Intrinsic Time-scale Decomposition Research Articles

Classification of Alzheimer’s dementia EEG signals using deep learning

Alzheimer’s dementia (AD) is a predominant neurological disorder arising from corruptions in brain functions and is characterized by a chronic or progressive nature. While the precise etiology of dementia remains incompletely elucidated, its manifestation is frequently associated with discernible structural and chemical alterations in the brain. Living with dementia significantly impacts individuals’ daily lives due to the resultant loss of cognitive functions. This study presents a novel method to monitor and detect AD using advanced signal processing applied to electroencephalography (EEG) signals. The intrinsic time-scale decomposition (ITD) algorithm is employed to extract proper rotation components (PRCs) from EEG signals, utilizing a 5-second EEG segment duration. The proposed method is compared with the detection of 5-second raw EEG segments using a custom one-dimensional convolutional neural network (1D CNN). Additionally, four different quartiles (Quartile 1 (Q1), Q2, Q3, and Q4) of EEG signals are considered to identify the most significant contributor to AD. Experimental results demonstrate that the ITD-based approach yields better detection performance compared to using raw EEG signals. The most promising result is achieved by the EEG-PRCs method in Q1, with an accuracy of 94.00%, sensitivity of 93.50%, and specificity of 93.90%. In contrast, the highest-performing result of the raw EEG segments method is in Q2, with an accuracy of 88.40%, sensitivity of 89.10%, and specificity of 87.60% in terms of detecting AD.

Ensemble difference mode decomposition based on transmission path elimination technology for rotating machinery fault diagnosis

Difference mode decomposition (DMD) is an effective technique for accurately separating a signal into fault, natural, and noise components. However, DMD relies on the assumption that noise spectral lines have zero amplitude, making it less effective in cases with a low signal-to-noise ratio. In practical scenarios, signals from bearing faults are often weak and can get buried under strong noise due to the influence of the transmission path (TP). To broaden the application scope of DMD, we proposed the ensemble DMD (EDMD) method, incorporating the transmission path elimination (TPE) technology. Firstly, an Intrinsic time-scale decomposition (ITD)-based TPE approach is proposed to reduce the influence of excessive noise spectral line amplitude caused by the TP. Secondly, calculating the average of the difference between two kinds of normalized Fourier spectrums and using it as the initial weight of EDMD can improve the operation speed of EDMD. Finally, the signal with the transmission path eliminated is input to the EDMD to extract the faulty signal. Simulation and experimental verification demonstrate the capability of this method in accurately extracting fault features in rolling bearings and gears under the influence of the TP.

EEG-based finger movement classification with intrinsic time-scale decomposition.

Brain-computer interfaces (BCIs) are systems that acquire the brain's electrical activity and provide control of external devices. Since electroencephalography (EEG) is the simplest non-invasive method to capture the brain's electrical activity, EEG-based BCIs are very popular designs. Aside from classifying the extremity movements, recent BCI studies have focused on the accurate coding of the finger movements on the same hand through their classification by employing machine learning techniques. State-of-the-art studies were interested in coding five finger movements by neglecting the brain's idle case (i.e., the state that brain is not performing any mental tasks). This may easily cause more false positives and degrade the classification performances dramatically, thus, the performance of BCIs. This study aims to propose a more realistic system to decode the movements of five fingers and the no mental task (NoMT) case from EEG signals. In this study, a novel praxis for feature extraction is utilized. Using Proper Rotational Components (PRCs) computed through Intrinsic Time Scale Decomposition (ITD), which has been successfully applied in different biomedical signals recently, features for classification are extracted. Subsequently, these features were applied to the inputs of well-known classifiers and their different implementations to discriminate between these six classes. The highest classifier performances obtained in both subject-independent and subject-dependent cases were reported. In addition, the ANOVA-based feature selection was examined to determine whether statistically significant features have an impact on the classifier performances or not. As a result, the Ensemble Learning classifier achieved the highest accuracy of 55.0% among the tested classifiers, and ANOVA-based feature selection increases the performance of classifiers on five-finger movement determination in EEG-based BCI systems. When compared with similar studies, proposed praxis achieved a modest yet significant improvement in classification performance although the number of classes was incremented by one (i.e., NoMT).

