Search Results (126)

The accurate estimation of lithium-ion battery state of health (SOH) is crucial for battery monitoring, safety, and degradation assessment; however, it remains challenging because of the nonlinear nature of battery degradation, measurement noise, and variability in the battery aging trajectory. This study aims to solve these problems by proposing a hybrid attention-based BiLSTM–RF model, which combines wavelet-based signal denoising, incremental capacity analysis (ICA)-based feature extraction, stacked Bidirectional Long Short-Term Memory (BiLSTM) networks, multi-head self-attention, principal component analysis (PCA)-based feature compression, and ensemble regression using a Random Forest (RF) model with adaptive weighted fusion. The proposed framework was tested on the NASA battery datasets (B0005, B0006, B0007 and B0018) and was further validated on the Oxford Battery Degradation Dataset using leave-one-battery-out cross validation conditions. Experimental results indicated that, in general, the proposed framework outperformed the evaluated benchmark models (CNN-LSTM, BiLSTM, and RF models) in terms of the prediction error, with a minimum RMSE value of 0.0229 for NASA battery B0007 and 0.0024 for Oxford Cell3. Ablation analysis also showed that the combination of wavelet denoising, PCA compression, temporal sequence learning and ensemble regression played a role in the overall SOH estimation performance. These results show that the proposed hybrid approach is effective and stable for SOH estimation in different battery degradation trajectories under the tested experimental conditions. Full article

Chinese social media cyberbullying detection faces three major challenges: implicit aggressive semantics, diverse adversarial expression patterns, and severe long-tailed class imbalance. To address these issues, this paper proposes a Hierarchical Multi-Committee Ensemble (HMCE) framework for Chinese cyberbullying detection. At the representation level, a hybrid architecture integrating pre-trained language models, multi-scale TextCNN, and attention pooling is designed to capture both global contextual dependencies and fine-grained local N-gram offensive cues. At the decision level, a three-tier progressive ensemble architecture is constructed. Specifically, the Tier-0 Committee Ensemble Layer introduces heterogeneous committees with differentiated training strategies to generate diverse Out-of-Fold (OOF) probability features. The Tier-1 Aggregation Layer employs an XGBoost-based meta-learner to model nonlinear complementary relationships among committees and improve decision fusion capability. Furthermore, the Tier-2 Calibration Layer incorporates probability calibration and adaptive threshold optimization to alleviate prediction bias under long-tailed distributions and improve minority-class recognition performance. Experiments conducted on a real-world dataset containing 23,080 Chinese social media posts demonstrate that the proposed HMCE framework achieves a Macro-F1 score of 90.26% and an accuracy of 92.50%, outperforming conventional pre-trained language models and existing ensemble approaches. The results validate the effectiveness, robustness, and generalization performance of HMCE for cyberbullying detection in complex Chinese linguistic environments. Full article

Breast cancer remains the leading cause of cancer-related deaths among women globally. Early detection through mammography is vital for improving survival rates; however, the large volume of medical images and subtle variations in lesion characteristics pose significant challenges to manual interpretation. Recent automated diagnostic models based on deep learning have shown strong potential for breast cancer classification, but challenges such as overfitting, high computational complexity, limited generalization, and insufficient interpretability remain unresolved. This paper proposes a computationally efficient and context-aware deep learning framework for breast cancer classification using transformer-based multi-scale attention mechanisms and explainable artificial intelligence (XAI). The proposed architecture integrates the Hierarchical Multi-Scale Transformer (HMT) and Edge-Aware Local Transformer (ELT) modules to jointly capture global contextual dependencies and boundary-sensitive local representations from mammographic images. ELT improves feature refinement in high-entropy regions, while HMT models global semantic interactions across multiple feature scales. In addition, an Adaptive Contextual Refinement (ACR) module is introduced to preserve semantically consistent feature representations across spatial resolutions. A Meta-Ensemble Classification (MEC) framework combining weighted SVM and K-Nearest Neighbors (KNN) classifiers is further employed using validation-guided class-adaptive weighting. The proposed framework is evaluated on four benchmark mammography datasets, namely CBIS-DDSM, DDSM, INBreast, and MIAS. The proposed model has demonstrated superior accuracy of over 99% across all breast cancer datasets. The model surpassed transformer-based baselines including Swin-T and ViT while maintaining lower parameter complexity and achieving approximately 7% higher accuracy on the CBIS-DDSM dataset. The proposed framework also demonstrated strong cross-dataset generalization and consistently achieved high precision, recall, and F1-score values across all benchmark datasets. To improve model interpretability, Grad-CAM, SHAP, Occlusion Sensitivity Analysis (OSA), and the proposed TIxAI consistency analysis framework are incorporated to provide preliminary explainability assessment for mammographic classification. The explainability analysis demonstrated spatially consistent saliency behavior across benchmark datasets; however, the current evaluation is based on internal saliency consistency rather than external clinical validation using expert lesion annotations. Overall, the proposed framework provides an effective and computationally efficient approach for automated breast cancer classification while improving model explainability and interpretability. Full article

