Search Results (21,876)

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

Background/Objectives: This review explores the role of artificial intelligence (AI), particularly with deep learning and machine learning, in the detection and classification of papilledema using retinal fundus imaging. Methods: The study synthesizes historical, technical, and clinical insights, comparing AI-based diagnostic accuracy with conventional methods. Results: Our findings demonstrate that AI systems, especially convolutional neural networks (CNNs), offer sensitivity and specificity comparable to, or even surpassing, expert-level fundoscopy. Conclusions: These results suggest significant implications for early diagnosis, triage, and telemedicine integration in ophthalmic care. 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

Urban air pollution, especially the problem of PM_2.5, is one of the major health challenges facing the planet today. To provide accurate PM_2.5 predictions despite data noise and missing data, the authors proposed a deep learning model. We constructed a Stacked Autoencoder–Convolutional Neural Network–Bidirectional Long Short-Term Memory–Long Short-Term Memory (SAE-CNN-BiLSTM-LSTM) model that (1) utilises convolutional layers to extract spatial features from the input data, (2) employs bidirectional LSTM layers to capture long-term temporal dependencies, and (3) utilises an autoencoder to learn latent representations of the data to mitigate the effects of missing data. The model was trained on a large dataset of hourly measurements of air quality and meteorological parameters collected between 2018 and 2020 in Klang, Malaysia. The performance of the model on data that were not used during training was evaluated using a range of metrics. The SAE-CNN-BiLSTM-LSTM model achieved a test RMSE of approximately 11.97 µg/m³ and an R² statistic of approximately 0.85 for PM_2.5 concentrations, outperforming the other models tested on the same datasets. The additional metrics of MAE, MAPE, Mean Bias Error, and Index of Agreement confirmed the model’s accuracy and low bias in the prediction of air pollution levels. Statistical tests, such as the Diebold–Mariano test, confirmed the significance of the model’s accuracy over the CNN-LSTM models. These findings indicate that the proposed model effectively captures the dynamics of the air pollution data. The proposed model structure efficiently achieved an accurate and lightweight model for urban air pollution forecasting. Full article

Data-driven models can be used to understand basin-wide hydrological processes and generate predictions for future conditions, particularly in cases of scarce data availability related to basin characteristics. Although they have long been applied in hydrological modeling, there is still limited information regarding their ability to produce reliable long-term projections under climate change conditions. This study evaluates the long-term predictive performance of data-driven models by employing a hybrid deep learning architecture combining Wavelet Transform (WT) and Deep Neural Network (DNN). The dataset used in this study was obtained from the Yamula Reservoir Basin, a semi-arid agricultural basin in Türkiye. Monthly streamflow was simulated based on climate projection data from the HadGEM2-ES model under the RCP4.5 and RCP8.5 scenarios. Results showed that the WT–DNN framework was successful in learning the system dynamics and reproducing observed streamflow behavior. The model produced continuous projections for the future period; however, these projections should be interpreted with caution due to the increasing uncertainty associated with long-term climate forcing and the sensitivity of data-driven approaches to shifts in climatic and hydrological regimes. Full article

Predicting thermal breakthrough and optimizing injection-production parameters are essential for sustainable geothermal development. Traditional hydrothermal coupled simulations in porous media entail substantial computational costs, which limits their use in dense multi-parameter screening. This study develops a physics-constrained surrogate workflow for the Qihe geothermal doublet system by using COMSOL to generate hydrothermal simulation data and a deep neural network (DNN) to emulate the simulator response within a predefined operating domain. The DNN was trained on physics-driven synthetic outputs rather than independent field observations, and a 2.0 °C decrease in production temperature was used as the thermal breakthrough criterion. Under scenario-wise validation, the surrogate model achieved a test-set R² of 0.9995 and an RMSE of 0.0351 °C, indicating accurate approximation of the deterministic simulator response within the bounded parameter space. The surrogate-based global scan identified a favorable operating region near a well spacing of 462 m, a reinjection temperature of 20 °C, and a reinjection rate of 150 m³/h. To evaluate whether this result was affected by sparse well-spacing sampling, additional COMSOL simulations were performed at 430, 440, 450, 460, 462, 470, 480, 490, and 500 m under the same reinjection temperature and rate. These simulator-based validation cases showed a continuous thermal response with increasing well spacing. The 2.0 °C thermal breakthrough time increased from 46 yr at 430 m to 61 yr at 500 m, while the 50-year cumulative heat extraction increased from 6594.2 to 6722.9 TJ. The 430 and 440 m cases experienced thermal breakthrough before the 50-year design life, whereas the 450 m case was close to the design boundary. The 460 and 462 m cases did not reach the 2.0 °C decline threshold within the 50-year design life and retained relatively high heat-extraction efficiency per unit well spacing. Therefore, the engineering recommendation is revised from a single precise optimum to a locally validated spacing interval of approximately 460–462 m under the present equivalent-porous-medium assumption. The proposed workflow does not replace hydrothermal simulation; instead, it provides a rapid screening tool that narrows the design space before targeted simulator verification and field calibration. Full article

