variability. Full article

This study examines the determinants of regulated electricity contract prices in Colombia during the period 2009–2021, with a particular focus on the role of electricity-market fundamentals and macroeconomic conditions. Although regulated contracts are designed to reduce exposure to short-term volatility, limited evidence exists on how their price formation behaves across different segments of the distribution. To address this issue, the analysis combines quantile regression with autoencoder-based dimensionality reduction, allowing the incorporation of a large set of macroeconomic variables without overparameterizing the model. The results show that regulated contract prices are more consistently associated with electricity-system factors than with broad macroeconomic conditions. In particular, the spot price becomes significant only in the upper quantiles, where it appears to operate as an indicator of operational stress, while hydropower and thermal generation exhibit localized effects across the distribution. By contrast, most macroeconomic factors display weak, uneven, or non-significant effects, with only the exchange-rate-related component becoming clearly relevant at relatively high price levels. A robustness analysis based on principal component analysis broadly supports these patterns. Overall, the evidence suggests that the Colombian regulated market behaves as a relatively stable contractual system, in which price formation is shaped mainly by electricity-sector conditions, indexation rules, and long-term risk-management mechanisms, while macroeconomic influences appear more limited and non-uniform across quantiles. Full article

Hyperspectral imaging has emerged as a powerful tool for food quality assessment, yet most existing methods rely on supervised classification and require prior knowledge of adulterant categories. This study applies a non-targeted screening approach based on a deep spectral autoencoder to detect adulterants in Fritillaria. While autoencoder-based anomaly detection has been established in other hyperspectral domains, its application to congeneric species discrimination and exogenous adulterant screening in Fritillaria has not been systematically explored. A deep spectral autoencoder was constructed and trained exclusively on pure samples to learn the intrinsic spectral distribution of authentic materials. During inference, reconstruction error was used as an anomaly score, and samples deviating from the learned spectral manifold were identified as suspicious. Spectral data augmentation and band trimming were applied to enhance model robustness, while the anomaly threshold was determined solely from the distribution of pure samples. The proposed method achieved strong discrimination performance, with an area under the receiver operating characteristic curve (AUC) of 0.9903 and high detection rates across multiple adulterant types. Typical exogenous adulterants such as starch and talc powder were completely detected, while congeneric species also showed high detection sensitivity despite their spectral similarity to authentic samples. Latent space visualization and residual spectral analysis further revealed clear separation patterns and interpretable spectral deviations. These results demonstrate the proof-of-concept viability of the proposed non-targeted framework for open-set screening of adulteration risks. However, the authentic samples used for training originated from a single source, and only a limited set of anomaly types was tested. Therefore, the current model should be regarded as an early proof-of-concept only, not as a ready-to-deploy screening tool. Further validation with diverse authentic samples and a wider range of adulterants under realistic variability is necessary before the method can be considered a practical strategy for quality control. Full article

This study investigates class imbalance in motor fault diagnosis. Fault samples, especially those at different severity levels, are often much fewer than healthy samples. To address this issue, a self-attention guided Wasserstein conditional GAN with gradient normalization (SWGAN) is proposed. The method is based on synchronized three-phase current and vibration measurements. It separately generates label-conditioned current spectra and vibration spectra to supplement minority fault classes. Self-attention is used to capture long-range spectral dependencies. Gradient normalization is introduced to improve adversarial training stability. The generated current and vibration spectra are then fused at the feature level and fed into a stacked autoencoder (SAE)-based multi-modal classifier. Experiments were conducted on a PMSM stator fault dataset and a variable-speed three-phase asynchronous motor dataset. On the PMSM dataset, SWGAN achieved highest accuracies of 98.90% and 97.81% under two fault-category imbalance settings. On the variable-speed motor dataset, the proposed method achieved accuracies of 98.10% and 97.65%, respectively. These results show that SWGAN can provide effective supplementary samples for minority fault classes. They also indicate that the proposed method improves diagnostic performance under both fixed-speed and variable-speed conditions. Full article

