【摘要】：針對(duì)特征選擇算法對(duì)不同類型的數(shù)據(jù)集性能不穩(wěn)定的問題,提出一種基于概率模型與改進(jìn)Shapley權(quán)力指數(shù)的通用特征選擇算法.首先,計(jì)算特征對(duì)類簇表征與類簇判別的重要性值;然后,計(jì)算特征對(duì)類簇的不確定度;最終,合并特征的重要性值與不確定度,提取合適的特征.因?yàn)楦怕誓Ｐ蛯?duì)數(shù)據(jù)類型、數(shù)據(jù)缺陷具有較好的魯棒性,所以對(duì)不同的數(shù)據(jù)集獲得了穩(wěn)定、高性能的特征選擇效果.基于人工合成數(shù)據(jù)與benchmark數(shù)據(jù)集的實(shí)驗(yàn)結(jié)果表明,本算法對(duì)不同的數(shù)據(jù)集保持了穩(wěn)定的特征選擇效果,優(yōu)于其他算法.
[Abstract]:A general feature selection algorithm based on probabilistic model and improved Shapley power index is proposed to solve the problem of unstable performance of feature selection algorithm for different types of data sets. Firstly, the importance of feature to cluster representation and cluster discrimination is calculated; then, the uncertainty of feature to cluster is calculated; finally, the importance value and uncertainty of feature are merged to extract the appropriate feature. Because the probabilistic model is robust to data types and data defects, it can obtain a stable and high performance feature selection effect for different data sets. Experimental results based on synthetic data and benchmark datasets show that the proposed algorithm has a stable feature selection effect on different datasets and is superior to other algorithms.
【作者單位】： 鎮(zhèn)江市高等�？茖W(xué)校裝備制造學(xué)院;
【分類號(hào)】：TP301.6
，

本文編號(hào)：2177612