Search Results (869)

This study proposes a novel two-dimensional Empirical Mode Decomposition (2D EMD)-based deep learning framework to enhance model performance in multi-class image classification tasks and potential early detection of diseases in healthcare using medical imaging. To validate this approach, we apply it to gastrointestinal (GI) endoscopic image classification using the publicly available Kvasir dataset, which contains eight GI image classes with 1000 images each. The proposed 2D EMD-based design procedure decomposes images into a full set of intrinsic mode functions (IMFs) to enhance image features beneficial for AI model development. Integrating 2D EMD into a deep learning pipeline, we evaluate its impact on four popular models (ResNet152, VGG19bn, MobileNetV3L, and SwinTransformerV2S). The results demonstrate that subtracting IMFs from the original image consistently improves accuracy, F1-score, and AUC for all models. The study reveals a notable enhancement in model performance, with an approximately 9% increase in accuracy compared to counterparts without EMD integration for ResNet152. Similarly, there is an increase of around 18% for VGG19L, 3% for MobileNetV3L, and 8% for SwinTransformerV2. Additionally, explainable AI (XAI) techniques, such as Grad-CAM, illustrate that the model focuses on GI regions for predictions. This study highlights the efficacy of 2D EMD in enhancing deep learning model performance for GI image classification, with potential applications in other domains. Full article

The accurate forecasting of electricity sales volumes constitutes a critical task for power system planning and operational management. Nevertheless, subject to meteorological perturbations, holiday effects, exogenous economic conditions, and endogenous grid operational metrics, sales data frequently exhibit pronounced volatility, marked nonlinearities, and intricate interdependencies. This inherent complexity compounds modeling challenges and constrains forecasting efficacy when conventional methodologies are applied to such datasets. To address these challenges, this paper proposes a novel decomposition–integration forecasting framework. The methodology first applies Variational Mode Decomposition (VMD) combined with the Zebra Optimization Algorithm (ZOA) to adaptively decompose the original data into multiple Intrinsic Mode Functions (IMFs). These IMF components, each capturing specific frequency characteristics, demonstrate enhanced stationarity and clearer structural patterns compared to the raw sequence, thus providing more representative inputs for subsequent modeling. Subsequently, an improved RevInformer model is employed to separately model and forecast each IMF component, with the final prediction obtained by aggregating all component forecasts. Empirical verification on an annual electricity sales dataset from a commercial building demonstrates the proposed method’s effectiveness and superiority, achieving Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Squared Percentage Error (MSPE) values of 0.044783, 0.211621, and 0.074951, respectively—significantly outperforming benchmark approaches. Full article

Large-scale climatic oscillations (COs) modulate extreme climate events (ECEs) globally and can trigger the Indian summer monsoons and associated ECEs. In this study, we introduced a Time-dependent Intrinsic Correlation (TDIC) analysis to quantify teleconnections between five major COs—the El Niño–Southern Oscillation (ENSO), Atlantic Multidecadal Oscillation (AMO), Indian Ocean Dipole (IOD), North Atlantic Oscillation (NAO), and Pacific Decadal Oscillation (PDO)—and multiple extreme climate indices (ECIs) over the southern Indian Peninsula. Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was employed to decompose COs and ECIs into intrinsic mode functions across varying timescales, enabling a dynamic TDIC assessment. The results revealed statistically significant correlations between COs and ECIs, with the strongest influences in low-frequency modes (>10 years). Distinct COs predominantly modulate specific ECIs (e.g., ENSO with monsoon rainfall extremes; AMO and PDO with temperature extremes). These findings advance the understanding of Indian climate system dynamics and support the development of improved ECE forecasting models. Full article

