Search Results (1,245)

Aiming at the issues of low recognition accuracy and high model computational complexity for power quality disturbances (PQDs) in strong-noise environments, this paper proposes a novel lightweight PQD-recognition method that integrates a hybrid architecture of variational mode decomposition (VMD), convolutional neural network (CNN), and transformer. Firstly, a hybrid optimization algorithm named the monkey–genetic hybrid optimization algorithm (MGHOA) is proposed to optimize VMD parameters for denoising disturbance signals, thereby enhancing recognition accuracy in noisy environments. Secondly, to fully extract disturbance signal features and reduce the computational complexity of the model, a lightweight CNN–transformer model is designed. Depthwise separable convolution (DSC) is employed to extract local features and the multi-head attention mechanism of transformer is utilized to mine the long-distance dependence and global features, thereby enhancing the feature representation. Thirdly, a multitask joint-learning method is proposed to collaboratively optimize classification accuracy and temporal localization tasks, enhancing the discrimination of similar disturbances. Additionally, a dual-pooling global feature fusion strategy is designed to further enhance the model’s ability to discriminate complex disturbances. Comparative experiments on 16 typical PQD types demonstrate that the proposed method achieves excellent performance in recognition accuracy, model robustness, and computational efficiency. The integration of the MGHOA–VMD module improves recognition accuracy by 1.08%, while the multitask joint-learning method contributes an additional 0.55% improvement. When achieving recognition accuracy comparable to complex models, the training time of the proposed method is 36.51% of that required by DeepCNN and merely 5.90% of that required by bidirectional long short-term memory (BiLSTM), with a 31.22% reduction in parameter scale. This work provides a novel solution for intelligent power quality disturbance recognition. Full article

This study proposes a robust data-driven control framework, LSTM-MPC, designed to enhance the velocity stabilization of Autonomous Underwater Vehicles (AUVs) operating under stochastic marine disturbances. Traditional control methods often struggle with the highly nonlinear and time-varying hydrodynamics of irregular waves. To address this, we employ a Long Short-Term Memory (LSTM) recurrent neural network to capture complex temporal dependencies and provide accurate multi-step-ahead velocity predictions. These predictions are integrated into a Model Predictive Control (MPC) scheme, which optimizes control actions while respecting actuator constraints. A key contribution is the integration of an error-triggered online learning mechanism. Utilizing run-time weight synchronization via MATLAB Coder, the framework dynamically adapts to plant mismatches and high-frequency MEMS noise without an explicit analytical model. The architecture was validated using experimental data from a Pixhawk/ArduSub baseline. Results demonstrate that, under these stochastic conditions, the data-driven approach significantly outperforms the standard PID-based baseline. While adaptive PID variants offer improvements, the suggested framework drastically reduces tracking errors in rotational axes while maintaining high precision in translational velocities. This research confirms that adaptive, data-driven strategies can effectively bridge the gap between simulation and real-world deployment, offering a scalable solution for robust AUV autonomy in unpredictable environments. Full article

Arrhythmia is a common and potentially life-threatening cardiovascular condition. Photoplethysmography (PPG) has emerged as a noninvasive alternative to electrocardiography for cardiac rhythm monitoring, yet most PPG-based methods remain limited to binary classification. In this study, a new deep learning approach is suggested for categorizing six arrhythmia types from PPG data: sinus rhythm (SR), premature ventricular contraction (PVC), premature atrial contraction (PAC), ventricular tachycardia (VT), supraventricular tachycardia (SVT), and atrial fibrillation (AF). The raw PPG signal is enhanced by extracting its first and second derivatives to capture morphological features not readily apparent in the original signal. A hybrid architecture, VGG-BiLSTM, is utilized, merging VGG convolutional layers for spatial features extraction with bidirectional long short-term memory layers for modeling temporal dependencies. A stratified data splitting strategy is further adopted to address class imbalance across arrhythmia types. A publicly available dataset containing 46,827 PPG segments from 91 individuals was employed to assess the effectiveness of the suggested technique. The method yielded an overall accuracy, sensitivity, specificity and F1 score of 88.7%, 78.5%, 97.6% and 80.5% correspondingly. Full article