Design of fault degree diagnosis algorithm for circuit breaker spring based on fuzzy clustering

This paper proposes a design of a fault diagnosis algorithm for circuit breaker springs based on fuzzy clustering. The features of the fault state signal are extracted by combining the methods of Intrinsic Time-Scale Decomposition and Singular Spectrum Analysis. Using the fuzzy clustering method, this study classifies circuit breaker spring faults, extracts fault features, and achieves fault degree diagnosis. The experimental results show that the algorithm has high accuracy in fault diagnosis.

Rotating Machinery Fault Detection Using a New Version of Intrinsic Time-Scale Decomposition

Rotating Machinery Fault Detection Using a New Version of Intrinsic Time-Scale Decomposition

Intelligent processing of electromagnetic data using detrended and identification

The application of the electromagnetic method has accelerated due to the demand for the development of mineral resource, however the strong electromagnetic interference seriously lowers the data quality, resolution and detect effect. To suppress the electromagnetic interference, this paper proposes an intelligent processing method based on detrended and identification, and applies for wide field electromagnetic method (WFEM) data. First, we combined the improved intrinsic time scale decomposition and detrended fluctuation analysis algorithm for removing the trend noise. Then, we extracted the time domain characteristics of the WFEM data after removing the trend noise. Next, the arithmetic optimization algorithm was utilized to search for the optimal smoothing factor of the probabilistic neural network (PNN) algorithm, which realized to intelligently identify the noise data and WFEM effective data. Finally, the Fourier transform was performed to extract the spectrum amplitude of the effective frequency points from the reconstructed WFEM data, and the electric field curve was obtained. In these studies and applications, the fuzzy c-mean and PNN algorithm are contrasted. The proposed method indicated that the trend noise can be adaptively extracted and eliminated, the abnormal waveform or noise interference can be intelligently identified, the reconstructed WFEM data can effectively recover the pseudo-random signal waveform, and the shape of electric field curves were more stable. Simulation experiments and measured applications has verified that the proposed method can provide technical support for deep underground exploration.

Compound faults identification for rolling bearing based on variable step-size multiscale weighted Lempel-Ziv complexity

Due to the mutual coupling between sub-faults in the case of compound faults in rolling bearings, coupled with external noise, energy attenuation during information transmission, etc., the acquired fault information is usually very weak and complex. This greatly increases the difficulty of extracting features from bearing compound faults. To further enhance the accuracy of fault feature extraction and achieve precise identification of rolling bearing compound faults, this paper presents an innovative compound fault diagnosis method that integrates variable step-size multiscale weighted Lempel-Ziv complexity (VMW-LZC) and intrinsic time-scale decomposition (ITD). First, considering that the traditional Lempel-Ziv complexity (LZC) method can only extract single-dimensional fault information without thoroughly exploiting fault characteristics, we optimize the coarse-graining process of proper rotation components (PRCs) after ITD using a variable step-size multiscale strategy. Additionally, LZCs obtained from variable step-sizes in each scale are fused and reconstructed using a weighted method. Meanwhile, multiple variable step-size multiscale LZCs are combined into a new signal evaluation index, VMW-LZC. In addition, with the new signal evaluation index VMW-LZC, the optimal PRC which is best representative of fault characteristic information is chosen. Furthermore, frequency spectrum of autocorrelation function of optimal PRC is used to identify multiple faults of bearings. To exemplify the efficiency of presented method, a comparison has been made among the optimal PRC chosen by the methods with VMW-LZC, traditional LZC (T-LZC), multiscale LZC(M-LZC), and classical kurtosis as signal evaluation indexes. The result has indicated that fused signal evaluation index VMW-LZC can actualize more precise option of sensitive fault component signals and the proposed ITD-VMW-LZC method can do a more precise job in identifying a compound fault of bearings.