Occupational mental-health risk in knowledge-work settings is an important public-health and psychosocial-support concern because workload demands, career insecurity, limited mentoring, uneven institutional support and barriers to care can increase psychological risk, including in early-career academic environments. Workplace well-being assessments rely on aggregate survey summaries or conventional prediction models, limiting calibration, interpretability, subgroup evaluation and transfer validation. This study develops a computational-intelligence framework for public mental-health decision support using heterogeneous workplace survey data with early-career academics treated as a motivating knowledge-work context rather than as the direct empirical cohort. The proposed approach combines attention-based tabular learning, variational autoencoder latent profiling, stacked ensemble prediction, probability calibration, feature attribution, perturbation analysis, fairness assessment and cross-dataset adaptation. Calibrated probabilities are converted into a transparent 0–100 risk index to support preventive outreach, psychosocial-support planning and resource-allocation decisions. The model is compared with baselines, including logistic regression, support vector machine, random forest, XGBoost, LightGBM, CatBoost, TabNet, FT–Transformer, NODE and DCN. Results show strong held-out performance with AUC = 0.885, average precision = 0.872, F1 = 0.808, Brier score = 0.145 and expected calibration error = 0.022, outperforming tested baselines. Five-fold robustness analysis produced a conservative mean test AUC of $0.809\pm 0.044$, indicating moderate partition sensitivity. Key predictors include work interference, perceived stress, care access and support variables. Latent profiling identifies two behavioural subgroups with distinct risk patterns. After feature harmonization, target-domain adaptation and recalibration, external evaluation on an occupational burnout dataset achieves AUC = 0.941 and average precision = 0.936, supporting calibrated, interpretable and subgroup-aware decision support under dataset shift. Full article

The Industrial Internet of Things (IIoT) is central to modern industrial automation, yet its growing connectivity exposes critical systems to evolving cyber threats. Traditional intrusion detection methods struggle in IIoT environments due to class imbalance and limited adaptability to zero-day attacks. This systematic review evaluates generative AI techniques for IIoT intrusion detection and identifies deployment requirements for industrial environments. We searched five databases (IEEE Xplore, ACM Digital Library, Springer, ScienceDirect, and arXiv) for studies published between January 2019 and December 2025, applying predefined inclusion criteria. Following a systematic selection process (identification plus three progressive screening stages) across 342 records, 42 primary studies were included for systematic synthesis. We examined four GenAI paradigms—Generative Adversarial Networks, Transformers, Diffusion Models, and Variational Autoencoders—analyzing nine state-of-the-art frameworks through comparative performance analysis. Hybrid Transformer architectures (e.g., Transformer-GAN-AE) achieve the most consistent detection performance, while diffusion-based models (e.g., Diff-IDS) provide computational advantages for edge deployments. However, substantial variability in evaluation methodologies and limited reporting of statistical rigor indicate important gaps in current research practices. These findings inform the development of GenAI-driven strategies tailored to industrial infrastructure constraints and highlight key directions for advancing IIoT cybersecurity. Full article

Medical image segmentation is challenging due to subtle pathological patterns and the inherent ambiguity of clinical descriptions. Although vision–language models have shown promise, they frequently lack fine-grained perception of structural variability. To address these limitations, we propose the Symmetry- and Variability-Perceiving Conditional Variational Autoencoder (SVP-CVAE). The proposed method integrates a clinical attribute encoder with a morphology-aware enhancement module that incorporates a cross-bilateral symmetry mechanism to explicitly capture symmetry-related variations. By reformulating the segmentation task as a probabilistic prior-to-posterior inference process, SVP-CVAE models the one-to-many mapping between textual attributes and visual realizations. Furthermore, we introduce an attribute-latent contrastive objective to ensure that the latent space encodes discriminative morphological information. Extensive experiments demonstrate that the proposed framework achieves superior segmentation accuracy compared to state-of-the-art methods. Results indicate that SVP-CVAE effectively captures diverse yet anatomically plausible structural variations while maintaining high sensitivity to bilateral symmetry. Comprehensive ablation studies confirm that the performance gains are synergistically driven by the proposed symmetry-perceiving module and the contrastive semantic alignment objective, rather than relying solely on the probabilistic formulation. In conclusion, integrating explicit symmetry perception with probabilistic modeling significantly enhances the reliability and interpretability of multimodal medical image segmentation in complex clinical scenarios. Full article

