Search Results (14,673)

Sleep-related respiratory disturbances are difficult to monitor continuously outside specialized laboratories because conventional polysomnography is resource-intensive and intrusive. This study presents a contactless edge-AI engineering prototype for detecting controlled voluntary respiratory-motion suppression and motion artifacts using a 60 GHz frequency-modulated continuous-wave radar. The system integrates a 60 GHz radar front end, lightweight local preprocessing, an INT8 one-dimensional convolutional neural network deployed on the Analog Devices MAX78000 CNN accelerator (Analog Devices Thailand, Chon Buri, Thailand), and an event-driven Raspberry Pi Zero 2W gateway for alert transmission. Evaluation was performed using a controlled healthy-volunteer dataset consisting of normal breathing, voluntary breath-holding-induced respiratory suppression, and deliberate motion artifact. The final valid test set contained 270 technically valid 30 s windows balanced across the three classes. The INT8 model achieved an overall accuracy of 92.6% (95% confidence interval: 88.8–95.2%), with a macro-averaged precision, recall, and F1-score of 92.6%, 92.6%, and 92.5%, respectively. Active CNN inference on the MAX78000 consumed 0.152 ± 0.011 mJ and was completed in 5.20 ± 0.11 ms, corresponding to approximately 280-fold lower active inference energy than Python 3.14.6/TensorFlow Lite 2.21.0-based execution on the Raspberry Pi Zero 2W. These results demonstrate the feasibility of privacy-aware, low-power respiratory-pattern classification at the edge. However, the study should be interpreted strictly as an engineering proof-of-concept based on controlled voluntary breathing and movement tasks in healthy volunteers. It is not a clinically validated apnea or obstructive sleep apnea detection system and did not include polysomnography, oxygen saturation measurement, airflow sensing, sleep staging, or diagnosed patient cohorts. Full article

Early fault detection in microsatellite thermal control systems (TCS) faces fundamental challenges: high-dimensional redundant telemetry channels, overlapping multi-scale periodicities that obscure anomaly signatures, and severely limited daily data downlink (1–2 passes per day) that restricts the temporal window for diagnosis. Existing data-driven approaches either rely on supervised learning, requiring labeled fault data that are scarce in practice, or employ univariate analysis that fails to capture inter-sensor spatial correlations. To address these limitations, this paper introduces a hybrid framework integrating information-theoretic feature selection and spatiotemporal deep learning. The Generalized Maximum Information Coefficient (GMIC) quantifies nonlinear dependencies between temperature channels for key channel selection, reducing dimensionality by 82% while preserving diagnostic information. A dual-level Seasonal Trend Decomposition (STL) method disentangles orbital-periodic dynamics from diurnal cycles, effectively isolating distinct thermal characteristics at multiple timescales. Each decomposed component is modeled using Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) networks to capture spatiotemporal dependencies for accurate temperature prediction. An adaptive threshold-based weighted error fusion mechanism enables early fault detection within a single day of telemetry data. Experimental validation on real satellite telemetry data demonstrates that the proposed framework achieves high-precision fault detection across multiple fault types using a minimal set of temperature channels, significantly outperforming existing benchmarks in both prediction accuracy and detection reliability. Full article

Efficient management of soil–water resources is critical for global food security under intensifying climatic and demographic pressures. This review provides a comprehensive synthesis of artificial intelligence (AI) and distributed deep learning methodologies applied to soil–water interactions in precision agriculture. The physical and hydraulic foundations of soil–water systems—including water retention, unsaturated flow governed by the Richards equation, and soil degradation processes—are examined and situated within a unified framework of AI-based modeling and decision support. Classical machine learning (ML) algorithms (Random Forests, Support Vector Machines, gradient boosting) and deep learning architectures (convolutional neural networks, long short-term memory networks, transformers) are evaluated with respect to their capacity to predict soil moisture dynamics, estimate hydraulic properties, support smart irrigation scheduling, and generate digital soil maps at field-to-regional scales. Distributed training paradigms, federated learning for privacy-preserving multi-farm analytics, and edge AI deployment on low-power IoT hardware are assessed as enabling infrastructures for scalable agricultural intelligence. This review further addresses explainability, uncertainty quantification, and ethical dimensions inherent to AI-driven agricultural systems. Key challenges—including training data scarcity in data-poor regions, model interpretability, integration with physics-based hydrological models, and real-time deployment constraints—are critically discussed. Prospective research directions encompass physics-informed neural networks, foundation models for earth observation, autonomous digital twins of soil–water systems, and federated learning architectures aligned with data sovereignty frameworks. The synthesis underscores AI’s transformative potential for sustainable agricultural water management while delineating the technical and sociotechnical barriers that must be resolved to realize this potential at a global scale. Full article

