An Optimistic K-Nearest Neighbor Algorithm for Detecting Brain Stroke in Comparison with Logistic Regression Algorithm to Improve the Accuracy

A. Chandra, Jaisharma K.

2023

Abstract

The study aimed to improve stroke prediction accuracy using the Novel Optimistic K-Nearest Neighbor Algorithm (NOKNN) and contrast its efficacy with Logistic Regression (LR). The research utilized both the NOKNN and LR algorithms to diagnose brain strokes through machine learning. A sample of 40 was employed for evaluation, split equally between the two algorithms. The aim was to amplify the overall precision of the research. The ClinCalc tool was used for accuracy assessment, set with specific parameters like a 0.8 alpha, 0.8 G-Power, 0.05 significance value, and a 95% Confidence Interval. Results demonstrated NOKNN’s superior performance with an accuracy of 98.5%, compared to LR’s 93.05%. Following an independent T-test, statistical significance was evident. Advances in technology underline the importance of sophisticated supervised solutions, with NOKNN outperforming LR in this context.

Paper Citation

in Harvard Style

Chandra A. and K. J. (2023). An Optimistic K-Nearest Neighbor Algorithm for Detecting Brain Stroke in Comparison with Logistic Regression Algorithm to Improve the Accuracy. 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 37-43. DOI: 10.5220/0012543400003739

in Bibtex Style

@conference{ai4iot23,
author={A. Chandra and Jaisharma K.},
title={An Optimistic K-Nearest Neighbor Algorithm for Detecting Brain Stroke in Comparison with Logistic Regression Algorithm to Improve the Accuracy},
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={37-43},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012543400003739},
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 Optimistic K-Nearest Neighbor Algorithm for Detecting Brain Stroke in Comparison with Logistic Regression Algorithm to Improve the Accuracy
SN - 978-989-758-661-3
AU - Chandra A.
AU - K. J.
PY - 2023
SP - 37
EP - 43
DO - 10.5220/0012543400003739
PB - SciTePress