Accurately mapping surface freshwater bodies (e.g., ponds, reservoirs, and small lakes) is vital for managing insular ecosystems and communities. However, satellite-based extraction in coastal settings is challenged by seawater intrusion, complex topography, and cloud cover. Focusing on bedrock islands outside China’s Pearl River Estuary, this study developed a robust method to address these issues. We used both Gaofen-1 (GF-1) optical and Gaofen-3 (GF-3) Synthetic Aperture Radar (SAR) imagery, supported by field-collected water quality samples from surface freshwater body shorelines for model training and validation. The performance of two index-based methods (the Normalized Difference Water Index, NDWI, and the Normalized Difference Vegetation Index, NDVI), two machine learning algorithms (Random Forest, RF, and Support Vector Machine, SVM), and a U-Net convolutional neural network (U-Net) deep learning model was compared. The U-Net model achieved the highest accuracy, with Area Under the Curve (AUC) values of 0.881 (GF-1) and 0.840 (GF-3). It effectively discriminated freshwater from seawater and mitigated cloud interference, demonstrating superior precision and robustness over traditional methods. This work establishes a high-precision framework for monitoring island freshwater resources, supporting sustainable water management. The proposed framework provides a practical tool for tracking freshwater availability under climate variability and anthropogenic pressures, contributing to the monitoring of Sustainable Development Goal (SDG) indicator 6.3.2 on ambient water quality. Full article

Artificial Neural Networks (ANNs) are a key component of construction research as Construction 4.0 and data-based problem-solving continue to shape the construction industry. In this paper, a Scopus-based bibliometric analysis of ANNs in construction research was conducted from 2015 to 2025. From an initial set of 9149 publications, 3800 English-language publications were identified and analysed using publication, source, country, citation, and keyword mapping techniques in VOSviewer (version 1.6.20). The publications showed a significant increase after 2018, peaking in 2024. China, India, and the US were key players in ANNs in construction research, and key publications focused on optimisation, concrete property prediction, machine learning, and deep learning. Key publications in ANNs in construction came from Construction and Building Materials, IEEE Transactions on Geoscience and Remote Sensing, and Energy. ANNs in construction research are moving towards hybrid, digitally integrated, and data-based applications, although gaps persist in sustainability, social equity, climate resilience, and underrepresented regions. Full article

Reliable age information is needed for fisheries assessment, but conventional otolith reading requires trained readers and considerable time. This study evaluated whether convolutional neural networks could classify reader-assigned age classes of Japanese jack mackerel Trachurus japonicus directly from sagittal otolith images. Otolith images from fish aged 0 to 4 years were used to compare three image-only backbones: Inception v3, Xception, and EfficientNet B4. The models were trained under the same data split, preprocessing, augmentation, and evaluation framework. In Stage 1, Inception v3 showed the highest validation macro F1 score (0.933) and was selected as the image-only baseline. After additional optimization, the selected model reached a validation macro F1 score of 0.944, validation exact accuracy of 0.935, and validation agreement within one age class of 1.000. On the independent test set, the optimized image-only model achieved exact accuracy of 0.866, macro F1 score of 0.873, and agreement within one year of 1.000. These results indicate that otolith images contain useful age-related visual information. Convolutional neural networks may support age class screening in T. japonicus, although they should complement rather than replace expert otolith reading. These findings apply to the initial screening of T. japonicus within the 0 to 4 age range represented in commercial purse seine catches, and performance for ages older than 4 was not evaluated. Full article

