Recognition algorithm of Parkinson's disease based on weighted local discriminant preservation projection embedded ensemble algorithm

Konferenz: BIBE 2019 - The Third International Conference on Biological Information and Biomedical Engineering
20.06.2019 - 22.06.2019 in Hangzhou, China

Tagungsband: BIBE 2019

Seiten: 6Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Liu, Yuchuan; Tan, Xiaoheng; Wang, Pin; Li, Yongming (School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China)
Zhang, Yanling (First Affiliated Hospital of Army Medical University, Chongqing, China)

Machine learning is an important tool for data analysis and mining in Parkinson. The current problems with Parkinson's disease data are high redundancy, high noise, and small sample size. Dimension reduction can effectively solve these problems. However, there are few literatures on dimensionality reduction methods for data analysis and mining of Parkinson's disease, meanwhile the stability and accuracy are not satisfactory. In order to solve this problem, this paper proposes a weighted local discriminant preservation projection embedded ensemble algorithm. Compared with the existing feature selection and feature extraction algorithm, the algorithm proposed in this paper can significantly improve the diagnostic accuracy of Parkinson's disease.