The integration of Selective Laser Melting (SLM) into high-end manufacturing necessitates robust machine-condition monitoring and subsystem fault classification to navigate the intricate coupling and dynamic transients inherent in these systems. Current diagnostic frameworks often struggle to decouple high-dimensional state variables or track their underlying temporal evolution. To overcome these bottlenecks, this paper develops a spatiotemporal deep learning architecture by coupling Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) units. This hybrid approach leverages CNNs to distill multi-dimensional spatial features from subsystem sensor arrays, while LSTMs interpret the sequential dependencies critical for identifying systemic drifts. The proposed framework was validated using an extensive industrial dataset comprising over 310,000 temporal samples across seven critical SLM subsystems, including optical, cooling, and energy units. We systematically investigated three data-handling strategies—feature weighting, balancing, and distribution-based synthesis—to optimize the model’s sensitivity to rare-event anomalies. Benchmarking across six architectural variants reveals that a specific CNN × 3 + LSTM × 1 configuration yields superior diagnostic fidelity, achieving a classification accuracy of 98.81%. Visualization of the feature space confirms high inter-class separability, demonstrating the model’s ability to isolate faults within complex manufacturing cycles. This research offers a scalable paradigm for the intelligent monitoring of SLM equipment and provides a technical benchmark for equipment health management and predictive maintenance in advanced additive manufacturing. Full article

Quantitative trading systems require predictive models that simultaneously deliver accurate forecasts, calibrated uncertainty quantification, and actionable risk measures. This paper proposes an information-theoretic semiparametric regression framework combining a convolutional neural network–Transformer (CNN–Transformer) network for nonlinear temporal dependencies with a Gaussian process (GP) prior for residual autocorrelation and calibrated predictive distributions. Three theoretical results are established: an identifiability theorem guarantees joint recoverability of the nonparametric and GP components; a consistency theorem showing that the penalised maximum likelihood estimator converges at a rate $n^{-1/(2+d_{\mathrm{eff}})}$; and a coverage theorem proving asymptotic nominal coverage of the GP’s credible intervals. The framework enables an entropy-regulated trading module where predictive differential entropy informs position sizing via an uncertainty-penalised Kelly criterion, Kullback–Leibler divergence quantifies model uncertainty, and CVaR-constrained optimisation controls the tail risk. Simulations show the method outperforms the CNN, long short-term memory (LSTM), Transformer, XGBoost, random forest, least absolute shrinkage and selection operator (LASSO), and standard GP regression approaches. Backtesting on four Chinese A-share stocks yielded annualised returns of 15.9–22.4% with Sharpe ratios of 0.49–0.62, maximum drawdowns below 15%, and daily 95% CVaR reductions of 28–31% relative to a full-Kelly baseline, confirming both predictive accuracy and risk management effectiveness. Full article

This paper proposes a hybrid PINN + LSTM framework for the high-precision solution of malware propagation dynamics in wireless sensor networks. A seven-compartment SVEHLQR model is developed to capture this complex transmission process. To overcome the limitations of standard physics-informed neural networks (PINNs) in long-term prediction, including gradient vanishing and error accumulation, we integrate LSTM’s temporal memory capability into the PINN architecture. Comprehensive comparisons are conducted among the proposed PINN + LSTM, standard PINN, and Fourier PINN, using the fourth-order Runge–Kutta method as the benchmark. Experimental results demonstrate that PINN + LSTM significantly outperforms both baseline methods, achieving an average relative error of $3.88\times {10}^{-3}$ compared to $7.20\times {10}^{-2}$ for PINN and $2.81\times {10}^{-1}$ for Fourier PINN, representing a 94.6% accuracy improvement over PINN. These results validate that incorporating LSTM’s recursive memory mechanism enables the accurate and efficient solution of complex time-dependent dynamical systems. Additionally, the model’s robustness is verified under 1%, 5%, and 10% Gaussian noise. PINN + LSTM maintains extremely low relative errors, not exceeding 0.0049, and outperforms PINN and Fourier PINN significantly, confirming its strong noise immunity and stable dynamics learning ability in realistic environments. Full article