To meet the requirements of precise temperature regulation in solar greenhouses, traditional machine learning algorithms often suffer from poor adaptability, high energy consumption, and difficulties in integrating agronomic expertise. This study developed an intelligent greenhouse temperature regulation framework based on Model Predictive Control (MPC). The core components of the framework include: (1) an expert-experience-based simulator using a Sparrow Search Algorithm-optimized Random Forest (SSA-RF) model to digitize the temperature management strategies of high-yield farmers into dynamic reference trajectories and (2) a hybrid prediction model (CNN-BiLSTM-Attention) combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise-Permutation Entropy (CEEMDAN-PE) denoising with a Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Attention mechanism to achieve high-precision multi-step temperature forecasting. Validation in a cucumber solar greenhouse demonstrated that the SSA-RF model achieved an R² of 0.976 on the test set, showing a significant improvement over the traditional RF model. Compared to the conventional LSTM model, the hybrid prediction model reduced the RMSE to 0.642 and 0.947 for 15 min and 30 min predictions, respectively, with a maximum R² of 0.994 and excellent generalization capabilities. Finally, these two components were theoretically integrated into an MPC-oriented decision framework. The framework describes how expert reference trajectories, multi-step predictions, actuator constraints, and control increments can be combined in a receding-horizon optimization problem. Since online actuator control data were not available, the MPC module was formulated as a theoretical decision framework rather than a fully validated closed-loop controller. This study provides a modelling basis and technical path for future real-time greenhouse temperature control. Full article

Occupational mental-health risk in knowledge-work settings is an important public-health and psychosocial-support concern because workload demands, career insecurity, limited mentoring, uneven institutional support and barriers to care can increase psychological risk, including in early-career academic environments. Workplace well-being assessments rely on aggregate survey summaries or conventional prediction models, limiting calibration, interpretability, subgroup evaluation and transfer validation. This study develops a computational-intelligence framework for public mental-health decision support using heterogeneous workplace survey data with early-career academics treated as a motivating knowledge-work context rather than as the direct empirical cohort. The proposed approach combines attention-based tabular learning, variational autoencoder latent profiling, stacked ensemble prediction, probability calibration, feature attribution, perturbation analysis, fairness assessment and cross-dataset adaptation. Calibrated probabilities are converted into a transparent 0–100 risk index to support preventive outreach, psychosocial-support planning and resource-allocation decisions. The model is compared with baselines, including logistic regression, support vector machine, random forest, XGBoost, LightGBM, CatBoost, TabNet, FT–Transformer, NODE and DCN. Results show strong held-out performance with AUC = 0.885, average precision = 0.872, F1 = 0.808, Brier score = 0.145 and expected calibration error = 0.022, outperforming tested baselines. Five-fold robustness analysis produced a conservative mean test AUC of $0.809\pm 0.044$, indicating moderate partition sensitivity. Key predictors include work interference, perceived stress, care access and support variables. Latent profiling identifies two behavioural subgroups with distinct risk patterns. After feature harmonization, target-domain adaptation and recalibration, external evaluation on an occupational burnout dataset achieves AUC = 0.941 and average precision = 0.936, supporting calibrated, interpretable and subgroup-aware decision support under dataset shift. Full article

