Search Results (591)

Urban rail transit networks in developing countries are rapidly expanding, entering a networked operational phase where accurate passenger flow forecasting is crucial for optimizing vehicle scheduling, resource allocation, and transportation efficiency. In the short term, accurate real-time forecasting enables the dynamic adjustment of train headways and crew deployment, reducing average passenger waiting times during peak hours and alleviating platform overcrowding; in the long term, reliable trend predictions support strategic planning, including capacity expansion, station retrofitting, and energy management. This paper proposes a novel hybrid forecasting model, EEMD-TiDE, that combines improved Ensemble Empirical Mode Decomposition (EEMD) with a Time Series Dense Encoder (TiDE) to enhance prediction accuracy. The EEMD algorithm effectively overcomes mode mixing issues in traditional EMD by incorporating white noise perturbations, decomposing raw passenger flow data into physically meaningful Intrinsic Mode Functions (IMFs). At the same time, the TiDE model, a linear encoder–decoder architecture, efficiently handles multi-scale features and covariates without the computational overhead of self-attention mechanisms. Experimental results using Xi’an Metro passenger flow data (2017–2019) demonstrate that EEMD-TiDE significantly outperforms baseline models. This study provides a robust solution for urban rail transit passenger flow forecasting, supporting sustainable urban development. Full article

Traditional ultrasonic bolt stress measurement is hindered by high power consumption. Lowering excitation voltage reduces power but degrades signal-to-noise ratio (SNR), compromising accuracy. This paper proposes a synergistic algorithm combining Empirical Mode Decomposition (EMD) with Adaptive Threshold Wavelet Denoising (ATWD). The method preserves transient features by reconstructing high-frequency components via EMD, then suppresses noise by precisely processing low-frequency components using ATWD. Finally, cross-correlation estimates ultrasonic delay. Evaluated at excitation voltages from 12 V to 0.5 V, the EMD-ATWD method maintains measurement errors below 10% even at 0.5 V, improving accuracy by over 48% compared to conventional Finite Impulse Response (FIR) and Threshold Wavelet Denoising (WTD) methods, while enhancing key echo waveform fidelity by over 35%. This method provides a reliable low-power bolt stress monitoring idea for engineering applications. Full article

In order to solve the problem of false alarms and missed alarms in pipeline monitoring caused by a large amount of noise in the negative pressure wave signal collected by pressure sensors, a new pressure signal denoising method based on the black-winged kite algorithm (BWK) is proposed. First, the variational mode decomposition (VMD) parameters are optimized through BWK. Next, the effective modal components are screened by sample entropy, and the secondary noise reduction of the signal is carried out by using the wavelet thresholding (WT). Finally, the signal is reconstructed to achieve noise reduction. Simulation experiments show that, compared with WT and empirical mode decomposition (EMD), the method proposed in this paper can achieve the best noise reduction effect under both high and low signal-to-noise ratio (SNR) conditions. The method proposed in the paper can achieve the highest SNR of 14.2280 dB, compared to WT’s SNR of 12.6458 dB and EMD’s SNR of 5.5292 dB. To further validate the performance of the algorithm, an experimental platform for simulating pipeline leaks is built. Compared with WT and EMD, the method proposed in this paper also shows the best noise reduction effect. This method provides a high-precision and adaptive solution for leak detection in urban water supply pipelines and has strong engineering application value. Full article

Accurate early diagnosis and precise assessment of disease severity are imperative for the treatment and rehabilitation of schizophrenia patients. To achieve this, we propose a computer-aided diagnostic method for schizophrenia that utilizes fusion features derived from microstate analysis and empirical mode decomposition (EMD) based on Electroencephalography (EEG) signals. At the same time, the obtained fusion features from microstate analysis and EMD are input into the Least Absolute Shrinkage and Selection Operator (LASSO) feature selection algorithm to reduce the dimensionality of feature vectors. Finally, the reduced feature vector is fed to a Logistic Regression classifier to classify SCH and healthy EEG signals. In addition, the ability of the integrated features to distinguish the severity of schizophrenia symptoms was evaluated, and the Shapley Additive Explanations (SHAP) algorithm was used to analyze the importance of the classification features that differentiate schizophrenia symptoms. Experimental results from both public and private datasets demonstrate the efficacy of EMD features in identifying healthy controls, while microstate features excel in classifying the severity of symptoms among schizophrenia patients. The classification evaluation metrics of the fused features significantly outperform those obtained using EMD or microstate analysis features independently. The fusion feature method proposed in this study achieved accuracies of 100% and 90.7% for the classification of schizophrenia in public datasets and private datasets, respectively, and an accuracy of 93.6% for the classification of schizophrenia symptoms in private datasets. Full article