Anxiety disorders pose an increasing challenge to the mental health of individuals, particularly in regions with limited healthcare access. This study investigated the potential of integrating a brain–computer interface for processing electroencephalography (EEG) data with deep learning models to accurately classify anxious and non-anxious states. In the first phase, a convolutional neural network (CNN) was developed and validated on the public GAMEEMO dataset, achieving a classification accuracy of 95.72%. In the second phase, we conducted a separate experimental validation with seven participants (aged 18–60 years) using a within-subjects design. The protocol comprised a custom Stroop test to elicit acute cognitive stress and anxiety-related arousal, followed by a guided 4–7–8 breathing exercise to induce relaxation. EEG data from this experiment were used to classify anxious versus non-anxious states with the same CNN architecture after domain adaptation. On this self-collected dataset, the CNN achieved an accuracy of 86.58%. These results demonstrate proof-of-concept transferability while highlighting the performance gap between controlled benchmark data and real-world, small-sample recordings. The deep learning model can subsequently be coupled with neurofeedback techniques to manage anxiety levels. Overall, the findings support the potential of the developed automated system for detecting stress-induced anxious states, with possible future integration into neurofeedback-based management systems. Full article

Glaucoma, the leading cause of irreversible vision loss, often goes undetected in early stages due to its asymptomatic behaviour. Early diagnosis typically involves visual analysis of the optic disc (OD) in eye fundus images. Machine and deep learning techniques have emerged as valuable tools for automating this process; however, their integration into clinical practice still faces limitations. These challenges include the presence of image regions that are not directly related to glaucoma assessment, such as retinal vasculature, the macula, and background structures, which may introduce irrelevant information and negatively affect classification performance, as well as a general lack of transparency in the decision-making process. This article proposes a methodology that enhances both the accuracy and interpretability of glaucoma detection by focusing solely on the OD region. First, a metaheuristic-based strategy is employed for precise OD detection and cropping, generating an OD-centric dataset with glaucoma-labeled images, which is composed of different public datasets. Four convolutional neural networks (CNNs), namely VGG-19, MobileNet-V2, ResNet-50, and DenseNet-161, are trained on this dataset using transfer learning. To address the need for model explainability, Grad-CAM, Score-CAM, and Eigen-CAM are applied to the trained models to generate post hoc visual explanations of their predictions. The experimental results showed that DenseNet-161 achieved the best overall performance on the assembled public dataset, using an 80%-10%-10% training, validation, and testing split, with a test accuracy of 0.9369 and an AUC of 0.9831. By isolating the OD region and incorporating explainability techniques, the methodology provides a robust and interpretable second opinion, supporting more accurate and efficient glaucoma screening. Full article

In the past few years, cyber-attacks have risen at an exponential rate across all sectors, and both private and public institutions have faced increasingly sophisticated threats. As this upward trend continues, the need for advanced and efficient threat detection systems is essential. This paper investigates the use of feature importance (FI) Coefficients to improve Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) models, leveraging feature selection to enhance model interpretability and optimize performance. By systematically filtering out the weaker features, we examine the reduced features’ impact on model accuracy, precision, recall, and F1 score. Experiments were conducted on two new datasets, UWF-ZeekDataSum2025-1 and UWF-ZeekDataSum2025-2, using a baseline ANN/CNN architecture and multiple architectural variants. The results on UWF-ZeekDataSum2025-1 show a clear performance gain for certain feature importance thresholds, with models such as ANN-Minimal, ANN-Overfit-Wide, ANN-Shallow-Low-Optimization, CNN-Shallow, and CNN-Very-Shallow outperforming the baseline after reducing the feature space from seventeen features to fewer than four. For UWF-ZeekDataSum2025-2, improvements occur across a broader range of thresholds, with models including ANN-Deep-Sub-Conv, ANN-Shallow-Low-Opt, CNN-Shallow, CNN-Very-Shallow, and ANN-Minimal exceeding 95% performance around the 0.25–0.28 thresholds, with additional gains at 0.31–0.32 for some architectures. These findings demonstrate that by strategically leveraging feature importance coefficient thresholds, we can significantly enhance neural network intrusion detection systems, offering a reproducible pathway for adapting these methods on similar environments. Full article

