Search Results (10,050)

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

With the acceleration of urbanization, public transit systems face prominent challenges, including insufficient passenger flow prediction accuracy and low scheduling efficiency. This study analyzes passenger flow variation patterns from both spatial and temporal dimensions, constructs spatiotemporal matrices, and employs matrix dimensionality reduction methods to extract key features. We propose a passenger flow prediction model based on GCN-AM-LSTM and a dynamic real-time intelligent scheduling strategy. For passenger flow prediction, the model first utilizes Graph Convolutional Networks (GCNs) to extract spatial features of the transit network, then employs Attention Mechanism-enhanced Long Short-Term Memory networks (AM-LSTM) to perform weighted extraction of temporal features, and finally integrates external factors such as weather conditions to generate prediction outputs. For scheduling optimization, a dynamic real-time scheduling mode is adopted: the foundational framework optimizes dynamic departure timetables using a multi-objective particle swarm optimization algorithm, which is then combined with real-time passenger flow data to adjust departure intervals at the route level and implement stop-skipping strategies at the station level. Validation was conducted using Xiamen BRT Line 1 as a case study. Experimental results demonstrate that the proposed GCN-AM-LSTM prediction model reduces Mean Absolute Error (MAE) by 14% and 22% compared to CNN and LSTM models, respectively, achieving significantly improved prediction accuracy. Regarding scheduling optimization, the number of departures decreased by 15.24%, passenger waiting time costs were reduced by 3.7%, and transit operating costs decreased by 3.19%, effectively balancing service quality and operational efficiency. Full article

Clouds are a key factor affecting solar radiation, and their dynamic variations directly cause uncertainty and fluctuations in photovoltaic (PV) power output. To improve PV power prediction accuracy, this paper proposes an enhanced short-term photovoltaic power forecasting approach based on a hybrid neural network architecture using features extracted from satellite cloud images. First, a dual-layer image fusion method is developed for satellite cloud images from different wavelengths and spectral bands, effectively improving fusion accuracy. Second, texture descriptors derived from the Gray-Level Co-occurrence Matrix and multiscale information obtained via the wavelet transform are employed for feature extraction from fused images. Combined with a residual network (ResNet), an optical flow method, as well as an LSTM-based temporal modeling module, multidimensional features of the predicted cloud images are obtained. An improved Bayesian optimization (IBO) algorithm is then employed to derive the optimal fused features, thereby improving the matching between cloud image features and PV power. Third, an enhanced hybrid architecture integrating a convolutional neural network and long short-term memory units with a multi-head self-attention mechanism is developed. Numerical weather prediction (NWP) meteorological features are incorporated, and a tilted irradiance model is introduced to calculate the solar irradiance received by PV modules for use in near-term photovoltaic power forecasting. Finally, measurements collected at a photovoltaic power plant located in Hebei Province are used to validate the proposed method. The results show that, relative to the SA-CNN-MSA-LSTM and BO-CNN-LSTM models, the developed approach lowers the RMSE to an extent of 22.56% and 4.32%, while decreasing the MAE by 24.84% and 5.91%, respectively. Overall, the proposed model accurately captures the characteristics of predicted cloud images and effectively improves PV power prediction accuracy. Full article

