phat 24(1):

Research Article

Autism Spectrum Disorder Classification Using Machine Learning and Deep Learning- A Survey

Download105 downloads
  • @ARTICLE{10.4108/eetpht.9.4240,
        author={Reeja S R and Sunkara Mounika},
        title={Autism Spectrum Disorder Classification Using Machine Learning and Deep Learning- A Survey},
        journal={EAI Endorsed Transactions on Pervasive Health and Technology},
        volume={9},
        number={1},
        publisher={EAI},
        journal_a={PHAT},
        year={2023},
        month={10},
        keywords={ASD, CNN, Machine Learning, DBN},
        doi={10.4108/eetpht.9.4240}
    }
    
  • Reeja S R
    Sunkara Mounika
    Year: 2023
    Autism Spectrum Disorder Classification Using Machine Learning and Deep Learning- A Survey
    PHAT
    EAI
    DOI: 10.4108/eetpht.9.4240
Reeja S R1,*, Sunkara Mounika1
  • 1: Vellore Institute of Technology University
*Contact email: reeja.sr@vitap.ac.in

Abstract

Modern, highly developed technology has impacted reputable procedures in the medical and healthcare industries. Smart healthcare prediction to the senior sick patient is not only for quick access to data but also to get dependable treatment in an accurate prediction by healthcare service provider. smart health prediction helps in the identification of numerous diseases. Based on patient experience, Deep learning technology provides a robust application space in the medical sector for health disease prediction problems by applying deep learning techniques to analyze various symptoms. In order to classify things and make precise predictions about diseases, deep learning techniques are utilized. people's health will be more secure, medical care will be of a higher caliber, and personal information will be kept more secret. As deep learning algorithms become more widely used to construct an interactive smart healthcare prediction and evaluation model on the basis of the deep learning model, CNN is upgraded. Advanced deep learning algorithms combined with multi-mode approaches and resting-state functional magnetic resonance represent an innovative approach that researchers have taken. A DL structure for the programmed ID ASD using highlights separated from the corpus callosum and cerebrum volume from the Stand dataset is proposed. Imaging is used to reveal hidden diseased brain connectome patterns to find diagnostic and prognostic indicators.