Search Results (2,115)

Impulsive alpha (α)-stable noise, characterized by heavy tails and intense outliers, is a key ingredient in simulating financial, medical, seismic, and digital communication technologies. It poses versatile challenges to conventional machine learning (ML) algorithms in predicting noise parameters for multidisciplinary artificial intelligence (AI)-embedded devices. In this study, we adopted a two-phase methodology to investigate the complexity and performance of supervised ML algorithms while classifying impulsive noise parameters. We generated synthetic datasets of α-stable noise distributions for experimentation in a controlled environment. It was followed by experimental evaluation to derive the complexity and performance of ML classifiers—k-nearest neighbors (KNN), Support Vector Machine (SVM), Naïve Bayes (NB), Decision Tree (DT), and Random Forest (RF). Moreover, we employed a very high channel noise level of −15 dB in the test datasets to ensure that the derived analysis applies to real-world devices. The results demonstrate the high performance of DT and RF in structured binary classification of the α regime and the sign of skewness, while incurring satisfactory computational costs. However, SVM and kNN are comparatively more robust for multi-class classification, albeit with higher memory and training costs. On the contrary, NB fails to address the skewed and impulsive behavior of α-stable noise. We observed that even the most effective classifiers struggle to achieve perfect accuracy in multi-class classification. Overall, the experimental results reveal significant trade-off relationships between the complexity and performance of ML classifiers. Conclusively, simple models are well-suited for coarse-grained tasks, such as α-approximation and sign-of-skewness classification. In contrast, sophisticated models can be deployed to predict noise parameters to some extent. Our study provides a clear set of trade-offs for future applied AI devices that address adversarial and impulsive noise. Full article

Motor fault diagnosis under small-sample conditions remains challenging because limited labeled data often cause deep models to overfit and generalize poorly. To address this problem, we propose STR-DDPM, a fault data augmentation framework that combines moving-average-based seasonal–trend–residual decomposition with a denoising diffusion probabilistic model. Specifically, multichannel signals are decomposed into trend, seasonal, and residual components, and class-conditional diffusion modeling is performed only in the residual domain. This design emphasizes fault-related stochastic variations while reducing interference from deterministic structures. To improve generation stability, we adopt velocity prediction and develop an enhanced one-dimensional U-Net with multi-scale convolutions, channel attention, self-attention, and feature-wise linear modulation for controllable conditional generation. Experiments on the University of Ottawa and Paderborn motor fault datasets demonstrate that the proposed method generates samples that are highly consistent with real data and improves diagnostic performance under multiple synthetic-data-assisted settings. These results indicate that STR-DDPM provides an effective and practical solution for data augmentation in data-limited motor fault diagnosis. Full article

The semantic segmentation of sparse array synthetic aperture radar (SAR) 3D point clouds remains a significant challenge. These datasets are characterized by extreme sparsity, irregular distribution, and structural discontinuity, factors that diminish the reliability of local neighborhoods and impede the performance of traditional segmentation algorithms. This study introduces an enhanced PointNet++ framework specifically tailored for the semantic segmentation of sparse array-SAR 3D point clouds. Utilizing PointNet++ as a hierarchical backbone, the proposed architecture incorporates three geometry-oriented modifications: a feature enhancement strategy integrating normalized height, surface normals, and local density; an EdgeConv module positioned at an intermediate abstraction stage to reinforce local geometric modeling; and an FP-Refine module designed to optimize cross-scale feature propagation and recovery within sparse regions. Rather than proposing a fundamentally distinct universal architecture, this research focuses on a task-oriented adaptation of PointNet++ to address the neighborhood instability and structural gaps inherent in sparse array-SAR data. Experimental evaluations using the SARMV3D-1.0 dataset indicate that the proposed method consistently outperforms the PointNet++ baseline, maintaining stable performance across various random seeds with an mIoU between 55% and 58%. Further validation through ablation studies, parameter sensitivity analyses, and perturbation-based robustness assessments confirms the utility of the integrated components. Additionally, cross-dataset experiments on S3DIS and Toronto3D suggest that the framework generalizes effectively to point clouds with varying densities and spatial configurations. The findings demonstrate that the method is particularly successful for categories defined by distinct vertical geometry and structural continuity, such as trees, roofs, and facades, though performance remains limited for weakly structured classes like roads. Full article

