Multiscale Dispersion Entropy Research Articles

Research on Novel Bearing Fault Diagnosis Method Based on Improved Krill Herd Algorithm and Kernel Extreme Learning Machine

In this paper, a novel bearing intelligent fault diagnosis method based on a novel krill herd algorithm (NKH) and kernel extreme learning machine (KELM) is proposed. Firstly, multiscale dispersion entropy (MDE) is used to extract fault features of bearings to obtain a set of fault feature vectors composed of dispersion entropy. Then, it is imported into the kernel extreme learning machine for fault diagnosis. But considering the kernel function parameters σ and the error penalty factor C will affect the classification accuracy of the kernel extreme learning machine, this paper uses the novel krill herd algorithm (NKH) for their optimization. The opposite populations are added to the NKH in the initialization of population to improve its speed and prevent local optimum, and during the period of looking for the optimal solution, the impulse operator is introduced to ensure it has enough impulse to rush out of the local optimal once into the local optimum. Finally, in order to verify the effectiveness of the proposed method, it was applied to the bearing fault experiment of Case Western Reserve University and XJTU‐SY bearing data set. The results show that the proposed method not only has good fault diagnosis performance and generalization but also has fast convergence speed and does not easily fall into the local optimum. Therefore, this paper provides a method for fault diagnosis under different loads. Meanwhile, the new method (NKH‐KELM) is compared and analyzed with other mainstream intelligent bearing fault diagnosis methods to verify the effectiveness and accuracy of the proposed method.

Multiscale Fluctuation-Based Dispersion Entropy and Its Applications to Neurological Diseases

Fluctuation-based dispersion entropy (FDispEn) is a new approach to estimate the dynamical variability of the fluctuations of signals. It is based on Shannon entropy and fluctuation-based dispersion patterns. To quantify the physiological dynamics over multiple time scales, multiscale FDispEn (MFDE) is developed in this paper. MFDE is robust to the presence of baseline wanders or trends in the data. We evaluate MFDE, compared with popular multiscale sample entropy (MSE), multiscale fuzzy entropy (MFE), and the recently introduced multiscale dispersion entropy (MDE), on selected synthetic data and five neurological diseases' datasets: 1) focal and non-focal electroencephalograms (EEGs); 2) walking stride interval signals for young, elderly, and Parkinson's subjects; 3) stride interval fluctuations for Huntington's disease and amyotrophic lateral sclerosis; 4) EEGs for controls and Alzheimer's disease patients; and 5) eye movement data for Parkinson's disease and ataxia. The MFDE avoids the problem of the undefined MSE values and, compared with the MFE and MSE, leads to more stable entropy values over the scale factors for white and pink noises. Overall, the MFDE is the fastest and most consistent method for the discrimination of different states of neurological data, especially where the mean value of a time series considerably changes along with the signal (e.g., eye movement data). This paper shows that MFDE is a relevant new metric to gain further insights into the dynamics of neurological diseases' recordings. The MATLAB codes for the MFDE and its refined composite form are available in Xplore.

Detection of Acute Tonic Cold Pain From Microwave Transcranial Transmission Signals Obtained via the Microwave Scattering Approach

To investigate the feasibility of detecting acute tonic cold pain (CP) perception from recordable microwave transcranial transmission (MTT) signals by using machine learning techniques. CP and no-pain (NP) MTT signals collected from 15 young subjects are analyzed in the wavelet packet transformation (WPT) and variational mode decomposition (VMD) domains. In addition, features such as relative energy change, refined composite multiscale dispersion entropy, refined composite multiscale fuzzy entropy, and autoregressive model coefficients are extracted in the WPD, VMD, VMD-WPD, and WPD-VMD domains. Simultaneously, support vector machine (SVM) is selected as the classifier, and feature indexes are input into the classifier by using the 10-fold cross validation method to obtain the best training and test datasets. Principal component analysis is used to reduce the feature dimensions of the training and test datasets and to improve classification accuracy. Then, the test dataset is imported into the trained classifier for the calculation and evaluation of the model's classification performance. In the validation of the SVM classifier, feature extraction in the WPD-VMD domain is the best pain detection algorithm. It provides high values of sensitivity (91.30%), specificity (90.47%), positive predictive value (91.30%), accuracy (90.90%), and area under curve (0.806). The microwave scattering technique can be used as a direct, objective, and experimentally stable method to detect acute CP perception, this approach has a high application prospect for clinical real-time diagnosis.

Noise Reduction Method of Underwater Acoustic Signals Based on CEEMDAN, Effort-To-Compress Complexity, Refined Composite Multiscale Dispersion Entropy and Wavelet Threshold Denoising.

