Taylor Water Cycle Algorithm Trained Deep Residual Network For Skin Cancer Detection

Abstract

In today s scenario, the skin cancer is one of the dangerous threat to the human life. It may be because, the modern lifestyle requirements are forcing the humans to make use of artificial products for livings. So, it is important to detect the skin cancer in the early stages and prevent the loss to human life. The primary aim of this research is to develop the method for skin cancer detection. There are several attempts made by the researchers by using different techniques in the different domains including machine learning. But, accuracy enhancements and computational cost are the issues, which are still not answered satisfactorily. Deep Residual network along with an optimization algorithm is core of the model classifier required for the skin cancer detection. Image based Deep Residual network classifier is used for detection of the skin cancer. The classifier will be trained using developed optimization algorithm, named Taylor Water Cycle Optimization (TWCO) algorithm. The developed TWCO approach will be newly devised by integrating the Water Cycle Optimization Algorithm (WCA) and Taylor series. The reason to use TWCO algorithm is that, the suggested technique can effectively classify skin cancer with a high degree of accuracy, and that it can also identify skin lesions for melanoma detection. Keywords accuracy, Deep Residual network, machine learning, skin cancer, Taylor Water Cycle Optimization newline