• Shruti Pathak
• Vaibhavi Raul
• Pushpak Desale
• Deep Bhandari
• Priti Sanjekar

In marine operations, sonar devices are essential, especially for finding submerged objects like rocks and mines. Ensuring maritime safety and security requires the ability to distinguish between these things with accuracy. We provide a thorough comparison of machine learning algorithms in this research study to help determine if sonar returns are indicative of rocks or mines. Using a dataset of sonar sound characteristics, we assess several supervised learning algorithms: random forests, k-nearest neighbours, support vector machines, and deep neural networks. We examine the models' performance in terms of F1-score, recall, accuracy, and precision in classification. We also investigate how feature selection strategies and hyperparameter adjustments affect the performance of the model. By means of comprehensive testing and analysis, we offer insights into the effectiveness of different machine learning approaches for sonar-based object classification, ultimately contributing to enhanced maritime security and underwater navigation systems

SONAR, Underwater Object Classification, Maritime Security, Rock Detection, Mines Detection, Supervised machine learning, Feature Selection, Hyperparameter Tuning.

"SONAR Rock Vs Mine Prediction Using Machine learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.p579-p582, May-2024, Available :http://www.jetir.org/papers/JETIR2405G78.pdf

"SONAR Rock Vs Mine Prediction Using Machine learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppp579-p582, May-2024, Available at : http://www.jetir.org/papers/JETIR2405G78.pdf