The South China Sea (SCS) sea surface temperature (SST) plays a crucial modulating effect on the climate of East Asia. While the interannual variability of South China Sea SST has been extensively examined, the decadal-scale linkages and underlying physical mechanisms between South China Sea SST and the three major ocean basins (the Atlantic, Pacific, and Indian Oceans) remain inadequately comprehended. To fill the gap, the study investigates the decadal variability of winter SST in the SCS during 1940–2023, utilizing long-term observational datasets and methods such as empirical orthogonal function decomposition, regression analysis, and teleconnections analysis. The first dominant mode of this decadal variability is characterized by basin-warming across the SCS, which is mainly driven by the Atlantic Multidecadal Oscillation (AMO, r = 0.62, p < 0.05). Specifically, the AMO imposes its remote influence on the SCS through three distinct pathways: the tropical Pacific pathway, the North Pacific pathway, and the tropical Indian Ocean pathway. These pathways collectively trigger an anomalous cyclone in the western North Pacific and SCS, and further induce basin-wide SST warming via a positive feedback that includes SST, sea level pressure, cloud cover, and longwave radiation. The second leading mode of SCS winter SST decadal variability displays a north–south dipole pattern, which is positively correlated with the Interdecadal Pacific Oscillation (IPO, r1 = 0.85, p1 < 0.05). Notably, this South China Sea SST dipole–IPO relationship weakened significantly after 1985 (r2 = 0.23, p2 < 0.05), related to the strengthening of the anomalous anticyclone over the SCS and the weakening of the anomalous cyclone over the tropical Indian Ocean. Furthermore, both the AMO and IPO influence the SST in the northern SCS by regulating wind field anomalies in the bifurcation region of the North Equatorial Current. This wind-driven modulation subsequently affects the intensity of Kuroshio intrusion into the SCS. These findings provide a novel mechanistic pathway for interpreting decadal-scale climate variability over East Asia, with implications for improving long-term climate prediction in the region. Full article

Soft robotics represents a rapidly advancing and significant subfield within modern robotics. However, existing soft actuators often face challenges including unwanted deformation modes, limited functional diversity, and a lack of versatility. This paper presents a four-chamber multimodal soft actuator with a centrally symmetric layout and independent pneumatic control. While building on existing multi-chamber concepts, the design incorporates a cruciform constraint layer and inter-chamber gaps to improve directional bending and reduce passive chamber deformation. An empirical model based on the vector superposition of single- and dual-chamber inflations is developed to describe the bending behavior. Experimental results show that the actuator can achieve omnidirectional bending with errors below 5% compared to model predictions. To demonstrate versatility, the actuator is implemented in two distinct applications: a three-finger soft gripper that can grasp objects of various shapes and perform in-hand twisting maneuvers, and a steerable crawling robot that mimics inchworm locomotion. These results highlight the actuator’s potential as a reusable and adaptable driving unit for diverse soft robotic tasks. Full article

To address the issue of weak geoelectric current field signals that are severely affected by noise and cannot be directly used for geological structure analysis in injected geoelectric current field detection technology, this study proposes a complete ensemble empirical mode decomposition with adaptive noise and improved wavelet thresholding collaborative denoising (CEEMDAN-IWT) method to enhance the interpretation accuracy of geoelectric current signals. The method performs signal decomposition through CEEMDAN and selects the effective intrinsic mode function (IMF) components based on the variance contribution criterion for preliminary denoising. It then combines the improved wavelet thresholding function for further fine denoising and reconstruction, obtaining high signal-to-noise ratio (SNR) electrical data. Simulation and real-world data validation show that in a simulation experiment with an initial SNR of −5 dB, the method improves the $SNR$ to 18.65 dB, and the SNR enhancement is superior to traditional methods under various noise intensities. In practical applications, the normalized cross-correlation (NCC) between the denoised signal and the original injected signal reaches as high as 0.9254, significantly outperforming traditional methods. At the same time, it balances the preservation of signal features with noise suppression, offering significant application value for improving the reliability of injected geoelectric current field detection data. Full article

