An Improved Composite Multiscale Fuzzy Entropy for Feature Extraction of MI-EEG

Li, Mingai; Wang, Ruo-Tu; Xu, Dongqin

doi:10.3390/e22121356

Cited by 13 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many nonlinear measures have been proposed to investigate EEG's nonlinear dynamic characteritics. For example, multivariate multi-scale weighted permutation entropy (PE) has been used to analyze the EEG complexity of Alzheimer's disease [7], multivariate transfer entropy has been shown to measure brain network deterioration in schizophrenia [8], and fuzzy entropy has been applied to explore the temporal variability in spatial topology during motor imagery EEG and resting-state network dynamics [9,10]. Symbolic dynamic measure is considered an important methodology for characterizing the nonlinear features of the complex system [11].…”

Section: Introductionmentioning

confidence: 99%

Cortical complexity and connectivity during isoflurane-induced general anesthesia: a rat study

et al. 2022

View full text Add to dashboard Cite

Objective: The investigation of neurophysiologic mechanisms of anesthetic drug-induced loss of consciousness (LOC) by using the entropy, complexity, and information integration theories at the mesoscopic level has been a hot topic in recent years. However, systematic research is still lacking. Approach: We analyzed electrocorticography (ECoG) data recorded from nine rats during isoflurane-induced unconsciousness. To characterize the complexity and connectivity changes, we investigated ECoG power, symbolic dynamic-based entropy (i.e., permutation entropy (PE)), complexity (i.e., permutation Lempel-Ziv complexity (PLZC)), information integration (i.e., permutation cross mutual information (PCMI)), and PCMI-based cortical brain networks in the frontal, parietal, and occipital cortical regions. Main results: Firstly, LOC was accompanied by a raised power in the ECoG beta (12-30 Hz) but a decreased power in the high gamma (55-95 Hz) frequency band in all three brain regions. Secondly, PE and PLZC showed similar change trends in the lower frequency band (0.1-45 Hz), declining after LOC (p<0.05) and increasing after recovery of consciousness (p<0.001). Thirdly, intra-frontal and inter-frontal-parietal PCMI declined after LOC, in both lower (0.1-45Hz) and higher frequency bands (55-95Hz) (p<0.001). Finally, the local network parameters of the nodal clustering coefficient and nodal efficiency in the frontal region decreased after LOC, in both the lower and higher frequency bands (p<0.05). Moreover, global network parameters of the normalized average clustering coefficient and small world index increased slightly after LOC in the lower frequency band. However, this increase was not statistically significant. Significance: The PE, PLZC, PCMI and PCMI-based brain networks are effective metrics for qualifying the effects of isoflurane.

show abstract

Section: Introductionmentioning

confidence: 99%

Cortical complexity and connectivity during isoflurane-induced general anesthesia: a rat study

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To eliminate individualized differences, in our experiments, the signal was normalized using Z-score before the power calculation ( Shi et al., 2022 ). As ( Li et al., 2020 ), the signals x ( n ) was first divided into L segments x ′ by the sliding window as

where

represents the number of segments. N and w are the length of x ( n ) and the sliding window (the segment length), respectively.…”

Section: Methodsmentioning

confidence: 99%

“…To eliminate individualized differences, in our experiments, the signal was normalized using Z-score before the power calculation (Shi et al, 2022). As (Li et al, 2020), the signals x(n) was first divided into L segments x ′ by the sliding window as…”

Section: Powermentioning

confidence: 99%

Machine learning-aided detection of heart failure (LVEF ≤ 49%) by using ballistocardiography and respiratory effort signals

Feng

Wu²,

Bao³

et al. 2023

Front. Physiol.

