ADHD Classification Using Convolution Neural Network | ||||
| International Journal of Engineering and Applied Sciences-October 6 University | ||||
| Article 16, Volume 1, Issue 1, July 2024 PDF (516.43 K) | ||||
| Document Type: Research Article | ||||
| DOI: 10.21608/ijeasou.2024.374365 | ||||
 View on SCiNiTO | ||||
| Abstract | ||||
| attention deficit hyperactivity disorder (ADHD) is one of the most common neurodevelopmental disorders in childhood. Some people with ADHD primarily experience symptoms of inattention. Others mostly have symptoms of hyperactivity and impulsivity; some people experience both types of symptoms. This was further confirmed by preprocessing the fMRI raw data and extracting optimal feature methodology. Moreover, the CNN model that was used as a learning model was able to drive an accurate model with preprocessed fMRI data and features extracted. Stochastic gradient ratios with momentum (SGDM) optimizers of the fMRI datasets. Using this optimization technique for adapting the classification system of ADHD cases, it was concluded that the accuracy of PROP 1 is 97.5%, accuracy for PROP 2 is 95%, and accuracy for PROP 3 is 98.75. Finally, it’s found that PROP 3 is the best because of its high accuracy, so the system is improved. | ||||
| Keywords | ||||
| ADHD; fMRI; CNN; and Deep Learning | ||||
|
Statistics Article View: 254 PDF Download: 159 |
||||
