Search Results (1,746)

High-dynamic amusement ride conditions involving impacts, rapid rotations, and abrupt posture changes introduce severe motion artifacts that degrade vital sign quality and destabilize physiological state recognition. This study aims to develop an engineering-ready closed-loop framework for robust passenger monitoring and intelligent diagnosis. A multimodal sensing and modeling pipeline was designed to jointly leverage physiological signals such as heart rate and SpO₂ and kinematic measurements, including acceleration, angular rate, velocity, and attitude. Inertial and PPG signals were preprocessed into supervised samples through wavelet multiresolution denoising and coordinate frame unification, while a strapdown inertial navigation system was used to propagate a 12-channel physical quantity sequence. To ensure interpretability and standards compliance, constraints from GB 8408-2018 were translated into executable threshold rules, enabling standards-driven auto-labeling and rule-based early warning. Building on this foundation, three learning modules were developed: a fusion model for high-dynamic heart rate estimation, a CNN–LSTM dynamic-threshold-enhanced network TAPNet for rapid kinematic anomaly screening, and an attention-augmented hybrid model HS-BANet integrating one-dimensional residual blocks, bidirectional LSTM, and multi-head attention for fine-grained arrhythmia classification. Experimental results demonstrated accurate and consistent heart rate estimation with RMSE of 1.18 bpm on HSSH-I and 1.24 bpm on the independent HSSH-II set, strong agreement with training and testing correlations of 0.9928 and 0.9865, and near-zero bias in Bland–Altman analysis. TAPNet achieved 96.9% validation accuracy and 98.2% test accuracy for kinematic anomaly recognition, maintaining robust generalization under class imbalance. HS-BANet enabled multi-class identification of PVC, PAC, VT, SVT, and AF, achieving an accuracy of 92.37%, an F1-score of 86.87%, a precision of 88.45%, a sensitivity of 88.14%, and a specificity of 89.42%. Overall, the proposed two-stage multimodal closed-loop—fast, interpretable early warning based on physical quantity thresholds followed by fine-grained diagnosis from physiological signals—supports stable feature extraction and reliable decision-making under strong motion artifacts and non-stationary dynamics, balancing responsiveness and diagnostic credibility, while showing potential for practical safety early warning and future deployment-oriented operational support in amusement ride scenarios. 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

A single user-invariant tensor, kinematically impossible for any human finger to produce, bypasses bidirectional long short-term memory (BiLSTM) continuous-authentication defenders with numerically identical structure across four independently trained generators. We arrive at this finding by training generative adversarial networks against BiLSTM defenders on 51 users across three independent random seeds, with the data partition held fixed, to test the prevailing assumption that successful generative attacks must reproduce the victim’s kinematic behavior. Aggregate attack success rate varies from 31.4% to 45.1% across seeds, a 13.7 percentage-point spread arising purely from optimization stochasticity, demonstrating how unreliable single-seed reporting is as an estimator of the true attack surface. A four-group descriptive stratification shows that 8% of users are attacked across all three seeds, 31% are consistently safe, and 61% exhibit seed-dependent outcomes. Classifier accuracy on zero-effort impostors does not predict adversarial vulnerability (Spearman $\rho =-0.058$, permutation $p=0.688$), whereas intra-user behavioral variance does ($\rho =+0.351$, permutation $p=0.012$, Bonferroni-corrected). The mechanism is not behavioral emulation but convergence to an Adversarial Skeleton Key, a tensor located in an unregularized region of the BiLSTM’s decision surface that the network reliably maps to acceptance, despite lying many standard deviations outside any genuine human distribution. The mimicry-centric evaluation paradigm underestimates the real threat surface. Input-space plausibility must be treated as a defensive layer rather than a preprocessing concern. Full article