Early fault vibration signals of rolling bearings are non-stationary and nonlinear, with weak fault signatures easily masked by noise. Traditional denoising methods (e.g., wavelet thresholding, empirical mode decomposition (EMD)) struggle to accurately extract effective features. Although variational mode decomposition (VMD) overcomes mode mixing, its core parameters rely on empirical selection, making it prone to local optima and limiting its denoising performance. To address this critical issue, this study aims to propose a hybrid model with adaptive parameter optimization and efficient denoising capabilities, enhancing the signal-to-noise ratio (SNR) and feature discriminability of early fault signals in rolling bearings. The novelty of this work is reflected in three aspects: (1) An improved edge strategy whale optimization algorithm (IEWOA) is proposed, incorporating six enhancements to balance global exploration and local exploitation. Using the minimum average envelope entropy as the objective function, the IEWOA achieves adaptive global optimization of VMD parameters. (2) A hybrid framework of “IEWOA-VMD + dataset-specific wavelet thresholding for secondary denoising” is constructed. The optimized VMD first decomposes signals to separate noise and effective components, followed by secondary denoising, ensuring both adaptable signal decomposition and precise denoising. (3) Comprehensive validation is conducted across five models using two public datasets (Case Western Reserve University (CWRU) and Paderborn Universität (PU)). Key findings demonstrate that the proposed method achieves a root-mean-square error (RMSE) as low as 0.00013–0.00041 and a Normalized Cross-Correlation (NCC) of 0.9689–0.9798, significantly outperforming EEMD, traditional VMD, and VMD optimized by single algorithms. The model effectively suppresses noise interference, preserves the fundamental and harmonic components of fault features, and exhibits strong robustness under different loads and fault types. This work provides an efficient and reliable signal preprocessing solution for early fault diagnosis of rolling bearings. Full article

Frequency-modulated continuous-wave (FMCW) light detection and ranging (LiDAR) is a high-precision ranging and imaging system that has been widely used in various areas, such as self-driving vehicles and industrial inspection. However, during detection, the system is susceptible to noise interference. This interference results in a decrease in the signal-to-noise ratio (SNR) of mixed signals, which affects the ranging accuracy. In this study, a MATLAB r2021b simulation is used to generate LiDAR transmitted and echo signals, and Gaussian noise is introduced. After mixing, empirical mode decomposition (EMD) and wavelet transform (WT) are used to denoise mixed signals, and the denoising effects of different wavelet basis functions under different SNRs are analysed. Furthermore, an experimental FMCW LiDAR system is set up to collect practical target echo signals, and the simulation results are validated through experiments under various illumination conditions. The results also show that the noise in FMCW LiDAR signals is dominated by Gaussian noise and that the influence of environmental noise is minimal. The combined EMD-WT denoising algorithm and its wavelet basis optimisation strategy proposed in this study can be directly applied to practical scenarios with strict requirements for FMCW LiDAR signal quality, such as autonomous driving, aircraft navigation, and precision industrial measurement, providing theoretical basis and experimental support for wavelet basis selection and denoising strategies in different noise environments. Full article