Dengue is a mosquito-borne viral disease which is predominantly endemic in tropical and subtropical countries. In Bangladesh, 321,179 dengue cases were reported in 2023, followed by 101,214 cases in 2024, which highlights a severe and ongoing public health challenge. Dengue transmission risks are shaped by climatic variability, rapid urbanization, socio-economic vulnerability, and healthcare strain. But existing dengue surveillance models remain limited in their ability to capture district-level disparities in Bangladesh. This study aimed to develop a district-level dengue early warning system that integrates climatic, socio-demographic, economic, healthcare, and environmental determinants to generate accurate and interpretable predictions. We examined dengue cases across all 64 districts in Bangladesh from 2017 to 2024, integrating Directorate General of Health Services (DGHS) case records with climate, socio-demographic, economic, and healthcare indicators. Machine learning and deep learning approaches, including Multi-Layer Perceptron (MLP) and Convolutional Long Short-Term Memory (ConvLSTM), were combined with SHAP (Shapley Additive Explanations)-based explainable artificial intelligence. We also used Bayesian spatio-temporal models to capture spatial clustering, temporal dependence, and the lagged transmission effects of dengue. Dengue outbreaks peaked in September 2023, with Dhaka recording 113,233 cases. DENV-4 (Dengue Virus type 4) emerged in 2022, accounting for 27% of infections in 2023. Climate was the strongest predictor of dengue transmission (humidity SHAP = 0.314; minimum temperature SHAP = 0.146; rainfall RR = 1.303). Poverty (SHAP = 0.193) and healthcare capacity (nursing/midwifery density SHAP = 0.073) mostly contributed to dengue prediction. The MLP model achieved the best yearly performance (accuracy = 0.93; ROC-AUC = 0.99), ConvLSTM was the best model in monthly prediction (recall = 0.88; ROC-AUC = 0.81), and Bayesian BYM2_RW2 with lagged effects improved predictive fit (DIC = 3671.055). Our integrated framework delivers transparent, interpretable predictions and district-level early warnings, supporting adaptive dengue outbreak preparedness and resource allocation in Bangladesh. Full article

While walking robots possess significantpotential for various real-world applications, the reliance on high-performance sensors and complex control architectures for precise gait control remains a significant barrier to commercialization and lightweight design. To overcome these engineering limitations and lay the groundwork for a sensing paradigm adaptable to complex terrains, this study proposes an AI-based sensorless feedback control framework that incorporates the biological principles of proprioception. To this end, a walking robot leveraging the morphological intelligence of the Klann linkage was developed. We constructed a time-series dataset by defining motor current signals as ‘interoceptive sensing’ information—analogous to biological muscle feedback—and synchronizing them with absolute angular data. This dataset was used to train an Attention-LSTM (A-LSTM) model, which predicts future motor states in real-time by decoding nonlinear physical information embedded within internal current data, independent of external environmental sensors. By integrating the proposed model into a PI controller, a stable biomimetic walking loop was successfully implemented without the need for additional position sensors. Full article

A persistent challenge for Deaf and Hard-of-Hearing individuals is the communication gap between sign language users and the hearing community, particularly in regions with limited automated translation resources. In Saudi Arabia, this gap is amplified by the reliance on Saudi Sign Language (SSL) and the scarcity of real-time, sentence-level translation systems. This paper presents a real-time system for sentence-level recognition of continuous SSL and direct mapping to natural spoken Arabic. The proposed system operates end-to-end on live video streams or pre-recorded content, extracting spatio-temporal landmark features using the MediaPipe Holistic framework. For classification, the input feature vector consists of 225 features derived from hand and body pose landmarks. These features are processed by a Bidirectional Long Short-Term Memory (BiLSTM) network trained on the ArabSign (ArSL) dataset to perform direct sentence-level classification over a vocabulary of 50 continuous Arabic sign language sentences, supported by an idle-based segmentation mechanism that enables natural, uninterrupted signing. Experimental evaluation demonstrates robust generalization: under a Leave-One-Signer-Out (LOSO) cross-validation protocol, the model attains a mean sentence-level accuracy of 94.2%, outperforming the fixed signer-independent split baseline of 92.07%, while maintaining real-time performance suitable for interactive use. To enhance linguistic fluency, an optional post-recognition refinement stage is incorporated using a large language model (LLM), followed by text-to-speech synthesis to produce audible Arabic output; this refinement operates strictly as post-processing and is not included in the reported recognition accuracy metrics. The results demonstrate that direct sentence-level modeling, combined with landmark-based feature extraction and real-time segmentation, provides an effective and practical solution for continuous SSL sentence recognition in real-time. Full article

