Search Results (137)

To address the limitations of traditional tourism demand forecasting models in leveraging multi-source data and their lack of interpretability, this study proposes an integrated multi-data-driven interpretable forecasting framework incorporating historical visitor volumes, social media activities, holiday schedules, weather conditions, and seasonal indicators. This study develops a system-oriented tourism demand forecasting framework that integrates a Variable Selection Network (VSN) and an enhanced long short-term memory (xLSTM) architecture to jointly model and interpret multi-source demand drivers. The VSN module employs a dynamic feature weighting mechanism to automatically discern distribution characteristics and relevance variations across heterogeneous data sources, thereby assigning adaptive weights to input variables. The xLSTM model incorporates innovative exponential gating and matrix memory structures, enabling rapid adaptation to sudden tourist flow fluctuations while effectively capturing long-term cyclical dependencies. By combining VSN-derived feature importance weights with SHAP-based prediction attribution analysis, this framework offers dual-level interpretability—in both input feature selection and output explanation. Experimental results demonstrate that social media data significantly reflect tourist attention and travel intention and reveal distinctive demand-driving mechanisms for various types of tourism destinations. The study provides theoretical insights and empirical support for advancing tourism demand forecasting and management strategies. Full article

Background: Dental disorders, such as cavities, periodontal disease, and periapical infections, remain major global health issues, often resulting in pain, tooth loss, and systemic complications if not identified early. Traditional diagnostic methods rely heavily on visual inspection and manual interpretation of panoramic X-ray images by dental professionals, making them time-consuming, subjective, and less accessible in resource-limited settings. Objectives: Accurate and timely diagnosis is vital for effective treatment and prevention of disease progression, reducing healthcare costs and patient discomfort. Recent advances in deep learning (DL) have demonstrated remarkable potential to automate and improve the precision of dental diagnostics by objectively analyzing panoramic, periapical, and bitewing X-rays. Methods: In this research, a hybrid feature-fusion framework is proposed. It integrates handcrafted Histogram of Oriented Gradients (HOG) features with deep representations from DenseNet-201 and the Shifted Window (Swin) Transformer models. Sequential dependencies among the fused features were learned utilizing the Long Short-Term Memory (LSTM) classifier. The framework was evaluated on the Dental Radiography Analysis and Diagnosis (DRAD) dataset following preprocessing steps, including resizing, normalization, Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement, and image cropping. Results: The proposed LSTM-based hybrid model achieved 96.47% accuracy, 91.76% specificity, 94.92% precision, 91.76% recall, and 93.14% F1-score. Conclusions: The proposed framework offers flexibility, interpretability, and strong empirical performance, making it suitable for various image-based recognition applications and serving as a reproducible framework for future research on hybrid feature fusion and sequence-based classification. Full article

Automatic sleep staging technology based on wearable photoplethysmography can provide a non-invasive and continuous solution for large-scale sleep health monitoring. This study accordingly developed a novel cross-scale dynamically coupled extended long short-term memory network (SleepXLSTM) to realize automatic sleep staging based on heart rate signals collected by wearable devices. SleepXLSTM models the relationship between heart rate fluctuations and sleep stage labels by correlating physiological features with clinical semantics using a knowledge graph neural network. Furthermore, an excitation–inhibition dual-effect regulator is applied in an improved multiplicative long short-term memory network along with memory mixing in a scalar long short-term memory network to extract and strengthen the key heart rate timing features while filtering out noise produced by motion artifacts, thereby facilitating subsequent high-precision sleep staging. The benefits and functions of this comprehensive heart rate feature extraction were demonstrated using sleep staging prediction and ablation experiments. The proposed model exhibited a superior accuracy of 91.25% and Cohen’s kappa coefficient of 0.876 compared to an extant state-of-the-art neural network sleep staging model with an accuracy of 69.80% and kappa coefficient of 0.040. On the ISRUC-Sleep dataset, the model achieved an accuracy of 87.51% and F1 score of 0.8760. The dynamic coupling strategy employed by SleepXLSTM for automatic sleep staging using the heterogeneous temporal representation of heart rate data can promote the development of smart wearable devices to provide early warning of sleep disorders and realize cost-effective technical support for sleep health management. Full article