With the rapid growth of photovoltaic (PV) installed capacity, accurate prediction of PV power is crucial for the safe and flexible operation of power grids. However, PV output sequences exhibit strong non-stationarity and a superposition of high-frequency disturbances and low-frequency trends, resulting in multi-frequency aliasing. Traditional models struggle to capture both long-term dependencies and short-term details, while multi-task learning (MTL) often suffers from negative transfer, limiting prediction accuracy. This paper proposes a hybrid PV power forecasting framework integrating complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN), PatchTST reconstruction, and progressive layered extraction (PLE) MTL. First, conventional models tend to prioritize learning low-frequency features while ignoring weak high-frequency signals under multi-frequency aliasing, which cannot meet the requirement for precise frequency-sensitive PV power prediction. To address this problem, CEEMDAN is employed to decompose the PV sequence into intrinsic mode functions (IMFs). Next, the fluctuation complexity of each IMF is quantified via RCMSE and K-means clustering: high-frequency components are captured using small patches to preserve details, while low-frequency components use larger patches to learn long-term trends. Subsequently, a PatchTST-BiLSTM reconstruction network with patch partitioning and multi-head attention is adopted to capture temporal dependencies and optimize data representation, overcoming the bottleneck caused by the imbalance between long-term and short-term features. Finally, recursive feature elimination (RFE) feature selection combined with a PLE multi-task network can coordinate expert models to mitigate negative transfer and enhance high-frequency response capability. Experiments on the Alice Springs dataset show that the proposed method significantly outperforms conventional deep learning and new multi-task models in the mean absolute error (MAE) and root mean square error (RMSE). The results show that, compared with the MTL_Attention_LSTM method, the proposed method reduces the average MAE by 45.9% and RMSE by 44.6%, achieving more accurate forecasting of PV power. Full article

Second-order damping oscillation models are incapable of precisely predicting superimposed and multi-fruit collision-induced oscillations. In view of this problem, an ARIMA-EEMD-LSTM hybrid model for predicting the oscillation trajectories of trellised tomatoes was proposed in this study. First, the oscillation trajectories of trellised tomatoes under different picking forces were captured with the aid of the Nokov motion capture system, and then the collected oscillation trajectory datasets were then divided into training and test subsets. Afterwards, the ensemble empirical mode decomposition (EEMD) method was employed to decompose oscillation signals into multiple intrinsic mode function (IMF) components, of which different components were predicted by different models. Specifically, high-frequency components were predicted by the long short-term memory (LSTM) model while low-frequency components were predicted by the autoregressive integrated moving average (ARIMA) model. The final oscillation trajectory prediction model for trellised tomatoes was constructed by integrating these components. Finally, the constructed model was experimentally validated and applied to an analysis of single-fruit oscillations and multi-fruit oscillations (including collision oscillations and superposition oscillations). The following experimental results were yielded: Under single-fruit oscillation conditions, the prediction accuracy reached an RMSE of 0.1008–0.2429 mm, an MAE of 0.0751–0.1840 mm, and an MAPE of 0.01–0.06%. Under multi-fruit oscillation conditions, the prediction accuracy yielded an RMSE of 0.1521–0.6740 mm, an MAE of 0.1084–0.5323 mm, and an MAPE of 0.01–0.27%. The research results serve as a reference for the dynamic harvesting prediction of tomato-picking robots and contribute to improvement of harvesting efficiency and success rates. Full article

Accurate probabilistic load forecasting is essential for secure power system operation and efficient energy management, particularly under increasing renewable integration and demand-side complexity. However, traditional forecasting methods often struggle with issues such as non-linearity, non-stationarity, feature redundancy, and quantile crossing, which hinder reliable uncertainty quantification. To overcome these challenges, this study proposes a hybrid probabilistic load forecasting framework that integrates empirical mode decomposition (EMD), LASSO-based feature selection, and a monotone composite quantile regression neural network (MCQRNN) enhanced with kernel density estimation (KDE). First, EMD decomposes the raw load series into intrinsic mode functions and a trend component to mitigate non-stationarity. Then, LASSO selects the most informative features from both the decomposed components and the original time series, effectively reducing dimensionality and multicollinearity. Subsequently, the proposed MCQRNN model generates multiple quantiles under monotonicity constraints, eliminating quantile crossing and improving multi-quantile coherence through a composite loss function. Finally, Gaussian kernel density estimation reconstructs a continuous probability density function from the predicted quantiles, enabling full distributional forecasting. The framework is evaluated on two public datasets—GEFCom2014 and ISO New England—using point, interval, and density evaluation metrics. Experimental results demonstrate that the proposed EMD–LASSO–MCQRNN–KDE model outperforms benchmark approaches in both point and probabilistic forecasting, providing a robust and interpretable solution for uncertainty-aware grid operation and energy planning. Full article