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

With the improvement scale of grid connection renewable power, accurately forecasting and effectively coordinating systems with various energy sources has become much more important for power system scheduling and operation. Considering the uncertain characteristics of renewable energy and CHP units, this paper proposes an optimal dispatch method with multi-prediction models and an improved solving method by series correction and parallel coupling analysis. Firstly, multiple-model stationary time series are obtained by EMD (empirical mode decomposition) of the prediction results from multiple models. Then, series decomposition is updated by the UKF (unscented Kalman filter). Using the least-squares method, the parallel coupling of the correction results is solved. A complex optimal scheduling model with multiple renewable energy sources and CHP units is proposed and solved with the help of the improved GA and PSO combined algorithm to avoid the algorithm falling into local optimal conditions. Simulations show that the proposed optimal dispatch model and algorithm are able to consider the uncertain characteristics of renewable energy and CHP units with better performance than some typical methods, such as the baseline method that combines single-model BP forecasting with conventional PSO-based dispatch. These results demonstrate that the proposed EMD–UKF-based multi-model forecasting combined with the improved GA–PSO-based dispatch framework provides an effective and practically applicable tool for enhancing the economic and low-carbon operation of multi-energy systems with high renewable penetration. Full article

The timely identification of rock fractures is crucial in deep subterranean engineering. However, it remains necessary to identify reliable warning indicators and establish effective warning levels. This study introduces the Acoustic Emission Transformer for FRActure Prediction (AET-FRAP) multi-input time series forecasting framework, which employs acoustic emission feature parameters. First, Empirical Mode Decomposition (EMD) combined with Fast Fourier Transform (FFT) is employed to identify and filter periodicities among diverse indicators and select input channels with enhanced informative value, with the aim of predicting cumulative energy. Thereafter, the one-dimensional sequence is transformed into a two-dimensional tensor based on its predominant period via spectral analysis. This is coupled with InceptionNeXt—an efficient multiscale convolution and amplitude spectrum-weighted aggregate—to enhance pattern identification across various timeframes. A secondary criterion is created based on the prediction sequence, employing cosine similarity and kurtosis to collaboratively identify abrupt changes. This transforms single-point threshold detection into robust sequence behavior pattern identification, indicating clearly quantifiable trigger criteria. AET-FRAP exhibits improvements in accuracy relative to long short-term memory (LSTM) on uniaxial compression test data, with R² approaching 1 and reductions in Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). It accurately delineates energy accumulation spikes in the pre-fracture period and provides advanced warning. The collaborative thresholds effectively reduce noise-induced false alarms, demonstrating significant stability and engineering significance. Full article

Bridges serve as vital connectors in the transportation network and infrastructure. Given their significance, it is crucial to continuously monitor bridge conditions to ensure the efficient operation of transportation systems. With advancements in sensing technologies, transportation infrastructure assessment has evolved through the integration of structural health monitoring (SHM) methodologies. Traditionally, bridge monitoring has relied on direct sensor instrumentation; however, this method encounters practical obstacles, including traffic disruptions and limited sensor availability. In contrast, indirect bridge health monitoring (iBHM) utilizes data from moving traffic on the bridge itself. This innovative approach eliminates the need for embedded instrumentation, as sensors on vehicles traverse the bridge, capturing the dynamic characteristics of the bridge. In this paper, system identification methods are explored to analyze the acceleration data gathered using a bicycle-mounted sensor traversing the bridge. To explore the feasibility of this micromobility-based approach, bridge responses are measured under varying traversing conditions combined with dynamic rider–bicycle–bridge interaction for comprehensive evaluation. The proposed method involves a hybrid approach combining Wavelet Packet Transform (WPT) with Synchro-extracting Transform (SET), which are employed to analyze the time–frequency characteristics of the acceleration signals of bike-based iBHM. The results indicate that the combination of WPT-SET demonstrates superior robustness and accuracy in isolating dominant nonstationary frequencies. The performance of the proposed method is compared with another prominent signal processing algorithm known as Time-Varying Filtering Empirical Mode Decomposition (TVF-EMD). Ultimately, this study underscores the potential of bicycles as low-cost, mobile sensing platforms for iBHM that are otherwise inaccessible to motorized vehicles. Full article