Modern neural networks have achieved remarkable success in visual recognition; however, due to their sensitivity to domain shifts, Unsupervised Domain Adaptation (UDA) remains an open research problem. A key reason for this limitation is that source-trained models rely primarily on texture, lacking the explicit geometric information required for object recognition. To overcome this problem, we introduce CoDA, an object-centric learning framework inspired by infant cognitive development, specifically the process of object individuation. By introducing a geometric prior, our approach employs a physically grounded generation pipeline that uses a textureless “Sculpture Mode” and object isolation to complement textural information with 3D geometric features, capturing shape information that is often ignored during training. To enable robust training from scratch, we further integrate two control mechanisms: a Network Stability Scheduler to orchestrate training progression based on convergence stability, and a Dynamic Top-K Pseudo-Labeling strategy that adapts confidence thresholds for each individual class. Extensive evaluations on three real-world target datasets (VegFru, Fruits-262, and Open Images v7) demonstrate that CoDA, trained on a source dataset of just 12,000 synthetic images, achieves comparable results to (and in specific domains surpasses) ImageNet-pretrained models (leveraging 1.2 million images), significantly outperforming state-of-the-art adversarial and semi-supervised domain adaptation methods. Full article

Automated detection of defects in welds are inevitable in the assurance of structural integrity, but this faces serious challenges due to the microscopic characteristics of the discontinuities, low visual contrast and infrequent occurrence of defect samples. Conventional deep learning methods, while accurate, often lack interpretability and exhibit low recall for rare defects. This paper proposes a novel hybrid system combining a Generative Adversarial Network (GAN), a Convolutional Neural Network (CNN), and Extreme Gradient Boosting (XGBoost 2.0.0) to enhance weld defect classification performance and transparency. Firstly, a Deep Convolutional GAN (DCGAN) creates synthetic images of the minority classes; thus, the problem of class imbalance is resolved. Then, a pretrained ResNet50V2 CNN is used to extract features of the deep layers from the original images as well as from the generated ones. After that, these features are fed into an XGBoost classifier, which uses tree-based learning to optimize classification results and make the process more understandable to the user. Furthermore, interpretation is also facilitated by Grad-CAM rendering of the CNN regions of interest and SHAP analysis to measure the involvement of the features in XGBoost. Experiments using the available LoHi-WELD datasets show that the overall accuracy is significantly improved, the per-class recall of the rare defects is also enhanced, and the robustness is also improved. The proposed hybrid method not only achieves better results but also generates visual/explainable output, which is very valuable when the system is implemented in industrial welding inspection systems. This paper serves as a liaison between the latest AI technology and the practical interpretability requirements of the mechanical and welding engineering fields. Full article

Extreme low-light image enhancement (ELLIE) targets the restoration of visual quality under ultra-dim environments (<0.1 lux). Conventional image signal processing (ISP) pipelines often fail in such scenarios due to the limitations of heuristic, hand-crafted algorithms. While deep learning has advanced the field via end-to-end mapping, existing models suffer from constrained generalization and suboptimal perceptual fidelity, primarily stemming from the scarcity of large-scale, high-diversity datasets. To bridge this gap, we present the Day and Night (DaN) dataset, a semi-synthetic benchmark synthesized through a rigorous physics-based noise model. This approach effectively captures authentic noise characteristics while enabling the scalable generation of paired samples across multifaceted illumination conditions and scenes. Furthermore, we propose No Longer Vigil (NLV), a fully differentiable AI-ISP framework. By replacing traditional rigid blocks with adaptive non-linear networks, NLV facilitates scene-dependent transformations without requiring manual priors. Comprehensive evaluations demonstrate that our method significantly outshines state-of-the-art approaches, yielding a 4.15 dB gain in PSNR and a 0.026 improvement in SSIM. Full article

Animal-vehicle collisions (AVCs) pose a significant threat to road safety, wildlife conservation, and transportation systems worldwide. Advances in artificial intelligence (AI) and computer vision have enabled intelligent detection and mitigation systems aimed at reducing such collisions. This review synthesizes the current state of AI-powered AVC prevention systems, examining deep learning architectures, multimodal sensor technologies, real-time processing frameworks, and system-level integration strategies. We analyze the transition from traditional computer vision methods to modern deep neural networks, evaluate sensor fusion approaches, and assess existing wildlife detection datasets and benchmarking practices. Key technical challenges are identified, including environmental variability, long-range detection constraints, dataset scarcity, cross-species generalization limitations, and real-time safety requirements. Rather than framing AVC prevention solely as an object detection task, this review conceptualizes it as a safety-critical perception and risk assessment pipeline operating under strict latency and deployment constraints. Persistent gaps in wildlife-specific detection, standardized evaluation protocols, and scalable edge deployment are discussed. To organize these insights, we present WildSafe-Edge as a conceptual reference architecture derived from the literature, synthesizing system-level design considerations and highlighting open research directions. Future research directions include transfer learning, synthetic data augmentation, vehicle-to-everything (V2X) integration, and edge-centric architectures to enable robust, real-world collision mitigation systems. Full article

