About this document

KNN vs SVM for Biomedical Anomaly Detection by Kalpana Murthy is a document available to read on EtoBox.

This study presents an automated pipeline for detecting anomalies in biomedical images using K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) classifiers, focusing on texture-based features extracted via Gray Level Co-occurrence Matrix (GLCM). The KNN model outperformed SVM, achieving 67.56% accuracy and an AUC of 0.72, while SVM showed only 50.16% accuracy and a high disagreement rate of 48.27% between the models. The findings highlight the importance of effective feature extraction and classifie

Author

Kalpana Murthy

Language

EN