Autism spectrum disorder classification in videos: A hybrid of temporal coherency deep networks and self-organizing dual memory approach

Document Type

Conference Item

Publication Date

1-1-2020

Abstract

Autism is at the moment, a common disorder. Prevalence of Autism Spectrum Disorder (ASD) is reported to be 1 in every 88 individuals. Early diagnosis of ASD has a significant impact to the livelihood of autistic children and their parents, or their caregivers. In this paper, we have developed an unsupervised online learning model for ASD classification. The proposed approach is a hybrid approach, consisting, the temporal coherency deep networks approach, and, the self-organizing dual memory approach. The primary objective of the research is, to have a scalable system that can achieve online learning, and, is able to avoid the catastrophic forgetting phenomena in neural networks. We have evaluated our approach using an ASD specific dataset, and obtained promising results that are well inclined in supporting the overall objective of the research.

Keywords

Artificial intelligence, Neural networks

Divisions

ai

Funders

Frontier Research Grant from University of Malaya (FG003-17AFR),University Malaya Research Grant (RP061C-18SBS),Office of Naval Research (ONRG-NICOP-N62909-18-1-2086)/IF017-2018,UAEU-AUA Joint Research Program Fund

Volume

621

Publisher

SPRINGER-VERLAG SINGAPORE PTE LTD

Publisher Location

152 BEACH ROAD, #21-01/04 GATEWAY EAST, SINGAPORE, 189721, SINGAPORE

Event Title

iCatse International Conference on Information Science and Applications (ICISA)

Event Location

Seoul, South Korea

Event Dates

16-18 December 2019

Event Type

conference

Additional Information

iCatse International Conference on Information Science and Applications (ICISA), Seoul, SOUTH KOREA, DEC 16-18, 2019

This document is currently not available here.

Share

COinS