Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193731,
        author = {Mrs. R Sujatha and G. Swarnakala and G Venkatesh and T Yogesh and Y Rushitha and N Uday Kiran},
        title = {DETECTION OF SUBMERGED NAVAL MINES USING SONAR FREQUENCY DATA AND MACHINE LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {2421-2425},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193731},
        abstract = {In modern naval defense operations, submarines play a crucial role but significant threats from submerged naval mines capable of causing severe damage. Sonar systems are commonly employed to detect under water objects by analyzing reflected acoustic frequency signals; however, reliably distinguishing navel mines from natural objects such as rocks remains a challenging task due to environmental variability and signal noise. This project presents a machine-learning-based approach for submerged naval mine detection using sonar frequency data. Existing systems often rely on complex ensemble-based models that achieve high accuracy but suffer from increased computational complexity and reduced suitability real-time deployment. To address these limitations, the proposed system employs a random forest classifier-based classification model that focuses on dominant sonar frequency features to achieve fast, interpretable, and stable detection performance. A real-world sonar data set is used for training and evolution, and performance of the proposed models is analyzed in comparison with ensemble-based approaches. Experimental results indicate that the proposed method provides reliable mine-rock classification with reduced false alarms and improved real-time applicability, supporting safer and more efficient underwater naval operations.},
        keywords = {Submerged Naval Mine Detection, Five-Frequency SONAR Features, Threshold Based Classification, Linear Regression Model, Real-Time Underwater Detection.},
        month = {March},
        }