Designing a supervised feature selection technique for mixed attribute data analysis
Designing a supervised feature selection technique for mixed attribute data analysis
复制标题
DOI：
10.1016/j.mlwa.2022.100431
复制
发表时间：
2022-11
影响因子：
--
通讯作者：
D. Jeong;Bong-Keun Jeong;Nandi O. Leslie;Charles A. Kamhoua;Soo-Yeon Ji
中科院分区：
文献类型：
--
作者：
D. Jeong;Bong-Keun Jeong;Nandi O. Leslie;Charles A. Kamhoua;Soo-Yeon Ji
识别最佳特征对于提高数据分类的整体性能至关重要。本文介绍了一种用于分析混合属性数据的有监督特征选择技术。它使用用户定义的性能标准来衡量特征的数据分类性能，并确定最佳特征以提高整体数据分析性能。通过方差分析、卡方检验、主成分分析和互信息等现有特征选择技术进行性能评估，以突出该技术的有用性。可视化也被用来理解在分类具有不同特征的实例时的差异。从比较性能测试和评估，我们发现5 - 10%的性能改进所提出的技术。总体而言，评价结果表明，我们提出的特征选择技术在混合属性数据分析的实用性。
Identifying optimal features is critical for increasing the overall performance of data classification. This paper introduces a supervised feature selection technique for analyzing mixed attribute data. It measures data classification performances of features with a user-defined performance criterion and determines optimal features to boost the overall data analysis performance. A performance evaluation is managed to highlight the usefulness of the technique with existing feature selection techniques such as analysis of variance test, chi-square test, principal component analysis, and mutual information. Visualization is also utilized to understand the differences in classifying instances with different features. From a comparative performance testing and evaluation, we found 5∼ 10% performance improvements with the proposed technique. Overall, evaluation results showed the usefulness of our proposed feature selection technique in mixed attribute data analysis.