Industrial robots are widely used in critical tasks such as assembly, welding, and material handling as core components of modern manufacturing systems. For the reliable operation of these systems, early and accurate detection of execution failures is crucial. In this study, a comprehensive comparison of machine learning and deep learning methods is conducted for the classification of robot execution failures using data acquired from force–torque sensors. Three different feature engineering approaches are proposed. The first is a Baseline approach that includes 90 raw time-series features. The second is the Domain-6 approach, which consists of 6 basic statistical features per sensor (36 in total). The third is the Domain-12 approach, which comprises 12 comprehensive statistical features per sensor (72 in total). The domain features include the mean, standard deviation, minimum, maximum, range, slope, median, skewness, kurtosis, RMS, energy, and IQR. In total, ten classification algorithms are evaluated, including eight machine learning methods and two deep learning models: Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbors (KNN), Artificial Neural Network (ANN), Naive Bayes (NB), Decision Trees (DT), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM-LGBM), as well as a One-Dimensional Convolutional Neural Network (CNN-1D) and Long Short-Term Memory (LSTM). For traditional machine learning algorithms, 5 × 5 nested cross-validation is used, whereas for deep learning models, 5-fold cross-validation with a 20% validation split is employed. To ensure statistical reliability, all experiments are repeated over 30 independent runs. The experimental results demonstrate that feature engineering has a decisive impact on classification performance. In addition, regardless of the feature set, the highest accuracy (93.85% ± 0.90) is achieved by the Naive Bayes classifier using the Baseline features. The Domain-12 feature set provides consistent improvements across many algorithms, with substantial performance gains. The results are reported using accuracy, precision, recall, and F1-score metrics and are supported by confusion matrices. Finally, permutation feature importance analysis indicates that the skewness features of the Fx and Fy sensors are the most critical variables for failure detection. Overall, these findings show that time-domain statistical features offer an effective approach for robot failure classification. Full article

Against the backdrop of sustainable development and global climate governance, this study focuses on the evaluation and trend prediction of provincial carbon emission efficiency and constructs a multi-model integrated analytical framework featuring “data preprocessing—efficiency decomposition—dynamic forecasting—policy deduction”. First, economic, energy consumption and carbon emission data for 30 provinces in China from 2009 to 2019 are collected. Data cleaning is performed through outlier identification and Lagrange interpolation, and a cross-regionally comparable quantification system is established based on a unified carbon emission standard, laying a foundation for subsequent analysis. Second, data envelopment analysis (DEA) is adopted to decompose carbon emission efficiency. It is found that approximately 23% of provinces lie on the technical efficiency frontier, with the average variance share of technical inefficiency being 0.62; 6% of provinces have the potential for scale expansion; and 10% suffer from diseconomies of scale, reflecting significant structural efficiency losses in regions concentrated with high-carbon industries. Third, the long short-term memory (LSTM) neural network is employed for dynamic forecasting and scenario simulation of carbon emissions by 2025. The model’s prediction error in 2019 is controlled within 8.7%. Simulation results show that when the share of clean energy rises to 35%, China’s national carbon emission growth rate can be reduced to 1.2% by 2025. However, multi-scenario sensitivity analysis indicates that the achievement of this target highly depends on policy enforcement intensity and power grid accommodation capacity. In addition, stochastic frontier analysis (SFA) reveals the heterogeneous contributions of different energy types to economic and social outputs. The consumption elasticities of electricity, liquefied petroleum gas and gasoline are significantly positive, whereas the negative elasticities of oil, fuel oil and coal deeply reflect the low energy utilization efficiency and rigid lock-in of high-carbon industries in some regions. Finally, combined with efficiency evaluation, trend prediction and mechanism analysis, differentiated emission reduction strategies are proposed for technologically backward provinces, scale-imbalanced provinces and clean energy base provinces, forming a complete closed loop from “efficiency diagnosis” to “future deduction” and then to “policy feedback”. This study breaks through the limitations of a single model. Through the coupling of parametric and non-parametric methods, as well as the integration of dynamic forecasting and scenario simulation, it effectively addresses issues such as data heterogeneity. It provides scientific support for local governments to formulate emission reduction policies and optimize energy structures, establishes a methodological foundation for industrial efficiency analysis and international carbon responsibility allocation research, and helps to promote regional clean, low-carbon, and sustainable development. Full article

