Search Results (1,574)

Real-time seismic reservoir monitoring of geologic reservoirs requires both large-scale data management and efficient computational workflows. Addressing these challenges is facilitated by developing techniques capable of selectively capturing critical geologic features, thereby increasing computational efficiency and reducing data storage requirements. This paper proposes a double-compression framework integrating Haar wavelet transforms with machine learning (ML) for efficient multiparameter seismic inversion. First, Haar wavelet compression significantly reduces the dimensionality of the input elastic models, preserving essential geologic structures while limiting data volumes. Next, a convolutional neural network with the long short-term memory (CNN-LSTM) architecture, including dual encoders and multi-decoders, compresses seismic data into a latent space to generate a multi-scale P-wave velocity estimate. By leveraging transfer learning to speed up convergence and enhance prediction accuracy, we fine-tune the latent representation to estimate the P-to-S-wave velocity ratio and acoustic impedance at multiple resolution scales. Tests on the synthetic ${\mathrm{CO}}_2$-injection Kimberlina model show that wavelet-based compression—including detuning large-scale trends—minimizes artifacts in simulated wavefields and accelerates neural-network training. The results demonstrate that combining wavelet-based pre-compression for reservoir models with data-driven latent encodings for seismic data achieves high compression ratios, reduces computational costs, and maintains the fidelity of subsurface imaging. Compared with a redundant-decimation baseline, the proposed framework reduces network training time by approximately 70% and GPU memory usage by 33–73%, achieves a wavefield energy loss below 0.1% at a 16:1 model-dimension reduction, and produces multi-resolution predictions of $V_{\mathrm{P}}$, $V_{\mathrm{P}}/V_{\mathrm{S}}$, and acoustic impedance with normalized errors below 0.04 across all six wavelet decomposition levels. Thus, the double-compression framework enables robust and scalable seismic monitoring of elastic reservoir parameters. Full article

The widespread availability of image editing tools and generative AI has made image forgery more accessible and deceptive, demanding more advanced localization techniques. Existing CNN-based methods are limited by local receptive fields, struggling with long-range dependencies, while Transformers suffer from the quadratic complexity of self-attention, hindering practical deployment. Moreover, effectively utilizing multi-scale features remains challenging. To address these challenges, we propose a Multi-scale Wavelet-enhanced U-Mamba network (MWEU-Mamba). The proposed framework employs a Mamba-based state space model as the backbone to achieve global contextual modeling with linear complexity. A wavelet enhancement module is introduced to integrate spatial–frequency representations, improving sensitivity to subtle manipulation traces across scales, while a channel attention mechanism further amplifies forgery-relevant feature responses. Extensive experiments on six public benchmark datasets (e.g., CASIA and Coverage) demonstrate that the proposed method achieves state-of-the-art performance on multiple datasets in terms of pixel-level F1-score. Full article

Motor imagery (MI)-based brain–computer interfaces (BCIs) have led to great interest as a result of their potential use in neurorehabilitation, assistive robotics, and human–computer interaction. However, decoding electroencephalographic (EEG) signals with high accuracy continues to be a difficult task due to the weak signal-to-noise ratio, differences among subjects, and the complicated temporal–spectral–spatial neural dynamics. Deep learning methods recently developed, such as convolutional neural networks, recurrent architectures, graph neural networks, and adversarial transfer learning, have enhanced MI decoding performance, yet many models are still concentrating on a single representation domain or they need costly adaptation phases in terms of computation. To tackle these shortcomings, we present NeuroCrossNet, a unified tri-modal deep learning model that is able to learn the temporal, spectral, and spatial EEG features jointly for robust and calibration-free MI decoding. The suggested network combines a Temporal HyperMixer Block for capturing long-range temporal dependencies, a wavelet transformer for learning localized time–frequency representation, and a Graph Attention Network for EEG topology-aware spatial reasoning. Additionally, a Dynamic Residual Attention Gate (DRAG) has been developed to adaptively merge heterogeneous feature streams, and a compact subject-aware normalization (SAN) method enhances cross-subject generalization without the use of labeled target-domain calibration data. Our proposed model was tested following the rigorous leave-one-subject-out (LOSO) approach on BCI Competition IV-2a and High-Gamma datasets. NeuroCrossNet reached a classification accuracy of 91.30%, surpassing several strong benchmark methods, including CNN-LSTM, EEGNet, DeepConvNet, spectral CNN, and graph-based EEG decoding frameworks. Furthermore, a large number of ablation studies reveal that the integration of temporally, spectrally, and spatially complementary representations considerably boosts robustness and inter-subject consistency. Full article