Reliable short-term prediction of bus travel time on signalized urban arterials is essential for improving service reliability and may provide a useful forecasting basis for prediction-informed transit signal priority (TSP) and arterial coordination applications. However, bus operations on urban arterials are highly variable due to stop dwell times, signal delays, and interactions with mixed traffic, leading to nonlinear and nonstationary travel time patterns with strong spatiotemporal dependence. This study proposes a hybrid KNN–ConvLSTM framework for short-term arterial bus travel time prediction using real-world field data. A K-nearest neighbors (KNNs) module is first employed to retrieve historical operation sequences that are most similar to the current corridor state, thereby reducing interference from mismatched traffic regimes and improving robustness. Smart-card (IC card) transaction data are incorporated as demand-related features to represent passenger activity and its impact on dwell time and travel time variability. The selected sequences are then organized into a corridor-ordered spatiotemporal representation and further refined by lightweight temporal enhancement operations, including relevance gating, multi-scale aggregation, adaptive feature fusion, and residual enhancement, before being fed into the convolutional long short-term memory (ConvLSTM) predictor. The proposed approach is evaluated using weekday service-hour data extracted from 30 days of real-world bus operation records collected from a typical urban arterial corridor in Changchun, China, and is compared with several benchmark models, including ARIMA, KNN, LSTM, CNN, ConvLSTM, Transformer, and DCRNN. The results indicate that the proposed KNN–ConvLSTM framework achieves an MAE of 40.1 s, an RMSE of 55.8 s, a SMAPE of 10.7%, and an R² of 0.878, outperforming all benchmark models. Specifically, compared with the Transformer baseline, the proposed framework reduces MAE by 1.5%, RMSE by 5.1%, and SMAPE by 7.0%, while increasing R² by 0.014. Compared with the DCRNN baseline, it reduces MAE by 10.7%, RMSE by 1.9%, and SMAPE by 2.7%, while increasing R² by 0.008. These findings demonstrate that similarity-aware retrieval combined with spatiotemporal deep learning can substantially enhance short-term bus travel time prediction on signalized urban arterials. More accurate short-term forecasts may support prediction-informed transit signal priority and arterial coordination by providing more reliable downstream arrival-time estimates. However, the generalizability of the reported results is still constrained by the relatively short 30-day observation period and the single-corridor case setting, and the operational and environmental effects of downstream applications remain to be validated through dedicated closed-loop control evaluation in future work. Full article

With the increasing demand for sleep health monitoring, automatic sleep staging using single-channel electroencephalogram (EEG) signals has become increasingly prominent due to its clinical practicality. Existing methods have achieved notable progress, but they often fail to adequately capture long-term temporal dependencies and struggle to characterize transition phases. We propose SleepLT, an automated sleep staging framework that integrates multi-scale wavelet decomposition (MWD) and multi-head latent Fourier attention (MLFA). The MLFA module incorporates Fourier analysis into self-attention mechanisms and employs a partially weight-sharing bottleneck to optimize Key/Value generation, effectively capturing sleep rhythms. Extensive experiments on SleepEDF-78 and SHHS datasets demonstrate strong and consistent performance, with Macro F1 improvements of 2.1–3.2% over the compared baselines. Visualizations confirm that SleepLT enhances inter-class discriminability between sleep stages, robustly detects salient waveforms, and effectively captures transitions through long-sequence modeling. These results indicate that SleepLT is effective for automatic sleep staging from single-channel EEG, particularly in improving the recognition of ambiguous transitional stages such as N1 and REM. Full article

Soil salinization constrains the sustainability of irrigated oasis agriculture in arid regions. Using repeated post-harvest monitoring of 125 fixed cropland sites in Bachu County, southern Xinjiang, from 2018 to 2021, this study investigated the short-term spatiotemporal variability of topsoil total salt content (TSC) and pH. Descriptive statistics, one-way ANOVA with Tukey’s HSD test, Universal Kriging interpolation, class-transition analysis, hotspot recurrence, centroid migration, and principal component analysis were used to characterize temporal variation, spatial structure, and environmental gradient associations. TSC showed a mitigation–rebound sequence, decreasing to 4.88 ± 5.21 g kg⁻¹ in 2020 and increasing to 6.90 ± 5.93 g kg⁻¹ in 2021, whereas pH increased first and then declined. Salinity remained consistently concentrated in downstream cropland, while pH showed weaker and more year-dependent zonal differentiation. Class-transition analysis revealed marked salinity reorganization in 2021, mainly driven by conversion from lower-salinity classes to moderately and severely saline classes. Severe-salinity hotspots were temporally intermittent but spatially recurrent in the downstream zone, whereas high-pH hotspots were short-lived and mainly confined to the upstream zone. PCA further showed that TSC and pH were aligned with different environmental gradient combinations. Overall, the four-year sequence should be interpreted as short-term interannual variability rather than a robust long-term sequence. These results indicate that TSC and pH should not be treated as interchangeable indicators in oasis cropland assessment, and they provide a transferable basis for zone-specific salinity monitoring and management, with priority given to persistent downstream sink areas. Full article

