In this paper, R wave peak interval independent atrial fibrillation detection algorithm is proposed based on the analysis of the synchronization feature of the electrocardiogram signal by a deep neural network. Firstly, the synchronization feature of each heartbeat of the electrocardiogram signal is constructed by a Recurrence Complex Network. Then, a convolution neural network is used to detect atrial fibrillation by analyzing the eigenvalues of the Recurrence Complex Network. Finally, a voting algorithm is developed to improve the performance of the beat-wise atrial fibrillation detection. The MIT-BIH atrial fibrillation database is used to evaluate the performance of the proposed method. Experimental results show that the sensitivity, specificity, and accuracy of the algorithm can achieve 94.28%, 94.91%, and 94.59%, respectively. Remarkably, the proposed method was more effective than the traditional algorithms to the problem of individual variation in the atrial fibrillation detection.

Orthogonal experimental design in general belongs to a single target design, using conventional visual analysis and variance analysis to select the best and the most influential factors combination. However, in actual production, the product needs more than one indicator to be inspected, belonging to multi-index test design, and each index on the influence degree of product performance is different, and there is a reasonable question of empowerment. Aiming at the difficulties in determining each experiment index weight by experimental design of an integrated multi-index weighted scoring method, this paper analyzed the respective shortcomings of current widely used subjective and objective weighting approach, proposed taking into account the subjective preferences and objective information in a comprehensive weight assignment method, so that a comprehensive analysis of the weighted scoring system more reasonable, in order to enhance the reliability of analysis results to find a new way.

No abstract

No abstract

No abstract