In this study, we employ seven well-established machine learning algorithms for the stochastic simulation of tropical cyclones in the Northwest Pacific, namely Support Vector Machine (SVM), Random Forest (RF), Bayesian Network (BN), Backpropagation Neural Network (BPNN), Wavelet Neural Network (WNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) network. First, based on the CMA (China Meteorological Administration) Tropical Cyclone Best-Track Dataset, we statistically analyze key typhoon parameters within each 5° × 5° grid over the Northwest Pacific. Second, the Random Forest method is applied to rank the importance of feature factors for predicting typhoon translation speed, storm heading, and central pressure in each grid. Third, each algorithm is used to develop prediction models, with hyperparameters optimized via a time-series cross-validation scheme. Fourth, the prediction models are compared to identify the best-performing model for predicting translation speed, storm heading, and central pressure, respectively. The optimal models are then evaluated in terms of computational efficiency and overfitting/underfitting, and validated both against traditional statistical methods and through multi-lead-time (1–72 h) predictions for four independent typhoons: Lekima 2019, Doksuri 2023, Ragasa 2025, and Yagi 2024. The results show that the optimal machine learning models outperform traditional statistical benchmarks, achieve a direct position error of <7 km and R² ≥ 0.979 at 1 h lead time, with track prediction remaining useful up to 48–72 h, while effective intensity prediction does not exceed 24 h. This study provides a robust data-driven framework for short-term typhoon forecasting within stochastic simulation, with future work aiming to extend to long-term predictions. Full article

Transitioning predictive maintenance from expensive, high-frequency piezoelectric sensors to affordable, edge-deployed MEMS sensors poses a significant challenge in industrial tool condition monitoring (TCM). Both technologies differ in signal quality, frequency capability, robustness, and reliability, which would affect how accurately machine faults can be detected. This work presents a systematic framework to bridge this gap, enabling real-time tool wear prediction and cross-sensor transferability. The methodology employs unsupervised Wavelet Packet Decomposition (WPD) and dynamic programming on high-resolution vibration signals to establish ground-truth wear phases: initial, steady-state, and accelerated. Multi-resolution time-frequency features are extracted and globally ranked using a multi-metric scoring system. A multi-task Bidirectional Long Short-Term Memory (Bi-LSTM) network is then trained to simultaneously predict a continuous wear index and classify discrete wear zones. To ensure model portability, Canonical Correlation Analysis (CCA) is utilised to align the high-fidelity piezoelectric feature space with the lower-frequency MEMS domain. The optimised multi-task Bi-LSTM architecture achieved up to 97.9% zone classification accuracy and a mean absolute error of 0.042 for wear index regression. Furthermore, CCA-based domain adaptation successfully transferred a model trained on piezoelectric data to classify unseen low-cost MEMS sensor data, maintaining a robust 87% accuracy. Combining optimised WPD features with CCA effectively overcomes hardware and sampling rate discrepancies, proving the viability of using low-cost sensors for reliable industrial retrofitting and real-time degradation tracking. Full article

Traditional taste evaluation relies heavily on manual sensory analysis, which is highly subjective and inefficient with poor cross-individual generalization, limiting its application in industrial flavor detection. To achieve accurate cross-subject taste recognition, this paper proposes an electroencephalogram (EEG) classification method based on a meta-learning wavelet graph convolutional neural network (ML-WGCNet) under sweet- and bitter-taste stimuli. Sucrose (sweetness) and quinine (bitterness) were used as stimulation sources, each prepared at six concentration gradients, including a water control. EEG signals were detected from 20 subjects. First, the Morlet wavelet transform was applied to decompose the EEG signals in the time–frequency domain, extracting the maximum and average energy values from five frequency bands as core features. A graph structure was then constructed using electrodes as nodes and Pearson correlation coefficients between electrodes as edge weights. A lightweight graph convolutional neural network (GCN) is employed to model spatial correlations among brain regions. Finally, by integrating a meta-learning framework and adopting leave-one-subject-out cross-validation, the model can rapidly adapt to new subjects. The experimental results show that the proposed method achieves average accuracies of 76.03% and 77.01% in cross-subject classification of sweet and bitter tastes, respectively. The corresponding precision values are 79.94% and 79.53%, the recall values are 75.77% and 78.51%, and the F1-scores are 78.24% and 78.08%, respectively, demonstrating that the proposed model significantly outperforms existing mainstream EEG classification methods. Full article

