In this paper, automatic electrocardiogram (ECG) recognition and classification algorithms based on multifractal detrended fluctuation analysis (MF-DFA) and multifractal detrended cross-correlation analysis (MF-DXA) were studied. As human heart is a complex, nonlinear, chaotic system, using multifractal analysis to analyze chaotic systems is also a trend. We performed a comparison study of the multifractal nature of the healthy subjects and that of the cardiac dysfunctions ones. To analyze multifractal property quantitatively, the ranges of the Hurst exponent (Δh) are computed by MF-DFA and MF-DXA. We found that for MF-DFA, the area of Hurst exponents for atrial premature beat (APB) people was narrower than normal sinus rhythm (NSR) subjects, and for MF-DXA, the difference of Δh (Δ(Δh)) of NSR and APB subjects was larger than that of MF-DFA. We then regarded the Hurst exponents (h) as the input vectors and took them into support vector machine (SVM) for classification. The results showed that h obtained from MF-DXA led to a higher classification accuracy than that of MF-DFA. This is related to the widening of the difference in the values of Hurst exponents in MF-DFA and MF-DXA. The proposed MF-DFA-SVM and MF-DXA-SVM systems achieved classification accuracy of 86.54% ± 0.068% and 98.63% ± 0.0644%, achieved classification sensitivity of 75.03% ± 0.1323% and 90.77% ± 0.1309%, achieved classification specificity of 86.66% ± 0.1131% and 96.47% ± 0.0891%, respectively. In general, the Hurst exponents obtained from MF-DXA played an important role in classifying ECG of the healthy and that of the cardiac dysfunctions subjects. Moreover, MF-DXA was more accurate than MF-DFA in the classification of ECG studied in this paper. The research in automatic medical diagnosis and early warning of major diseases has very important practical value.

中文翻译：

---

MF-DFA 和 MF-DXA 之间的心电图分类比较

本文研究了基于多重分形去趋势波动分析（MF-DFA）和多重分形去趋势互相关分析（MF-DXA）的心电图（ECG）自动识别和分类算法。由于人的心脏是一个复杂的、非线性的、混沌系统，使用多重分形分析来分析混沌系统也是一种趋势。我们对健康受试者和心脏功能障碍受试者的多重分形性质进行了比较研究。为了定量分析多重分形性质，赫斯特指数的范围（ΔH) 由 MF-DFA 和 MF-DXA 计算。我们发现，对于 MF-DFA，房性早搏 (APB) 人的 Hurst 指数区域比正常窦性心律 (NSR) 受试者窄，而对于 MF-DXA，差异ΔH(Δ(ΔH)) 的 NSR 和 APB 受试者大于 MF-DFA。然后我们考虑赫斯特指数（H) 作为输入向量并将它们带入支持向量机 (SVM) 进行分类。结果表明，H从 MF-DXA 获得的分类精度高于 MF-DFA。这与 MF-DFA 和 MF-DXA 中赫斯特指数值差异的扩大有关。所提出的 MF-DFA-SVM 和 MF-DXA-SVM 系统实现了86.54% ± 0.068%和98.63% ± 0.0644%，实现了分类灵敏度75.03% ± 0.1323%和90.77% ± 0.1309%，实现了分类特异性86.66% ± 0.1131%和96.47% ± 0.0891%， 分别。一般来说，从 MF-DXA 获得的 Hurst 指数在分类健康和心功能不全受试者的心电图方面发挥了重要作用。此外，在本文研究的心电图分类中，MF-DXA 比 MF-DFA 更准确。重大疾病的自动医学诊断与预警研究具有非常重要的实用价值。