Search Results (1,154)

The emerging scope of the Industrial Internet of Services (IIoS) requires a robust intrusion detection system to detect malicious attacks. The increasing frequency of sophisticated and high-impact cyber attacks has resulted in financial losses and catastrophes in IIoS-based manufacturing industries. However, existing solutions often struggle to adapt and generalize to new cyber attacks. This study proposes a unique approach designed for known and zero-day network attack detection in IIoS environments, called Denoising Adaptive Multi-Branch Architecture (DA-MBA). The proposed approach is a smart, conformal, and self-adjusting cyber attack detection framework featuring denoising representation learning, hybrid neural inference, and open-set uncertainty calibration. The model merges a denoising autoencoder (DAE) to generate noise-tolerant latent representations, which are processed using a hybrid multi-branch classifier combining dense and bidirectional recurrent layers to capture both static and temporal attack signatures. Moreover, it addresses challenges such as adaptability and generalizability by hybridizing a Multilayer Perceptron (MLP) and bidirectional LSTM (BiLSTM). The proposed hybrid model was designed to fuse feed-forward transformations with sequence-aware modeling, which can capture direct feature interactions and any underlying temporal and order-dependent patterns. Multiple approaches have been applied to strengthen the dual-branch architecture, such as class weighting and comprehensive hyperparameter optimization via Optuna, which collectively address imbalanced data, overfitting, and dynamically shifting threat vectors. The proposed DA-MBA is evaluated on two widely recognized IIoT-based datasets, Edge-IIoT set and WUSTL-IIoT-2021 and achieves over 99% accuracy and a near 0.02 loss, underscoring its effectiveness in detecting the most sophisticated attacks and outperforming recent deep learning IDS baselines. The solution offers a scalable and flexible architecture for enhancing cybersecurity within evolving IIoS environments by coupling feature denoising, multi-branch classification, and automated hyperparameter tuning. The results confirm that coupling robust feature denoising with sequence-aware classification can provide a scalable and flexible framework for improving cybersecurity within the IIoS. The proposed architecture offers a scalable, interpretable, and risk sensitive defense mechanism for IIoS, advancing secure, adaptive, and trustworthy industrial cyber-resilience. Full article

Hyperspectral anomaly detection (HAD) aims to identify pixels that significantly differ from the background without prior knowledge. While deep learning-based reconstruction methods have shown promise, they often suffer from limited feature representation, inefficient training cycles, and sensitivity to imbalanced data distributions. To address these challenges, this paper proposes a novel contrastive–transfer-synergized dual-stream transformer for hyperspectral anomaly detection (CTDST-HAD). The framework integrates contrastive learning and transfer learning within a dual-stream architecture, comprising a spatial stream and a spectral stream, which are pre-trained separately and synergistically fine-tuned. Specifically, the spatial stream leverages general visual and hyperspectral-view datasets with adaptive elastic weight consolidation (EWC) to mitigate catastrophic forgetting. The spectral stream employs a variational autoencoder (VAE) enhanced with the RossThick–LiSparseR (R-L) physical-kernel-driven model for spectrally realistic data augmentation. During fine-tuning, spatial and spectral features are fused for pixel-level anomaly detection, with focal loss addressing class imbalance. Extensive experiments on nine real hyperspectral datasets demonstrate that CTDST-HAD outperforms state-of-the-art methods in detection accuracy and efficiency, particularly in complex backgrounds, while maintaining competitive inference speed. Full article

In modern cybersecurity and deep learning, conditional password guessing plays a critical role in improving password-cracking efficiency by leveraging known patterns and constraints. In contrast with traditional brute-force or dictionary-based attacks, we developed an approach that adopts a latent diffusion model to simulate human password selection behavior, generating more realistic password candidates. We incorporated masked character inputs as conditions and applied advanced feature extraction to capture common patterns such as character substitutions and typing habits. Furthermore, we employed visualization techniques, including autoencoders and principal component analysis, to analyze password distributions, enhancing model interpretability and aiding both offensive and defensive security strategies. Full article

