量子神经网络在心电图分类中的应用

Neural Network Algorithm and Application of the ECG Classification

将量子叠加的概念引入前向神经网络,提出了量子神经网络的计算模型。量子神经网络分类器是将量子迁移(量子间隔)概念引入前向神经网络,在隐含层和输出层借鉴量子理论中的量子迁移(量子间隔)思想,神经元采用多个激励函数的叠加,形成对特征空间的多级划分,在训练过程中,量子神经元能够根据需要伸展或坍塌。当输入模糊信息时,该算法可以学习数据集中的不精确性或不确定性,具有较高的分类精度。将该算法应用于心电图诊断中,结果表明具有较好的分类效果和较快的训练速度。

By introducing quantum superposition into neural networks, this paper proposes a model of quantum neural network, in which the units in the hidden and output layers adopt the superposition of multi-level activation functions to obtain the multi-lever partitions of the feature space. During the training, the units can be ＂collapsed-in＂ and ＂spread-out＂ according to practical requirement. Moreover, this proposed algorithm can learn the inaccuracy and uncertainties from the input of fuzzy information. It is shown from the application for ECG classification that the proposed algorithm has faster training speed and better performance.