2014 | OriginalPaper | Chapter
Classification of Early Autism Based on HPLC Data
Author : T. Kristensen
Published in: XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
In this work a technique for early autism identification has been developed. For classification a Multi-Layered Perceptron (MLP) neural network and a Support Vector Machine (SVM) have been used. Early identification of autism is important because the prognosis for treating autism is then much better. The patterns used to train both systems are extracted from HPLC data of urine. The database consists of two types of samples, from normal and autistic children. The classification rate has been estimated to about 80 % or better for both algorithms. From the experiments we may conclude that the algorithm that gave the best results was SVM. All the software to do the analysis has been developed in Java.