Owing to the problems that imperfect decomposition process of empirical mode decomposition (EMD) denoising algorithm and poor self-adaptability, it will be extremely difficult to reduce the noise of signal. In this paper, a noise reduction method of underwater acoustic signal denoising based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), effort-to-compress complexity (ETC), refined composite multiscale dispersion entropy (RCMDE) and wavelet threshold denoising is proposed. Firstly, the original signal is decomposed into several IMFs by CEEMDAN and noise IMFs can be identified according to the ETC of IMFs. Then, calculating the RCMDE of remaining IMFs, these IMFs are divided into three kinds of IMFs by RCMDE, namely noise-dominant IMFs, real signal-dominant IMFs, real IMFs. Finally, noise IMFs are removed, wavelet soft threshold denoising is applied to noise-dominant IMFs and real signal-dominant IMFs. The denoised signal can be obtained by combining the real IMFs with the denoised IMFs after wavelet soft threshold denoising. Chaotic signals with different signal-to-noise ratio (SNR) are used for denoising experiments by comparing with EMD_MSE_WSTD and EEMD_DE_WSTD, it shows that the proposed algorithm has higher SNR and smaller root mean square error (RMSE). In order to further verify the effectiveness of the proposed method, which is applied to noise reduction of real underwater acoustic signals. The results show that the denoised underwater acoustic signals not only eliminate noise interference also restore the topological structure of the chaotic attractors more clearly, which lays a foundation for the further processing of underwater acoustic signals.

Intelligent fault diagnosis of rotating machinery using improved multiscale dispersion entropy and mRMR feature selection

Intelligent fault diagnosis of rotating machinery is essentially a pattern recognition problem. Meanwhile, effective feature extraction from the raw vibration signal is an important procedure for timely detection of mechanical health status and the assessment of fault recognition results. Therefore, to efficiently extract fault feature information and improve fault diagnosis accuracy, a novel fault diagnosis technique based on improved multiscale dispersion entropy (IMDE) and max-relevance min-redundancy (mRMR) is proposed in this paper. Firstly, the IMDE method is developed to capture multi-scale fault features from the collected original vibration signal, which can overcome the deficiencies of traditional multiscale entropy and improve the stability of the recently presented multiscale dispersion entropy (MDE). Then, the mRMR algorithm is utilized to select automatically the sensitive features from the candidate multi-scale features without any prior knowledge. Finally, the sensitive feature vector set after normalization treatment is inputted into the extreme learning machine (ELM) classifier to train the intelligent diagnosis model and provide fault diagnosis results. The validity of our proposed method is assessed through two experimental examples. The experimental results show that our proposed method works efficiently for identification of different fault conditions of mechanical components including rolling bearing and gearbox. Moreover, our proposed method gives better diagnosis results as compared to some existing approaches (e.g. MSE and MPE) when being utilized for fault condition classification. This research provides a new perspective for fault information extraction and fault classification of rotating machinery.

Sleep stage classification using single-channel EOG

Sleep stage classification is an important task for the timely diagnosis of sleep disorders and sleep-related studies. In this paper, automatic scoring of sleep stages using Electrooculogram (EOG) is presented. Single channel EOG signals are analyzed in Discrete Wavelet Transform (DWT) domain employing various statistical features such as Spectral Entropy, Moment-based Measures, Refined Composite Multiscale Dispersion Entropy (RCMDE) and Autoregressive (AR) Model Coefficients. The discriminating ability of the features is studied using the One Way Analysis of Variance (ANOVA) and box plots. A feature reduction algorithm based on Neighborhood Component Analysis is used to reduce the model complexity and select the features with highest discriminating abilities. Random Under-Sampling Boosting (RUSBoost), Random Forest (RF) and Support Vector Machine (SVM) are employed to classify various sleep stages for 2–6 stage classification problem. Performance of the proposed method is studied using three publicly available databases, the Sleep-EDF, Sleep-EDFX and ISRUC-Sleep databases consisting of 8, 20 and 10 subjects respectively. The proposed method outperforms the state-of-the-art EOG based techniques in accuracy. In addition, its performance is shown to be on par or better than those of various single channel EEG based methods. An important limitation of existing sleep detection methods is the low accuracy of the S1 sleep stage classification for which the proposed method using the RUSBoost classifier gives a superior accuracy as compared to those of EOG and EEG based techniques.

Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy

As one of the most important components in rotating machinery, it’s necessary and essential to monitor the rolling bearing operating condition to prevent equipment failure or accidents. However, in vibration signal processing, the bearing initial fault detection under background noise is quite difficult. Therefore, in this paper a new feature extraction method combining sparse reconstruction and Multiscale Dispersion Entropy (MDErms) is proposed. Firstly, the Sliding Matrix Sequences (SMS) truncation and sparse reconstruction by Hankel-matrix are applied to the vibration signal. Then MDErms is utilized as a characteristic index of vibration signal, which is suitable for a short time series. Additionally, the MDErms is employed in the sparse reconstructed matrix sequences to achieve the Multiscale Fusion Entropy Value Sequence (MFEVS). The MFEVS keeps the fault potential feature information in different scales and is superior in distinguishing fault periodic impulses from heavy background noise. Finally, the designed FIR bandpass filter based on the MFEVS, shows prominent features in denoising and detecting weak bearing faults, which is separately verified by simulation studies and artificial fault experiments in different cases. By comparison with traditional methods like EEMD, Wavelet Packet (WP), and fast kurtogram, it can be concluded that the proposed method has a remarkable ability in removing noise and detecting rolling bearing faint fault.

Changes in the Complexity of Heart Rate Variability with Exercise Training Measured by Multiscale Entropy-Based Measurements.

Quantifying complexity from heart rate variability (HRV) series is a challenging task, and multiscale entropy (MSE), along with its variants, has been demonstrated to be one of the most robust approaches to achieve this goal. Although physical training is known to be beneficial, there is little information about the long-term complexity changes induced by the physical conditioning. The present study aimed to quantify the changes in physiological complexity elicited by physical training through multiscale entropy-based complexity measurements. Rats were subject to a protocol of medium intensity training () or a sedentary protocol (). One-hour HRV series were obtained from all conscious rats five days after the experimental protocol. We estimated MSE, multiscale dispersion entropy (MDE) and multiscale SDiff from HRV series. Multiscale SDiff is a recent approach that accounts for entropy differences between a given time series and its shuffled dynamics. From SDiff, three attributes (q-attributes) were derived, namely SDiff, and . MSE, MDE and multiscale q-attributes presented similar profiles, except for SDiff. showed significant differences between trained and sedentary groups on Time Scales 6 to 20. Results suggest that physical training increases the system complexity and that multiscale q-attributes provide valuable information about the physiological complexity.

Multiscale dispersion entropy for the regional analysis of resting-state magnetoencephalogram complexity in Alzheimer's disease.

Alzheimer's disease (AD) is a progressive and irreversible brain disorder of the nervous system affecting memory, thinking, and emotion. It is the most important cause of dementia and an influential social problem in all the world. The complexity of brain recordings has been successfully used to help to characterize AD. We have recently introduced multiscale dispersion entropy (MDE) as a very fast and powerful tool to quantify the complexity of signals. The aim of this study is to assess the ability of MDE, in comparison with multiscale permutation entropy (MPE) and multiscale entropy (MSE), to discriminate 36 AD patients from 26 elderly age-matched control subjects using resting-state magnetoencephalogram (MEG) recordings. The results showed that MDE, unlike MSE, does not lead to undefined values. Moreover, the differences between the MDE values for AD palatines versus controls were more significant than their corresponding MSE- and MPE-based values. In addition, the computation time for our recently developed MDE was considerably less than that for MSE and even MPE.

Refined Composite Multiscale Dispersion Entropy and its Application to Biomedical Signals.

We propose a novel complexity measure to overcome the deficiencies of the widespread and powerful multiscale entropy (MSE), including, MSE values may be undefined for short signals, and MSE is slow for real-time applications. We introduce multiscale dispersion entropy (DisEn-MDE) as a very fast and powerful method to quantify the complexity of signals. MDE is based on our recently developed DisEn, which has a computation cost of O(N), compared with O(N2) for sample entropy used in MSE. We also propose the refined composite MDE (RCMDE) to improve the stability of MDE. We evaluate MDE, RCMDE, and refined composite MSE (RCMSE) on synthetic signals and three biomedical datasets. The MDE, RCMDE, and RCMSE methods show similar results, although the MDE and RCMDE are faster, lead to more stable results, and discriminate different types of physiological signals better than MSE and RCMSE. For noisy short and long time series, MDE and RCMDE are noticeably more stable than MSE and RCMSE, respectively. For short signals, MDE and RCMDE, unlike MSE and RCMSE, do not lead to undefined values. The proposed MDE and RCMDE are significantly faster than MSE and RCMSE, especially for long signals, and lead to larger differences between physiological conditions known to alter the complexity of the physiological recordings. MDE and RCMDE are expected to be useful for the analysis of physiological signals thanks to their ability to distinguish different types of dynamics. The MATLAB codes used in this paper are freely available at http://dx.doi.org/10.7488/ds/1982.