In order to supplement the lost information in feature compression, this method extracts 10-dimension principal components by PCA. The 10-dimension features and 2-dimension CpG island features, based on integrated features, are put into the BP neural network classifier.
为了弥补在特征压缩过程中缺失了一部分特征信息,提取基因序列的CpG岛信息作为补充特征,将这2维CpG岛特征与10维主成分特征进行特征综合,共同作为BP神经网络的输入来识别启动子。
参考来源 - 基因序列数据的启动子识别系统研究·2,447,543篇论文数据，部分数据来源于NoteExpress
The problem of feature compression in high-resolution radar target recognition is studied.
研究了宽带高分辨雷达目标识别中的特征压缩问题。
Based on resolution reduction, neural network is then utilized for feature compression, which can effectively reduce the dimension of features.
在降低图像解析度的基础上使用神经网络来进行特征压缩，可以有效地降低特征维数。
The new fuzzy classification system has some advantages as follows: (1) good interpretability, (2) efficient feature compression, (3) comparative accuracy to the traditional methods.
新模糊分类系统具有以下优点：(1)可解释性好，(2)有效的特征压缩，(3)与传统方法相当的识别精度。
应用推荐