Grey Wolf Optimization-Based Hyper Parameter Tuning For Deep Neural Networks in Thyroid Disease Diagnosis

Thyroid disorders affect millions of people worldwide, however quick treatment is vulnerable by high rates of misdiagnosis. The lack of current clinical decision support systems inspires the development of novel approaches. In mandate to increase thyroid disease prediction, this study finds a gap in the use of machine learning, optimization and deep learning algorithms. The age and gender for thyroid data is predicted by using the proposed Deep Learning method based optimization technique called Grey Wolf Optimization based hyper parameter tuning with Deep Neural Network. Initially, data cleaning is applied to the thyroid data to replace missing values and for raw data conversion. Next, the data are featured using the Recursive Feature Elimination, to identifying its most important features and eliminating others from thyroid dataset. Finally, a GWO based DNN framework is processed to enhance the classification of thyroid disease diagnosis. Using python software the proposed framework an improved accuracy of 92% is accomplished when compared to other techniques.