To address the issues of insensitivity to high-impedance ground faults and difficulty in identifying reflected wavefronts in single-ended traveling-wave fault location methods for asymmetric ground faults in high-voltage AC transmission lines, this paper proposes a single-ended fault location method based on the modal amplitude ratio and deep learning. First, based on the dispersion characteristics of traveling waves, an approximate formula is derived between the fault distance and the amplitude ratio of the sum of the initial transient voltage traveling-wave 1-mode and 2-mode to 0-mode at the measurement point. Simulation verifies that the fault distance x from the measurement point at the line head is unaffected by transition resistance and fault inception angle, and that a nonlinear positive correlation exists between the distance x and the modal amplitude ratio. The multi-scale wavelet modal maximum ratio of the sum of 1-mode and 2-mode to 0-mode is used to characterize the amplitude ratio. This ratio serves as the input for a Residual Bidirectional Long Short-Term Memory (BiLSTM) network, which is optimized using the Dung Beetle Optimizer (DBO). The DBO-Res-BiLSTM model fits the nonlinear mapping between the fault distance x and the amplitude ratio. Simulation results demonstrate that the proposed method achieves high location accuracy. Furthermore, it remains robust against variations in fault type, location, transition resistance, and inception angle. Full article

The stock market is of paramount importance to economic development. Investors who accurately predict stock price fluctuations based on its high volatility can effectively mitigate investment risks and achieve higher returns. Traditional time series models face limitations when dealing with long sequences and short-term volatility issues, often yielding unsatisfactory predictive outcomes. This paper proposes a novel algorithm, MSNet, which integrates a Multi-scale Channel Attention mechanism (MSCA) and Sparse Perturbation Greedy Optimization (SPGO) onto an xLSTM framework. The MSCA enhances the model’s spatio-temporal information modeling capabilities, effectively preserving key price features within stock data. Meanwhile, SPGO improves the exploration of optimal solutions during training, thereby strengthening the model’s generalization stability against short-term market fluctuations. Experimental results demonstrate that MSNet achieves an MSE of 0.0093 and an MAE of 0.0152 on our proprietary dataset. This approach effectively extracts temporal features from complex stock market data, providing empirical insights and guidance for time series forecasting. Full article

Accurately estimating the absolute position of robots under external loads is challenging due to nonlinear dynamics, posture-dependent manipulability, and structural sensitivities. This study investigates a data-driven approach for absolute position prediction of a 2-DOF planar delta robot by learning time-series force signals generated during manipulability-driven free motion. Constant torques of opposite directions were applied to the robot without any position or trajectory control, allowing the mechanism to move naturally according to its configuration-dependent manipulability. Reaction forces measured at the end-effector and relative encoder variations were collected across a grid of workspace locations and used to construct a 12-channel time-series input. A hybrid deep learning architecture combining 1D convolutional layers and a bidirectional LSTM network was trained to regress the robot’s absolute X–Y position. Experimental results demonstrate that the predicted trajectories closely match the measured paths in the workspace, yielding overall RMSE values of 3.81 mm(X) and 2.94 mm(Y). Statistical evaluation using RMSE shows that approximately 83.73% of all test sequences achieve an error below 5 mm. The findings confirm that LSTM models can effectively learn posture-dependent dynamic behavior and force-manipulability relationships. Full article