To address the insufficient accuracy of short-term load forecasting caused by the strong randomness of distributed energy output, variable electricity consumption patterns, and complex meteorological factors, this study proposes a load forecasting method that integrates K-means scene clustering and a Transformer–BiGRU–Attention (CTBA) hybrid deep learning architecture. Different from conventional Transformer–BiGRU hybrid forecasters that train a single global predictor across all operating conditions, the proposed CTBA framework first partitions daily load curves into representative scenes and then routes each sample to a scene-specific Transformer–BiGRU–Attention predictor, thereby reducing distributional heterogeneity before temporal modeling. First, the K-means algorithm is used to perform scene clustering on historical daily load curves, and the optimal number of clusters is selected according to the silhouette coefficient and downstream prediction performance. Subsequently, the CTBA model is trained separately for each clustering subset. The Transformer encoder captures the long-range global dependencies of load sequences through the self-attention mechanism, the BiGRU module extracts local bidirectional temporal fluctuation features, and the Attention mechanism further focuses on key time nodes such as morning and evening peaks while fusing multi-source data including historical load, day-ahead electricity price, and multi-dimensional meteorological factors. Experimental results based on the German ENTSO-E power dataset show that the coefficient of determination R² of the proposed model reaches 0.9893, with MAE, RMSE, and MAPE as low as 0.0141, 0.0187, and 3.92%, respectively, which are significantly improved compared to benchmark models such as SVR, LSTM, CNN, and TCN-BiGRU. Ablation experiments further demonstrate that removing the clustering, Transformer, BiGRU, or attention layer will degrade performance, thus verifying the effectiveness and superiority of the method in short-term load forecasting and providing an accurate solution for the short-term load forecasting of power systems. Full article

Water and sanitation governance sits at the intersection of global development ambitions and highly localized service realities. While SDG6 sets universal targets for clean water and sanitation, the institutional and fiscal arrangements that translate those targets into actual service outcomes operate primarily at the subnational level. The discrepancy between globally defined objectives and locally executed delivery creates a structural research gap: how do the fiscal architectures of local governments influence progress towards SDG6? This study addresses this question for a panel of OECD countries by developing a deep learning-based estimation framework that combines bidirectional long short-term memory (BiLSTM) networks with Tianji’s horse racing optimization (THRO) algorithm. Three distinct operationalizations of fiscal decentralization are tested against SDG6 outcomes: subnational expenditure share (EFDM), subnational revenue share (RFDM), and a composite index balancing both dimensions (CFDM). Model adequacy is assessed using a layered diagnostic protocol involving regression fit, country-level residual patterns, error density profiles, Bland–Altman limits of agreement and inter-annual error trajectories. Among the three configurations, CFDM consistently records superior performance ($R^2=0.9216$; $RMSE = 1.4465$; $MAE = 1.0712$), while even the weakest specification clears $R^2=0.89$, attesting to the overall robustness of the proposed architecture. The margin by which CFDM outperforms its alternatives highlights a key finding: neither spending authority nor revenue capacity alone accurately reflects the fiscal reality of local water and sanitation governance; it is their combined effect that is important. The expenditure dimension is further proven to be the more influential of the two unidimensional proxies, consistent with the capital-intensive and maintenance-heavy nature of water infrastructure. On the other hand, coefficient findings show that fiscal decentralization is positively associated with SDG6 achievement for all models. Beyond its empirical contributions, the study introduces a methodological template for applying hybrid AI optimization to policy-relevant sustainability panels. It also connects two largely parallel bodies of scholarship, fiscal federalism and SDG research, that have rarely been examined together. Full article

Accurate rainfall monitoring is vital for hydrology and environmental sensing. This study presents a physics-aware deep learning framework using E-band (71–86 GHz) commercial microwave links (CMLs). Using the extensive urban CML dataset and methodology, a bi-directional Long Short-Term Memory (Bi-LSTM) model is developed to classify wet and dry periods under a temporal generalization framework across heterogeneous link configurations. The approach integrates physical signal decomposition, including baseline estimation, gaseous attenuation correction, and wet antenna attenuation (WAA) modeling, with sequence-based learning. Results demonstrate that the temporal deep learning model outperforms classical threshold-based and physical k–R approaches when evaluated over independent temporal validation blocks, effectively reducing sensitivity to path-length-related variability on heterogeneous paths. The model maintains stable performance (loss < 3%) under moderate signal-level noise. SHapley Additive exPlanations (SHAP) confirm the model relies on physical features, such as signal volatility and temporal trends, to reliably differentiate rainfall from WAA. This framework highlights the potential of E-band infrastructure as a distributed sensing network for integrated sensing and communication (ISAC) architectures. Full article