Plunger lift systems are vital for optimizing production in gas wells, but their performance can be compromised by various operational anomalies. Traditional diagnostic methods and conventional convolutional neural network (CNN) approaches often struggle with the complex, transient data from these systems, particularly in capturing long-range temporal dependencies and generalizing from limited, imbalanced datasets. This study presents an enhanced diagnostic framework for plunger lift anomaly detection by leveraging the strengths of a pre-trained Vision Transformer (ViT). The methodology transforms one-dimensional time-series pressure data into two-dimensional image representations using the element-wise summation of Gramian Angular Summation Field (GASF) and Gramian Angular Difference Field (GADF), which simultaneously preserves global operational trends and local transient dynamics for vision model analysis. The ViT model, initialized with pre-trained weights, is further optimized using Bayesian optimization (BO) for hyperparameter tuning, and a tailored data augmentation pipeline is employed to improve robustness. Comparative evaluations demonstrate that the proposed ViT-based approach, particularly the ViT + GAF + BO model, significantly outperforms baseline CNN models and their optimized variants, achieving the highest Precision, Recall, and F1-score, with an F1-score of 0.93. Visualizations using t-SNE confirm the ViT’s superior capability in learning discriminative features, showcasing well-separated clusters for different operational conditions compared to CNNs. This research underscores the potential of pre-trained ViTs combined with appropriate data representation and optimization techniques for achieving accurate and reliable anomaly detection in plunger lift systems. Full article

Accurate forecasting of offshore wind power is essential for the stability of power systems, yet it remains challenging due to the strong non-stationarity and complex multivariate coupling of meteorological data. To address the tendency of error accumulation in medium- and long-term predictions, this paper proposes a novel framework, termed ISSAVMD-TCN-SOFTS, which integrates adaptive signal decomposition with lightweight deep temporal modeling. Specifically, an improved sparrow search algorithm, enhanced by Lévy flight and sine–cosine modulation mechanisms, is introduced to adaptively optimize the parameters of variational mode decomposition (VMD). This optimization ensures the robust decomposition of highly non-stationary power series. Furthermore, the framework combines the capability of temporal convolutional networks (TCN) to extract multiscale local temporal features with the efficiency of the STAR module in SOFTS for modeling global channel dependencies. Experiments on multi-site, multi-horizon SCADA data from real offshore wind farms show that the proposed model reduces MAE and RMSE by 10–45% compared with mainstream linear models, recurrent neural networks, and Transformer-based models, and maintains high stability over extended forecasting horizons. The results confirm that the integration of adaptive decomposition and collaborative temporal-channel modeling provides an effective solution for the accurate and stable forecasting of offshore wind power. Full article