View full text Add to dashboard Cite

Purpose: Under the influence of COVID-19 and the in-hospital cost, the in-home detection of cardiovascular disease with smart sensing devices is becoming more popular recently. In the presence of the qualified signals, ballistocardiography (BCG) can not only reflect the cardiac mechanical movements, but also detect the HF in a non-contact manner. However, for the potential HF patients, the additional quality assessment with ECG-aided requires more procedures and brings the inconvenience to their in-home HF diagnosis. To enable the HF detection in many real applications, we proposed a machine learning-aided scheme for the HF detection in this paper, where the BCG signals recorded from the force sensor were employed without the heartbeat location, and the respiratory effort signals separated from force sensors provided more HF features due to the connection between the heart and the lung systems. Finally, the effectiveness of the proposed HF detection scheme was verified in comparative experiments.Methods: First, a piezoelectric sensor was used to record a signal sequences of the two-dimensional vital sign, which includes the BCG and the respiratory effort. Then, the linear and the non-linear features w.r.t. BCG and respiratory effort signals were extracted to serve the HF detection. Finally, the improved HF detection performance was verified through the LOO and the LOSO cross-validation settings with different machine learning classifiers.Results: The proposed machine learning-aided scheme achieved the robust performance in the HF detection by using 4 different classifiers, and yielded an accuracy of 94.97% and 87.00% in the LOO and the LOSO experiments, respectively. In addition, experimental results demonstrated that the designed respiratory and cardiopulmonary features are beneficial to the HF detection (LVEF ≤49%).Conclusion: This study proposed a machine learning-aided HF diagnostic scheme. Experimental results demonstrated that the proposed scheme can fully exploit the relationship between the heart and the lung systems to potentially improve the in-home HF detection performance by using both the BCG, the respiratory and the cardiopulmonary-related features.

show abstract

“…When the vibration signal contains strong interference and noise, the use of a single surface feature extraction method can easily lead to the reduction of diagnosis accuracy [31]. In recent years, Entropy theory has been applied to mechanical equipment fault diagnosis by many scholars in many forms such as Fuzzy Entropy [32], Sample Entropy [33], and Approximate Entropy [34]. The effectiveness of relevant entropy has been verified to a certain extent [35][36][37][38].…”

Section: B Feature Extractionmentioning

confidence: 99%

Combine Assembly Quality Detection Based on Multi-Entropy Data Fusion and Optimized LSSVM

Zhao

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

To solve the problems related to the complex structures, multiple parts, and imperceptible assembly quality of combines, this paper compares the performance of the empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), complete ensemble empirical mode decomposition (CEEMD), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and information entropy features in the detection data of combine assembly quality, and proposes a vibration detection method of combine assembly quality detection based on multi-entropy feature fusion and optimized least squares support vector machine. Firstly, the vibration signals of the combine are decomposed by various adaptive algorithms, and intrinsic modal function (IMF) components are obtained. Three entropy features are extracted from the components of the modes. The features are visualized by t-distributed stochastic neighbor embedding (t-SNE), and the performance of these entropy features in the combine assembly quality detection is analyzed. Secondly, a feature extraction method based on information entropy fusion is proposed. The optimized kernel principal component analysis (KPCA) is used to fuse and reduce the dimension of the entropy features, and form the fusion features. Finally, the extracted features are imported into optimization least squares support vector machine (LSSVM) model for training to judge the working state and assembly quality problem type of combine. The results show that the accuracy of using the unfused entropy features is 82.5%, the accuracy of the fused features is 87.9%. After WOA optimization, the accuracy of the final classification reaches 92.1%, which is better than 89.6% by GA and 90.5% by PSO. It shows that the method proposed in this paper can accurately identify combine problems with different conditions and can be applied to combine assembly quality detection.

show abstract

An Improved Composite Multiscale Fuzzy Entropy for Feature Extraction of MI-EEG

Cited by 13 publications

References 21 publications

Cortical complexity and connectivity during isoflurane-induced general anesthesia: a rat study

Cortical complexity and connectivity during isoflurane-induced general anesthesia: a rat study

Machine learning-aided detection of heart failure (LVEF ≤ 49%) by using ballistocardiography and respiratory effort signals

Combine Assembly Quality Detection Based on Multi-Entropy Data Fusion and Optimized LSSVM

Contact Info

Product

Resources

About