Teacher professional development (TPD) is increasingly mediated by online platforms, yet emotion analysis in this context remains underdeveloped because teachers’ professional discourse is often reflective, evaluative, and shaped by professional norms. To address this challenge, this study proposes a fine-grained, low-intrusion affective-appraisal analysis framework for TPD-oriented online professional learning that integrates textual evidence with platform interaction logs. The framework retains pleasure, arousal, and dominance from the pleasure–arousal–dominance (PAD) model and introduces utility as an appraisal-related dimension, capturing teachers’ perceived usefulness, value judgment, and professional learning gain. Methodologically, it combines textual representations based on Bidirectional Encoder Representations from Transformers (BERT), intra-week long short-term memory (LSTM) aggregation, interpretable behavioral-log features, and feature-level fusion. Data were collected from an authentic TPD-oriented online course involving 107 pre-service teachers, yielding 1276 teacher-week samples from 4300 texts and 264,028 interaction records. Results show that intra-week sequential modeling improves the macro-averaged F1 score (Macro-F1) over both the term frequency–inverse document frequency plus support vector machine (TF-IDF+SVM) baseline and BERT-based weekly text concatenation, with statistically significant gains over the non-sequential BERT-concat model across all four dimensions. Adding interaction logs improves accuracy across all dimensions and provides complementary process-based evidence, especially for arousal and utility. By linking a four-dimensional affective-appraisal framework with text-log fusion, this study offers a scalable and context-sensitive approach to affective-appraisal analytics in pre-service teacher professional learning. Full article

Modern distribution networks undergo frequent topology reconfiguration, volatile bi-directional flows, and noisy measurements, making five-class line-loss anomaly classification both valuable and challenging. In this study, PC-LossGNN is proposed—a physics-consistent spatiotemporal graph neural network for edge-level classification into Normal, Infrastructure, Documentation, Metering, and Theft. A static topology prior is fused with a measurement-adaptive graph and confidence-aware multi-source features; power-flow physics is injected via residual-guided attention using active/reactive balance, voltage-drop, and ohmic-loss residuals. A dual-path decoder is employed to yield calibrated probabilities and interpretable class evidence, trained under an uncertainty-weighted curriculum objective. On six months of real utility data, macro-F1 of 0.8503 and accuracy of 0.9915 are achieved, surpassing XGBoost, LSTM, GCN, STGCN, and two recent physics-aware spatiotemporal GNN baselines including ST-RGNN and PA-STGCN. Ablation indicates that physics-consistent regularization is pivotal, while adaptive topology and interactive temporal encoding further improve performance. Robustness tests with injected Gaussian noise show more graceful degradation than baselines. These results suggest that PC-LossGNN provides accurate, physically plausible, and interpretable five-way line-loss diagnostics suitable for real-world operations. Full article

Aero-engine predictive maintenance is challenged by heterogeneous operating conditions, complex degradation patterns, and the need for interpretable maintenance alerts rather than solely numerical life estimates. This study investigates a condition-aware data-driven framework for jet engine health assessment using the NASA C-MAPSS dataset, which contains four benchmark subsets (FD001–FD004) with different operating conditions and fault modes. Instead of formulating the task as conventional remaining useful life regression, this study reformulates degradation assessment as a three-class health state classification problem, including Normal, Warning, and Fault. A unified preprocessing pipeline is developed, incorporating condition-wise normalization, first-order differential feature construction, and per-unit sliding window segmentation to reduce operating-condition bias, capture degradation dynamics, and prevent data leakage. Five representative models are evaluated under the same framework, including XGBoost, LightGBM, Random Forest, a context-aware multi-scale temporal attention convolutional neural network, and a bidirectional long short-term memory network. The results show that the proposed framework achieves consistently high classification accuracy across all four subsets, with the best results of 0.9841 on FD001, 0.9764 on FD002, 0.9891 on FD003, and 0.9832 on FD004. In addition, Bi-LSTM outperforms MSTA-CNN on all subsets, for example improving accuracy from 0.9614 to 0.9747 on FD002 and from 0.9773 to 0.9806 on FD004, which is consistent with the importance of long-term temporal dependency modeling for this task. These findings suggest that the proposed framework provides an effective and maintenance-decision-aligned solution for C-MAPSS-based health monitoring, where the three-class alert output offers clearer operational meaning than a single numerical life estimate. Full article

