Search Results (1,992)

Industrial control systems (ICSs) are cyber–physical environments in which physical process data and network communication data are generated simultaneously. Existing studies have mainly focused on either sensor-based or network-based anomaly detection, making it difficult to capture diverse attack indicators and motivating the use of multimodal methods that can leverage complementary information from both modalities. In this paper, we propose an unsupervised multimodal anomaly detection framework for ICSs that jointly uses sensor and network modalities. For each modality, autoencoder-based single-modality models are trained in an unsupervised manner, and their anomaly scores and latent feature vectors are extracted. These outputs are temporally aligned to construct a time-aligned multimodal table, which is then used to implement and compare two fusion strategies: anomaly score fusion and latent feature fusion. In latent feature fusion, aligned modality-specific latent features are combined with canonical correlation analysis (CCA)-derived cross-modal correlation features. The experimental results showed that latent feature fusion achieved stable performance across multiple sensor–network encoder combinations. In particular, the gated recurrent unit–convolutional neural network (GRU–CNN) combination achieved the best F1-score of 0.9166 and ROC-AUC of 0.9795. In addition, the complementarity analysis showed that latent feature fusion recovered some missed detections by integrating complementary sensor and network evidence. These results demonstrate that latent feature fusion is an effective multimodal strategy for ICS anomaly detection. Full article

Rolling bearing fault diagnosis remains challenging due to environmental noise, insufficient information sharing between diagnosis and prediction tasks, and poor model generalization ability. To address these issues, this paper proposes a fault diagnosis and severity prediction method integrating probabilistic principal component analysis (PPCA) and empirical mode decomposition (EMD) with a one-dimensional convolutional neural network (1DCNN) and bidirectional gated recurrent unit (BiGRU). The proposed model consists of two parallel branches for fault diagnosis and fault severity prediction. A self-attention mechanism is integrated into both branches to enhance feature extraction via adaptive feature weighting. In addition, parameter sharing and weighted loss functions are adopted to improve the training efficiency and collaborative learning between the two tasks. PPCA and EMD are employed for signal denoising and reconstruction while preserving fault-related features. Experiments on public datasets and industrial production-line data show that the proposed method improves the fault classification accuracy from 92.43% to 99.71% under different load conditions, while achieving 98.99% accuracy in fault severity prediction. Noise interference tests further demonstrate the effectiveness of the model. A production-line case study further illustrates the feasibility of applying the proposed method to real monitoring signals. These results confirm the effectiveness and practical potential of the proposed method for rolling bearing fault diagnosis and health assessment. Full article

Urban acoustic environments and performing-arts spaces strongly influence speech communication quality, acoustic comfort, and public wellbeing, particularly in noise-exposed shared environments such as transport hubs, campuses, healthcare spaces, public service facilities, music-education settings, and rehearsal or performance-related spaces. To address speech–noise separation in low signal-to-noise ratio and acoustically complex scenarios, this study proposes a lightweight two-stage deep learning framework termed LCGRU–Wave-SkipConvNet. In the preprocessing stage, a Lightweight Convolutional Gated Recurrent Unit (LCGRU) model is employed to achieve preliminary separation of target speech and background noise by capturing both spatial and temporal acoustic features. In the post-processing stage, a Wave-SkipConvNet model is introduced to further suppress residual noise and enhance speech quality. Experimental results demonstrate that the proposed framework achieves superior performance under different signal-to-noise ratios, sound-source angles, and target angle errors. For example, in the preprocessing stage, the LCGRU model achieved a perceptual evaluation of speech quality (PESQ) score of 2.64 at source angles between 0° and 30°, outperforming the convolutional neural network-long short-term memory (CNN-LSTM) model by 1.17. In the post-processing stage, the Wave-SkipConvNet model achieved higher short-time objective intelligibility (STOI) and segmental signal-to-noise ratio (segSNR) values than the comparison models under different SNR conditions. The proposed framework provides an effective and deployment-oriented AI solution for improving speech accessibility and acoustic comfort in urban acoustic environments and performing-arts spaces. Beyond speech enhancement, it offers practical potential for supporting healthier, more inclusive, and more equitable acoustic environments in noise-sensitive public and educational spaces. It should be noted that this study focuses on the objective acoustic environment and signal-level speech enhancement, rather than subjective soundscape perception, musical perception, or human perceptual evaluation. Full article

