Prediction of Underwater Surface Target Through SONAR: A Case Study of Machine Learning

Abstract

The discovery of rocks and minerals would have been very difficult past the development of the SONAR technique, which relays on certain parameters to be able to detect the obstacle or the surface is a rock or a mine. Machine learning has drawn the attention of maximum part of the technology-related and based industries, by showing advancements in the predictive analytics. The main aim is to emanate a capable prediction representative, united by the machine learning algorithmic characteristics, which can figure out if the target of the sound wave is either a rock or a mine or any other organism or any kind of other body. This attempt is a clear-cut case study which comes up with a machine learning plan for the grading of rocks and minerals, executed on a huge, highly spatial and complex SONAR dataset. The attempts are done on highly spatial SONAR dataset and achieved an accuracy of 83.17%, and AUC came out to be 0.92. With random forest algorithm, the results are further optimized by feature selection to get the accuracy of 90%. Assuring results are found, when the fulfillment of the designed groundwork is set side by side with the standard classifiers like SVM, random forest, etc., using different evaluation metrics like accuracy, sensitivity, etc. Machine learning is performing a major role in improving the quality of detection of underwater natural resources and will tend be better in the near future.