Liquid State Machines (LSMs), a reservoir computing model based on recurrent spiking neural networks, provide a powerful framework for solving spatiotemporal classification tasks by leveraging rich temporal dynamics and event-driven processing. Although the traditional LSM formulation assumes a fixed, randomly generated reservoir, recent research has explored optimization strategies to improve liquid dynamics. However, most existing approaches focus primarily on optimizing synaptic connectivity or reservoir structure, while the role of neuron-level parameters remains largely underexplored. This work proposes a neuroevolutionary strategy based on a Genetic Algorithm (GA) that encodes both neuron configurations and their spatial positions, explicitly treating neuron-level parameters as optimization targets. By evolving neuron-specific parameters and spatial positions, the method induces diverse reservoir dynamics. Unlike approaches that directly optimize synaptic weights, the proposed representation maintains an encoding whose dimensionality scales linearly with the number of neurons. The approach was evaluated on four synthetic benchmark tasks, including one Frequency Recognition task and three Pattern Recognition tasks, using compact reservoirs composed of only 20 Leaky Integrate-and-Fire neurons. Despite the small reservoir size, the method achieved state-of-the-art or highly competitive performance, reaching mean accuracies of up to 99.71%. In the most challenging case (PR12), performance improved when the reservoir size was increased to 64 neurons. The method was further evaluated on two real-world datasets, N-MNIST and the Free Spoken Digit Dataset (FSDD), using reservoirs of 300 neurons, achieving 90.65% and 81.47% accuracy, respectively, while using substantially fewer neurons than many existing LSM-based approaches. These results highlight the potential of evolving neuron configurations and spatial organization to produce compact and effective liquid reservoirs. Full article

Illegal drone intrusion near airport runways poses a critical threat to civil aviation safety, creating an urgent need for runway-side vision systems that can detect intruding UAVs early enough for safety warning and collision-risk mitigation. However, the development of such detectors is severely hindered by the scarcity of annotated real-world data in this high-security scenario. To address this bottleneck, we present SynthAirDrone, the first high-fidelity synthetic dataset for UAV intrusion detection in airport runway environments, together with an intelligent data generation framework integrating scene-aware placement and multi-criteria quality assessment. The proposed method uses sky-region segmentation to guide physically plausible drone placement, and combines perspective-aware scaling, Poisson image editing, and a four-dimensional quality scoring system—covering sky overlap, lighting consistency, size plausibility, and edge continuity—to improve visual plausibility and semantic consistency. The resulting dataset comprises 6500 high-quality images, all annotated in YOLO-compatible format. Using the lightweight YOLOv11n model, we show that models trained solely on SynthAirDrone exhibit non-trivial cross-domain transfer to Anti-UAV, while mixed training with limited real data provides the strongest real-world performance under the present setting. Ablation studies further confirm that a quality threshold of $\tau =0.6$ achieves the best trade-off between diversity and fidelity. Overall, this work delivers a reproducible and efficient synthetic data solution for UAV detector development in high-security, data-scarce airport-runway scenarios. Full article

Stain variability in digital pathology affects both cross-center diagnostic consistency and the robustness of downstream computational analysis. In this work, we formulate stain normalization as a variational inverse problem and derive a Screened Poisson Normalization (SPN) model from the steady-state reaction–diffusion mechanism underlying histological staining. In the CIE $L^{*}{a}^{*}{b}^{*}$ space, the model couples a gradient-domain fidelity term with a chromatic anchoring term, yielding a screened Poisson equation that preserves tissue morphology while enforcing color consistency. We prove that the corresponding variational problem is well-posed in $H^1\left(\Omega \right)$ and stable with respect to perturbations of the input data. We further show that the screening term induces an intrinsic localization length ${\ell }_c\sim {\lambda }_c^{-1/2}$, so that boundary perturbations decay exponentially away from tile interfaces. Based on this locality, we develop a non-overlapping tiled DCT-based spectral solver for gigapixel whole-slide images, enabling consistent tile-wise stain normalization and seamless whole-slide reassembly without heuristic boundary blending. Experiments on multi-scanner, multi-protocol, and archival-fading pathology datasets show that SPN achieves stable stain normalization with competitive chromatic alignment and strong preservation of diagnostically relevant microstructure, particularly in full-slide and tiled reconstruction settings. Supplementary experiments on synthetic pathology-like images further support the robustness of SPN under controlled color perturbations and indicate good generalization across diverse staining variations. Full article