Accurate forecasting of groundwater level (GWL) fluctuations in drought-prone and data-limited regions remains a major challenge for sustainable groundwater management. The complexity of nonlinear and dynamic groundwater systems, influenced by spatiotemporal variability and limited observational data, further complicates the development of reliable predictive models. Groundwater is a critical resource for irrigation and domestic use in drought-prone northwestern Bangladesh, requiring accurate forecasting of GWL dynamics for sustainable management. To address this challenge, the present study evaluates seven deep learning (DL) approaches: GRU, LSTM, hybrid LSTM–GRU, and their Genetic Algorithm (GA)- and Particle Swarm Optimization (PSO)-variants, using time-series data from nine observation wells. The developed models were benchmarked against the widely used univariate time-series forecasting model, ARIMA. Model performance varied spatially. The GA-LSTM model performed best at Bagha–Arani (R = 0.879, IOA = 0.906, NRMSE = 0.149), while the standalone LSTM achieved superior results at Bagmara–Auchpara (R = 0.940, IOA = 0.958, NRMSE = 0.155). All DL models outperformed the benchmark ARIMA model across all locations. Overall, the best models achieved R = 0.724–0.940, IOA = 0.707–0.958, NRMSE = 0.149–0.285, and MAD = 0.369–1.369 m, indicating strong predictive skill. Optimization (GA, PSO) improved accuracy, particularly for GRU-based models, though LSTM remained competitive in several sites. Hybrid and optimized models required higher computational cost due to iterative tuning but often yielded improved accuracy. A CRITIC–EDAS multi-criteria decision-making framework, based on six statistical metrics, identified no universally superior model; instead, optimal choices varied by location. Selected models successfully forecasted future GWL trends, capturing temporal variability. The integrated modelling–ranking framework provides a robust, scalable approach for groundwater management in data-limited, drought-affected regions. Full article

WiFi channel state information (CSI) has become a compelling sensing modality for contactless human activity recognition. However, differences in datasets, preprocessing protocols and model configurations make consistent comparison and reproducibility challenging. This study presents a unified baseline evaluation of four widely adopted deep learning architectures: multilayer perceptron (MLP), convolutional neural network (CNN), gated recurrent unit (GRU) and a hybrid CNN–GRU model across multiple publicly available CSI datasets encompassing a range of sensing tasks. We harmonize the datasets, implement a standardized preprocessing and training pipeline to reduce experimental inconsistencies and support controlled within-dataset comparisons of model behavior. Evaluations include single-person activity recognition, fall-risk estimation, multiperson occupancy classification and localization-aware activity recognition, representing progressively higher temporal and spatial complexity. Our results show dataset-dependent trends: CNNs provide an efficient accuracy–complexity trade-off in several structured activity scenarios, whereas GRUs are advantageous when temporal dynamics are more prominent, although with greater training and inference costs. In contrast, MLPs generally underperform due to limited capacity to capture spatial and temporal dependencies. Confusion matrix analysis reveals that dynamic behaviors and low-motion states remain challenging to distinguish, underscoring the importance of temporal modeling. By releasing the complete experimental pipeline and benchmarking results, this work establishes a reproducible reference framework for the research community and highlights directions for future investigation, including cross-dataset generalization, hybrid model design and lightweight deployment strategies. Full article

To address the limited adaptability of fixed-parameter PID controllers under dynamically varying reference signals and the strong dependence of data-driven PID methods on training-data quality, this paper proposes a GRU-based online PID gain-scheduling framework supported by high-quality dataset construction. Diverse reference excitations are first designed, and sequential quadratic programming (SQP) is used as an expert label generator to produce trajectory-level PID gain labels. A region-of-interest (ROI)-based dynamic sample selection strategy is then introduced to retain informative transient samples and reduce the dominance of redundant steady-state data. The gated recurrent unit (GRU) network learns a temporal mapping from error-state sequences to PID gains and is deployed online with closed-loop safeguards, including filtered derivative information, gain denormalization, smoothing, and actuator constraints. In a representative nominal neural-controller benchmark, GRU-PID achieves a rise time of 0.59 s, a settling time of 0.97 s, ISE = 2.10, ITAE = 39.35, and TV = 394.48, showing a favourable balance between tracking accuracy and control-signal smoothness. Five-seed tests further indicate that GRU-PID provides stable nominal performance comparable to competitive neural schedulers, while simulation-based robustness evaluations suggest lower tracking errors than the tested neural baselines under measurement noise, step disturbance, actuator saturation, and combined uncertainty scenarios within the considered benchmark setting. Full article

