论文部分内容阅读
Ｋ－Ｌ变换是均方误差准则意义下的最佳交换，是心电地图数据压缩的重要方法．但Ｋ－Ｌ变换的常规算法计算量大，目前又无快速算法，实现困难．本文采用人工神经网络算法来实现Ｋ－Ｌ变换，并将其应用于心电地图的数据压缩，实验结果表明：该网络算法具有设计简单、易于实现以及对数据扰动的稳健性等优点，其压缩效果与Ｋ－Ｌ变换常规算法相当．
K-L transform is the best exchange under the mean square error criterion, which is an important method of ECG data compression. However, the conventional algorithm of K-L transform has a large amount of computation, and at present, there is no fast algorithm to realize the difficulty. In this paper, the artificial neural network algorithm is used to realize K-L transform, which is applied to data compression of ECG map. The experimental results show that the proposed algorithm has the advantages of simple design, easy implementation and robustness to data perturbations. The compression The effect is equivalent to the conventional K-L transform algorithm.