Cardiovascular diseases are the primary causes of mortality worldwide, often characterized by subtle onset and acute progression. Traditional ECG electrodes may cause skin irritation, limiting routine monitoring and early risk assessment. Relying on the advantages of non-contact monitoring, millimeter-wave radar-based cardiac monitoring combined with deep learning has become a popular research direction recently. To overcome the poor generalization of methods trained from single-source datasets, this study designed seven experimental scenarios covering wakefulness and sleep. A novel deep learning network consisting of encoder and decoder structures named PMG-SATNet was proposed. The encoder comprises a parallel multi-scale feature extraction module and a global temporal relationship modeling module to capture fine-grained local patterns and long-range dependencies. The decoder employs a temporal convolutional network augmented with a spectral attention mechanism to emphasize clinically relevant ECG frequency bands and suppress respiration and body motion interference. After being validated on the self-built dataset, PMG-SATNet outperformed baseline models in terms of Pearson correlation coefficient and root mean square error, with an improvement of 3.3% and 3.8%, and 16.4% and 23.8%, respectively. The validation results imply that PMG-SATNet is capable of recovering ECG signals from millimeter-wave radar-derived chest vibrations with high fidelity and can potentially be implemented in real-life cardiac health monitoring. Full article

Accurate prediction of effluent water quality is essential for the intelligent and sustainable operation of wastewater treatment plants (WWTPs). However, this task remains challenging due to the strong nonlinearity, long-term temporal dependencies, and severe fluctuations inherent in influent characteristics. In this study, a novel data-driven framework termed the Multi-Scale Temporal Representation-Enhanced Informer (MTRE-Informer), is proposed to predict key effluent quality indicators, including total nitrogen (TN), total phosphorus (TP), and chemical oxygen demand (COD). To ensure data quality and computational efficiency, a generative recurrent learning framework is first employed for anomaly detection and correction, followed by variance inflation factor (VIF)-based feature selection to mitigate multicollinearity. Furthermore, feature contribution analysis is conducted to improve model interpretability. Subsequently, the core MTRE-Informer architecture utilizes hierarchical multi-scale temporal representation learning to simultaneously capture local patterns and long-term dependencies within the complex dynamics of the wastewater treatment process. Experimental results demonstrate that the MTRE-Informer achieves robust and stable predictive performance across diverse operational datasets. For TN prediction, the proposed framework attains a coefficient of determination () of 0.9637 and a mean absolute percentage error (MAPE) of 3.39%. Compared with baseline approaches, the improvement ranges from 3.8% to 14.2%, validating its superior capability. To further enhance model robustness, an anomaly detection and correction strategy based on a generative recurrent learning framework is employed. In addition, feature contribution analysis and VIF-based feature selection are conducted to improve interpretability, mitigate multicollinearity, and enhance computational efficiency. Overall, this framework provides a reliable and practical solution for real-time effluent quality prediction, facilitating the intelligent management of WWTPs. Full article

Breast-conserving therapy, consisting of lumpectomy followed by adjuvant radiotherapy, is the standard of care for early-stage breast cancer, providing oncologic outcomes equivalent to mastectomy while preserving breast anatomy and quality of life. Radiotherapy remains a cornerstone of treatment across disease stages, significantly reducing local recurrence rates and improving long-term survival. Advances in radiotherapy techniques—including conventional fractionation, hypofractionation, tumor-bed boost delivery, and regional nodal irradiation—have optimized oncologic efficacy while inducing a broad spectrum of time-dependent morphological changes in breast tissue. Accurate imaging surveillance is therefore essential to distinguish expected post-radiotherapy changes from tumor recurrence and to avoid unnecessary diagnostic or therapeutic interventions. This review provides a comprehensive overview of contemporary breast radiotherapy protocols, their impact on post-treatment imaging appearances, and current recommendations for imaging surveillance. Characteristic findings across mammography, ultrasound, magnetic resonance imaging, and nuclear medicine modalities are discussed, with emphasis on their temporal evolution from acute inflammatory changes to chronic fibrosis, fat necrosis, and architectural distortion. Recognition of these imaging patterns, together with integration of radiotherapy-related parameters into image interpretation, is crucial for accurate diagnosis, early detection of recurrence, and informed clinical management of breast cancer survivors. Full article

