Heart sound signals reflect valuable information about heart condition. Previous studies have suggested that the information contained in single-channel heart sound signals can be used to detect coronary artery disease (CAD). But accuracy based on single-channel heart sound signal is not satisfactory. This paper proposed a method based on multi-domain feature fusion of multi-channel heart sound signals, in which entropy features and cross entropy features are also included. A total of 36 subjects enrolled in the data collection, including 21 CAD patients and 15 non-CAD subjects. For each subject, five-channel heart sound signals were recorded synchronously for 5 min. After data segmentation and quality evaluation, 553 samples were left in the CAD group and 438 samples in the non-CAD group. The time-domain, frequency-domain, entropy, and cross entropy features were extracted. After feature selection, the optimal feature set was fed into the support vector machine for classification. The results showed that from single-channel to multi-channel, the classification accuracy has increased from 78.75% to 86.70%. After adding entropy features and cross entropy features, the classification accuracy continued to increase to 90.92%. The study indicated that the method based on multi-domain feature fusion of multi-channel heart sound signals could provide more information for CAD detection, and entropy features and cross entropy features played an important role in it.

As a severe hazard in coal mining and rock excavation, the rockburst is usually induced by the high energy tremor. Microseismic (MS) monitoring is suggested to forecast the rockburst risk to reduce its damage. The paper aims to investigate contribution of multi-MS data, including MS raw wave data and MS energy data, to prediction of the high energy tremor, using support vector machine (SVM) together with genetic algorithm (GA). MS monitoring data recorded for more than 400 days at Wudong coal mine of Xinjiang, China, were used in the paper. 132 and 24 features are initially extracted from MS raw wave and energy data in the frequency domain, entropy and time-frequency domain, respectively. GA is not only used to select effective ones among initially extracted features, but also optimize hyperparameters for SVM to classify high energy tremors from general MS events. The performances of the proposed approach based on multi-MS data are evaluated by cross-validation. The results show that the classifier achieves 98% sensitivity, 88% accuracy and 87% specificity using both MS raw wave and energy data, which is better than solely utilizing MS raw wave (98% sensitivity, 84% accuracy and 83% specificity) or energy data (98% sensitivity, 86% accuracy and 85% specificity). These findings suggest that MS raw wave data makes important contribution to rockburst risk prediction as well as MS energy data, and the better performance can be achieved when utilizing two kinds of data simultaneously.

Heart rate variability (HRV) has been widely used in the non-invasive evaluation of cardiovascular function. Recent studies have also attached great importance to the cardiac diastolic period variability (DPV) examination. Short-term variability measurement (e.g., 5 min) has drawn increasing attention in clinical practice, since it is able to provide almost immediate measurement results and enables the real-time monitoring of cardiovascular function. However, it is still a contemporary challenge to robustly estimate the HRV and DPV parameters based on short-term recordings. In this study, a refined fuzzy entropy (rFuzzyEn) was developed by substituting a piecewise fuzzy membership function for the Gaussian function in conventional fuzzy entropy (FuzzyEn) measure. Its stability and robustness against additive noise compared with sample entropy (SampEn) and FuzzyEn, were examined by two well-accepted simulation models—the $$ 1/f^{\alpha } $$ noise and the Logistic attractor. The rFuzzyEn was further applied to evaluate clinical short-term (5 min) HRV and DPV of the patients with coronary artery stenosis and healthy volunteers. Simulation results showed smaller fluctuations in the rFuzzyEn than in SampEn and FuzzyEn values when the data length was decreasing. Besides, rFuzzyEn could distinguish the simulation models with different amount of additive noise even when the percentage of additive noise reached 60%, but neither SampEn nor FuzzyEn showed comparable performance. Clinical HRV analysis did not indicate any significant differences between the patients with coronary artery disease and the healthy volunteers in all the three mentioned entropy measures (all p > 0.20). But clinical DPV analysis showed that the patient group had a significantly higher rFuzzyEn (p < 0.01) than the healthy group. However, no or less significant difference was observed between the two groups in either SampEn (p = 0.14) or FuzzyEn (p = 0.05). Our proposed rFuzzyEn outperformed conventional SampEn and FuzzyEn in terms of both stability and robustness against additive noise, particularly when the data set was relatively short. Analysis of DPV using rFuzzyEn may provide more valuable information to assess the cardiovascular states than the other entropy measures and has a potential for clinical application.