An Accurate Approach to Classify Real Time Indian Twins Using SVM and Compare the Performance over Logistic Regression

Vallipi Dasaratha, J. Sheela

2023

Abstract

The study aims to increase the accuracy of comparing and classifying the Real Time Indian Twins using Support Vector Machine (SVM) over Logistic Regression (LR) algorithm.Face Recognition of twins with face and ID recognition using Support Vector Machine(SVM) over Logistic Regression. Here the analysis was carried out with two groups named as Group 1 and 2 with sample iteration of 40 where each group consist of 20 sample iterations, for a sample size of 1430. Results and Discussion: Compare and identify The Real Time Indian Twins and also its Performance using SVMand Logistic Regression Algorithms. The SVM and LR have achieved the accuracy of 62.2650% and 31.0225%. respectively. By comparing the accuracy of the two algorithms, independent samples tests reveal an accuracy gap between the two methods that is statistically significant of p=0.001 (p<0.05) which shows that the hypothesis is significant and is carried out using an independent sample T- test. Conclusion: The findings clearly demonstrates that SVM has an excellent accuracy of 62.265% when compared to Logistic Regression whose accuracy is 31.0225%.

Paper Citation

in Harvard Style

Dasaratha V. and Sheela J. (2023). An Accurate Approach to Classify Real Time Indian Twins Using SVM and Compare the Performance over Logistic Regression. In Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT; ISBN 978-989-758-661-3, SciTePress, pages 378-384. DOI: 10.5220/0012772700003739

in Bibtex Style

@conference{ai4iot23,
author={Vallipi Dasaratha and J. Sheela},
title={An Accurate Approach to Classify Real Time Indian Twins Using SVM and Compare the Performance over Logistic Regression},
booktitle={Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT},
year={2023},
pages={378-384},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012772700003739},
isbn={978-989-758-661-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Artificial Intelligence for Internet of Things: Accelerating Innovation in Industry and Consumer Electronics - Volume 1: AI4IoT
TI - An Accurate Approach to Classify Real Time Indian Twins Using SVM and Compare the Performance over Logistic Regression
SN - 978-989-758-661-3
AU - Dasaratha V.
AU - Sheela J.
PY - 2023
SP - 378
EP - 384
DO - 10.5220/0012772700003739
PB - SciTePress