Multi-atlas Graph Convolutional Networks and Convolutional Recurrent Neural Networks-Based Ensemble Learning for Classification of Autism Spectrum Disorders
- Title
- Multi-atlas Graph Convolutional Networks and Convolutional Recurrent Neural Networks-Based Ensemble Learning for Classification of Autism Spectrum Disorders
- Creator
- Lamani M.R.; Benadit P.J.; Vaithinathan K.
- Description
- Autism spectrum disorder (ASD) has an influence on social conversation and interaction, as well as encouraging people to engage in repetitive behaviors. The complication begins in childhood and persists through adolescence and maturity. Autism spectrum disorder has become the most common kind of childhood development worldwide. ASD hinders the capacity to interact, socialize, and build connections with individuals of all ages, and thus its early intervention is critical. This paper discusses some of the most recent approaches to diagnostics using convolutional networks and multi-atlas graphs for autism spectrum disorders. Also, several pre-processing approaches are elaborated. Graph convolutional neural networks (GCNs) to diagnose autism spectrum disorder (ASD) because of their remarkable effectiveness in illness prediction using multi-site data. Convolutional neural network (CNN) and recurrent neural networks (RNN) infrastructure studies functional connection patterns between various brain regions to find particular patterns to diagnose ASD. In our research, we implemented the GCN + CRNN ensemble method and achieved 89.01% accuracy based on resting-state data from the fMRI (ABIDE-II), a novel framework for detecting early signs of autism spectrum disorders is presented and discussed. 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.
- Source
- SN Computer Science, Vol-4, No. 3
- Date
- 2023-01-01
- Publisher
- Springer
- Subject
- Autism spectrum disorder; Automatic diagnosis; Deep learning; Ensemble learning; Graph convolution network
- Coverage
- Lamani M.R., Computer Science and Engineering, CHRIST (Deemed to be University), Bangalore, India; Benadit P.J., Computer Science and Engineering, CHRIST (Deemed to be University), Bangalore, India; Vaithinathan K., Computer Engineering, Karaikal Polytechnic College, Varichikudy, Karaikal, India
- Rights
- Restricted Access
- Relation
- ISSN: 2662995X
- Format
- Online
- Language
- English
- Type
- Article
Collection
Citation
Lamani M.R.; Benadit P.J.; Vaithinathan K., “Multi-atlas Graph Convolutional Networks and Convolutional Recurrent Neural Networks-Based Ensemble Learning for Classification of Autism Spectrum Disorders,” CHRIST (Deemed To Be University) Institutional Repository, accessed March 4, 2025, https://archives.christuniversity.in/items/show/14271.