Soluble solids content (SSC) is one of the most important indicators of sweetness, ripeness, and market quality in sweet cherries. However, conventional SSC determination is destructive, labor-intensive, and unsuitable for rapid or large-scale quality assessment. Therefore, there is a need for fast, non-destructive, and data-driven sensing approaches that can estimate internal fruit quality without damaging the sample. This study aimed to develop a non-destructive approach for SSC prediction in sweet cherries by combining open-ended coaxial probe dielectric spectroscopy with deep learning models. An open-ended coaxial probe measurement system was designed and developed to determine the dielectric properties of sweet cherries and was coupled with an Agilent E4991A impedance analyzer operating over a frequency range of 5–3005 MHz. A total of 10,080 dielectric measurements and 2100 reference SSC measurements were collected over 26 experimental days. The dielectric constant (ε′), loss factor (ε″), and loss tangent (tan δ) were extracted and used to construct separate ε′, ε″, tan δ, and integrated combined datasets. Six deep learning architectures, namely convolutional neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU), CNN-LSTM, and convolutional long short-term memory (ConvLSTM), were trained and optimized using Bayesian optimization and early stopping. CNN achieved the best performance on the tan δ dataset (test R² = 0.9099, RMSE = 0.8354 °Brix, MAE = 0.6599 °Brix), whereas GRU yielded the highest accuracy on the integrated combined dataset (test R² = 0.8622, RMSE = 1.0331 °Brix, MAE = 0.7958 °Brix). ConvLSTM provided the most consistent performance across all four datasets (test R² = 0.8081–0.8651), demonstrating strong predictive capability and practical computational efficiency. These findings confirm the potential of reduced-range dielectric spectroscopy combined with deep learning for rapid, non-destructive SSC assessment in sweet cherries. Full article

To solve the low-precision prediction problem of noisy non-stationary goaf subsidence sequences, this study aims to establish a high-accuracy hybrid prediction model for mining surface deformation monitoring. The Global Navigation Satellite System (GNSS) monitoring data of surface subsidence in goaf areas exhibits non-stationary and noisy characteristics, which limits the accuracy of traditional prediction models. In this paper, a hybrid prediction model, namely the Improved Radial Movement Optimization–Variational Mode Decomposition–Gated Recurrent Unit (IRMO-VMD-GRU) model, is proposed. The IRMO algorithm is employed to globally optimize the key parameters of VMD, achieving adaptive and stable decomposition of the settlement sequences. The obtained Intrinsic Mode Function (IMF) sub-sequences are input into the GRU network for independent training and prediction, followed by superposition and reconstruction. The model is validated using the GNSS monitoring data from three monitoring points at a coal mine in Shaanxi Province, China. The results show that the proposed model outperforms the comparison models in all four evaluation indicators, namely Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R²), with all R² values exceeding 0.8. The model demonstrates superior fitting performance, correlation, and generalization ability, which provides important practical technical support for goaf subsidence early warning, geological disaster prevention and engineering safety management in mining areas. Full article

Accurate multi-horizon Significant Wave Height (SWH) forecasting is vital for offshore safety and efficiency. Beyond scheduling maintenance windows, reliable lead-time predictions provide critical early warnings to protect personnel and high-value assets from hazardous high-wave conditions. However, the non-stationary and multi-scale nature of sea states poses challenges for consistent long-term accuracy. To address this challenge, we propose a robust three-stage framework for decomposition, feature selection, and multi-horizon forecasting. Specifically, Optimal Variational Mode Decomposition (OVMD) is adopted to construct multiscale and multi-view representations of nonlinear SWH sequences, while a Triangulated Maximally Filtered Graph (TMFG) constructs a sparse dependency network to select informative and non-redundant predictors from decomposed components and environmental variables. A hybrid prediction model then combines a Temporal Convolutional Network (TCN) for local multi-scale patterns with a Bidirectional Gated Recurrent Unit (BiGRU) for long-range dependencies. Experiments on real-world buoy observations show that the proposed approach improves accuracy and robustness over commonly used statistical and deep-learning baselines across short-, medium-, and long-term horizons. Ablation studies confirm that integrating modal decomposition with sparse feature selection enhances model robustness, offering reliable decision support for offshore window planning and high-wave condition monitoring. Full article

