【摘要】 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．更多还原

【Abstract】 K-L transform is an optimal transform under the criteria of MMSE and an important data compression method of body surface potential maps (BSPM). In this paper, the neural network calculation method is discussed and applied to the K-L transform and the data compression of BSPM. Experiments show that K-L transform based on neural network is as good as the conventional calculation method.更多还原