To enhance the monitoring and conservation efforts for China’s Class II endangered species, specifically the wild giant salamander and its ecosystems, this study addresses the urgent need to counteract the rapid decline of its wild population caused by habitat loss and insufficient surveillance. We present an innovative localization system based on passive Ultra-High-Frequency Radio Frequency Identification (UHF RFID) technology, employing a Double-Transform (D-Tr) methodology that integrates an enhanced 3D LANDMARC algorithm with GAIN generative adversarial networks. This system effectively reconstructs missing Received Signal Strength Indicator (RSSI) data due to environmental barriers by applying a log-distance path loss model. The D-Tr framework simultaneously generates RSSI sequences alongside their first-order differential characteristics, allowing for a comprehensive analysis of spatiotemporal signal relationships. Field tests conducted in the Hubei Xianfeng Zhongjian River Giant Salamander National Nature Reserve reveal that the positioning error consistently remains within 10 cm, with average accuracy improvements of 20.075%, 15.331%, and 12.925% along the X, Y, and Z axes, respectively, compared to traditional time-series models such as long short-term memory (LSTM) and gated recurrent unit (GRU). This system, designed to investigate the behavioral patterns and movement paths of farmed giant salamanders, achieves centimeter-level tracking of their cave-dwelling activities. It provides essential technical support for quantitatively assessing their daily activity patterns, habitat choices, and population trends, thereby promoting a shift from passive oversight to proactive monitoring in the conservation of endangered species. Full article

Cough sounds are a key acoustic indicator for detecting respiratory diseases in laying hens, which have become increasingly prevalent with the intensification of poultry housing systems. As an important early signal, cough sounds play a vital role in disease prevention and precision health management through timely recognition and spatial localization. In this study, an improved BiLSTM–TDOA method was proposed for the accurate recognition and localization of laying hen cough sounds. Nighttime audio data were collected and preprocessed to extract 81 acoustic features, including formant parameters, MFCC, LPCC, and their first and second derivatives. These features were then input into a BiLSTM-Attention model, which achieved a precision of 97.50%, a recall of 90.70%, and an F1-score of 0.9398. An improved TDOA algorithm was then applied for three-dimensional sound source localization, which resulted in mean absolute errors of 0.1453 m, 0.1952 m, and 0.1975 m along the X, Y, and Z axes across 31 positions. The results demonstrated that the proposed method enabled accurate recognition and 3D localization of abnormal vocalizations in laying hens, which will provide a novel approach for early detection, precise control, and intelligent health monitoring of respiratory diseases in poultry houses. Full article

The proliferation of terrestrial and space-based communication systems introduces significant radio frequency interference (RFI), which severely compromises data acquisition for radio telescopes, necessitating robust and dynamic scheduling solutions. This study addresses this challenge by implementing a Deep Recurrent Reinforcement Learning (DRL) framework for the control and dynamic scheduling of the X-Y pedestal-mounted KMITL radio telescope, explicitly trained for RFI avoidance. The methodology involved developing a custom simulation environment with a domain-specific Convolutional Neural Network (CNN) feature extractor and a Long Short-Term Memory (LSTM) network to model temporal dynamics and long-horizon planning. Comparative evaluation demonstrated that the recurrent DRL agent achieved a mean effective survey coverage of 475 deg²/h, representing a 72.7% superiority over the non-recurrent baseline, and maintained exceptional stability with only 1.0% degradation in median coverage during real-world deployment. The DRL framework offers a highly reliable and adaptive solution for telescope scheduling that is capable of maintaining survey efficiency while proactively managing dynamic RFI sources. Full article

The gearbox is a core component of drilling rigs, valued for its high efficiency and load capacity. However, prolonged operation under heavy loads makes it prone to wear and failure. Complicating diagnosis, the vibration signals generated are highly complex and nonlinear. To achieve accurate fault diagnosis under varying operating conditions, we propose a novel method named T-DCAx, which integrates a Dual-path Convolutional Attention network, an extended Long Short-Term Memory network (xLSTM), and a Transformer. Our model leverages the complementary strengths of these components: the xLSTM module, enhanced with exponential gating and a novel memory mechanism, excels at modeling long-term temporal dependencies and mitigating gradient vanishing issues. The Transformer module effectively captures global contextual information through self-attention. These are synergized with a dual-path convolutional attention structure to ensure effective joint learning of both local–temporal and global patterns. Finally, a dedicated gearbox test platform was established to collect vibration signals under various conditions and fault types. The proposed T-DCAx method was validated on this dataset and demonstrated superior performance against several benchmark methods in comparative analyses. Full article

