Search Results (541)

The widespread development of medium-voltage and high-voltage direct current transmission systems has highlighted the modular multilevel converter (MMC) as a crucial enabling technology. However, the overall performance and lifetime of the MMC strongly depend on the integrity of its submodules (SMs), making online capacitance condition monitoring a critical requirement. Unlike recent related studies that rely on computationally heavy matrix-based algorithms or “black-box” artificial neural networks requiring massive offline training datasets, this paper proposes a parametric, adaptive linear neuron network. Mapped directly to the physical equations of the MMC, the method simultaneously exploits the arm current, SM switching state, and capacitor voltage to identify online parametric variations caused by aging or harsh conditions. The proposed scheme is fully non-intrusive, requiring no additional hardware sensors or signal injections, thereby reducing implementation complexity. The simulation results obtained in MATLAB/Simulink (vR2024b) demonstrate the method’s fast convergence and a quantified steady-state estimation error within ±1%. Furthermore, the estimator exhibits strong robustness under severe operating conditions, successfully maintaining accuracy during a 20% capacitance reduction, a 100% active power step variation, dc-link voltage fluctuations, measurement noise, grid unbalances, and harmonic perturbations. Full article

Aiming at the problems of microseismic signals from rock mass fracture in deep-buried tunnels with low signal-to-noise ratio (SNR) suffering from coupled interference of multi-source noise, and traditional filtering methods having fixed parameters and poor processing effects on spectral aliasing, this study proposes a ternary coupled adaptive filtering method integrating the Sparrow Search Algorithm, Variational Mode Decomposition and Wavelet Threshold Denoising (SSA-VMD-DWT). First, the noise intrusion characteristics of low-SNR microseismic signals in deep-buried tunnels were analyzed, and the filtering difficulties of white noise, low-frequency noise, high-frequency noise and non-stationary noise were clarified. Subsequently, a parameter optimization framework with the Sparrow Search Algorithm (SSA) as the core was constructed to optimize the key parameters, including the penalty factor α and modal number K of Variational Mode Decomposition (VMD), as well as the wavelet basis and decomposition layers of Wavelet Threshold Denoising (DWT), respectively. A dual-index threshold decision function based on kurtosis and correlation coefficient, and a wavelet packet entropy weighted reconstruction algorithm were designed to realize the collaborative adaptive adjustment of decomposition depth and threshold rules. Finally, the performance of the algorithm was verified through simulation signal experiments and an engineering case of a deep-buried tunnel in Southwest China. The results show that for the simulated signal with a low SNR of 2 dB, the SNR is increased to 12.43 dB, and the root mean square error is reduced to 2.36 × 10⁻⁷ after denoising by this algorithm, which is significantly superior to the Empirical Mode Decomposition (EMD) and traditional DWT methods. In the engineering case, the information entropy of the filtered signal is the lowest among all methods, which can effectively suppress multi-band noise and retain the core characteristics of microseismic signals from rock mass fracture, solving the problems of spectral aliasing, detail loss and empirical parameter setting of traditional methods. This method provides a new technical paradigm for the processing of low-quality microseismic signals in deep tunnel engineering and can improve the accuracy of monitoring and early warning for rock mass dynamic disasters. Full article

Non-Intrusive Load Monitoring (NILM) represents a powerful approach for energy disaggregation, which enables detailed insights into energy consumption patterns without requiring extensive sensor deployment. While significant advances have been achieved in residential NILM applications, commercial and industrial buildings remain largely underexplored despite their substantial contribution to global energy consumption. This study addresses this gap by developing and evaluating multiple artificial intelligence approaches for energy disaggregation across residential, commercial, and industrial buildings under a unified experimental protocol. We implement and compare several AI-based models, including Vision Transformer (ViT), Variational Autoencoder (VAE), Random Forest (RF), and custom architectures inspired by TimeGPT and Prophet, alongside traditional baseline methods. The proposed framework is validated using three benchmark datasets representing residential (AMPds), commercial (COmBED), and industrial (IMDELD) environments. Experimental results demonstrate that architecture–load interactions, rather than model complexity alone, are the primary determinants of disaggregation accuracy: the ViT-small configuration achieves superior performance for complex industrial loads with R² values exceeding 0.94, Random Forest proves most effective for finite-state commercial HVAC systems with R² up to 0.97, and the Prophet-inspired model excels in capturing seasonal patterns in residential appliances. These findings provide evidence-based guidelines for selecting appropriate AI models based on load characteristics, signal-to-noise ratio, and building type, contributing to the practical deployment of NILM in heterogeneous building environments. Full article

