ADPDF: A hybrid attribute discrimination method for psychometric data with fuzziness

The existing approaches for attribute discrimination are applied to clinical data with unambiguous boundaries, and rarely take into careful consideration on how to utilize psychometric data with fuzziness. In addition, it is difficult for conventional attribute reduction methods to reduce attributes of psychometric data which are composed of a lot of attributes and contain a relatively small-scale samples. Importantly, these methods cannot be used to reduce options which are relevant to each other. In this paper, we first introduce new concepts, that is, option entropy and option influence degree, which are employed to describe the relation and distribution of options. Then, we propose a hybrid attribute discrimination method for psychometric data with fuzziness, called a hybrid attribute discrimination for psychometric data with fuzziness (ADPDF). ADPDF contains three essential techniques: 1) a fuzzy option reduction method, which aims to combine a fuzzy option to adjacent options, and is used to reduce the fuzziness of options in a psychometry and 2) k-fold attribute reduction method, which partitions all samples into several subsets and negotiates the reduction results of different subsets, and reduces the noise for the purpose of accurately discovering key attributes. In order to show the advantages of the proposed approach, we conducted experiments on two real datasets collected from clinical diagnoses. The experimental results show that the proposed method can decrease the correlation between options effectively. Interestingly, we find three reserved options and one hundred samples in each subset show the best classification performance. Finally, we compare the proposed method with typical attribute discrimination algorithms. The results reveal that our method can improve the classification accuracy with the guarantee of time performance.