Binary Classification Deep Learning Model for the Sonar Dataset Using Keras

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: The purpose of this project is to construct a predictive model using various machine learning algorithms and to document the end-to-end steps using a template. The Sonar Dataset is a binary classification situation where we are trying to predict one of the two possible outcomes.

INTRODUCTION: The Sonar Dataset involves the prediction of whether an object is a mine or a rock given the strength of sonar returns at different angles. The dataset contains the patterns obtained by bouncing sonar signals off a metal cylinder or a rock at various angles and under various conditions. The transmitted sonar signal is a frequency-modulated chirp, rising in frequency. The data set contains signals obtained from a variety of different aspect angles, spanning 90 degrees for the cylinder and 180 degrees for the rock.

ANALYSIS: The baseline performance of the model achieved an average accuracy score of 79.48%. Using the same training parameters, the model processed the test dataset with an accuracy of 82.69%, which was even better than results from the training data.

CONCLUSION: For this dataset, the model built using Keras and TensorFlow achieved a satisfactory result and should be considered for future modeling activities.

Dataset Used: Connectionist Bench (Sonar, Mines vs. Rocks) Data Set

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://archive.ics.uci.edu/ml/datasets/Connectionist+Bench+%28Sonar,+Mines+vs.+Rocks%29

One potential source of performance benchmarks: https://machinelearningmastery.com/binary-classification-tutorial-with-the-keras-deep-learning-library/

The HTML formatted report can be found here on GitHub.