Accurate crack severity classification in rotating shafts remains a challenging task due to the strong spectral overlap between adjacent damage levels and the absence of distinct fault-specific frequency components. In such conditions, conventional vibration-based approaches relying on global spectral descriptors often fail to provide sufficient discriminatory information. This work proposes a stability-driven multi-resolution framework for crack severity classification based on the Wavelet Packet Transform (WPT). The approach aims to identify frequency bands that exhibit consistent diagnostic relevance across multiple decomposition levels while maintaining a monotonic relationship with crack severity. To this end, an interpretability-driven analysis based on Random Forest feature importance is combined with a frequency stability criterion and a monotonicity constraint, enabling the selection of physically meaningful and consistent spectral regions. The proposed framework has been evaluated on vibration data acquired from a rotating shaft test bench under multiple operating speeds and damage conditions. The results have shown that crack progression is characterised by distributed energy variations across specific frequency regions rather than by the emergence of isolated spectral peaks. It can be concluded that the proposed stability-driven band selection approach enables the identification of these regions in a consistent manner across spectral resolutions and operating conditions. Furthermore, the integration of WPT-based features with conventional time- and frequency-domain descriptors leads to a hybrid multi-scale representation that improves classification performance, particularly in intermediate severity regimes where spectral overlap is most pronounced. Overall, the proposed methodology provides a physically interpretable and consistent framework for vibration-based crack severity classification, with potential applicability to a wide range of rotating machinery diagnostics problems. Full article

The thyristor level is the basic unit of ultra-high-voltage and extra-high-voltage direct current (DC) converter valves, and its main-circuit parameters are important indicators for characterizing the health status of converter valves. To meet the demand for efficient detection of converter valve thyristor levels, this paper proposes a parameter inversion method for converter valve thyristor levels by combining the time-frequency-domain features of valve voltage and current, temporal characteristics of feedback signals from the thyristor-level monitoring unit, and a Grey Wolf Optimizer–Backpropagation Neural Network (GWO-BPNN). First, a six-pulse converter valve circuit simulation model is established. Based on this model, the original dataset is generated using the Latin hypercube sampling (LHS) method. Wavelet packet decomposition is then used to extract time-frequency-domain features, and dimensionality reduction is carried out by comparing the coefficient of variation and explained variance ratio so as to obtain input data suitable for neural network training. A BP neural network is then trained, and the network parameters are optimized using the Grey Wolf Optimizer to improve the accuracy and convergence speed of parameter inversion. Simulation comparison results show that the GWO-BP method is more efficient than the state equation method and is suitable for efficient inversion of damping parameters in multi-level thyristor systems. After GWO optimization, the maximum inversion errors of both parameters are reduced to below 5%. Compared with BP, GA-BP, and PSO-BP, the proposed GWO-BP model provides the best overall balance between resistance-inversion accuracy and training efficiency. By further incorporating feedback feature signals, the inversion error can be reduced to 1%. The proposed method provides a new technical route for efficient detection of thyristor converter valves and has broad application prospects. Full article

Soil surface roughness (SSR), referring to surface irregularities, is a key parameter for assessing soil condition and tillage outcomes. Characterizing roughness at fine scales—including clods and depressions—remains challenging for 2.5D digital elevation models (DEMs) collected at the meter scale in the field. This study presents two segmentation methods for high-resolution DEMs from an agricultural site. For clod segmentation, a wavelet-based approach from the literature was used, while a novel histogram-based method was introduced for depressions. Both methods were evaluated on natural soil surfaces with varying roughness levels and a simulated surface, with and without noise, using standard metrics (recall, precision, F1-score, IoU). The best clod segmentation results were achieved on fine seedbeds (95.2% recall, 97.3% precision, 96.2% F1-score), with slightly lower but strong performance on plowed surfaces (84.2% recall, 96.9% precision, 90.1% F1-score). Due to their lower frequency, depressions were primarily assessed visually under field conditions. For the simulated surface (with ground truth), IoU values ranged from 84.2% to 87.9% for clods and around 92% for depressions, demonstrating competitive performance. Additionally, the volume of roughness features was computed and visualized using cumulative distribution functions. These segmentation methods enable monitoring of soil surface conditions, with applications in precision agriculture, surface-water interactions, and meter-scale microwave remote sensing. Full article