Tea pest and disease named entity recognition (NER) faces challenges resulting from dense domain terminology, multi-granularity entity structures, and long-distance semantic dependencies. This paper proposes E-BERT-wwm-BiGRU-RAT-CRF, integrating whole-word masking E-BERT with three innovations—a trainable relative position bias matrix, a cross-layer hierarchical mask matrix, and a heterogeneous multi-head attention mechanism—followed by bidirectional gated recurrent units (BiGRU), residual attention (RAT), and conditional random fields (CRF). On a self-constructed tea pest and disease corpus of over 300,000 characters across seven entity categories, the model achieves 93.67% precision, 93.07% recall, and 93.37% F1-score, outperforming the baseline by 2.73 percentage points in F1-score. Ablation experiments confirm the contribution of each module. Full article

With the widespread use of social media and online platforms in the dissemination of public opinion within universities, the multi-class classification of risk-related texts has become a critical component of online public opinion analysis in higher education institutions. Existing multi-class risk classification methods often focus on static semantic representations, making it difficult to effectively capture the emotional evolution within texts and the differences between samples, which in turn affects the accuracy of risk classification. To address this, this paper proposes a multi-class risk classification model for university online public opinion that integrates contextual semantic modeling, emotional evolution detection, and adaptive confidence-based feature fusion. The model employs pre-trained BERT for context encoding and, while preserving high-level semantic information, enhances the model’s adaptability to domain-specific features through a selective unfreezing strategy. First, a Bidirectional Gated Recurrent Unit (BiGRU) is introduced to model the emotional evolution trajectory within text sequences, and an emotional transition intensity metric is constructed by calculating the difference between adjacent hidden states, thereby explicitly capturing the magnitude of emotional changes. Additionally, a convolutional feature branch is designed to capture local emotional patterns, enhancing the model’s ability to perceive local risk cues and fine-grained emotional fluctuations. Finally, the Emotion-Adaptive Feature Mixer (EAFM) is introduced. This module adaptively weights global emotional evolution features and local emotional pattern features based on sample confidence to adjust the contributions of different feature branches in risk classification. Experimental results demonstrate that the proposed model exhibits good convergence characteristics in the university online public opinion scenario represented by the CUOPO dataset and demonstrates strong interpretability through attention visualization and confidence coefficient analysis. Full article

Knowledge tracing aims to predict students’ future performance based on their historical learning interactions, thereby supporting learner modeling in online learning platforms and intelligent tutoring systems. Recent deep learning-based knowledge tracing models have achieved strong predictive performance, but many of them rely on increasingly complex architectures or additional optimization objectives, which may increase training difficulty and computational cost. To examine whether recurrent models can remain competitive when equipped with more effective exercise representation, this paper proposes ExerCAKT, an Exercise Context-Aware Knowledge Tracing model based on gated recurrent units. Different from conventional GRU-based knowledge tracing models that mainly use interaction sequences to update students’ knowledge states, ExerCAKT explicitly separates knowledge-state modeling and exercise-context modeling through two GRU-based feature extractors. The knowledge-state feature extractor captures students’ evolving mastery patterns, while the exercise feature extractor models contextual exercise information to enhance question-level prediction without introducing extra optimization objectives. Experiments on four public knowledge tracing datasets show that ExerCAKT achieves the best AUC results in six out of seven evaluation settings and obtains similar advantages in ACC. At the question level, ExerCAKT improves AUC by 2.00–4.71% over DKT on AL2005, AS2009, and NIPS34. At the knowledge-concept level on AS2009, AL2005, and NIPS34, it improves AUC by 0.24–1.95% over AKT. These results suggest that recurrent knowledge tracing models can still achieve competitive performance when exercise contextualization is explicitly modeled. Full article