Accurate ecological prediction is critical for sustainable environmental management and carbon cycle assessment, yet model development is often constrained by limited datasets and inconsistent preprocessing practices. Reliable litterfall prediction plays a key role in understanding nutrient cycling and supporting sustainable forest ecosystem management. Although gradient boosting models have shown promising performance in ecological applications, structured evaluations integrating preprocessing strategies with synthetic data augmentation remain limited under data-scarce conditions. This study proposes the Hybrid Preprocessing and Augmented Boosting Framework (HPABF), which combines multi-stage preprocessing—including MICE imputation, log transformation, and feature engineering—with synthetic data augmentation to enhance predictive robustness. The framework was evaluated across eight machine learning models using a 968-sample forest ecological dataset. To mitigate data scarcity, 5000 synthetic samples were generated while preserving the statistical distribution and multivariate structure of the original data (91% fidelity). Fractal dimension analysis was further introduced as a geometric validation metric to assess prediction structure and stability beyond conventional performance measures. Within the HPABF, gradient boosting models achieved a 7% improvement over baseline performance (R² = 0.96, MAE = 0.06) under cross-validation strategies designed to reduce overfitting. Training with synthetic data further improved predictive accuracy (R² = 0.98), demonstrating the framework’s effectiveness for data-scarce ecological applications. By improving prediction reliability under limited data conditions, the proposed framework supports more accurate environmental monitoring, informed decision-making, and sustainable management of forest ecosystems. Full article

Event detection is crucial for disaster response, public safety, and trend analysis, enabling real-time identification of critical events. Social media platforms provide a vast content source, offering timely and diverse event coverage compared to traditional news reports. However, challenges arise due to the informal and noisy nature of the text, along with the limited availability of ground truth data for training models. This study introduces SOCIAL (Social Media Event Classification using Integrated Artificial Learning and Natural Language Processing), a mathematically grounded framework for real-time social media event detection. SOCIAL integrates a formal representation of social media text with a customized CNN–LSTM architecture, combining convolutional operations for local feature extraction with sequential modeling to capture temporal dependencies, thereby enhancing classification accuracy. Generative AI is employed to create synthetic event-related samples, addressing data scarcity and ensuring a balanced dataset, while the design incorporates quantitative principles to guide embedding selection and model optimization. This study systematically evaluates six experimental configurations with TF-IDF and Word2Vec embeddings. The TF-IDF-based CNN–LSTM model achieved top performance with 98.59% accuracy, 98.13% precision, 99.06% recall, and 0.9719 MCC. Additionally, the $F_{0.5}$, $F_1$, and $F_2$ scores were 98.31%, 98.59%, and 98.87%, respectively, confirming the model’s strong predictive capabilities. TF-IDF integration enhanced event-specific term recognition, reducing misclassifications and improving reliability. These results demonstrate that SOCIAL is not only a fast, accurate, and scalable tool for crisis event detection, but also a formally principled framework for modeling and analyzing social media signals. Full article

Accurate wind speed forecasting is critical for reliable wind-power integration, yet it remains challenging due to the strongly non-stationary and inherently multi-scale nature of atmospheric processes. While deep learning models—such as LSTM, GRU, and Transformer architectures—achieve competitive short- and medium-term performance, they frequently suffer from spectral bias, hyperparameter sensitivity, and reduced generalization under heterogeneous operating regimes. To address these limitations, we propose a multi-scale spectral–recurrent framework, termed RFF-RNN, which integrates multi-band Random Fourier Feature (RFF) encodings with parameterizable recurrent backbones. A key innovation of our approach is the deliberate relaxation of strict shift-invariance constraints; by jointly optimizing spectral frequencies, phase biases, and bandwidth scales alongside the neural weights, the framework dynamically shapes a fully data-driven spectral embedding. To ensure robust adaptation, we employ a two-stage optimization strategy combining gradient-based inner-loop learning with outer-loop Bayesian hyperparameter tuning. Our extensive evaluations on a controlled synthetic benchmark and six geographically diverse real-world wind datasets (spanning the USA, China, and the Netherlands) demonstrate the superiority of the proposed framework. Statistical validation via the Friedman test confirms that RFF-enhanced models—particularly RFF-GRU and RFF-LSTM—systematically outperform standard recurrent networks and state-of-the-art Transformer architectures (Autoformer and FEDformer). The proposed approach yields significantly lower error metrics (MAE and RMSE) and higher explained variance ($R^2$), while exhibiting remarkable resilience against error accumulation at extended forecasting horizons. Full article