Cross-subject emotion recognition using EEG remains challenging due to substantial inter-individual variability. To address this, we propose a Multi-scale Spatio-Temporal Convolution and Multi-order Gated Spatial-Channel Aggregation Network (MCF-SCA). The model leverages multi-scale spatio-temporal convolution to capture rich temporal and spatial features and applies Fast Fourier Transform to transform EEG signals into the frequency domain, enhancing emotion-related representations. A multi-order spatial-channel aggregation module is then introduced, which adaptively integrates features across spatial and channel dimensions through a gating mechanism, enabling dynamic feature weighting and more expressive emotional representations. Experiments on the DEAP dataset show accuracy gains of up to 11–30% for arousal and 12–31% for valence compared with TSception, CNN, LSTM, EEGNet, and MLP. On the DREAMER dataset, improvements reach 5–33% and 3.7–34%, respectively. These results confirm that MCF-SCA achieves superior accuracy and cross-subject adaptability, providing strong support for emotion-based brain–computer interface applications. Full article

Background: Amid rising trade, urbanization, and carbon emissions in MENA countries, sustainable logistics faces major constraints. This study develops an enhanced Green Logistics Performance Index (GLPI) using min-max normalization and Principal Component Analysis (PCA) to integrate the World Bank’s Logistics Performance Index (LPI) and Yale’s Environmental Performance Index (EPI). The study uses fixed-effects panel regression on data from 20 MENA countries (2018–2024), identifies key drivers, and applies ARIMA and LSTM models for 2030 projections. The prior ratio-based GLPI suffered from scale sensitivity and volatility; this refined version provides improved stability and predictive utility for Green Supply Chain Management (GSCM). Methods: Panel data from 20 MENA countries (2018–2024) were analyzed. The enhanced GLPI normalizes and weights LPI and EPI scores via PCA. Fixed-effects regression identifies drivers, while ARIMA and LSTM enable scenario-based forecasting (baseline, optimistic, and pessimistic). Results: Renewable energy share positively influences GLPI, while trade openness has a negative effect. Projections indicate the regional GLPI will reach about 0.65 by 2030, with Saudi Arabia potentially achieving 25% higher under optimistic conditions. Conclusions: The refined GLPI advances GSCM theory by operationalizing triple bottom line trade-offs through a robust, predictive metric. It bridges descriptive limitations in prior literature, enabling forward-looking insights into sustainable logistics in emerging economies, with potential applicability beyond MENA. Full article

Timely and accurate detection of sow oestrus is crucial for enhancing reproductive efficiency and reducing non-productive days (NPDs) in large-scale pig farms. However, traditional manual observation is labour-intensive and subjective, while cloud-based deep learning solutions face challenges such as high latency and privacy risks when applied in intensive housing environments. This study developed an edge-intelligent monitoring system that integrates deep temporal modelling with sound source localisation technology. A three-stage hierarchical screening strategy was utilised to select and deploy a lightweight Stacked-LSTM model on the resource-constrained ESP32-S3 hardware platform. This model was trained and calibrated using a high-quality acoustic dataset validated against serum reproductive hormones, specifically follicle-stimulating hormone (FSH), luteinising hormone (LH), and progesterone ($P_4$). Experimental results demonstrate that the optimised model achieved a classification accuracy of 96.17%, with an inference latency of only 41 ms, thereby fully satisfying the stringent real-time monitoring requirements while maintaining a minimal memory footprint. Furthermore, the system integrates a localisation algorithm based on Generalised Cross-Correlation with Phase Transform (GCC-PHAT). Through spatial geometric modelling, the system successfully implements the functional mapping of vocalisation events to individual gestation stalls (Stall IDs). Laboratory pressure tests validated the robustness and low-cost deployment advantages of the “edge recognition–cloud synchronization” architecture, providing a reliable technical framework for the precision management of smart livestock farming. Full article

