Identification of vulnerability analysis using convolutional neural networks and compare prediction accuracy over support vector machine.

Autor:	Kumar, K. Lakshman, Thinakaran, K.
Předmět:	CONVOLUTIONAL neural networks SUPPORT vector machines IDENTIFICATION STATISTICAL significance AUTOMATIC speech recognition
Zdroj:	AIP Conference Proceedings; 2023, Vol. 2822 Issue 1, p1-7, 7p
Abstrakt:	The main motto of the study is to detect hatred speech by using CNN and SVM algorithms to detect hatred speech and comparing their accuracy. Detects hatred speech using Machine learning algorithm using Convolutional Neural Network and Support Vector Machine. Here the pretest power analysis was carried out with 80% and the sample size for the two groups are CNN (N=10) and SVM (N=10) to predict hatred speech.CNN has significantly got better accuracy (96.97%) compared to SVM accuracy (88.87%). The statistical significance of CNN.05 (p<0.05 independent sample test) is high.CNN Means clustering performs significantly better than the SVM in detection of hatred speech. [ABSTRACT FROM AUTHOR]
Databáze:	Complementary Index
Externí odkaz:	Zobrazit plný text záznamu