Grouting power serves as a critical parameter reflecting real-time energy input during grouting operations, and its accurate prediction is essential for intelligent control and engineering safety. Existing prediction methods often struggle to handle the strong nonlinearity, noise interference, adaptability to varying conditions in grouting power data. To address these challenges, an intelligent grouting system that integrates real-time data collection and core control modules has been developed. Subsequently, a grouting power prediction model is then proposed, which combines Complete Ensemble Empirical Mode Decomposition and Adaptive Noise (CEEMDAN) with a Convolutional Neural Net-work-Bidirectional Long Short-Term Memory Neural Network (CNN-BiLSTM) is proposed. The approach employs CEEMDAN to decompose the nonlinear and non-stationary power sequence into multiple intrinsic mode functions (IMFs). Each IMF is then separated into linear and nonlinear components using a moving average method. The linear components are predicted using an Autoregressive Integrated Moving Average (ARIMA) model, while the nonlinear components are predicted using a CNN-BiLSTM model. The final prediction is obtained by reconstructing the results from both components. Experimental comparisons under both normal and heaving grouting conditions demonstrate that the proposed model significantly outperforms LSTM, CNN-LSTM, and CNN-BiLSTM models. With 80% of the dataset used for training, the RMSE for normal conditions is reduced by 95.69%, 85.11%, and 80.55%, respectively, and for heaving conditions by 94.91%, 90.71%, and 84.62%, respectively. This research provides high-precision predictive support for grouting regulation under complex working conditions, offering substantial engineering application value. Full article

We propose a novel predictor for functional time series (FTS) based on the robust estimation of the modal regression within a functional statistics framework. The robustness of the estimator is incorporated through the $L^1$-estimation of the quantile density. Such consideration improves the precision of conditional mode estimation. A principal theoretical contribution of this work is the establishment of the asymptotic normality of the proposed estimator. This result is of considerable importance, as it provides the foundation for statistical inference, including hypothesis testing and the construction of confidence intervals. Therefore, the obtained asymptotic result enhances the practical usability of the modal regression prediction. On the empirical side, we evaluate the performance of the estimator under various smoothing structures using both simulated and real data. The real data application highlights the ability of the $L^1$-conditional mode predictor to perform robust and reliable short-term forecasts, with very high effectiveness in the analysis of economic data. Full article

Based on a cloud water resources (CWR) diagnostic dataset with a 1° × 1° resolution over China from 2000 to 2019, this study systematically analyzes the spatiotemporal patterns of CWR in the complex terrain of the North China Region. The results indicate the following: (1) CWR-related physical quantities exhibit significant seasonal differences, with most being highest in summer and lowest in winter; water vapor convergence is strongest in summer and weakest in autumn, while hydrometeor convergence is smallest in summer and largest in winter; and the water surplus (precipitation minus evaporation) is minimal and negative in spring, indicating severe spring drought. (2) At the annual scale, precipitation is highly correlated with cloud condensation (r > 0.99), and CWR variation is primarily controlled by hydrometeor influx (r > 0.99). (3) The regional annual CWR and precipitation increase at rates of 34.8 mm/10 years and 49.2 mm/10 years, respectively, but exhibit seasonal asynchrony—CWR increases in all four seasons, while precipitation shows a slight decreasing trend in winter. (4) Spatially, CWR show a pattern of “more in the south and north, less in the central region; more in the east, less in the west,” with significant increases in the central–southern parts (southern Shanxi and Hebei, Beijing, and Tianjin). (5) Empirical orthogonal function (EOF) analysis reveals two dominant modes of CWR anomalies: a “region-wide consistent pattern” and a “north–south out-of-phase dipole pattern,” the latter being related to terrain-induced differences in water vapor transport and uplift condensation. The results statistically elucidate the distribution patterns of CWR under the influence of complex topography in NCR, providing a scientific reference for the development and utilization of regional CWR. Full article