Research on early fault feature extraction technology of aviation bearing based on noise estimation ITD

Early indications of faults in aircraft bearings are frequently accompanied by excessive noise. To enhance the accuracy of signal decomposition, this study presents the ensemble noise-reconstructed intrinsic time-scale decomposition (ENITD) technique. In addition, a highly sensitive mode component selection method is suggested to attain the goal of improving the precision of fault feature extraction. The findings demonstrate that the ENITD approach is successful in addressing the mode mixing issue and enhancing the precision of fault feature extraction. Unlike established decomposition methods, the estimated noise is applied for denoising instead of incorporating white noise. Furthermore, the estimated noise can introduce diverse frequency signals to their corresponding proper rotation component (PRCs), aiding in resolving the mode mixing problem. This paper examines the efficacy of the ENITD approach for extracting early fault features in aircraft bearings using both simulated and experimental signals.

Detection and time–frequency analysis of multiple plant-wide oscillations using adaptive multivariate intrinsic chirp component decomposition

Analyzing plant-wide oscillations is a challenging task owing to the presence of noise, nonstationarity, and multiple modes in a process control system. Multivariate intrinsic chirp component decomposition (MICCD) is a novel powerful tool for multivariate signal processing. Nevertheless, MICCD requires users to provide component number in advance, which restricts its adaptability. This study proposes an adaptive MICCD (AMICCD) that can adaptively determine the component number by utilizing the permutation entropy of instantaneous frequency. An AMICCD-based time–frequency analysis framework is presented to detect and characterize the multiple plant-wide oscillations. Compared to the latest methods, such as multivariate empirical mode decomposition and multivariate intrinsic time-scale decomposition, the proposed method can process not only single/multiple plant-wide oscillations, but also time-invariant/time-varying plant-wide oscillations. In particular, the proposed method can directly provide the time–frequency curves of multiple plant-wide oscillations, which have not been achieved by the state-of-the-art techniques. Finally, the effectiveness and advantages of the proposed approach are demonstrated on a wide variety of simulations and industrial cases.

Time domain differential protection scheme applied to power transformers

This paper presents a new differential protection scheme for power transformers based on Intrinsic Time-Scale Decomposition (ITD) and Ensemble of Bagged Tree (EBT) as a classifier. The ITD decomposes the input nonstationary signal into Proper Rotation Components (PRCs) and a monotonic trend signal. In the proposed scheme, statistical time-domain features extracted from the ITD output are fed to the EBT classifier, which classifies different events, including internal fault, internal fault combined with inrush current, different inrush currents (energizing transformer, sympathetic, and recovery inrush current), and external fault. The combination of ITD and EBT tools requires only a limited sample of post-fault data to protect the transformer. The proposed scheme is tested under various operating conditions to confirm its accuracy, and the effect of current transformer (CT) saturation on the scheme's performance is evaluated. The scheme is immune to noisy conditions and does not require transformer parameters. The power systems were simulated using PSCAD/EMTDC and MATLAB software.

Sea clutter suppression algorithm in low SCR based on improved fractional Fourier transform

Sea clutter suppression and target detection under complex sea states in low signal-to-clutter ratio (SCR) is the key of current maritime detection research. The target extraction ability of most algorithms is mostly based on accurate modeling of sea clutter, but sea clutter is complex and unstable, which is difficult to accurately model, especially in poor sea states. According to the characteristics of the target echo signal, this paper introduces intrinsic time-scale decomposition (ITD) to preprocess the echo signal to improve the algorithm effect under low SCR. Secondly, the too much cycles in searching for optimal transformation in fractional Fourier transform (FRFT) is improved to reduce the calculation cost and extract the target signal accurately. The effectiveness and reliability of the proposed method are verified by simulation and measured experiments under different SCR and different transform order interval Δp, and the sea clutter suppression ability and target extraction accuracy are measured by parameters such as the detection rate, the gain of SCR and the running time. Compared with FRFT-related algorithms, the results indicates that the proposed algorithm can effectively suppress sea clutter and accurately extract target signal even at SCR = −25 dB in less than half the running time of the comparison algorithms.