Accurate waveform classification in noisy environments is an important task in modern communications, radar signal analysis, biomedical signal interpretation, industrial monitoring and other signal processing systems. This paper investigates the performance of three neural network architectures: Multilayer Perceptron (MLP), one-dimensional Convolutional Neural Network (1D-CNN), and Long Short-Term Memory (LSTM) for multiclass waveform classification in the presence of Additive White Gaussian Noise (AWGN). A time series dataset consisting of multiple waveform classes is generated and corrupted with AWGN across a wide range of signal-to-noise ratio (SNR) levels to simulate noisy signal distortion conditions. The three models are trained and evaluated under identical conditions to ensure a fair comparison. Their classification performance is evaluated in terms of accuracy, Confusion Matrix (CM), Receiver Operating Characteristic (ROC) curve and the Area Under the ROC curve (AUC) across varying SNR values. Simulation results demonstrate that the 1D-CNN effectively captures local temporal patterns and achieves superior robustness in classification at moderate and high SNR levels. The LSTM model demonstrates the ability to capture temporal dependencies in sequential waveform data but exhibits sensitivity to waveform variations due to amplitude, phase and frequency changes and noise at lower SNR values. The MLP, although computationally simpler, shows comparatively limited performance in low-SNR conditions due to its lack of temporal feature extraction capability. For the case of multiclass deterministic waveforms, the accuracy of classification for the 1D-CNN and LSTM is nearly 100% at SNR = 5 dB showing their robustness in classification, whereas the accuracy of MLP is approximately 70% that shows poor classification in noisy conditions. When there is random amplitude, frequency and phase variations in the waveforms, the accuracy of the 1D-CNN and MLP increases with SNR, and 1D-CNN superior to MLP. However, the LSTM accuracy fails to improve with SNR, resulting in poor classification performance in such a scenario. The results provide an insight into the suitability of different neural architectures for waveform classification tasks in noisy communication or other time series applications and highlight the advantages of convolutional feature extraction for robust signal recognition. Full article

Lung diseases are among the leading global causes of morbidity and mortality, and existing reviews on deep learning (DL) for pulmonary diagnosis rarely integrate imaging, acoustic, and electronic health record (EHR) modalities within a single framework. We aimed to synthesize the state of the art (2019–2024) in multimodal DL for lung disease detection and classification, identifying dominant architectures, performance benchmarks, and translational barriers across chest X-rays, CT scans, respiratory sounds, and EHRs. A structured narrative review was conducted using PubMed, Scopus, IEEE Xplore, and Web of Science, applying explicit inclusion criteria for peer-reviewed studies; performance metrics, dataset characteristics, and reported limitations were extracted. Research involving convolutional neural networks (CNNs) and more recent models such as Transformers have reported high performance in chest X-ray classification, whereas acoustic approaches based on spectrograms and self-supervised representations (e.g., Wav2Vec 2.0) show promising but dataset-dependent results. Full article

The high prevalence of cardiovascular diseases and the extensive application wearable electrocardiogram (ECG) devices for long-term monitoring have posed significant challenges for the transmission, storage, and real-time processing of massive amounts of ECG data. Consequently, efficient ECG compression and reconstruction have become a research priority in remote ECG monitoring. Traditional compressed sensing is complex and has high computational overhead, while single deep learning models cannot simultaneously extract local waveforms and model temporal dependencies. To address these shortcomings in the reconstruction process, this paper presents a CNN-LSTM-Attention hybrid model. This model utilizes a convolutional neural network (CNN) to capture local ECG waveform features, employs a long short-term memory (LSTM) network to learn long-term temporal dependencies, and introduces an attention mechanism to weight and fuse key diagnostic features, enabling accurate focus on key components including the QRS complex and ST segment. Experimental results on the MIT-BIH Arrhythmia dataset demonstrate that across the full compression range of 0.1–0.9, the proposed model achieves favorable comprehensive performance. Its PRD is stabilized at 10–12%, the SNR stays above 20 dB, and the RMSE is mostly lower than 0.25 mV. In terms of reconstruction accuracy and stability, our model outperforms the single CNN and CNN-LSTM models by a large margin. Full article

Existing intelligent fault diagnosis methods ignore the influence of sensors at different positions on the model fault diagnosis performance. Furthermore, the lack of interpretability leads to insufficient reliability of the model fault diagnosis results. Therefore, a physics-informed multi-sensor information fusion method for gearbox fault diagnosis is proposed. The method consists of a physics-informed shallow feature extraction module, a hierarchical multi-scale graph learning module, and an adaptive feature fusion module. The shallow feature extraction module is composed of Laplacian convolution. Multi-scale Laplacian convolution kernels are used to capture multi-frequency and multi-scale feature information, enriching fault representations. The hierarchical multi-scale graph learning module adopts graph convolutional neural networks to conduct deep multi-sensor fault feature extraction for generating high-level features. The adaptive feature fusion module realizes the weighting of important sensor data and the suppression of redundant information through attention scores. This method is validated on two gearbox datasets. The results show that when applied to the SEU dataset, the proposed method achieves a diagnosis accuracy 5.8% higher than that of the state-of-the-art method (MIFNet) under small-sample conditions. In noisy environments, the proposed method achieves an average diagnostic accuracy 1.8% higher than that of the state-of-the-art method (LiConvFormer). This indicates that the proposed method exhibits superior fault diagnosis performance and can effectively handle fault diagnosis tasks under small-sample conditions and in noisy environments. Full article

