The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Prediction of Parkinson's Disease Severity Based on Feature Optimization
Abstract
Voice disorders are one of the incipient symptoms of Parkinson's disease (PD). Most of the existing PD severity prediction methods are based on baseline features, and generally select features with high relevance for dimensionality reduction. To further improve the prediction performance, the LDFSF and GWT-RF-Att methods are proposed respectively from the perspective of feature selection and feature transformation. The LDFSF method utilizes dynamic feature selection strategy based on SOM clustering to select feature subsets with high correlation, low redundancy, and high complementarity from voice features. The GWT-RF-Att method uses graph wavelet transform to extract the more effective feature set based on the baseline features, and uses random forest improved by attention mechanism to improve the prediction performance of the model. The results on the Parkinson's telemonitoring dataset show that the performance of the two methods is better than that of the existing comparison methods, thus verifying their effectiveness.
Related Content
Yu Bin, Xiao Zeyu, Dai Yinglong.
© 2024.
34 pages.
|
Liyin Wang, Yuting Cheng, Xueqing Fan, Anna Wang, Hansen Zhao.
© 2024.
21 pages.
|
Tao Zhang, Zaifa Xue, Zesheng Huo.
© 2024.
32 pages.
|
Dharmesh Dhabliya, Vivek Veeraiah, Sukhvinder Singh Dari, Jambi Ratna Raja Kumar, Ritika Dhabliya, Sabyasachi Pramanik, Ankur Gupta.
© 2024.
22 pages.
|
Yi Xu.
© 2024.
37 pages.
|
Chunmao Jiang.
© 2024.
22 pages.
|
Hatice Kübra Özensel, Burak Efe.
© 2024.
23 pages.
|
|
|