An Effective Data-driven Audio Watermarking Technique

Abstract: Audio piracy remains a persistent issue, highlighting the crucial need to protect audio signals and respect intellectual property rights. To tackle this challenge, we propose a two-step procedure consisting of intrinsic time scale decomposition (ITD) and Singular Value Decomposition (SVD).In our approach, the audio to be watermarked is initially divided into intrinsic mode functions and a low-frequency residue component using an iterative time scale decomposition technique. Subsequently, we apply Singular Value Decomposition to both the low-frequency component and the watermark. This allows us to embed the watermark within the residue component of the audio.To generate the watermarked audio, we combine the intrinsic mode functions with the watermarked residue component using inverse Intrinsic Time Scale Decomposition. This ensures that the watermark becomes integrated into the audio signal. Notably, our proposed approach effectively addresses computational complexity, a common challenge, while also prioritizing robustness and imperceptibility in line with advanced methods employed in the field.

Analysis and classification of gait patterns in osteoarthritic and asymptomatic knees using phase space reconstruction, intrinsic time-scale decomposition and neural networks

Analysis and classification of gait patterns in osteoarthritic and asymptomatic knees using phase space reconstruction, intrinsic time-scale decomposition and neural networks

Faulty phase identification and ground detection in TCSC compensated lines integrated with wind farms

Nowadays there is a trend for offshore wind farms to be connected with power grids through a TCSC series controlled compensating device employed in transmission lines for the improvement of large power flows. In such transmission lines, faulty phase identification and ground detection create a challenge for conventional distance relaying schemes because of non-linear output power fluctuation due to variations in wind speed and different firing angle operations of TCSC. Therefore, to overcome the problem of such transmission lines relaying, a novel time-frequency analysis-based intrinsic time scale decomposition (ITD) method is proposed in this paper. The proposed intrinsic time scale decomposition method uses only a three-phase grid side current from relaying end for faulty phase and ground detection and ITD supported random forest classifier for fault classification accuracy approach. The evaluation of the proposed scheme is tested on several fault cases with varying system parameters and non-fault transient events through the EMTDC/PSCAD platform during different wind speeds and varying firing angle operations of TCSC. The performance of the proposed scheme is also verified through a real-time interface dSPACE DS 1104 control prototype hardware. Finally, a comparison analysis with existing techniques demonstrated the effectiveness of the presented method to assess the mentioned problem of the conventional protective relaying schemes. The proposed method demonstrated a 100% accuracy for faulty phase selection and a 99.99% accuracy for fault classification.

A fault diagnosis for rolling bearing based on multilevel denoising method and improved deep residual network

Aiming at the problem that weak faults in rolling bearings make effective fault diagnosis difficult under strong noise, this paper proposes a multilevel denoising technology based on improved singular value decomposition (ISVD) and intrinsic timescale decomposition (ITD), combined with an improved deep residual network (ResNet), for fault diagnosis in rolling bearings. Firstly, the difference ratio (DR) index is introduced to optimize singular value decomposition, combined with ITD for multilevel denoising of strong noise signals. Effective fault information in bearing vibration signals is extracted and converted into grayscale images. Secondly, the multi-scale feature extraction module (MFE-Module) is introduced to enhance the feature extraction capability of ResNet, and the support vector machine (SVM) is used instead of the Softmax function to identify and classify the fault features. The experimental results indicate that, compared with other methods, the proposed method can more accurately realize the fault diagnosis of rolling bearings in strong noise environments.

Complex Disturbances Identification: A Novel PQDs Decomposition and Modeling Method

In the context of unprecedented attention to renewable energy, wind and photovoltaic power generation are widely used. However, this process introduces a large number of solid-state switching and non-linear loads, which makes power quality disturbances (PQDs) complex and brings unknown challenges to power-pollution control. As a prerequisite for power-pollution control, this paper proposes an automatic PQDs classification approach that is suitable for complicated phenomena. First, an ensemble intrinsic time-scale decomposition (EITD) method is proposed to decompose the PQDs, which overcomes the decomposition level's endpoint effect and frequency aliasing by adding Gaussian noise and integrating multiple sub-components. Then, utilizing the global depth-wise convolution layer and parameter rectified linear unit, a global depth-wise shuffle CNN (GSCNN) is proposed to improve the performance and reduce the number of parameters. Based on EITD and GSCNN, an automatic framework is proposed to identify and classify complex PQDs. Simulation experiments and hardware platform tests show that the proposed framework has superior performance for complex and even nonlinear disturbances under different noise.

