NeuroSpectra : Revolutionizing Autism detection through AI
Priyanka H. L , Pavan. B , Rohithnaik. S , S. M Yathin , Sinchana S. V
Malnad College of Engineering, Hassan-573202, Karnataka, India
phl@mcehassan.ac.in, pavanbasavaraj25@gmail.com, rohithnaiks2003@gmail.com, sm.yathin4@gmail.com , janapada147@gmail.com
Abstract: Identifying and Assessing Autism Spectrum Disorder is usually dependent on the behavioral Developments in the human life and the condition known as Autism Spectrum Disorder is an neurological and developmental disorder which occurs during the initial stages of the child life i.e the initial two years of child birth. As per the recent census this a neurodevelopmental condition characterized by challenges in social interaction and communication affects 1% across the entire world’s population. While its primary origin lies in genetics, early detection is crucial, and leveraging machine learning offers a promising avenue for a faster and more cost-effective diagnosis. This disorder is mainly caused due to environmental changes it is very essential for the world to detect and diagnose this disorder in the early stages of the life as it brings behavioral changes in the human beings so in order to detect this disorder and to increase the accuracy in the detection of this disorder we apply the AI technologies specifically the predictive models powered by machine learning and Neural networks. In the Machine learning models our approach involves supervised learning algorithms such as the Support Vector-based classifiers Random Forest algorithms to detect the disorder in Adults and We apply convolutional neural networks (CNN) in conjunction with a Recurrent Neural Network (RNN) to detect ASD in Children. Where the machine learning algorithm works on feature selection and the symptoms which are there in the Autism spectrum disorder which includes the behavioural changes which will be present in the individual if they are having autism spectrum disorder.
Keywords : Autism spectrum disorder, Neural network, Machine learning, Feature selection, Supervised learning