Early detection is a key tool for mitigating the devastating effects of wildfires. Single-frame detection methods that do not consider inter-frame dependencies often fail to detect smoke plumes at the earliest stage and at greater distances, or produce excessive false alarms. Biological vision is particularly sensitive to motion cues, and this translates well to automated systems. Recent temporal-memory approaches have demonstrated improved performance over purely spatial methods, but typically rely on complex, computationally heavy multi-stage architectures. This study investigates the possibility of encoding temporal and contextual information into additional image channels as a basis for compiling data models with increased information content. Seven distinct data models were proposed, and corresponding datasets were generated to train standard YOLO architectures without modifications to the network structure. The datasets were compiled from real wildfire footage collected from an operational wildfire surveillance system in Croatia, comprising 333 annotated sequences of real fires recorded between 2018 and 2024. Experimental evaluation compared the performance of YOLO models trained on the information-enriched datasets with those trained on standard RGB images. Based on the results, the best data model for early wildfire smoke detection, combining original RGB channels with short-term and long-term temporal memory, was selected. Comparative evaluation demonstrated improved detection accuracy, achieving up to 5 percent higher true-positive detection rate for models trained on spatio-temporal data compared to standard RGB images, while maintaining low inference latency. The proposed approach shifts the focus to the structure and information content of the data while preserving the efficiency of standard convolutional neural network architectures. This approach could be applied to other problems requiring high efficiency and real-time operation, where temporal and contextual information can improve detection performance. Full article

The extensive deployment of automatic water quality monitoring stations has generated substantial volumes of time-series data. Effectively utilizing these data is crucial for enhancing prediction accuracy. To address the limitations of existing models in capturing complex inter-indicator relationships and multi-scale temporal features, this paper proposes a hybrid prediction model integrating time series decomposition with deep learning techniques. Adopting a “decomposition–prediction–reconstruction” paradigm, the model first decomposes the raw time series into trend, seasonal, and residual components using STL (Seasonal–Trend decomposition using LOESS). For the trend component, an improved Graph Convolutional Network (GCN) is designed to explicitly model the spatial dependencies among different water quality indicators. For the seasonal component, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method is employed for multi-scale signal analysis, followed by a coupled Long Short-Term Memory–Convolutional Neural Network (LSTM-CNN) unit to capture both long-term dependencies and local features. To validate the efficacy of the proposed model, experiments were conducted on three real-world water quality datasets from different watersheds. Experimental results demonstrate that the proposed model outperforms mainstream baseline models, including StemGCN, LSTM-CNN, CEEMDAN-LSTM-CNN, and Attention-CLX. Across the three datasets, the model consistently outperforms the best-performing baseline, achieving reductions in MAE ranging from 13.8% to 24.5% and up to a 45.3% reduction in RMSE on a single dataset, while the highest correlation coefficient between predicted and observed values reaches 0.855. These findings demonstrate that the proposed decomposition–integration framework effectively enhances the accuracy and stability of multivariate water quality prediction, offering a promising tool for supporting sustainable water resource management. Full article

Understanding the spatiotemporal formation mechanisms of built cultural heritage is essential to interpreting regional cultural landscapes and informing differentiated conservation strategies. Using Fujian Province, China, as a representative mountain–sea transitional region, this study constructs a province-scale, multi-category, and dynamically oriented analytical framework to investigate the temporal evolution, spatial structure, and driving mechanisms of immovable cultural relics. Based on a georeferenced dataset of 940 immovable cultural relics, textual historical records were standardized into continuous temporal variables and integrated with GIS-based kernel density estimation, spatial autocorrelation analysis, distance-to-coast modeling, and category co-occurrence analysis. The results reveal a pronounced temporal concentration in the Ming–Qing and modern periods, with a primary formation peak during the Qing Dynasty and a secondary peak in the early 20th century driven by modern heritage. Spatially, relics exhibit significant positive spatial autocorrelation (Global Moran’s I = 0.375, p < 0.001) and form a structured dual-core pattern, consisting of a persistent coastal heritage belt and a distinct inland modern core centered in western Fujian. More than 75% of relics are located within 110 km of the coastline, confirming strong maritime orientation, while regression analysis reveals that this inland shift is primarily driven by the Modern Era rather than representing a continuous long-term trend. Category-level correlation analysis further demonstrates a clear spatial decoupling between traditional heritage and modern sites, indicating fundamentally different locational logics. Synthesizing these findings, this study proposes a dual-core driven model under a mountain–sea geographical framework, in which a path-dependent, economically reinforced coastal core coexists with a historically contingent, politically driven inland core. The results advance quantitative understanding of how multiple cultural logics, operating across different temporal scales, jointly shape complex regional heritage systems and provide a transferable framework for heritage analysis and spatially differentiated conservation planning. Full article