Effect of Subject-Specific Region of Interest on Motor Imagery Brain–Computer Interface

A brain–computer interface (BCI), as a solution to disabled people’s concerns, has drawn attention in biomedical engineering over the last decade. However, the most existing brain–computer interface systems are based on the time or frequency domain of feature extraction, and it is associated with inaccurate detection of event-related desynchronization (ERD). In this study, a new algorithm relating to subject-specific regions of interest (ROIs) with intrinsic time-scale decomposition (ITD) was investigated to achieve satisfactory classification accuracy. ROI-based discrete wavelet transform (DWT) combined with an artificial neural network was used to validate the ROI-based ITD method. Experimentally recorded data of motor imagery movement tasks (right hand, left hand, both hands and both feet) were collected from 15 subjects. The parameters of the subject-specific regions of interest were investigated and optimized. An optimal condition was observed at a specific region of interest and the accuracy increased by 12.76 to 15.17% compared to that without ROI estimation. ITD showed higher classification accuracy, sensitivity, specificity and Kappa coefficient of 9.47%, 8.99%, 9.79% and 12.09%, respectively, for the four classes of motor imagery movements compared to DWT. The developed ITD model was validated using the dataset from BCI Competition IV. On average, ITD with ROIs showed 8.56% and 7.32% higher classification accuracy compared to common spatial patents (CSP) and DWT with ROIs.

Quantitative identification of pulse-like ground motions based on intrinsic time-scale decomposition technique

Pulse-like earthquake ground motions may cause great seismic demands in engineering structures, and identifying these ground motions is significant in earthquake engineering. The intrinsic time-scale decomposition (ITD) is a self-adaptive time-frequency decompaction method that decomposes signals into proper rotation components. The instantaneous frequency and amplitude of the components are well defined, and the temporal information of frequency and amplitude has the exact resolution with the time-scale of extreme of the original signal. ITD was introduced in this study to decompose the non-stationary earthquake ground motion signals. A procedure for filtering and extracting the low-frequency pulses was constructed, and a quantitative criterion for classifying the pulse-like ground motions was proposed. The proposed method was tested on many ground motions and compared with the existing classification methods. The proposed method was demonstrated as an effective way to identify the pulse-like ground motion records, which can be readily implemented in earthquake engineering practices.

An improved multifractal detrended fluctuation analysis method for estimating the dynamic complexity of electrical conductivity of karst springs

Abstract Due to the influences of geological structures, many confined ascending springs occur in North China's karst area. The electrical conductivity (EC) of karst spring flow is a fundamental variable in characterizing karst systems. However, deeply exploring hidden nonlinear dynamic characteristics is challenging. To avoid overreliance on the fitting polynomial order in the detrending process via classic multifractal detrended fluctuation analysis (MFDFA), the intrinsic time-scale decomposition (ITD) method was applied to identify the external data trend term by decomposing the original data into different frequency modes, and the ITD-MFFA method was proposed to reveal the formation mechanism of spring EC complex characteristics in Jinan's spring area. The results showed that the EC sequences of North China's karst springs are characterized by multifractal behavior and anti-persistence and exhibit multiyear complexity with an overall decreasing trend. Different recharge sources, formation conditions, and seasonal precipitation could be the primary factors driving spring EC complexity. Compared to those of the traditional MFDFA method, the ITD-MFFA method achieved improved anti-interference ability and stability. Timely determination of spring EC data dynamic complexity and monitoring future spring water quality trends can provide guiding significance for protecting karst springs.

Detecting the Third Heart Sound: Separation and Localization from Lung Sound using Intrinsic Time Scale Decomposition

Detecting the Third Heart Sound: Separation and Localization from Lung Sound using Intrinsic Time Scale Decomposition