High-Velocity Air-Fuel (HVAF) spraying of Fe-based amorphous coatings involves strong nonlinear coupling among multiple process parameters, while practical optimization is severely constrained by limited experimental data and poor model interpretability. To address these challenges, a systematic data-driven optimization framework integrating the Denoising Diffusion Probabilistic Model (DDPM)-based data augmentation with explainable machine learning is proposed. Coating microhardness and hardness uniformity were jointly selected as target properties to capture both performance level and spatial reliability. Three generative models—Generative Adversarial Network (GAN), Variational Autoencoder (VAE), and DDPM—were comparatively evaluated using statistical matching and distribution-consistency metrics, revealing that DDPM most faithfully reproduces the intrinsic statistical characteristics of real HVAF process data. We benchmarked ten representative regression algorithms covering classical statistical learning, ensemble methods, and deep learning paradigms, with GBR demonstrating the highest predictive accuracy and stability. The inclusion of 10% DDPM-generated samples further improved the predictive precision of the GBR model. SHapley Additive exPlanations (SHAP) quantitatively identified spraying distance as the dominant parameter governing coating hardness, while elucidating the coupled effects of multiple parameters on hardness uniformity. By interpolatively expanding the process parameter space, a two-stage screening strategy identified 98 high-performance parameter combinations. Experimental validation confirmed that the optimal parameter set simultaneously achieved higher hardness and improved uniformity compared with the original best condition, resulting in a 13.6% reduction in wear rate. Full article

The rise of SIM cloning, identity spoofing, and covert manipulation in mobile and IoT networks has created an urgent need for continuous post-registration verification. This work introduces an unsupervised deep learning framework for detecting behavioral anomalies in SIM-tagged network flows by modeling the intrinsic structure of benign behavioral descriptors (TTL, timing drift, payload statistics). A Temporal Deep Autoencoder (TDAE) combining Conv1D layers and an LSTM encoder is trained exclusively on normal traffic and used to identify deviations through reconstruction error, enabling one-class (label-free) training. For deployment, alarms are set using an unsupervised quantile threshold ${\tau }_{\alpha }$ calibrated on benign traffic with a false-alarm budget; ${\tau }^{*}$ is reported only as a diagnostic reference for model comparison. To ensure realism, a large-scale corpus of 3.6 million SIM-tagged flows was constructed by enriching public IoT traffic with pseudo-operator identifiers (synthetic SIM tags derived from device identifiers) and controlled anomaly injections. Cross-domain experiment transfer under SIM-grouped protocol: Training on clean Cassavia-like traffic and testing on attack-rich Guarascio-like flows yields a PR-AUC of 0.93 for the proposed Conv-LSTM Temporal Deep Autoencoder, outperforming Dense Autoencoder, Isolation Forest, One-Class SVM, and LOF baselines. Conversely, the reverse direction collapses to PR-AUC $\approx 0.5$, confirming the absence of data leakage and the validity of one-class behavioral learning. Sensitivity analysis shows that performance is stable around the unsupervised quantile operating point. Overall, the proposed framework provides a lightweight, interpretable, and data-efficient behavioral verification layer for detecting cloned or unauthorized SIM activity, complementing existing registration mechanisms in next-generation telecom and IoT ecosystems. Full article

Reliable environmental monitoring in remote or sparsely instrumented regions is hindered by the cost, maintenance demands, and inaccessibility of dense physical sensor deployments. To address these challenges, this study introduces VSG-SGL, a unified virtual sensor generation framework that integrates Sparse Gaussian Process Regression (SGPR) and Bayesian Ridge Regression (BRR) with deep generative learning via Variational Autoencoders (VAE) and Conditional Tabular GANs (CTGAN). Real meteorological datasets from multiple South Korean cities were preprocessed using thresholding and Isolation Forest anomaly detection and evaluated using distributional alignment (KDE) and sequence-learning validation with BiLSTM and BiGRU models. Experimental findings demonstrate that VAE-augmented virtual sensors provide the most stable and reliable performance. For temperature, VAE maintains predictive errors close to those of BRR and SGPR, reflecting the already well-modeled dynamics of this variable. In contrast, humidity and wind-related variables exhibit measurable gains with VAE; for example, SGPR-based wind speed MAE improves from 0.1848 to 0.1604, while BRR-based wind direction RMSE decreases from 0.1842 to 0.1726. CTGAN augmentation, however, frequently increases error, particularly for humidity and wind speed. Overall, the results establish VAE-enhanced VSG-SGL virtual sensors as a cost-effective and accurate alternative in scenarios where physical sensing is limited or impractical. Full article

