Soft Computing Models for the Predictive Grading of Childhood Autism- A Comparative Study
Anju Pratap1, C. S. Kanimozhiselvi2, R. Vijayakumar3, K. V. Pramod4
1Anju Pratap, Research Scholar, Anna University, Chennai, India.
2Dr. C. S. Kanimozhiselvi, Department of Computer Science and Engineering, Kongu Engineering College, Perundurai, Erode, India.
3Dr. R. Vijayakumar, School of Computer Sciences, Mahatma Gandhi University, Kerala, India.
4Dr. K. V. Pramod, School of Computer Applications, Cochin University of Science and Technology, Kerala, India
Manuscript received on June 25, 2014. | Revised Manuscript received on July 03, 2014. | Manuscript published on July 05, 2014. | PP: 64-67 | Volume-4, Issue-3, July 2014. | Retrieval Number: C2293074314 /2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Artificial intelligence technique is a problem solving method, by simulating human intelligence where reasoning is done from previous problems and their solutions. Soft computing consists of artificial intelligence based models that can deal with uncertainty, partial truth, imprecision and approximation. This article discusses about the performance of some soft computing models for the predictive grading of childhood autism. Now a day’s, childhood autism is a common neuro-psychological developmental problem among children. Early and accurate intervention is needed for the correct grading of this disorder. Result demonstrates that soft computing techniques provide acceptable prediction accuracy in autism grading by dealing with the uncertainty and imprecision.
Keywords: Soft computing, autism, naïve bayes model, neural network, classifier combination model.