“Comparative Study of Classification Algorithms on Sonar Rock and Mine Dataset”

Accurate classification is essential for the safety of naval operations and is a difficult problem in marine mine removal. In this research, this study compares and contrasts six popular machine learning algorithms for classifying rocks and mines: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Logistic Regression (LR), Linear Discriminant Analysis, Gaussian Naive Bayes, Decision tree. The models are trained and evaluated using different performance metrics, such as accuracy, precision, recall, and F1 score. The data were carefully analyzed and compared, and it was discovered that SVM performed better than the other algorithms, obtaining an accuracy of 94.23%. The creation of more precise and effective classification models in numerous real-world applications, such as naval operations and other undersea pursuits, will be significantly impacted by these discoveries. The study emphasizes the significance of choosing the right method for classification tasks.