A primary bottleneck in deploying Fiber Bragg Grating (FBG) sensors lies in their inherent dual sensitivity to thermal and mechanical variations, which mandates robust decoupling mechanisms for precise parameter extraction. To address this persistent cross-sensitivity issue, this study introduces a novel interrogation scheme that integrates a Convolutional Neural Network with a Bidirectional Long Short-Term Memory (CNN-BiLSTM) architecture. Instead of relying on conventional peak-tracking algorithms or isolated central wavelengths, our proposed data-driven strategy directly mines structural features from the full reflection spectra, thereby substantially mitigating cross-interference errors. The experimental results reveal that the coefficients of determination (R²) for strain and temperature prediction reach 99.37% and 99.75% each, while the root mean square errors (RMSEs) are 13.51 µε and 1.42 °C, respectively. The proposed method requires only a single FBG sensor, which reduces the sensor requirements, showing great potential in sensing applications requiring low costs and high adaptability. In addition, in some special environments, temperature information cannot be obtained, so we utilize another reference FBG to realize the temperature compensation. Meanwhile, we proposed a spectral differencing method (SDM) by differencing the spectra of the two FBGs to obtain the spectra containing only strain information and sent them as a dataset for model training, with a 4-times improvement in accuracy over traditional compensation methods. Finally, we also explored the application of the system for distributed FBGs, achieving an absolute peak wavelength interrogation precision of approximately ±0.02 nm. The system is expected to be applied in the field of structural health monitoring, which is promising even in harsh environments. Full article

This study introduces a new method for predicting carbon emissions from campus buildings, which is crucial to achieving low-carbon campuses in higher education and meeting “Carbon Peaking and Carbon Neutrality Goals”. The method begins with manually classifying buildings and introducing a carbon emission correlation factor, linking each building type’s emissions to the total category emissions. Using this factor, three models—Seasonal Autoregressive Integrated Moving Average (SARIMA), Long Short-Term Memory (LSTM), and Random Forest (RF)—were developed to predict emissions. The results show improved accuracy after adding the correlation factor: 17.23%, 6.159%, and 3.949% for the SARIMA model in Categories A, B, and C, respectively; 2.76%, 12.636%, and 3.370% for LSTM; and 3.61%, 10.893%, and 4.776% for Random Forest. These results demonstrate the value of using carbon emission correlation factors to improve prediction accuracy and promote sustainable campus development. Full article

The integration of distributed photovoltaics (PV) introduces time-varying electrical coupling in active distribution networks, limiting the efficacy of conventional forecasting methods that rely on incomplete topological information and static physical models. This paper proposes a physics-informed spatio-temporal graph attention network (PI-STGAT) for probabilistic load forecasting under highly fluctuating conditions. A condition-adaptive correlation blending mechanism, derived from voltage–power sensitivity principles, fuses physical priors with statistical correlations using a PV-weighted strategy to capture time-varying electrical connectivity. An impedance-weighted continuous physical gating architecture maps voltage correlation coefficients into continuous attention biases, reflecting the spatial continuity of electrical distances while suppressing long-range noise. An uncertainty-aware adaptive physical constraint strategy dynamically modulates physical loss weights based on prediction variance and PV penetration, balancing fitting accuracy against physical consistency. Validation on real-world distribution network data demonstrates that, over a 24 h day-ahead horizon, PI-STGAT achieves a MAPE of 5.50%, a 3.7% relative reduction compared with LSTM. The model further attains a prediction interval coverage probability of 97.9%, confirming reliable uncertainty estimates under complex conditions. Full article

The emergence of the Internet of Things (IoT) has introduced major security challenges. Deep learning models have shown strong potential for intrusion detection. However, they often require large datasets and high computational resources. In contrast, IoT environments are resource-constrained and lack sufficient labeled data. This paper proposes a lightweight intrusion detection approach based on Long Short-Term Memory (LSTM) networks and homogeneous transfer deep learning. The model is first trained on a subset of the BoT-IoT dataset as a source domain. It is then fine-tuned on a disjoint subset containing a rare attack type. This setup represents adaptation to unseen attack behaviors within the same environment. By freezing earlier layers and fine-tuning only the final layers, the method reduces training overhead while preserving performance. This is important to meet the IoT requirement for frequent, lightweight model updates on resource-constrained devices. The proposed model achieved 99.9% accuracy, a macro F1-score of 0.96, and a 47.8% reduction in training time compared to training from scratch. Extensive experiments confirm that it maintains balanced detection across both common and rare classes. Full article