Compressed air leakages represent a major source of energy waste and financial loss in industrial facilities. However, accurately detecting and quantifying these leaks remains challenging due to the wide variation in the accuracy, cost, usability, and practical applicability of available methods. This paper presents a structured review and evaluation of leakage localization and quantification methods for compressed air systems (CASs), categorized into hardware-, software-, and non-technical-based approaches. Based on expert interviews and a comprehensive literature review, a set of evaluation criteria was defined and applied within a multi-criteria decision analysis (MCDA) framework. The Analytic Hierarchy Process (AHP) was used to derive criteria weights, while the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) was employed to rank the alternatives separately for localization and quantification tasks. To enhance practical relevance, five expert interviews were conducted with industrial stakeholders from diverse professional backgrounds, including maintenance engineers and energy managers. A questionnaire was also distributed to assess the methods. The results provide illustrative insights into the relative suitability of different methods. Within the scope of this exploratory study, from a practical industrial perspective, the compressor duty cycle method and non-intrusive load monitoring (NILM) appear to be promising approaches to leakage quantification, while ultrasonic detection is preferred for localization. Notably, discrepancies between questionnaire-based rankings and expert interview insights highlight the limitations of purely survey-driven evaluations. The proposed framework supports industrial decision-makers in selecting leakage detection and quantification methods by balancing technical performance, implementation effort, and operational constraints, thereby contributing to reduced energy losses and improved system efficiency. Full article

Non-Intrusive Load Monitoring (NILM) systems are increasingly applied in residential and commercial environments to disaggregate energy consumption without requiring additional hardware sensors. The integration of Machine Learning (ML) techniques has enhanced the accuracy and efficiency of load identification and classification in smart meter-based systems. This study presents a systematic review and meta-analysis aimed at identifying, classifying, and quantitatively evaluating ML models applied to NILM. Searches were conducted in the IEEE Xplore and Scopus databases, restricted to peer-reviewed publications from 2017 to 2024. Thirty studies met the eligibility criteria and were included in the quantitative synthesis using a random-effects meta-analysis model (DerSimonian–Laird estimator). The primary effect measure was the F1-score. Statistical analyses were performed using R (version 4.5.0) and Python (version 3.10.0), including heterogeneity assessment and subgroup analyses according to model type. Hybrid models, such as SVDT-KNN-MLP, LE-CRNN, and RBFNN-MOGA, achieved the highest pooled F1-scores, although supported by a limited number of studies. Traditional approaches, including CNN, KNN, and Random Forest, demonstrated consistently strong performance and broader validation, whereas Boosted Trees and RNN-based models showed lower or more variable results. Substantial heterogeneity was observed across studies, highlighting the need for dataset standardization, reproducible evaluation frameworks, and further validation of emerging hybrid architectures in diverse operational scenarios. This study contributes by providing a quantitative synthesis of machine learning models applied to NILM using a structured PRISMA-based methodology and subgroup analysis by model architecture. Unlike previous narrative reviews, this work integrates scientometric analysis with meta-analytic performance aggregation, offering a consolidated and comparative evidence base for future NILM research. Full article

Non-Intrusive Load Monitoring (NILM) enables appliance-level classification from aggregate electrical measurements and supports efficient energy management in smart buildings. However, the accuracy of existing NILM methods is often limited by the inability of conventional feature extraction techniques to capture nonlinear steady-state behavior. This study proposes a novel feature extraction framework for appliance classification, which integrates phase-space reconstruction (PSR) with 2-D Fourier series to derive geometry-based descriptors of appliance current waveforms. Unlike traditional signal-processing methods, the proposed approach utilizes the nonlinear geometric structure revealed by PSR and encodes it through Fourier descriptors, offering a discriminative, low-dimensional feature space suitable for classification using supervised machine learning algorithms. The method is evaluated on the high-resolution controlled single-appliance recordings from the COOLL dataset using the K-Nearest Neighbor (KNN) classifier. Extension to aggregated multi-appliance NILM scenarios would require additional stages such as event detection and load separation. Sensitivity analysis demonstrates that classification performance depends strongly on the choice of time delay and harmonic order, with optimal settings yielding an accuracy of up to 99.52% using KNN. The results confirm that larger time delays and a small number of harmonics effectively capture appliance-specific signatures. The findings highlight the effectiveness of PSR–Fourier-based geometric features as a robust alternative to conventional NILM feature extraction strategies. Full article

Accurate estrus detection is essential for dairy farm productivity, yet traditional manual and wearable methods remain limited by high labor costs, delayed responses, and animal stress. To address these challenges, we propose CE-YOLO, a lightweight YOLOv11n-based vision model tailored for edge deployment, which detects mounting behavior by integrating a Channel-Aware Downsampling (CA-Down) module to preserve small-scale features, a SimSPPF module for efficient contextual fusion, and a DySample module for dynamic spatial alignment. Experiments on a curated estrus behavior dataset demonstrate that CE-YOLO achieves a precision of 94.9% and an mAP50 of 98.2%, significantly outperforming the baseline by 3.9% and 4.6% respectively. These results validate the model as an efficient, non-intrusive solution for real-time estrus monitoring, strongly supporting the advancement of smart livestock management. Full article

