Comparison of prediction strategy for high accuracy in autism diagnostic system (ADS) using ML classifiers.
In: AIP Conference Proceedings; 2023, Vol. 2477 Issue 1, p1-8, 8p; Jg. 2477 (2023-04-03) 1, S. 1-8
Konferenz
Zugriff:
According to the current statistics in the worldwide, it is estimated that one in 150 children are suffering from autism spectrum disorder, in which boys are four times more effected than girl child. Mostly the reasons are found with individual is genetic or chromosomal conditions causing the severity in ASD. It is also found that the medicine that parents consume during pregnancy is another root cause for occurrence of ASD in the early childhood. One of the general procedures for detection of ASD in children is regular visits of doctors. As of now there is no perfect medical test in particular. The child's developmental history is one of the basis to diagnose the ASD. Mostly ASD can be detected at the age of 18 months or still younger than that. The existing machine learning based detection methods relaying on few attributes that are not sufficient in confirming the better accuracy prediction analysis. This paper inflates the use of machine learning algorithms in prediction analysis with mere improvement in accuracies. The work carried out using three different algorithms i.e logistic regression, support vector machine (SVM) and decision tree. These three are selected basically due to their interdependency of attributes and also on complexity variation in the implementation. From the results it is observed that SVM has got better results with a prediction accuracy of 96%, followed by decision tree with a prediction accuracy of 92% for the chosen ASD dataset belongs to children below 3 years. However Logistic Regression is least considered due low accuracy prediction of 72%. [ABSTRACT FROM AUTHOR]
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Titel: |
Comparison of prediction strategy for high accuracy in autism diagnostic system (ADS) using ML classifiers.
|
---|---|
Autor/in / Beteiligte Person: | Parvathi, M. |
Quelle: | AIP Conference Proceedings; 2023, Vol. 2477 Issue 1, p1-8, 8p; Jg. 2477 (2023-04-03) 1, S. 1-8 |
Veröffentlichung: | 2023 |
Medientyp: | Konferenz |
ISSN: | 0094-243X (print) |
DOI: | 10.1063/5.0125291 |
Schlagwort: |
|
Sonstiges: |
|