Fault detection and diagnosis of three-phase inverter-fed motor drives is essential for ensuring system reliability, safety, and continuous operation in applications such as electric vehicles and industrial automation. This paper proposes a data-driven fault detection framework based on normalized current features and a lightweight bidirectional long short-term memory (BiLSTM) network which can be generalized to different motor power rating in the same controller system. A compact set of six time-domain features, consisting of the mean and root-mean-square (RMS) values of the phase currents, is extracted and normalized with respect to the average RMS value. This normalization effectively removes dependency on operating conditions, enabling the model to generalize across different load levels and motor power ratings without retraining. A lightweight BiLSTM architecture is employed, reducing computational complexity while maintaining high diagnostic performance. The proposed method is validated under various operating conditions, including different speeds, load variations, motor power ratings, and noisy conditions. The results demonstrate an overall classification accuracy of 99.65%, with reliable fault detection achieved within less than half of a fundamental cycle. The proposed approach provides an efficient, robust, and scalable solution for inverter fault detection and diagnosis, offering strong potential for practical deployment in modern motor drive systems. Full article

Multimodal sentiment analysis (MSA) has become a key research area in artificial intelligence, aiming to predict sentiment polarity or intensity by jointly modeling text, audio, and visual information. However, traditional methods still face significant challenges due to inherent heterogeneity among modalities, semantic representation discrepancies, and insufficient cross-modal interaction. To address these issues, this paper proposes a multimodal sentiment classification model that integrates bidirectional cross-modal attention with multi-level constraint optimization. Specifically, a unified multimodal feature encoding (UMFE) module combining BiLSTM and transformer architectures is first constructed to jointly model and extract robust unimodal representations from text, audio, and visual modalities, thereby enhancing both robustness and discriminative ability. On this basis, we introduce a bidirectional cross-modal attention mechanism, which performs Query–Key attention between modalities, enabling each modality to selectively aggregate complementary information and capture cross-modal semantic dependencies. Furthermore, a cross-modal re-fusion transformer (HMRT) module treats the textual modality as dominant to guide the deep fusion of high-level semantic features after cross-modal interaction, producing a compact unified representation. Finally, a multi-task joint optimization framework with uncertainty-based adaptive weighting dynamically balances unimodal supervision loss, cross-modal consistency loss, and sentiment classification loss, which helps improve representation learning and generalization ability. Full article

Wireless Body Area Networks (WBANs) have become an essential component of modern Internet of Medical Things (IoMT) healthcare systems, enabling continuous monitoring of patient physiological signals through wearable sensors. Despite their advantages, WBAN environments remain highly prone to cyber threats, privacy breaches, and single points of failure. To address these risks, this work proposes a Hybrid Multi-Metric Anomaly Detection (HM-MAD) framework deployed on the NodeMCU-32S platform with BLE 5.0 connectivity for secure continuous glucose monitoring (CGM) data transmission. The detection model simultaneously analyses physiological signals, system-level parameters, and network-level communication metrics, enabling the reliable identification of multiple cyberattacks. The proposed system focuses on securing data transmission against relay attacks, where attackers induce communication delay without modifying payloads, potentially leading to false glucose readings, improper insulin dosage delivery, unauthorized control or denial-of-service. The Convolutional Neural Network (CNN) and Bi-Directional Long Short Term Memory (BiLSTM) model classifies attack types including timing manipulation, replay attacks, power glitches, firmware tampering, and sensor spoofing. Experimental evaluation demonstrates that the proposed CNN + BiLSTM framework achieves 94.6% detection accuracy with an average inference latency of 15 ms, representing a 50% latency reduction compared to Transformer-based intrusion detection models (30 ms), while simultaneously reducing computational overhead by 28% in terms of floating-point operations and memory utilization. These results indicate that the HM-MAD framework provides an effective and scalable solution for protecting resource-constrained IoMT healthcare systems against emerging cyber threats. Full article

