RT info:eu-repo/semantics/article
T1 Multi-Class Classifier in Parkinson’s Disease Using an Evolutionary Multi-Objective Optimization Algorithm
A1 Rojas Valenzuela, Ignacio
A1 Valenzuela, Olga
A1 Delgado Márquez, Elvira
A1 Rojas, Fernando
A2 Economia Aplicada
K1 Economía
K1 Estadística
K1 Parkinson’s disease (PD)
K1 3D-discrete wavelet transform (3D-DWT)
K1 Support vector machine (SVM)
K1 Multi-objective optimization evolutionary algorithm (MOE)
K1 Minimum redundancy maximum relevance (mRMR)
AB [EN] In this contribution, a novel methodology for multi-class classification in the field ofParkinson’s disease is proposed. The methodology is structured in two phases. In a first phase,the most relevant volumes of interest (VOI) of the brain are selected by means of an evolutionarymulti-objective optimization (MOE) algorithm. Each of these VOIs are subjected to volumetric featureextraction using the Three-Dimensional Discrete Wavelet Transform (3D-DWT). When applying3D-DWT, a high number of coefficients is obtained, requiring the use of feature selection/reductionalgorithms to find the most relevant features. The method used in this contribution is based onMutual Redundancy (MI) and Minimum Maximum Relevance (mRMR) and PCA. To optimizethe VOI selection, a first group of 550 MRI was used for the 5 classes: PD, SWEDD, Prodromal,GeneCohort and Normal. Once the Pareto Front of the solutions is obtained (with varying degrees ofcomplexity, reflected in the number of selected VOIs), these solutions are tested in a second phase.In order to analyze the SVM classifier accuracy, a test set of 367 MRI was used. The methodologyobtains relevant results in multi-class classification, presenting several solutions with different levelsof complexity and precision (Pareto Front solutions), reaching a result of 97% as the highest precisionin the test data.
PB MDPI
LK https://hdl.handle.net/10612/19942
UL https://hdl.handle.net/10612/19942
NO Rojas-Valenzuela, I., Valenzuela, O., Delgado-Márquez, E., y Rojas, F. (2022). Multi-Class Classifier in Parkinson’s Disease Using an Evolutionary Multi-Objective Optimization Algorithm. Applied Sciences , 12(6), 3048. https://doi.org/10.3390/APP12063048.
DS BULERIA. Repositorio Institucional de la Universidad de León
RD 16-jun-2024