Few-shot fault diagnosis of intelligent high-speed train components remains challenging because fault samples are scarce and highly imbalanced. To address this issue, this paper proposes MR-DDIM, a class-conditional diffusion-based data augmentation framework for generating high-fidelity fault vibration signals from limited labeled data. A WT-UNet denoising backbone is developed by combining one-dimensional wavelet convolution with Feature-Wise Linear Modulation (FiLM) to capture multiscale time–frequency structures and enable class-controllable generation. To improve training stability and spectral fidelity, log-σ regularization and a multi-resolution STFT consistency loss are introduced into the optimization process. In addition, this paper proposed the multi-resolution spectral correlation coefficient (MR-SCC) and class-intrinsic maximum mean discrepancy (cMMD) to evaluate generation quality from spectral and distributional perspectives. Experiments on the BJTU-RAO datasets show that the proposed method can generate fault samples with high spectral consistency and reasonable intra-class diversity, thereby improving the robustness of downstream few-shot fault diagnosis. The results indicate that MR-DDIM provides an effective data augmentation solution for intelligent fault diagnosis in high-speed railway systems. Full article

Forest above-ground biomass (AGB) estimation is crucial for evaluating carbon dynamics. Although optical and synthetic aperture radar (SAR) data provide complementary spectral and structural information, limitations in existing fusion approaches restrict AGB estimation accuracy. This study proposes a multi-source data fusion framework comparing two image fusion strategies—the conventional Hue-Intensity-Saturation Wavelet (HIS-Wavelet) method and a deep learning-based HIS-Non-Subsampled Shearlet Transform combined with Pulse Coupled Neural Network (HIS-NSST + PCNN) approach—for forest AGB estimation using Gaofen-1 (GF-1), Gaofen-2 (GF-2), and Gaofen-3 (GF-3) satellite imagery in a subtropical forest area of Yunnan Province, China. Three regression models—Multiple Linear Stepwise Regression (MLSR), K-Nearest Neighbor (KNN), and KNN with Fast Iterative Feature Selection (KNN-FIFS)—were systematically compared to evaluate estimation performance and justify model selection. Results indicate that the HIS-NSST + PCNN method outperforms HIS-Wavelet in fusion quality metrics, with the GF-2 Red-Near-infrared-Blue (RNB) band and GF-3 combination using HH co-polarization achieving the highest image quality. The optimal AGB retrieval was achieved with the GF-1RNB and GF-3 combination under HIS-NSST + PCNN (coefficient of determination (R²) = 0.80, root mean square error (RMSE) = 14.79 t/ha), improving R² by 0.07 and RMSE by 2.35 t/ha over HIS-Wavelet. However, for GF-2 + GF-3, HIS-Wavelet achieved marginally better inversion accuracy (R² = 0.71) than HIS-NSST + PCNN (R² = 0.69), indicating that superior fusion quality does not directly translate to higher inversion accuracy. Bootstrap resampling analysis (1000 iterations) confirmed the statistical robustness, with the optimal KNN-FIFS yielding R² = 0.800 (95% confidence interval (CI): 0.678–0.924) and RMSE = 14.79 t/ha (95% CI: 12.51–17.22 t/ha), showing non-overlapping confidence intervals with both benchmark models. These findings demonstrate that spectral complementarity between optical and SAR data plays a more critical role than spatial resolution alone in fusion-based AGB estimation, and that adaptive feature selection is essential for maximizing inversion accuracy. Full article

The foot arch functions as a dynamic biomechanical system, maintained by the integrated actions of bones, ligaments, and muscles. A large body of clinical evidence indicates that, in addition to congenital foot deformities, acquired variations in the foot arch caused by factors such as poor gait, aging, weight, or injury can significantly affect quality of life. Early intervention upon detection of foot arch changes can help mitigate progression and prevent further deterioration. Despite the availability of multimodal sensor-integrated running platforms for gait analysis, such systems are inherently bulky and not conducive to routine walking measurement. To overcome the above limitations, this study employed a flexible plantar pressure insole with an integrated accelerometer and a dedicated acquisition circuit to capture plantar pressure and acceleration data. This smart insole system acquires plantar data, performs feature extraction via time–domain and wavelet analysis, and then employs machine learning to classify the foot arch type as a normal foot, flatfoot, or high-arched. A Random Forest classifier was then established to categorize foot arch types based on the collected data, which integrates numerous decision trees through bootstrap aggregation and random feature selection, with final classification determined by majority voting. A total of 30 volunteers participated, including 11 with normal arches, 11 with flat feet, and 8 with high arches. Compared with support vector machine, K nearest neighbors, and decision tree, the Random Forest achieved the highest recognition accuracy of 92%. This system reveals the patterns of plantar pressure distribution and acceleration fluctuations during walking across three foot arches and demonstrates that wavelet entropy can effectively quantify the changes in signal complexity included in foot arch differences. Compared with laboratory force plates, this system features lower cost and a smaller form factor, making it suitable for real-time monitoring. This system can lay the technical foundation for personalized foot orthopedics and health monitoring. Full article

