Improved Skin Cancer Detection Classification Residual Network Feature Engineering
Authors:
- 1 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 671-675
Abstract
Skin cancer is a prevalent kind of cancer, and early diagnosis significantly improves the chance of survival. The purpose of this article is to develop a deep learning feature engineering model with an optimised xg-boost classifier for the purpose of classifying dermal cell pictures and detecting skin cancer. Utilization of Methodology Classification method based on features mapped on nonlinear space using Resnet 50 basis feature engineering, followed by learning via Xg-boost structure optimization. Structure optimization is accomplished by grey wolf optimization. Within the Results The deep learning with xgboost model developed here was evaluated on standard datasets and combined datasets, and the metric accuracy and precision were found to be 98.34 percent and 97.35 percent, respectively. Conclude that a practitioner may use model-driven architecture to rapidly develop deep learning models for skin cancer prediction.Keywords
This publication has 4 references indexed in Scilit:
- Classification of Melanoma and Nevus in Digital Images for Diagnosis of Skin CancerIEEE Access, 2019
- Guest Editorial Skin Lesion Image Analysis for Melanoma DetectionIEEE Journal of Biomedical and Health Informatics, 2019
- The melanoma skin cancer detection and classification using support vector machine2017
- Skin tissue characterization of canine at microwave and millimeter-wave frequencies2017