Class imbalance is a common issue in machine learning, often causing bias in learning models toward the majority class and leading to poor predictive performance for the minority class data. To address the class imbalance problem, this paper presents the autoencoder-based generative adversarial network-synthetic minority over-sampling technique-particle swarm optimization (AEGAN-SMOTE-PSO) model. We compared the AEGAN-SMOTE-PSO model with three other state-of-the-art oversampling techniques. Those experimental results demonstrate that the AEGAN-SMOTE-PSO model effectively improves the classification performance of two support vector machine prediction models on two imbalanced medical cases. Compared to the other three oversampling methods, the AEGAN-SMOTE-PSO model effectively provides satisfactory predictive performance in terms of recall, precision, and F1-score. Full article

Non-destructive estimation of leafy vegetable fresh weight is crucial for precision management in both greenhouse and open-field production. However, mutual occlusion between plants in dense canopies poses a significant challenge to image-based estimation accuracy. This study systematically investigates the potential of deep learning-based image inpainting methods to reconstruct occluded regions in RGB lettuce images, thereby improving input data quality for downstream weight estimation models. Three state-of-the-art inpainting models—Vision Transformer-based Denoising Autoencoder (ViT-DAE), Aggregated Contextual–Transformation Generative Adversarial Network (AOT-GAN), and a conditional Diffusion Model (CDM)—were implemented and evaluated. A dataset comprising 503 individual lettuce images with artificially generated random occlusions was used for training and testing. Performance was assessed using pixel-level metrics (PSNR, SSIM) and, more importantly, by evaluating the fresh weight estimation accuracy (R², NRMSE, MAPE) of a pre-trained CNN model (CNN_284) using the inpainted images. Results indicated that AOT-GAN achieved the best overall performance, with an SSIM of 0.9379 and an R² of 0.8480 for weight estimation after inpainting under single-direction occlusion, closely matching the performance using original non-occluded images (R² = 0.8365). In complex multi-direction occlusion scenarios, AOT-GAN demonstrated superior robustness, maintaining an R² of 0.7914 and an MAPE of 12.02% for weight prediction, significantly outperforming the other models. This study demonstrates that advanced inpainting techniques, particularly AOT-GAN, can effectively mitigate the impact of occlusion, enhancing the reliability of vision-based leafy vegetable biomass estimation in practical production. Full article

The propagation of uncertainties in structural dynamic responses, arising from variations in material properties, geometry, and boundary conditions, is of critical concern to researchers in a variety of engineering instances. Conventional methods like high-fidelity Monte Carlo simulation are computationally prohibitive, while existing surrogate models can improve efficiency at the expense of accuracy. To achieve a trade-off between accuracy and efficiency, a Physics-Informed Conditional Variational Autoencoder (PI-CVAE) model is proposed. It integrates a novel dual-branch encoder for time-frequency feature extraction, a learnable frequency-filtering decoder, and a holistic physics-informed loss function so as to enable efficient generation of dynamic responses with high accuracy and adequate physics consistency. Comprehensive numerical analysis of plate structures demonstrates that the proposed approach achieves remarkable accuracy (maximum FRF error < 0.2% and $R^2$ > 0.99) and a computational speedup of 8–11 times in comparison with conventional simulation techniques. By maintaining high accuracy while efficiently propagating uncertainties, the PI-CVAE model provides a practical framework for probabilistic vibration analysis, especially during the acoustic design phase. Full article