Industrial surface defect detection constitutes a fundamental component in automated quality inspection but remains challenging due to complex textures, diverse defect scales, and stringent real-time constraints. To address these issues, we present MWYOLO, an enhanced YOLO11-based detection framework tailored for accurate and efficient industrial inspection. First, a C3k2-Mamba Spatial Fusion Block (C3k2-MSFB) that integrates global contextual information with local structural cues via state-space modeling, enabling more discriminative representations of fine-grained texture variations. Second, a multi-scale wavelet attention (MWA) module is embedded into the backbone, leveraging wavelet-domain feature decomposition and dual attention to capture multi-frequency patterns, thereby improving sensitivity to fine-grained and subtle defect patterns. Third, an Inner-CIoU loss is developed to emphasize interior geometric alignment during bounding-box regression, offering more stable optimization for ambiguous or low-contrast targets. Extensive experiments conducted on three representative industrial datasets—NEU-DET, HRIPCB, and a self-constructed GSD dataset—demonstrate the effectiveness of MWYOLO. The model achieves mAP50 scores of 81.4%, 98.1%, and 67.7%, respectively, while maintaining a lightweight design with only 3.2M parameters and 7.3 GFLOPs. The results validate MWYOLO as a robust and computationally efficient solution, offering a favorable balance between accuracy, interpretability, and deployability for real-world industrial defect detection tasks. Full article

The automated inspection of aluminum profile surface defects, which heavily relies on data acquired by machine vision sensors, is a critical task in industrial quality control. Addressing the current challenges of intense background texture interference and the difficulty in detecting defects with extreme aspect ratios on aluminum profiles, this research puts forward a complete end-to-end defect detection algorithm named WMC-DFINE (WIFA-MKSS-CSFF-DFINE) based on the DFINE framework. First, a Wavelet-Integrated Frequency Attention (WIFA) module is introduced, which utilizes a discrete wavelet transform to decouple features into the frequency domain, thereby dynamically suppressing high-frequency background noise and enhancing defect edge responses. Second, a Cross-Scale Feature Fusion (CSFF) module based on dual-channel pooling is designed to ensure the continuity of defect features, thereby resolving the semantic misalignment issue in traditional fusion. Third, a Multi-Kernel Strip Shuffle (MKSS) module is incorporated, utilizing decomposed convolution kernels to capture the geometric features of slender scratches. Finally, a knowledge distillation strategy is employed to transfer structured knowledge from a complex teacher model to a lightweight student model. Experiments on the Tianchi aluminum defect dataset demonstrate that WMC-DFINE achieves a mAP of 82.1%, which surpasses algorithms including YOLOv12, RT-DETR, and the baseline model DFINE. Furthermore, the distilled student model, WMC-DFINE-distill, improves the mAP by 3.2% compared to DFINE, reduces parameter count by 47%, and achieves an inference speed of 59.75 FPS on the experimental equipment. The proposed method effectively resolves the problem of balancing background suppression and defect detail feature preservation, offering a practical and efficient scheme for real-time industrial defect inspection. Full article

We propose various hybrid predictive systems to forecast the Bitcoin next-day price. In particular, we combine the decomposition methods based on signal processing techniques including maximum overlap discrete wavelet transform (MODWT), empirical wavelet transform (EWT), empirical mode decomposition (EMD), and variational mode decomposition (VMD) for feature extraction from original price series. Then, the extracted features are fed to the machine learning models for training and forecasting. We implemented five machine learning models, including regression Gaussian process (RGP), support vector regression (SVR), k-nearest neighbors algorithm (kNN), regression trees (RT), and feedforward neural networks (FFNN). The grey wolf optimization (GWO) algorithm is employed for hyperparameter optimization of the machine learning models. The root mean squared error (RMSE) is used for the evaluation and comparison of 20 hybrid predictive systems. The simulation results show that the RGP-GWO-VMD hybrid predictive system achieved the lowest forecasting error. In addition, RGP-GWO yielded on average the lowest forecasting error across all of the machine learning systems. Furthermore, among signal decomposition methods, the lowest forecasting error is generally achieved under the EWT. Hence, we presented the best results in forecasting Bitcoin prices from 20 hybrid prediction systems to serve as the baseline for future work and to guide traders, investors, and portfolio managers. Full article