Urban land subsidence poses a significant threat in rapidly urbanizing regions, threatening infrastructure integrity and sustainable development. This study focuses on Mandalay, Myanmar, and presents a novel clustering framework—Dynamic Time Warping and Trend-based Longest Common Subsequence with Agglomerative Hierarchical Clustering (DTLCS-AHC)—to classify spatiotemporal deformation patterns from Small Baseline Subset (SBAS) Interferometric Synthetic Aperture Radar (InSAR) time series derived from Sentinel-1A imagery covering January 2022 to March 2025. The method identifies four characteristic deformation regimes: stable uplift, stable subsidence, primary subsidence, and secondary subsidence. Time–frequency analysis employing Empirical Mode Decomposition (EMD) and Discrete Fourier Transform (DFT) reveals seasonal oscillations in stable areas. Notably, a transition from subsidence to uplift was detected in specific areas approximately seven months prior to the Mw 7.7 earthquake, but causal relationships require further validation. This study further establishes correlations between subsidence and both urban expansion and rainfall patterns. A physically informed conceptual model is developed through multi-source data integration, and cross-city validation in Yangon confirms the robustness and generalizability of the approach. This research provides a scalable technical framework for deformation monitoring and risk assessment in tropical, data-scarce urban environments. Full article

Automatic modulation recognition has regained attention as a critical application for cognitive radio, combining artificial intelligence with physical layer monitoring of wireless transmissions. This paper formalizes signal surface augmentation (SSA), a process that decomposes signals into informative subcomponents to enhance AI-based analysis. We employ Bivariate Empirical Mode Decomposition (BEMD) to break signals into intrinsic modes while addressing challenges like adjacent trends in long sample decompositions and introducing the concept of data overdispersion. Using a modern, publicly available dataset of synthetic modulated signals under realistic conditions, we validate that the presentation of BEMD-derived components improves recognition accuracy by 13% compared to raw IQ inputs. For extended signal lengths, gains reach up to 36%. These results demonstrate the value of signal surface augmentation for improving the robustness of modulation recognition, with potential applications in real-world scenarios. Full article

The regional integrated energy system (RIES) has emerged as a critical focus in energy systems research. The comprehensive incorporation of renewable energy and inherent multi-energy flow interconnection within RIES markedly elevates the complexity of “generation-load” balance regulation. Traditional model-driven dynamic state estimation methods, however, are constrained by fundamental limitations—complex modeling, inadequate representation of multi-energy flow interdependencies, and poor computational efficiency. This study proposes a data-driven dynamic state estimation method for RIES, utilizing multi-dimensional “generation-grid-load” characteristic information as its primary input and employing a synergistic framework of Empirical Mode Decomposition-Singular Value Decomposition (EMD-SVD) alongside an enhanced Bidirectional Long Short-Term Memory (BiLSTM) network. EMD-SVD preprocesses raw data to remove noise and extract essential features, while the enhanced BiLSTM serves a dual purpose: it first attains high-precision photovoltaic output prediction and multi-energy load forecasting and subsequently evaluates the node states of the multi-energy flow coupling system. A case study on a practical coupled RIES, comprising a 33-node power system, 7-node gas system, and 6-node thermal system, demonstrates that the proposed method achieves high estimation accuracy and remarkable computational efficiency while effectively addressing the inherent limitations of conventional model-driven approaches. 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

Brain–Computer Interface (BCI) technology facilitates direct communication between the human brain and external devices by interpreting brain wave patterns associated with specific motor imagery tasks, which are derived from EEG signals. Although BCIs allow applications such as robotic arm control and smart assistive environments, they face major challenges, mainly due to the large variation in EEG characteristics between and within individuals. This variability is caused by low signal-to-noise ratio (SNR) due to both physiological and non-physiological artifacts, which severely affect the detection rate (IDR) in BCIs. Advanced multi-stage signal processing pipelines, including efficient filtering and decomposition techniques, have been developed to address these problems. Additionally, numerous feature engineering techniques have been developed to identify highly discriminative features, mainly to enhance IDRs in BCIs. In this review, several pre-processing techniques, including feature extraction algorithms, are critically evaluated using deep learning techniques. The review comparatively discusses methods such as wavelet-based thresholding and independent component analysis (ICA), including empirical mode decomposition (EMD) and its more sophisticated variants, such as Self-Adaptive Multivariate EMD (SA-MEMD) and Ensemble EMD (EEMD). These methods are examined based on machine learning models using SVM, LDA, and deep learning techniques such as CNNs and PCNNs, highlighting key limitations and findings, including different performance metrics. The paper concludes by outlining future directions. Full article