Driven by the global energy transition and carbon-neutrality goals, virtual power plants (VPPs) are expected to aggregate distributed energy resources and participate in multiple electricity markets while achieving economic efficiency and low carbon emissions. However, the strong volatility of wind and photovoltaic generation, together with the coupling between electric and thermal loads, makes real-time VPP scheduling challenging. Existing deep reinforcement learning (DRL)-based methods still suffer from limited predictive awareness and insufficient handling of physical and carbon-related constraints. To address these issues, this paper proposes an improved model, termed SAC-LAx, based on the Soft Actor–Critic (SAC) deep reinforcement learning algorithm for intelligent VPP scheduling. The model integrates an Attention–xLSTM prediction module and a Linear Programming (LP) constraint module: the former performs multi-step forecasting of loads and renewable generation to construct an extended state representation, while the latter projects raw DRL actions onto a feasible set that satisfies device operating limits, energy balance, and carbon trading constraints. These two modules work together with the SAC algorithm to form a closed perception–prediction–decision–control loop. A campus integrated-energy virtual power plant is adopted as the case study. The system consists of a gas–steam combined-cycle power plant (CCPP), battery storage, a heat pump, a thermal storage unit, wind turbines, photovoltaic arrays, and a carbon trading mechanism. Comparative simulation results show that, at the forecasting level, the Attention–xLSTM (Ax) module reduces the day-ahead electric load Mean Absolute Percentage Error (${\mathrm{M}}_{\mathrm{A}\mathrm{P}\mathrm{E}}$) from 4.51% and 5.77% obtained by classical Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models to 2.88%, significantly improving prediction accuracy. At the scheduling level, the SAC-LAx model achieves an average reward of approximately 1440 and converges within around 2500 training episodes, outperforming other DRL algorithms such as Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Proximal Policy Optimization (PPO). Under the SAC-LAx framework, the daily net operating cost of the VPP is markedly reduced. With the carbon trading mechanism, the total carbon emission cost decreases by about 49% compared with the no-trading scenario, while electric–thermal power balance is maintained. These results indicate that integrating prediction enhancement and LP-based safety constraints with deep reinforcement learning provides a feasible pathway for low-carbon intelligent scheduling of VPPs. Full article

Long-term time series forecasting (LTSF) remains challenging, as models must capture long-range dependencies and remain robust to noise accumulation. Traditional recurrent models, such as Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM), often suffer from instability and information degradation over extended horizons. The state-of-the-art method xLSTMTime improves memory retention through exponential gating and enhanced memory-transition rules, but it still lacks principled guidance. To address these issues, we propose the Kalman-Optimal Selective Long-Term Memory (KOSLM) model, which embeds a Kalman-optimal selective mechanism driven by the innovation signal within a structured state-space reformulation of LSTM. KOSLM dynamically regulates information propagation and forgetting to minimize state estimation uncertainty, providing both theoretical interpretability and practical efficiency. Extensive experiments across energy, finance, traffic, healthcare, and meteorology datasets show that KOSLM reduces mean squared error (MSE) by 14.3–38.9% compared with state-of-the-art methods, with larger gains at longer horizons. The model is lightweight, scalable, and achieves up to 2.5× speedup over Mamba-2. Beyond benchmarks, KOSLM is further validated on real-world Secondary Surveillance Radar (SSR) tracking under noisy and irregular sampling, demonstrating robust and generalizable long-term forecasting performance. Full article

