Performance Comparison of Different Machine Learning Techniques for Early Prediction of Breast Cancer using Wisconsin Breast Cancer Dataset
Küçük Resim Yok
Tarih
2022
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Institute of Electrical and Electronics Engineers Inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
A significant health issue, cancer is becoming more prevalent globally and is a leading cause of mortality. Recent studies have shown that breast cancer is one of the most prevalent cancer type, particularly among women. Early detection can increase the chances of survival for those with breast cancer and lower treatment cost. However, there are drawbacks to the early diagnosis methods utilized in today's healthcare systems. These include the need for substantial human resources, long-term effects, and difficult access to these services for everybody. For early breast cancer diagnosis, technologies that are simple to use, yield reliable findings compared to scientific methodologies, and are available to everyone are required. Artificial Intelligence techniques enable the early diagnosis of breast cancer. This study aims to classify benign and malignant breast cancer image features. Artificial Neural Network, Support Vector Machine and Random Forest algorithms were used to classify features obtained from images. Experiments were performed on the Wisconsin Breast Cancer dataset. Experimental evaluation shows that 99% of the most successful results were achieved with the Artificial Neural Network algorithm. According to experimental findings, the classification technique can identify breast cancer in its early stages. The findings of the study are expected to shed on light new researches for investigation into breast cancer early detection. © 2022 IEEE.
Açıklama
Anahtar Kelimeler
Breast cancer, early prediction, machine learning, wisconsin breast cancer dataset, Classification (of information), Diagnosis, Diseases, Forestry, Learning systems, Medical imaging, Neural networks, Breast Cancer, Diagnosis methods, Early diagnosis, Early prediction, Health issues, Machine learning techniques, Machine-learning, Performance comparison, Treatment costs, Wisconsin breast cancer dataset, Support vector machines