In predicting tubing corrosion rates under multi-factor coupling, traditional methods often struggle to effectively analyze the nonlinear interactions among variables such as temperature, pressure, CO₂ partial pressure, and H₂S partial pressure, and they also lack interpretability in the prediction process. To address this, this study first establishes a corrosion dataset covering three typical steels (2205DSS, CT80, N80) through high-temperature and high-pressure weight-loss experiments. A machine learning framework is then proposed, integrating feature coupling analysis with a SHAP-Sobol-based interpretability framework. By incorporating the Context-Aware Sparse Attention (CASA) mechanism into the XGBoost ensemble, a CASA-XGBoost prediction model is constructed to systematically analyze interactions among multiple features and convert them into effective predictive information. Bayesian optimization enables adaptive hyperparameter tuning, while five-fold cross-validation tailored to different materials enhances model generalization and stability. Furthermore, the SHAP-Sobol weighting method systematically evaluates feature contributions and interaction effects across global sensitivity analysis and local sample interpretation, enabling feature coupling reconstruction. Experimental results demonstrate that the proposed framework outperforms benchmark models (Random Forest and Gaussian Process Regression) on three steel corrosion datasets, achieving test set R² values up to 0.98 with a low MAE and RMSE. The SHAP-Sobol-based interpretability framework also reveals material-specific sensitivities: 2205DSS is highly influenced by CO₂-H₂S interaction, CT80 by temperature–pressure coupling, and N80 shows reduced performance at high corrosion rates due to localized mechanisms. This study provides a reference for corrosion prevention and control by delivering high-accuracy and interpretable corrosion rate prediction for tubing under multi-factor coupling conditions, offering practical value for industrial modeling and decision-making. Full article

Financial forecasting research often prioritizes methodological sophistication over the authenticity of underlying training data. This study quantifies the “estimation–reality divide” by comparing models trained on estimated quarterly data versus genuine, re-stated SEC-reported cash flows. Using 244 firm-quarter observations from five large-cap U.S. technology firms (Microsoft, Apple, Amazon, Alphabet, Meta; 2011–2024), this case study shows that, within this specific set of firms, models trained on estimated data exhibit a large optimistic bias. For a state-of-the-art ensemble, this bias appears as a 43% lower error rate (4.5% vs. 7.9%) compared to the same model trained on authentic data. To address this, we introduce a forecasting framework that combines (i) a Hidden Markov Model for detecting economic regimes, (ii) models tailored to each regime (XGBoost and LSTM with attention), and (iii) a dynamic ensemble that adapts to recent performance. In realistic out-of-sample tests, our framework achieves a 7.9% error rate on authentic data, significantly outperforming standard benchmarks. We also show that a meta-learning approach reduces the data needed for a new firm by about 35% while improving accuracy by 24%. In plain terms, using real SEC data leads to more honest and useful forecasts than relying on estimated data. All claims are strictly limited to the five large-cap U.S. technology firms analyzed (Microsoft, Apple, Amazon, Alphabet, Meta). No claims of generalizability to other sectors, firm sizes, or markets are made or implied. Validation on broader samples is required before extending these findings. Full article

Accurate prediction of concrete compressive strength remains a challenging problem due to the complex and nonlinear interactions among mixture components and curing conditions. While machine learning approaches have shown promising results, existing studies are typically limited by static model integration strategies and insufficient consideration of structural relationships among input variables. To address these limitations, this study proposes a novel Adaptive Symmetry-Aware Physics-Informed Hybrid (ASAPH) learning framework. The proposed approach integrates three key components: (i) symmetry-consistent feature representation that preserves invariant relationships among mixture parameters, (ii) a stability-driven feature selection mechanism with a relevance–redundancy trade-off, and (iii) an adaptive input-dependent ensemble strategy that dynamically combines multiple learners. In contrast to conventional stacking methods, the proposed framework employs a learnable weighting function to adjust model contributions based on input characteristics, enabling more flexible, robust, and input-adaptive predictions. The framework combines an attention-based tabular model (TabNet) for representation learning and a tree-based ensemble model (XGBoost) for predictive robustness within a unified adaptive fusion architecture. Experimental results on a benchmark dataset using 10-fold cross-validation demonstrate that the proposed model achieves strong predictive performance, with R² = 0.9162, RMSE = 4.8271, and MAE = 3.4118, outperforming strong baseline models including XGBoost and TabNet. Furthermore, explainability analysis based on SHAP reveals that curing age, cement content, and water-related parameters are the most influential factors governing compressive strength, consistent with established engineering knowledge. Among these, curing age emerges as the most dominant factor, followed by water-related ratios and cement content, indicating strong alignment with established domain knowledge. These findings confirm that incorporating symmetry-aware and physics-informed representations enhances both interpretability and predictive reliability. Overall, the proposed framework provides a principled and generalizable approach for modeling complex engineering systems, bridging the gap between data-driven learning and physically consistent modeling. Full article