As power systems continue to expand and grow in complexity, power flow calculation remains a fundamental task in power system analysis and operation. Conventional methods rely on iterative solvers and detailed grid models, yet are often hindered by non-convergence and unreliable modeling assumptions. To address these limitations, this paper introduces a deep learning-based approach that integrates graph neural networks (GNNs) and recurrent neural networks (RNNs) for power flow calculation. The proposed model captures spatial dependencies through graph convolutional layers and temporal dynamics through recurrent layers, enabling accurate prediction of node voltage magnitudes, phase angles, and branch power flows. To enhance transparency, SHAP (Shapley Additive exPlanations)-based feature attribution and multi-modal visualizations are employed to interpret the model’s predictions. Experimental results on the IEEE 9-bus, 39-bus, and 118-bus systems demonstrate prediction errors within 4% and a computational speedup of approximately 40-fold over traditional Newton–Raphson methods. Beyond technical performance, these results suggest that the proposed method can support more efficient and reliable grid operation, thereby contributing to the integration of renewable energy, enhancement of grid resilience, and advancement of sustainable energy systems. Full article

Background/Objectives: Chest X-ray (CXR) images are a widely used first-line screening tool for pulmonary tuberculosis (TB) detection but are difficult to interpret, which has increased demand for an automated screening tool. Deep-learning-based computer-aided diagnosis systems have demonstrated a classification performance comparable to that of trained radiologists, but they rely on dense annotations such as lesion-level or pixel-level labels, which are costly and difficult to obtain in routine clinical workflows. We developed CPM-XNet, an annotation-efficient framework for lesion-annotation-free downstream TB classification in CXR images. Methods: CPM-XNet incorporates a compressing–projecting mask (CPM) to provide soft lung-aware modulation while preserving global contextual information. The CPM-modulated images are then used for downstream classification with multiple convolutional neural network backbones and a vision transformer baseline. Results: Experiments were conducted using an internal hospital dataset and public TB datasets, and CPM-XNet showed improved performance compared with baseline models trained on unmodulated images. In a repeated-seed evaluation of the main ResNet-101 configuration on the Tung cohort, CPM-ResNet101 showed higher and more stable performance than the non-CPM counterpart and demonstrated significant paired improvement using McNemar’s exact test. An ablation analysis indicated that CPM modulation was the main contributor to performance improvement while data augmentation and the classifier architecture further influenced the overall robustness. Conclusions: CPM-XNet provides an annotation-efficient strategy for lesion-annotation-free downstream TB classification in CXR images. The findings support preliminary technical feasibility, although larger, naturally imbalanced, cross-institutional validation is required before clinical deployment can be inferred. Full article

Effective waste sorting is central to circular economy goals and sustainable waste management: it maximizes recycling yields, diverts waste from landfills, and reduces the environmental burden of solid waste disposal. Accurate automated sorting using deep learning can achieve this at scale, yet high-performing classifiers are too computationally demanding for the low-cost embedded hardware used in sorting facilities. We propose the KD-Garbage Framework, which applies knowledge distillation to transfer predictive knowledge from a high-capacity teacher model to a lightweight student model, enabling deployment-ready classifiers that approach or exceed teacher-level accuracy without any added inference cost. We also introduce a 15,681-image garbage dataset organized into 13 classes defined by recycling and disposal pathway, assembled from 12 public sources and original photography, with all labels manually verified. Two teacher models were paired with 16 lightweight convolutional neural network (CNN) student architectures and benchmarked on a Raspberry Pi 5 at a minimum throughput of five frames per second. Knowledge distillation reduced misclassification rates by 10–25% across all student architectures. The best-performing student, RegNetY-1.6GF, achieved a balanced accuracy of 0.9129, surpassing both teacher models while sustaining real-time throughput on the target hardware, demonstrating a practical pathway toward scalable, AI-enabled sustainable waste management. Full article