Indoor localization finds wide-ranging applications in user navigation and intelligent building systems. Nevertheless, signal interference within complex indoor environments and challenges regarding localization generalization in multi-building and multi-floor scenarios have restricted the performance of traditional localization methods based on Wi-Fi fingerprinting. To tackle these issues, this paper presents the SE-MTCAELoc model, a multi-task convolutional autoencoder approach that integrates a squeeze-excitation (SE) attention mechanism for indoor positioning. Firstly, the method preprocesses Wi-Fi Received Signal Strength (RSSI) data. In the UJIIndoorLoc dataset, the 520-dimensional RSSI features are extended to 576 dimensions and reshaped into a 24 × 24 matrix. Meanwhile, Gaussian noise is introduced to enhance the robustness of the data. Subsequently, an integrated SE module combined with a convolutional autoencoder (CAE) is constructed. This module aggregates channel spatial information through squeezing operations and learns channel weights via excitation operations. It dynamically enhances key positioning features and suppresses noise. Finally, a multi-task learning architecture based on the SE-CAE encoder is established to jointly optimize building classification, floor classification, and coordinate regression tasks. Priority balancing is achieved using weighted losses (0.1 for building classification, 0.2 for floor classification, and 0.7 for coordinate regression). Experimental results on the UJIIndoorLoc dataset indicate that the accuracy of building classification reaches 99.57%, the accuracy of floor classification is 98.57%, and the mean absolute error (MAE) for coordinate regression is 5.23 m. Furthermore, the model demonstrates exceptional time efficiency. The cumulative training duration (including SE-CAE pre-training) is merely 9.83 min, with single-sample inference taking only 0.347 milliseconds, fully meeting the requirements of real-time indoor localization applications. On the TUT2018 dataset, the floor classification accuracy attains 98.13%, with an MAE of 6.16 m. These results suggest that the SE-MTCAELoc model can effectively enhance the localization accuracy and generalization ability in complex indoor scenarios and meet the localization requirements of multiple scenarios. Full article

Anomalous transaction behaviors in cryptocurrency markets exhibit high concealment, substantial diversity, and strong cross-modal coupling, making traditional rule-based or single-feature analytical methods insufficient for reliable detection in real-world environments. To address the research focus, a data-centric multimodal anomaly detection framework integrating generative augmentation, latent distribution modeling, and dual-branch real-time detection is proposed. The method employs a generative adversarial network with feature-consistency constraints to mitigate the scarcity of fraudulent samples, and adopts a multi-domain variational modeling strategy to learn the latent distribution of normal behaviors, enabling stable anomaly scoring. By combining the long-range temporal modeling capability of Transformer architectures with the sensitivity of online clustering to local structural deviations, the system dynamically integrates global and local information through an adaptive risk fusion mechanism, thereby enhancing robustness and real-time detection capability. Experimental results demonstrate that the generative augmentation module yields substantial improvements, increasing the recall from $0.421$ to $0.671$ and the F1-score to $0.692$. In anomaly distribution modeling, the multi-domain VAE achieves an area under the curve (AUC) of $0.854$ and an F1-score of $0.660$, significantly outperforming traditional One-Class SVM and autoencoder baselines. Multimodal fusion experiments further verify the complementarity of the dual-branch detection structure, with the adaptive fusion model achieving an AUC of $0.884$, an F1-score of $0.713$, and reducing the false positive rate to $0.087$. Ablation studies show that the complete model surpasses any individual module in terms of precision, recall, and F1-score, confirming the synergistic benefits of its integrated components. Overall, the proposed framework achieves high accuracy and high recall in data-scarce, structurally complex, and latency-sensitive cryptocurrency scenarios, providing a scalable and efficient solution for deploying data-centric artificial intelligence in financial security applications. Full article

Traffic classification remains a critical challenge in the Internet of Things (IoT), particularly for enhancing security and ensuring Quality of Service (QoS). Although deep learning methods have shown strong performance in traffic classification, learning diverse and complementary representations across heterogeneous network traffic patterns remains difficult. To address this issue, this study proposes a novel Mixture of Experts (MoE) architecture for multiclass traffic classification in IoT environments. The proposed model integrates five specialized expert networks, each targeting a distinct feature category in network traffic. Specifically, it employs a Dense Neural Network for general features, a Convolutional Neural Network (CNN) for spatial patterns, a Gated Recurrent Unit (GRU)-based model for statistical variations, a Convolutional Autoencoder (CAE) for frequency-domain representations, and a Long Short-Term Memory (LSTM) for temporal dependencies. A dynamic gating mechanism, coupled with an Attention-based Learnable Fusion (ALF) module, adaptively aggregates the experts’ outputs to produce the final classification decision. The proposed ALF-MoE model was evaluated on three public benchmark datasets, such as ISCX VPN-nonVPN, Unicauca, and UNSW-IoTraffic, achieving accuracies of 98.43%, 98.96%, and 97.93%, respectively. These results confirm its effectiveness and reliability across diverse scenarios. It also outperforms baseline methods in terms of its accuracy and the F1-score. Full article