Metal components such as rolling bearings are prone to wear, cracks, and defects in harsh environments and long-term use, leading to performance degradation and potential equipment failures. Therefore, detecting surface cracks and other defects in rolling bearings is of great significance for ensuring equipment reliability and safety. However, traditional signal decomposition methods like EEMD and FEEMD suffer from residual noise and mode mixing issues, while deconvolution algorithms such as CYCBD are sensitive to parameter settings and struggle in high-noise environments. To mitigate the susceptibility of fault signals to background noise interference, this paper proposes a fault feature extraction method based on fast complementary ensemble empirical mode decomposition (FCEEMD) and adaptive maximum second-order cyclostationarity blind deconvolution (ACYCBD). Firstly, we propose FCEEMD, which effectively eliminates the residual noise of ensemble empirical mode decomposition (EEMD) and fast ensemble empirical mode decomposition (FEEMD) by introducing paired white noise with opposite signs, solving the problems of traditional decomposition methods that are greatly affected by noise, having large reconstruction errors, and being high time-consuming. Subsequently, a new intrinsic mode function (IMF) screening index based on correlation coefficients and energy kurtosis is developed to effectively mitigate noise influence and enhance the quality of signal reconstruction. Secondly, the ACYCBD model is constructed, and the hidden periodic frequency is detected by the enhanced Hilbert phase synchronization (EHPS) estimator, which significantly enhances the extraction effect of the real periodic fault features in the noise. Finally, instantaneous energy tracking of bearing fault characteristic frequency is achieved through Teager energy operator demodulation, thereby accurately extracting fault state features. The experiment shows that the proposed method accurately extracts the fault characteristic frequencies of 164.062 Hz for inner ring faults and 105.469 Hz for outer ring faults, confirming its superior accuracy and efficiency in rolling bearing fault diagnosis. Full article

This study proposes a hybrid analytical framework for detecting chondromalacia using vibroacoustic (VAG) signals from patients with knee osteoarthritis (OA) and healthy controls (HCs). The methodology combines nonlinear signal decomposition, feature extraction, and deep learning classification. Raw VAG signals, recorded with a custom multi-sensor system during open (OKC) and closed (CKC) kinetic chain knee flexion–extension, underwent preprocessing (denoising, segmentation, normalization). Ensemble Empirical Mode Decomposition (EEMD) was used to isolate Intrinsic Mode Functions (IMFs), and Detrended Fluctuation Analysis (DFA) computed local (α₁) and global (α₂) scaling exponents as well as breakpoint location. Frequency–energy features of IMFs were statistically assessed and selected via Neighborhood Component Analysis (NCA) for support vector machine (SVM) classification. Additionally, reconstructed α₁/α₂-based signals and raw signals were converted into continuous wavelet transform (CWT) scalograms, classified with convolutional neural networks (CNNs) at two resolutions. The SVM approach achieved the best performance in CKC conditions (accuracy 0.87, AUC 0.91). CNN classification on CWT scalograms also demonstrated robust OA/HC discrimination with acceptable computational times at higher resolutions. Results suggest that combining multiscale decomposition, nonlinear fluctuation analysis, and deep learning enables accurate, non-invasive detection of cartilage degeneration, with potential for early knee pathology diagnosis. Full article

The ongoing global warming threatens the Greenland Ice Sheet (GIS), which has exhibited an overall mass loss since 1990. This loss varies annually and interannually, reflecting the intricate interactions between the ice sheet and atmospheric and oceanic circulations. We investigate GIS mass balance variations (2002–2024) using data from the Gravity Recovery and Climate Experiment (GRACE) and its Follow-On (GRACE-FO) missions. Monthly mass anomalies from the International Combination Service for Time-variable Gravity Fields (COST-G) solution are compared with cumulative climate indices (North Atlantic Oscillation—NAO, Greenland Blocking Index—GBI, Atlantic Multidecadal Oscillation—AMO) and meteorological parameters (temperature, precipitation, surface albedo). Empirical Orthogonal Function analysis reveals five principal modes of variations, the first capturing annual and interannual frequencies (4–7 and 11 years), while subsequent modes only describe interannual frequencies. Wavelet analysis shows significant annual correlations between GIS mass changes and temperature (r = −0.88), NAO (r = 0.74), and GBI (r = −0.85). An annual cycle connects GIS mass changes, climatic indices, and meteorological parameters, while interannual variations highlight the role of the AMO and the NAO. The presence of an 11-year periodicity with the mass variations for NAO, GBI, and temperature strongly correlates with solar activity. Full article