Structural Health Monitoring (SHM) increasingly relies on data-driven approaches to detect structural changes under environmental and operational variability, yet the limited availability and imbalance of baseline data remain critical challenges. This study proposes a novel framework for vibration-based SHM that combines Convolutional Neural Networks and Variational Autoencoders to model structural response in the frequency domain through Cross-Spectral Matrices. The methodology includes a tailored data representation based on Cholesky factorisation, a CNN-VAE architecture with structural constraints to ensure data consistency, and an Enhanced Loss Function designed to improve sensitivity to modal characteristics. The trained model is used both as a generative tool to produce realistic synthetic data and as a feature extractor through latent variable distributions. Validation on an experimental truss structure subject to thermal variability shows that the model accurately reproduces the statistical distribution of natural frequencies and spectral features, while generating plausible synthetic responses. The proposed approach enables baseline enhancement through data balancing and supports effective damage detection using both modal features and latent space indicators. These results demonstrate that the framework can improve the robustness of vibration-based SHM systems and can be integrated with existing frequency domain monitoring techniques, offering a practical data-driven solution for real-world applications. Full article

Hyperspectral remote sensing is increasingly utilized due to its high spectral resolution and broad observational capabilities, and hyperspectral unmixing aims to decompose mixed pixels into their constituent endmembers with corresponding classes. The core research directions in this area include how to construct a proprietary spectral library and how to optimize the corresponding abundance maps. However, due to the influence of complex terrain and variable illumination conditions, hyperspectral images (HSI) exhibit significant spectral variability (SV), which undermines the performance of traditional unmixing methods. In the paper, we propose an SV and class-constrained diffusion model (SVCDM) for unsupervised hyperspectral unmixing that integrates endmember extraction and abundance optimization. Specifically, a Dirichlet-based variational autoencoder is employed to construct a spectral library from the original HSI with a class constraint and prior distribution, which subsequently guide a conditional diffusion model to learn the distribution. During the reverse process, the endmembers are iteratively updated at each time step, enhancing diversity while ensuring class consistency. Subsequently, the endmember matrix is synthesized with the original HSI to optimize the abundance maps under the linear mixing assumption. The proposed SVCDM effectively mitigates the impact of SV induced by imaging characteristics. Experimental results demonstrate that the SVCDM achieves a root mean square error (RMSE) of 0.0371 for abundance maps on a synthetic dataset and a spectral angle mapper (SAM) for endmembers of 0.0309 on the Samson dataset, outperforming existing state-of-the-art hyperspectral unmixing methods on both synthetic and real datasets. Full article

Health monitoring of marine turbochargers under real-ship operation is complicated by operating-condition variability, recurrent online cleaning, and limited fault labels. This study presents a maintenance-aware temporal contrastive autoencoder (TCCL-AE) for health index (HI) learning from multivariate real-ship monitoring data. The framework aims to learn an HI that tracks degradation while reducing sensitivity to short-term operating-condition fluctuations by incorporating maintenance information into latent-state evolution and introducing temporal contrastive learning. The model includes a temporal encoder for window-level feature extraction, a latent decomposition module for separating degradation-related and condition-related information, and a Health Coupling Module for representing maintenance-induced recovery. The training objective combines temporal contrastive learning, observation reconstruction, and maintenance consistency. Experiments on multi-voyage real-ship data indicate that the learned HI reflects long-term degradation evolution and maintenance-related recovery, while remaining comparatively smooth under variable operating conditions. The resulting HI provides a continuous representation for condition tracking and maintenance-related interpretation during long-horizon monitoring. Full article

