AUTHOR=Zhao Feng , Ye Shixin , Zhang Mingli , Lv Ke , Qiao Xiaoyan , Li Yuan , Mao Ning , Ren Yande , Zhang Meiying 

TITLE=Multi-classifier fusion based on belief-value for the diagnosis of autism spectrum disorder

JOURNAL=Frontiers in Human Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/human-neuroscience/articles/10.3389/fnhum.2023.1257987

DOI=10.3389/fnhum.2023.1257987

ISSN=1662-5161

ABSTRACT=Autism spectrum disorder (ASD) have a significant impact on patients' health, and early diagnosis and treatment are crucial for improving their quality of life. Machine learning methods, including multi-classifier fusion, are widely studied for disease diagnosis and prediction. In this paper, we propose a multi-classifier fusion classification framework based on belief-value for ASD diagnosis. The belief-value measures the belief level of different samples based on distance information (the output distance of the classifier) and local density information (the weight of the nearest neighbor samples on the test samples), which is more representative than using a single type of information.Then belief-values are calculated under different features and capture the complementary relationship between them by using a multilayer perceptual (MLP) network. Compared to other fusion methods, MLP network produces better diagnostic results by capturing the nonlinear relationship between beliefvalues. Experimental results demonstrate the effectiveness of proposed classification framework for neuropsychiatric disorder diagnosis.