Wireless Sensor Networks (WSNs) are widely deployed for long-term monitoring in environments characterized by nonstationary sensing dynamics, intermittent connectivity and continuously evolving network topologies, while reliable, fine-grained labeled data capturing faults and adversarial behaviors remain scarce. This survey systematically reviews and synthesizes recent research that integrates autoencoder-based representation learning with self-supervised learning (SSL) objectives to enhance anomaly detection under these practical constraints. We structure the existing literature through a unified taxonomy encompassing autoencoder variants, self-supervised pretext tasks, spatio-temporal encoding mechanisms and the increasing use of graph-structured autoencoders for topology-aware modeling. Across distinct methodological categories, SSL-augmented frameworks consistently demonstrate improved robustness and stability compared to purely reconstruction-driven baselines, particularly in heterogeneous, dynamic and temporally drifting WSN environments. Nevertheless, this review also highlights several unresolved challenges that hinder real-world adoption, including uncertain scalability to large-scale networks, limited model interpretability, nontrivial energy and memory overheads on resource-constrained sensor nodes and a lack of standardized evaluation protocols and reporting practices. By consolidating publicly available datasets, experimental configurations and comparative performance trends, we derive concrete design requirements for robust and resource-aware anomaly detection in operational WSNs and outline promising future research directions, emphasizing lightweight model architectures, explainable learning mechanisms and federated AE–SSL paradigms to enable adaptive, privacy-preserving monitoring in next-generation IoT sensing systems. Full article

This paper proposes an applied framework for cyberattack and anomaly detection in resource-constrained embedded/IoT environments by combining signal-processing feature construction with supervised and unsupervised AI (Artificial Intelligence) models. The workflow covers dataset preparation and normalization, correlation-driven feature analysis, and compact representations via PCA (Principal Component Analysis), followed by classification and anomaly scoring. In addition to the original UNSW-NB15 (University of New South Wales—Network-Based Dataset 2015) traffic features, Fourier-domain descriptors, wavelet-domain descriptors, and Kalman-based smoothing/innovation features are considered to improve robustness under variability and measurement noise. Detection performance is assessed using classical and ensemble learning methods (SVM (Support Vector Machines), RF (Random Forest), XGBoost (Extreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine)), unsupervised baselines (K-Means and DBSCAN (Density-Based Spatial Clustering of Applications with Noise)), and DL (Deep-Learning) anomaly detectors based on Autoencoder reconstruction and GAN (Generative Adversarial Network)-based scoring. Experimental results on UNSW-NB15 indicate that ensemble-based models provide the strongest overall detection performance, while the signal-processing augmentation and PCA-based compactness support efficient deployment in embedded contexts. The findings confirm that integrating lightweight signal processing with AI-driven models enables effective and adaptable identification of malicious network traffic supporting deployment-oriented embedded cybersecurity and motivating future real-time validation on edge hardware. Full article

Ethanol stability is an important indicator for evaluating the quality and heat-processing suitability of raw milk. Traditional ethanol stability testing relies on destructive laboratory procedures, which are not suitable for large-scale industrial use. In contrast, parameters such as protein, fat, lactose and other basic compositional indicators are already measured routinely in dairy plants through sensor-based or spectroscopic systems. This provides the basis for developing a non-destructive soft sensing approach for ethanol stability. In this study, a soft sensing model was developed to predict ethanol stability from commonly monitored raw-milk intake indicators. An autoencoder was used to examine feature correlations and select variables with stronger relevance to ethanol stability. TabNet was then applied to build the classification model, and a TabDDPM-based data generation method was introduced to address class imbalance in the dataset. The proposed model was trained and tested using three years of industrial raw-milk intake data from a dairy company. It achieved an accuracy of 92.57% and a recall of 90.26% for identifying ethanol-unstable samples. These results demonstrate the model’s strong potential for practical engineering applications in real-world dairy quality monitoring. Full article