A STUDY ON DIAGNOSIS OF AUTISM SPECTRAL DISORDER USING ARTIFICIAL INTELLIGENCE TECHNIQUES
Author(s):
SOWMYASHREE K N, Dr. PADMASHREE S
Keywords:
ASD, deep learning; Convolution Neural Network; training classifiers; Graphics Processing Unit. EEG,MRI Scan.
Abstract
Autism Spectrum Disorder(ASD) is a collection of heterogeneous disorders with prevalent cognitive and behavioral abnormalities. It is a complex neurological disorder that have a lifelong effect on the event of assorted talents and skills. Electroencephalography (EEG) studies have been identified as one of the most widely used tool for assessing the cognitive functions. But now a days MRI scan also suggested for proper diagnosis of ASD. There is a discussion of deep learning on the raw signal without explicit hand-crafted feature extraction. Because the EEG signal has subject dependency, it is better to train the emotion model subject-wise, while there is not much epochs available for each subject. Deep learning algorithm provides a solution with a pre-training way using three layers of restricted Boltzmann machines (RBMs). Thus, epochs of all subjects to pre-training the deep network, and use back propagation to fine tuning the network subject by subject. The foremost vital goal of the paper is to review the autism problem, to detect the levels of autism with the help of data mining classification algorithms. The data mining has been typically accepted as a decision making process to facilitate higher resource utilization in terms of autism students’ performance.
Article Details
Unique Paper ID: 145074
Publication Volume & Issue: Volume 4, Issue 7
Page(s): 225 - 229
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024