Managing blood glucose in type 1 diabetes (T1D) remains a daily clinical challenge, and accurate short-term prediction of glucose levels can meaningfully improve insulin dosing decisions while reducing the risk of dangerous hypoglycaemic episodes. Although numerous machine learning approaches have been proposed for this task, comparing their relative merits is difficult because published studies differ widely in datasets, preprocessing choices, and evaluation criteria. In this work, we address this research gap by benchmarking ten machine learning methods—from a naïve persistence baseline through classical linear regressors, gradient-boosted ensembles, and recurrent neural networks to a novel hybrid that couples LightGBM with stochastic differential equation (SDE)-based glucose–insulin simulation—on two multi-patient datasets comprising 34 T1D subjects, across prediction horizons of 15, 30, 60, and 120 min. Every method is trained and tested under identical preprocessing and temporal splitting conditions to ensure a fair comparison. The proposed Hybrid LightGBM-SDE model consistently outperforms all alternatives, recording RMSE values of 22.42 mg/dL at 15 min, 28.74 mg/dL at 30 min, 33.89 mg/dL at 60 min, and 37.22 mg/dL at 120 min—an improvement of between 13.6% and 27.0% relative to standalone LightGBM. At the clinically important 30 min horizon, 99.7% of predictions lie within the acceptable A and B zones of the Clarke Error Grid. Wilcoxon signed-rank tests confirm that performance differences are statistically significant (p < 10⁻¹⁰), and SHAP-based analysis shows that the SDE-derived simulation features are among the most influential predictors, especially at longer horizons. All source code and evaluation scripts are publicly released to support reproducibility. Due to temporary data access constraints, all experiments reported here use physics-based synthetic datasets generated from the Bergman minimal model, replicating the structural properties of the D1NAMO and HUPA-UCM collections; validation on the original clinical recordings is planned. Among the two synthetic datasets, the D1NAMO-equivalent cohort (nine patients) proves more challenging, with systematically higher per-patient RMSE variance. The clinically acceptable prediction accuracy at the 30 min horizon (99.7% in Clarke zones A + B) suggests potential for integration into insulin dosing decision-support systems. Full article

In insurance portfolios, classifying customers without a prior history at a given company is particularly challenging due to the absence of historical behavior, extreme class imbalance, heavy-tailed loss distributions, and strict operational constraints. Traditional machine learning approaches, including the baseline methodology proposed in previous studies, typically optimize global predictive accuracy and therefore fail to capture business-critical outcomes, especially the identification of high-risk clients. This study extends the existing approach by evaluating two complementary business-aware classification strategies: (i) a balanced bagging ensemble specifically designed to handle class imbalance and maximize expected profit under explicit customer-omission constraints, and (ii) a lightweight Transformer-based architecture capable of learning richer feature representations. Both approaches incorporate the asymmetric financial cost structure of insurance and operate under operational selection limits. The empirical analysis is conducted on a proprietary large-scale auto insurance dataset comprising 51,618 customers and is complemented by validation on nine synthetic datasets to assess robustness. Model performance is evaluated using statistical tests (ANOVA, Friedman, and pair-wise comparisons) together with business-oriented metrics. The results show that both proposed approaches consistently outperform the baseline methodology (p < 0.001) in terms of profit, with the ensemble offering a better balance of performance and efficiency, while the Transformer shows stronger robustness and generalization under data perturbations. The balanced ensemble provides the most favourable trade-off between predictive performance, robustness, interpretability, and computational efficiency, making it suitable for deployment in regulated insurance environments, while the Transformer achieves competitive results and exhibits stronger generalization under data perturbations. The proposed approach aligns machine learning with actuarial portfolio optimization by explicitly integrating profit-driven objectives and operational constraints, offering two practical and scalable solutions for risk-based decision-making in real-world insurance settings. Full article