High-frequency non-intrusive load monitoring provides detailed harmonic information for appliances’ power disaggregation, and machine-learning approaches have demonstrated good performance in this task. However, these methods provide little transparency regarding the information structure of the aggregate signal. To address this, this paper models NILM as a coding-decoding process and applies information-theoretic measures to quantify uncertainty, recoverability, temporal contribution, and inter-appliance masking effects in aggregate signals. In the analyzed dataset, transfer entropy suggests negligible temporal gains, which is consistent with the observed effectiveness of pointwise models such as Random Forest. Moreover, conditional mutual information emphasizes the asymmetric masking relationships between appliances, with the laptop charger acting as a dominant interferer in the considered measurements. These findings are validated through a Random Forest regression model with minimum Redundancy Maximum Relevance feature selection. The results show that the mutual information between an appliance and the aggregate is a good predictor of disaggregation performance in the examined data, as appliances with high mutual information, such as hair dryer and electric water heater, achieve lower estimation errors, while others, such as iron, are difficult to recover despite stable distributions. This relationship is statistically supported by a strong negative monotonic correlation between normalized mutual information and the disaggregation error (Spearman $r_s=-0.81$, $p=0.015$). Hence, this work demonstrates how information-theoretic analysis can help characterize disaggregation difficulty prior to model training and assess the observability of appliances in high-frequency NILM. Full article

Remote tower (rTWR) operations are reshaping air traffic control but introduce significant human-factor risks, notably cognitive fatigue induced by prolonged screen-based visual surveillance. To mitigate these risks in a safety-critical domain where missed detections can be catastrophic, we propose a non-intrusive, multimodal fatigue detection framework fusing ocular and cardiac signals. A high-fidelity simulation study with 36 controllers was conducted to collect eye-tracking and electrocardiogram (ECG) data, from which a 12-dimensional feature vector—integrating gaze entropy and heart rate variability (HRV)—was extracted. Addressing the severe class imbalance and scarcity of fatigue samples in physiological data, we developed a cost-sensitive XGBoost classifier combining SMOTE oversampling with a dynamically weighted loss function. Experimental results show that the proposed framework performed well under mixed-subject evaluation and improved sensitivity to fatigue events. Although a marked performance drop was observed under LOSO evaluation, personalized calibration partially alleviated this limitation, indicating the potential of the framework for real-time fatigue monitoring in remote tower operations. Full article

Non-intrusive load monitoring (NILM) is a key enabler for smart-grid applications, yet practical deployment is often hindered by limited appliance-level labels and severe distribution shifts across households and operating conditions. As a result, many deep learning approaches become unreliable in small-sample and out-of-distribution (OOD) settings. In this paper, we propose CR-MAT, a causality-driven representation learning framework for few-shot NILM classification. Instead of relying on large-scale training or heavy data augmentation, CR-MAT injects causal representation learning into multi-appliance task modeling, encouraging the network to learn appliance-discriminative features that are stable across environments while suppressing spurious, domain-specific correlations. We conduct extensive experiments under multiple OOD scenarios and consistently observe improved classification robustness compared with deep NILM baselines. Further analysis indicates that causal representation learning enhances resilience to non-stationary consumption patterns and improves generalization under OOD scenarios. The proposed framework provides a practical route toward reliable NILM classification and supports downstream smart-grid applications such as flexible load control and demand response. Full article

Mobile ad hoc networks (MANETs) are highly vulnerable to denial-of-service (DoS) attacks because their decentralized operation, rapidly changing topology, and constrained node resources limit the use of heavyweight security mechanisms. This paper presents an Adaptive Clustering and Random-Forest-based Intrusion Detection System (ACRF-IDS), a lightweight intrusion detection framework that combines mobility-aware adaptive clustering with supervised learning to detect network-layer DoS behaviors. Cluster heads are elected using a multi-metric utility (residual energy, link stability, and mobility) to stabilize observations under node movement. Within fixed monitoring windows, cluster heads aggregate routing-, forwarding-, and energy-related features and classify nodes using a Random Forest model; a temporal voting scheme further suppresses transient mobility-induced alarms. Using ns-2.35 simulations with Ad hoc On-Demand Distance Vector (AODV) and both flooding and blackhole DoS scenarios, ACRF-IDS is compared with (i) a static clustering-based threshold IDS, (ii) a non-clustered Support Vector Machine (SVM)-based IDS, and (iii) AIFAODV, which specializes in flooding. Across the evaluated network sizes (4–50 nodes), the proposed method achieves a higher detection rate and F1-score while maintaining a lower false positive rate than the baseline techniques. We additionally quantify network-level impact using PDR, throughput, and routing overhead, showing that ACRF-IDS improves availability under DoS while adding bounded overhead. Future work will extend the evaluation to more diverse attack behaviors and validate the approach in real-world MANET testbeds. Full article