Rice plays a pivotal role in global food security, particularly for Asian populations. However, its production is significantly threatened by insect pests, with Chilo suppressalis being a major pest in Asian rice-growing regions. Therefore, developing accurate predictive models for C. suppressalis outbreaks is essential. This study presents a novel time series forecasting model (named ESD-TripleStream) for C. suppressalis population dynamics based on a multi-stream structure, which addresses the limitations of existing approaches, which often omit the further decomposability of and the timestamp information in the time series. This model integrates Exponential Smoothing Decomposition (ESD) to separate the trend and seasonal components of time series data, along with a temporal feature stream to form a three-stream network to capture multi-scale periodic patterns and temporal dependencies. For our evaluation, we collected and constructed a novel dataset, referred to as HNRP-6R, which includes rice pest monitoring data from the past two decades (2000–2022) alongside 13 meteorological factors across six key rice producing regions in Hunan Province, southern China. ESD-TripleStream was evaluated across short-term and medium-term C. suppressalis population prediction scales using HNRP-6R, demonstrating state-of-the-art performance. Specifically, in short-term prediction, ESD-TripleStream achieved a 31.8% reduction in Mean Squared Error (MSE) and 26.55% reduction in Mean Absolute Error (MAE) compared to the PatchMLP model, while outperforming the transformer-based TimeXer by 14.43% in MSE and 9.8% in MAE. For medium-term prediction, ESD-TripleStream has both MSE and MAE significantly lower than those of baseline models such as P-sLSTM and xPatch. Furthermore, generalization tests on Nilaparvata lugens (N. lugens) population prediction demonstrated the model’s adaptability to diverse pest dynamics. Full article

Ground-level ozone is a critical secondary air pollutant and greenhouse gas, especially in urban oil and gas regions, where it poses severe public health and environmental risks. Urban areas in North Texas have experienced persistently elevated ozone levels over the past two decades despite emission control efforts, highlighting the need for advanced forecasting tools. This study presents a hybrid recurrent neural network (RNN) model that combines Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) architectures to predict 8 h average ground-level ozone concentrations over a full annual cycle. The model leverages one-hour lagged ozone precursor pollutants (VOC and NO_x) and seven meteorological variables, using a novel framework designed to capture complex temporal dependencies and spatiotemporal variability in environmental data. Trained and validated on multi-year datasets from two distinctly different urban air quality monitoring sites, the model achieved high predictive accuracy (R² ≈ 0.97, IoA > 0.96), outperforming standalone LSTM and Random Forest models by 6–12%. Beyond statistical performance, the model incorporates Shapley Additive exPlanation (SHAP) analysis to provide mechanistic interpretability, revealing the dominant roles of relative humidity, temperature, solar radiation, and precursor concentrations in modulating ozone levels. These findings demonstrate the model’s effectiveness in learning the nonlinear dynamics of ozone formation, outperforming traditional statistical models, and offering a reliable tool for long-term ozone forecasting and regional air quality management. Full article

Background: Deep learning (DL)-based medical image classification is becoming increasingly reliable, enabling physicians to make faster and more accurate decisions in diagnosis and treatment. A plethora of algorithms have been developed to classify and analyze various types of medical images. Among them, Convolutional Neural Networks (CNNs) have proven highly effective, particularly in medical image analysis and disease detection. Methods: To further enhance these capabilities, this research introduces MediVision, a hybrid DL-based model that integrates a vision backbone based on CNNs for feature extraction, capturing detailed patterns and structures essential for precise classification. These features are then processed through Long Short-Term Memory (LSTM), which identifies sequential dependencies to better recognize disease progression. An attention mechanism is then incorporated that selectively focuses on salient features detected by the LSTM, improving the model’s ability to highlight critical abnormalities. Additionally, MediVision utilizes a skip connection, merging attention outputs with LSTM outputs along with Grad-CAM heatmap to visualize the most important regions of the analyzed medical image and further enhance feature representation and classification accuracy. Results: Tested on ten diverse medical image datasets (including, Alzheimer’s disease, breast ultrasound, blood cell, chest X-ray, chest CT scans, diabetic retinopathy, kidney diseases, bone fracture multi-region, retinal OCT, and brain tumor), MediVision consistently achieved classification accuracies above 95%, with a peak of 98%. Conclusions: The proposed MediVision model offers a robust and effective framework for medical image classification, improving interpretability, reliability, and automated disease diagnosis. To support research reproducibility, the codes and datasets used in this study have been publicly made available through an open-access repository. Full article