Single-lead electrocardiogram (ECG) is widely used in wearable devices for atrial fibrillation (AF) screening. Nevertheless, subtle pathological characteristics like P-waves and f-waves in practical signals are vulnerable to noise contamination. Meanwhile, the scarcity of high-quality annotated abnormal data instances leads to severe class imbalance. To mitigate these issues, we present an end-to-end framework designed for arrhythmia diagnosis using single-lead ECG signals, which integrates quality-aware data augmentation with a Peak-Enhanced attention mechanism. First, to mitigate the problem of data imbalance, a Quality-Aware Generative Adversarial Network (QA-GAN) is designed. This network integrates a signal quality evaluation module based on signal kurtosis, together with a dynamic soft-label training scheme, guiding the generator to prioritize learning high-quality morphological features, thereby synthesizing high-fidelity minority class samples. Second, to accurately capture subtle pathological features in electrocardiograms, a Peak-Enhanced Attention Convolutional Network (PEAC-Net) classification model is proposed. This model incorporates a Peak-Enhanced Attention (PE-Att) module, which employs learnable derivative convolutional kernels to precisely identify the transition points in the ECG signal. Furthermore, by integrating one-dimensional multi-scale dilated convolution (DSGC1D) with bidirectional LSTM, the model achieves effective capturing of both fine-grained local morphological features and long-range global rhythm patterns. Experimental results on the PhysioNet 2017 dataset indicate that the presented model attains an accuracy of 0.902 and a macro-F1 score of 0.880, respectively, outperforming other state-of-the-art models and also exhibiting robust data adaptability on the MIT-BIH dataset. Full article

With the goal of achieving more accurate wind power predictions by accounting for meteorological influences comprising wind speed, together with wind direction and air pressure, this thesis proposes a method combining fuzzy C-means (FCM) clustering with a TCN–Transformer hybrid model. After preprocessing the data to remove outage and missing records, we apply the Pearson correlation coefficient to identify average wind speed and wind direction that are suitable to serve as input features for the model, together with the atmospheric pressure, as key input features. FCM clustering is then applied to partition the data into low- and high-wind-speed operating conditions, mitigating the accuracy loss caused by uniform modeling. A TCN–Transformer model is subsequently constructed, integrating local temporal feature extraction with global dependency modeling to perform prediction under each condition. The experimental results demonstrate that the proposed FCM–TCN–Transformer framework consistently achieves superior forecasting performance under both low-wind-speed and high-wind-speed conditions. Compared with benchmark models, including TCN, LSTM, GRU, BiGRU, and Transformer, the proposed method achieves lower prediction errors and higher prediction accuracy across different forecasting horizons. Furthermore, repeated experiments with multiple random seeds verify the robustness and stability of the proposed framework. These results indicate that FCM-based wind regime classification effectively reduces data heterogeneity, while the hybrid TCN–Transformer architecture successfully captures both local temporal patterns and long-range temporal dependencies. Therefore, the proposed framework provides an effective and reliable solution for short-term wind power forecasting and contributes to the secure integration of wind energy into modern power systems. Full article

The integration of wind energy into power systems relies on forecasting technologies to address operational challenges caused by its volatility and intermittency. This paper proposes a computing architecture for ultra-short-term wind power forecasting. The methodology integrates an adaptive dual-stage signal processing technique with an optimized deep learning model. To manage the non-stationarity of meteorological variables, the Pearson and Maximal Information Coefficient (MIC) analyses are employed for feature selection. The ICEEMDAN algorithm is then used for initial decomposition, followed by sample entropy and K-Means clustering to assess component complexity. Variational Mode Decomposition (VMD) is applied only to the high-frequency component to further separate stochastic fluctuations while preserving relatively stable trend components. A Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) network is constructed to forecast the resulting multi-scale components. To reduce reliance on manual empirical tuning, the Crested Porcupine Optimizer (CPO) is used to fine-tune key network hyperparameters. Evaluations using operational wind-farm data indicate that the developed hybrid method captures the temporal dynamics of wind power and yields lower prediction errors than the tested benchmark models. This research provides a data-driven computing framework for renewable-energy forecasting and related operational analysis. Full article