The increasing reliance of Internet of Things (IoT) applications on low-power wide-area network technologies, particularly Long Range Wide Area Network (LoRaWAN), has amplified the need for security monitoring approaches that go beyond attack-specific signatures and generic traffic anomalies. Existing solutions are often tailored to individual threat scenarios or rely on statistical indicators, which limits their ability to systematically capture protocol-level misuse in an interpretable manner. This paper addresses this gap by proposing a protocol-aware validation methodology based on a Digital Twin abstraction of LoRaWAN communication behavior. The Over-The-Air Activation (OTAA) procedure is modeled as a finite-state machine that encodes expected message sequences, timing constraints, and specification-driven state transitions. Observed network events are continuously evaluated against this formal state model, enabling the identification of protocol-level deviations indicative of anomalous or non-conformant behavior. Illustrative examples include replay behavior, timing inconsistencies, and integrity-related anomalies, although the framework is not limited to predefined attack categories. The results demonstrate that state machine-based Digital Twin provides a structured and extensible foundation for protocol-aware security validation and Security Operation Center (SOC)-oriented telemetry enrichment. In this sense, the presented approach represents a concrete step toward protocol-aware intrusion detection for LoRaWAN networks by establishing a state-synchronized semantic validation layer upon which higher-level detection mechanisms can be built. Full article

Background: Sleep staging is vital for diagnosing sleep disorders, but the clinical gold standard, polysomnography, is too intrusive for routine home monitoring. While photoplethysmography (PPG) offers a wearable alternative, achieving high diagnostic accuracy remains challenging due to signal noise and individual variability. Methods: We developed DCA-Sleep, a deep learning framework using a Dual Cross-Attention (DCA) mechanism to capture long-range temporal dependencies from raw single-channel PPG. To overcome data scarcity, a cross-modality transfer learning strategy was implemented, pre-training the model on six electrocardiogram (ECG) datasets before extensive validation on a combined cohort of 9738 subjects across nine public datasets (including MESA and CFS). Results: DCA-Sleep demonstrated superior robustness, achieving an average F1-score of 0.731 and a Cohen’s Kappa of 0.652 on the MESA dataset, significantly outperforming state-of-the-art baselines. The model showed high sensitivity in detecting Wake and Deep Sleep stages, which are critical for clinical assessment. Conclusions: This study provides a large-scale validation of a PPG-based staging tool, confirming its reliability as a non-invasive, scalable solution for long-term sleep monitoring and clinical screening. Full article

Accurate river discharge estimation is fundamental for water resource management under increasingly variable hydrological conditions. While conventional in situ techniques remain hydrometric reference standards, their operational deployment is constrained by cost, accessibility, and limited spatial coverage. Advances in remote sensing and artificial intelligence (AI) have introduced non-contact discharge estimation frameworks based on image-derived observations. This systematic review, conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 reporting guidelines, examines the evolution of river discharge measurement methods between 2004 and 2024 through a structured two-stage design. An initial search in Web of Science and Scopus identified 2809 records, of which 249 were retained for first-stage synthesis. A focused second-stage screening isolated seven studies that directly integrate image-based data with machine learning or deep learning architectures for discharge estimation. The analysis reveals a methodological transition from instrument-based hydrometry toward computationally assisted, image-driven approaches. The retained studies employ close-range and satellite imagery combined with Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), and related models. Although reported validation metrics indicate strong predictive capability under specific conditions, performance remains dependent on site-specific calibration and reference discharge records. Broader operational deployment requires improved transferability, uncertainty integration, and cross-basin validation. Full article

Non-intrusive load monitoring (NILM) can provide actionable feedback for demand response (DR) when direct measurements of device states are unavailable. We propose a reproducible, engineering-oriented pipeline for detecting ON/OFF states of end-use load groups from an aggregated active power time series. The method uses robust hysteresis-based labeling with adaptive thresholds derived from the median and median absolute deviation, followed by compact feature engineering restricted to global active power (GAP). After removing collinear features (|r| > 0.98), permutation importance is used to retain informative predictors. Probabilistic binary classifiers (LGBM, Histogram-based Gradient Boosting, XGBoost, and CatBoost) are trained for each target load, and the decision threshold is optimized via F_β to balance missed events and false alarms. A post-processing stage stabilizes predictions by smoothing probabilities and suppressing spurious triggers. Model quality is assessed with both sample-wise metrics and event-based metrics that credit the correct detection of switching intervals within a time tolerance. Experiments on the open “Individual Household Electric Power Consumption” dataset (1-min resolution, 2007–2010) demonstrate that lightweight gradient boosting models, particularly LGBM, deliver reliable and interpretable state estimates suitable for practical DR integration and edge deployment. Full article