Human activity recognition (HAR) using Wi-Fi channel state information (CSI) offers a privacy-preserving and contactless sensing modality suitable for smart homes, healthcare monitoring, and pervasive mobile Internet of Things (IoT) environments. However, existing CSI-based HAR approaches often suffer from computational inefficiency, high latency, and limited feasibility on resource-constrained embedded platforms. This work presents STAR (Sensing Technology for Activity Recognition), an edge AI-optimized framework that integrates lightweight temporal modeling, adaptive signal processing, and hardware-aware co-optimization to enable real-time, energy-efficient HAR on low-power embedded devices. STAR employs a streamlined three-layer Gated Recurrent Unit (GRU) architecture that reduces model parameters by 33% compared to conventional Long Short-Term Memory (LSTM) designs while maintaining strong temporal modeling capability. To enhance signal quality, STAR incorporates a multi-stage pre-processing pipeline consisting of median filtering, an eighth-order Butterworth low-pass filtering, and empirical mode decomposition (EMD) to denoise CSI amplitude measurements and extract stable spatial-temporal features. For on-device deployment, the system is implemented on a Rockchip RV1126 processor equipped with an embedded Neural Processing Unit (NPU) and interfaced with an ESP32-S3 CSI acquisition module. Experimental results demonstrate a mean recognition accuracy of 93.52% across seven activity classes and 99.11% for human-presence detection using a compact 97.6k-parameter model. INT8-quantized inference achieves a processing throughput of 33 MHz with only 8% CPU utilization, achieving a six-fold improvement in inference speed over CPU-based execution. With sub-second response latency and low power consumption, the system ensures real-time, privacy-preserving HAR, offering a practical, scalable solution for mobile and pervasive computing environments. Full article

Rolling bearing vibration signals often exhibit strong nonstationarity and are susceptible to noise interference, which makes fault feature extraction and accurate diagnosis challenging under complex operating conditions. To address these issues, this paper proposes a fault diagnosis pipeline that sequentially combines an improved snow ablation optimizer (ISAO), variational generalized nonlinear mode decomposition (VGNMD), and a bidirectional temporal sequence fusion network (BiTSF-Net). Firstly, ISAO is used to optimize the key parameters of VGNMD, including the bandwidth penalty parameter and smoothing constraint parameter, with minimum envelope entropy as the fitness function. Secondly, the optimized VGNMD decomposes raw vibration signals into modal components, and the modal component with the minimum envelope entropy is selected to highlight fault-related impulsive characteristics. Thirdly, 11-dimensional time-domain statistical features are extracted from the selected optimal modal component to characterize bearing health states. Finally, these extracted features are used as the input to BiTSF-Net, which combines bidirectional temporal convolutional networks and bidirectional long short-term memory networks in a parallel structure to learn local transient features and temporal dependencies for fault classification. Experimental validation is conducted on the Case Western Reserve University dataset. Comparative results with convolutional neural networks, gated recurrent units, and long short-term memory networks demonstrate that the proposed pipeline achieves superior diagnostic performance, with an average accuracy of 99.63% and a maximum accuracy of 100%. These results confirm the effectiveness and robustness of the proposed ISAO-VGNMD feature extraction and BiTSF-Net classification pipeline for bearing fault diagnosis under complex nonstationary conditions. Full article

Sepsis is life-threatening organ dysfunction caused by a dysregulated host response to infection, making early detection critical for improving outcomes in intensive care units (ICUs). This study presents a retrospective comparative evaluation of deep learning architectures for predicting sepsis up to 6 h before the PhysioNet/Computing in Cardiology 2019 Challenge onset label using hourly structured electronic health record (EHR) variables, including vital signs, laboratory measurements, and demographics. Evaluated architectures include Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short-Term Memory (Bi-LSTM), Temporal Convolutional Network (TCN), Transformer, and hybrid Convolutional Neural Network–Vision Transformer (CNN-ViT) models. Median imputation and class-weighted loss were applied to address missing values and severe class imbalance, while Shapley Additive Explanations (SHAP) and attention analyses were used as complementary interpretability approaches. Among the evaluated models, CNN-ViT achieved the strongest overall minority-class performance, with 88.25% accuracy, 0.7480 recall, a 0.454 F1-score, and a 0.48 area under the precision–recall curve (AUPRC), although the numerical gains over other advanced temporal and hybrid architectures were modest. Leave-one-unit-out evaluation further demonstrated relatively stable performance under internal distribution shifts. The results suggest that combining local feature extraction with temporal and attention-based modeling can improve early sepsis prediction from structured ICU data. However, the study represents a retrospective computational benchmark using a public dataset and does not constitute prospective clinical validation or real-world deployment assessment. Full article