Background: Positron emission tomography (PET) provides physiologic information central to oncologic staging and treatment assessment, but its availability is limited by cost, radiation exposure, and scanner access. Synthesizing PET from computed tomography (CT) is attractive but challenging, as tracer uptake is only partially constrained by anatomy, making the mapping inherently one-to-many. Methods: We propose a conditional 3D latent diffusion framework (3D-LDM) for CT-to-PET synthesis in the head–neck and thoracic region. The pipeline localizes anatomy by segmenting lungs in CT and restricting the volume to reduce irrelevant variability. PET volumes are encoded into a compact latent space using a KL-regularized 3D autoencoder, and a conditional 3D diffusion U-Net learns to generate PET latents conditioned on CT via a denoising diffusion process. The model was trained and evaluated on 900 paired PET/CT studies. Performance was assessed in SUV space using MAE, PSNR, and SSIM, and compared against transformer-, CNN-, and GAN-based baselines. Results: On the held-out test cohort, 3D-LDM achieved the best overall quantitative fidelity (MAE = 303.05 ± 22.16 SUV units, PSNR = 32.64 ± 1.79, SSIM = 0.86 ± 0.03), outperforming all baselines with statistically significant differences (p < 0.001). At the lesion level, the model achieved a precision of 0.76 (95% CI: 0.71, 0.81) and recall of 0.76 (95% CI: 0.72, 0.80), detecting an average of 3.19 lesions per scan with a false-positive rate of 0.72/scan. Lesion-wise NMSE was 11.37%, significantly outperforming GAN and transformer baselines. Conclusions: 3D-LDM enables efficient, high-fidelity PET synthesis in the head–neck and thoracic regions, substantially improving lesion-level accuracy over state-of-the-art baselines. While it is not a replacement for diagnostic PET, these results support the model’s potential as a clinical decision support tool. Full article

The rising incidence of skin cancer necessitates scalable and accurate diagnostic tools. While dermoscopy-based systems have achieved expert-level performance, clinical smartphone images pose challenges due to variability in lighting, resolution, and artifacts. Recent advances in multimodal deep learning have shown promise, yet most approaches rely on simple feature concatenation or single-model classifiers, limiting their ability to capture complex cross-modal interactions. This study aims to bridge the diagnostic gap in resource-limited settings by developing a robust multimodal framework that synergizes clinical smartphone images with structured patient metadata for automated skin cancer classification. We propose a novel hybrid architecture integrating a Swin Transformer V2 (SwinV2-Tiny) for hierarchical visual feature extraction and a Denoising Autoencoder (DAE) with PCA for robust metadata embedding. These heterogeneous modalities are fused via a Gated Attention Mechanism that dynamically weighs feature importance across streams. Classification is performed by a Heterogeneous Meta-Stack Ensemble comprising CatBoost, LightGBM, XGBoost, and Logistic Regression, designed to maximize calibration and generalization across imbalanced classes. Evaluated on the PAD-UFES-20 dataset (2298 clinical smartphone images, six diagnostic classes), the proposed framework achieves state-of-the-art performance with a macro-averaged F1-score of 0.977, accuracy of 0.978, and an AUC of 0.990. It significantly outperforms unimodal baselines and existing multimodal methods, demonstrating superior sensitivity (0.974) and precision (0.981), particularly for underrepresented malignant classes like Melanoma (F1: 0.995) and Squamous Cell Carcinoma (F1: 0.960). The integration of clinical metadata with advanced visual embeddings via gated attention significantly enhances diagnostic reliability. Comprehensive ablation studies confirm the contribution of each architectural component. This framework offers a viable pathway for deploying high-precision, AI-driven dermatological screening tools on standard smartphone devices. Full article