Liang, Shuaibing and Loo, Chu Kiong and Sabri, Aznul Qalid Md (2020) Autism spectrum disorder classification in videos: A hybrid of temporal coherency deep networks and self-organizing dual memory approach. In: iCatse International Conference on Information Science and Applications (ICISA), 16-18 December 2019, Seoul, South Korea.
Full text not available from this repository.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.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| 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 |
| Additional Information: | iCatse International Conference on Information Science and Applications (ICISA), Seoul, SOUTH KOREA, DEC 16-18, 2019 |
| Uncontrolled Keywords: | Artificial intelligence; Neural networks |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Computer Science & Information Technology > Department of Artificial Intelligence |
| Depositing User: | Ms Zaharah Ramly |
| Date Deposited: | 01 Jun 2023 02:12 |
| Last Modified: | 01 Jun 2023 02:12 |
| URI: | http://eprints.um.edu.my/id/eprint/37086 |
Actions (login required)
 |
View Item |