Leakage detection in water distribution networks is a core component of smart water management. Addressing the limitations of traditional acoustic detection methods, which heavily rely on manual expertise, and the inadequate feature extraction and low recognition rates for minor leaks of existing deep learning models in complex noise environments, this study proposes a novel hybrid architecture CNN model named Incep-ResNet. The model innovatively integrates multi-scale feature extraction and deep residual learning, incorporating an SE attention mechanism to achieve adaptive recalibration of feature channels. Experimental results demonstrate that the model achieves a leakage identification accuracy of 96.6%, representing improvements of 6.7% and 7% compared to ResNet18 and GoogLeNet, respectively. It exhibits excellent noise resistance and feature extraction capabilities, providing a new technical solution for intelligent leakage detection. Full article

Systematic logistics plays a key role in fostering profitable development in supply chains. An intelligent logistics model can help create a more agile, sustainable, and resilient supply chain. In recent years, several brain-inspired deep learning architectures, such as long short-term memory networks, graph neural networks, and convolutional neural networks, have been introduced for intelligent decision-making tasks. From a biomimetic perspective, these models are inspired by biological information-processing mechanisms. Convolutional neural networks reflect hierarchical procedures similar to those in the visual cortex, graph neural networks mimic communication among biological neurons, and LSTM networks are motivated by short-term and long-term memory mechanisms in the brain. Inspired by these biomimetic computational principles, this study proposes a novel hybrid deep learning strategy composed of LSTM, convolutional layers and GraphSAGE geometric layers for smart supply chain logistics management. This strategy enables leveraging information pertaining to LSTM-based long-term dependencies, convolutional local patterns and graph-related hidden connections of the supply chain dataset for intelligent decision-making. The GraphSAGE framework helps with scalable graph learning, which enhances predictive accuracy in the case of unseen data. The optimizer in the proposed methodology performs sequential optimization using the biomimetic particle swarm optimizer and the Adam approach (PSO-Adam), considering the hybrid cost function. The prediction of logistics parameters is investigated using five datasets, including DataCo, Shipping, Smart Logistics, Hospital Supply Chain, and Pharmaceutical Supply Chain. The average accuracies of 97.8%, 100%, 96.6%, 98.7% and 99.4% are obtained for practical multi-category logistics parameter forecasts. The evaluation metrics for ten logistics predictions confirm the effectiveness of the proposed intelligent logistics model and highlight the potential of biomimetic geometric networks for complex supply chain decision-making. The model is a cost-efficient approach with consideration of the prediction capabilities, helping to reduce the occurrence of logistics risks, increase the productivity of the supply chain and affect the supply chain visibility, customer satisfaction, and industry reputation. Full article

Electric Vehicle Charging Stations (EVCSs) have become increasingly important due to the growing penetration of electric vehicles (EVs) and renewable-based power generation. However, challenges such as fluctuating renewable energy availability, increasing charging demand, power losses, operational cost, and charging delays continue to affect overall grid performance and stability. To address these issues, this study proposes a hybrid Goat Optimization Algorithm–Hierarchical Multi-Granularity Interaction Graph Convolutional Network (GOA–HMGIGCN) framework for intelligent smart grid energy management and EV charging coordination. The proposed framework combines the Goat Optimization Algorithm (GOA) for optimal EVCS placement and charging scheduling with the Hierarchical Multi-Granularity Interaction Graph Convolutional Network (HMGIGCN) for forecasting renewable generation, charging demand, and load variations. The framework was implemented and evaluated in MATLAB/Simulink R2024a using the IEEE 14-bus smart grid test system under varying operating conditions. Simulation results demonstrated that the proposed framework achieved superior performance compared with the Coot Optimization Algorithm–Fractional Backpropagation Physics-Informed Neural Network (COA-FBPINN), Dingo Optimization Algorithm–Convolutional Hypergraph Graph Neural Network (DOA-CHGNN), Self-Feedback Feedforward Artificial Neural Network (SFFANN), Deep Neural Network (DNN), and Golden Jackal Optimization–Attention-Based Probabilistic Convolutional Neural Network (GJO-APCNN) techniques by attaining the lowest operational cost of USD 1561, the highest efficiency of 99.2%, the minimum power loss of 10.6 kW, and the shortest charging time of 32 min. In addition, the proposed framework and overall grid reliability, confirming its effectiveness for intelligent renewable-integrated smart grid applications. Full article