An enhanced ensemble machine learning classification method to detect attention deficit hyperactivity for various artificial intelligence and telecommunication applications. (21st February 2022)

• Record Type: Journal Article
• Authors: Sheriff, Meeran; Gayathri, Rajagopal
• Is Part Of: Computational intelligence. Volume 38:Number 4(2022)
• Page Start: 1327
• Page End: 1337
• Publication Date: 2022-02-21
• Subjects: ADHD -- boosting -- classification -- ensemble method -- machine learning; Artificial intelligence -- Periodicals; Computational linguistics -- Periodicals; 006.3
• DOI: 10.1111/coin.12509
• Languages: English
• ISSNs: 0824-7935

Abstract

Abstract: Attention Deficit Hyperactivity Disorder (ADHD) is a common mental health disorder in teenager groups and it consists of a combination of problems. ADHD is a neurodevelopmental condition that manifests itself in children and adolescents as inattention, hyperactivity, and impulsivity. This research proposes a novel classification approach using BoostAlexNet model for ADHD automatic diagnosis. It consists of different pretrained methods like ResNet 101, NASNet, Xception, MobileNet, and InceptionV3. Based on the pretrained model, input MRI images are processed and integrated for the detection of abnormalities in ADHD MRI brain images of patients. The BoostAlexNet model is evaluated and comparatively observed with the existing techniques. The dataset for processing consists of 1359 CT images composed of ADHD and non‐ADHD. The validation range is set as 50 for each case with a total value of 150 and the network is trained with MRI images of 1069 for classification. The analysis of results expressed that BoostAlexNet exhibits higher accuracy, sensitivity, and specificity value of 93.67%, 0.93, and 0.97, respectively. The proposed BoostAlexNet classification technique achieves an accuracy of 93.67%. The developed model provides improved accuracy than the existing techniques.