In the current energy context, enhancing the precision of wind power prediction serves as a key enabler for the stable development of the power grid. In the existing wind power prediction models, there are often problems of modal aliasing and noise residue, or the prediction accuracy of the model is not high. In an effort to solve the problem of short-term wind power forecasting, a wind power series decomposition and reconstruction method based on improved complete ensemble empirical mode decomposition with adaptive noise-variational modal decomposition (ICEEMDAN-VMD) secondary decomposition is proposed. Using ICEEMDAN, wind power data (wind direction, wind speed, temperature, humidity, air pressure, etc.) is decomposed into several IMF sub-series, and these IMF sub-series are categorized into three different frequency components by combining sample entropy, Q statistics and sequence frequency. Secondly, the gray wolf optimization (GWO) is improved by using the empirical exchange strategy (EES), and the optimization performance of the EES-GWO proposed in this paper is verified by using 10 test functions. Finally, the EES-GWO-convolutional neural network–bidirectional gated recurrent unit–global attention (EES-GWO-CNN-BiGRU–Global attention) high-frequency component prediction model is constructed. Finally, we employ the XGBoost model to forecast the mid- and low-frequency components, thereby generating the corresponding forecasting results. The support vector machine (SVM) model nonlinearly integrates all the forecasting results to produce the final forecasting results. Through example analysis and comparison, the performance of the proposed model is verified from two perspectives. Full article

This paper presents a novel Multi-Scale Temporal Uncertainty-aware Hierarchical Adaptive Ensemble (MSTU-HAE) algorithm for intelligent ship emission monitoring and prediction in maritime environmental compliance applications. The maritime shipping industry contributes approximately 3% of global CO₂ emissions and significant amounts of nitrogen oxides and sulfur oxides, necessitating advanced predictive monitoring systems. The proposed MSTU-HAE algorithm integrates three key innovations: multi-scale temporal feature extraction using causal convolutions at short-term (5 samples), medium-term (20 samples), and long-term (60 samples) windows; gas-specific attention mechanisms that automatically weight temporal scales based on individual emission gas characteristics; and three-level hierarchical uncertainty quantification encompassing individual model uncertainty, ensemble disagreement, and regulatory compliance risk assessment. Experimental validation was conducted using emission data collected from a fishing vessel over 3 operational days (1732 original samples), augmented to 17,320 samples via controlled replication with noise injection to support model training. Rigorous temporal data splitting with 70%/15%/15% train/validation/test partitioning ensures no data leakage. Comparative analysis against six baseline methods (XGBoost, LSBoost, AdaBoost, Ridge Regression, Random Forest, and K-Nearest Neighbors) demonstrates that MSTU-HAE achieves superior average performance, with R² = 0.9670 and NSE = 0.9670 across all emission gases. This research contributes a robust, interpretable, and scalable prediction framework that advances the state of the art in maritime environmental monitoring through novel algorithmic innovations in temporal feature learning and uncertainty quantification. Full article

The output power of photovoltaic (PV) systems is influenced by various environmental factors, exhibiting strong nonlinearity and non-stationarity, which poses significant challenges for accurate forecasting. To address these issues, this paper proposes a short-term PV power forecasting method based on wavelet convolutional neural networks and an improved Transformer. First, the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is employed to decompose the original PV power sequence into several intrinsic mode functions (IMFs). Fuzzy entropy is then utilized to evaluate the complexity of each component, and subsequences with similar entropy values are reconstructed to reduce the non-stationarity of the original series. Subsequently, Pearson correlation coefficients and the maximal information coefficient (MIC) are applied to capture both linear and nonlinear relationships between each reconstructed component and meteorological features, enabling the selection of strongly correlated variables. On this basis, a wavelet convolutional network (WTConv) is introduced to perform multi-scale decomposition and frequency-band feature extraction on the reconstructed components by integrating wavelet transform with convolution operations, effectively expanding the receptive field and extracting deep-seated features of the sequences. Finally, an improved iTransformer model is adopted for time-series modeling, leveraging its inverted encoding structure and self-attention mechanism to fully capture long-term dependencies among multivariate variables. The proposed model is validated using actual power data from a PV plant in Ningxia, China, across four seasons. Comprehensive experiments, including ablation studies, comparative analyses, loss function convergence evaluation, and Diebold–Mariano significance tests, are conducted to thoroughly assess the model’s effectiveness and superiority. Experimental results demonstrate that the proposed model achieves excellent prediction accuracy and stability in spring, summer, autumn, and winter, showing strong potential for engineering applications. Full article

Skin cancer represents a significant public health challenge, necessitating early detection and timely treatment for optimal management. Timely and accurate evaluation of skin lesions is crucial, as delays can lead to more severe outcomes. However, identifying skin lesions accurately can be challenging due to differences in color, shape, and the various types of imaging equipment used for diagnosis. While recent studies have demonstrated the potential of ensemble convolutional neural networks (CNNs) for early diagnosis of skin disorders, these models are often too large and inefficient for processing contextual information. Although lightweight networks like MobileNetV3 and EfficientNet have been developed to reduce parameters and enable deep neural networks on mobile devices, their performance is limited by inadequate feature representation depth. To mitigate these limitations, we propose a new hybrid attention dual-stream deep learning model for skin lesion detection. Our model uses one training process to preprocess the images and splits the task into two branches. Each branch extracts different features using multi-stage and multi-branch attention techniques, improving the model’s ability to detect skin lesions accurately. The first branch processes the original image using a convolutional layer integrated with three novel attention modules: Enhanced Separable Depthwise Convolution (SCAttn), stage attention, and branch attention. The second branch utilizes Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the input image, improving local contrast and revealing finer details. The integration of CLAHE with SCAttn modules leverages enhanced local contrast to capture more nuanced features while maintaining computational efficiency. A classification module receives the concatenated hierarchical characteristics that were taken from both branches. Utilizing the PAD2020 and ISIC 2019 datasets, we assessed the proposed model and obtained an accuracy rate of 98.59% for PAD2020, surpassing the state-of-the-art performance by 2%, and stable performance accuracy for the ISIC 2019 dataset. This illustrates how well the model can integrate several attention mechanisms and feature enhancement methods, providing a reliable and effective means of detecting skin cancer. Full article

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

Incipient faults in power cables are difficult to diagnose because their transient signatures are weak, non-stationary, and easily masked by background noise, while labeled real-world samples are often scarce. To address these challenges, this paper proposes an offline diagnosis framework that integrates Whale Optimization Algorithm (WOA)-guided CEEMDAN with a TCN-BiLSTM-Multi-HeadAttention network. The proposed method has three main features. First, WOA is explicitly mapped to the CEEMDAN parameter optimization problem and is used to adaptively optimize the noise amplitude and ensemble number, thereby improving decomposition quality and enhancing weak fault-related components. Second, the optimized intrinsic mode functions are reconstructed into a multi-channel representation that preserves complementary fault information across different frequency bands. Third, a hybrid deep architecture combining Temporal Convolutional Networks, Bidirectional Long Short-Term Memory, and multi-HeadAttention is designed to jointly capture local transient characteristics, bidirectional temporal dependencies, and fault-sensitive feature interactions. Experimental results on both PSCAD/EMTDC simulation data and real-world measured data show that the optimized WOA-CEEMDAN achieves superior decomposition performance, with an RMSE of 0.097 and an SNR of 8.42 dB. On the real-world test dataset, the proposed framework achieves 96.00% accuracy, 97.25% precision, 96.84% recall, an F1-score of 0.970, and an AUC of 0.97, outperforming several representative baseline models. Additional ablation, noise-robustness, small-sample, confusion-matrix, and cross-cable validation results further demonstrate the effectiveness and robustness of the proposed framework for incipient cable fault diagnosis. Full article

Circulating tumor cells (CTCs) are essential biomarkers for cancer prognosis, yet their extreme rarity and biological heterogeneity pose significant challenges for label-free detection. This study presents an automated, non-invasive classification framework integrating a self-assembly cell array (SACA) microfluidic chip with hyperspectral imaging (HSI) and deep learning. By utilizing the SACA chip’s 5 µm gap design, patient-derived blood samples were organized into a flattened monolayer, ensuring high-purity spectral acquisition by minimizing cell overlapping. We implemented two deep-learning pipelines: an Attention-Based Adaptive Spectral–Spatial Kernel ResNet (A²S²K-ResNet) for pixel-level feature extraction and a modified ResNet50 for structural image analysis. While spectral classification achieved ~80% accuracy for cultured cell lines, its performance on patient-derived CTCs was hindered by subtle spectral overlap with white blood cells (WBCs). To overcome this, a multi-band ensemble strategy using majority voting across seven optimized spectral bands (470–900 nm) was developed. This hybrid approach significantly enhanced detection robustness, achieving an overall accuracy of >93.5% and precision exceeding 92%. These results demonstrate that combining microfluidic spatial control with multi-band deep learning offers a reliable, label-free pipeline for clinical liquid biopsy and real-time cancer monitoring. Full article