Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Breast cancer detection based on PCA feature selection process using an ensemble learning algorithm
Ist Teil von
AIP Conference Proceedings, 2024, Vol.2937 (1)
Ort / Verlag
Melville: American Institute of Physics
Erscheinungsjahr
2024
Beschreibungen/Notizen
Breast Cancer (BC), more than any other malignancy, is one of the main reasons of mortality amongst women. Due to disease’s intricacy, varying patient population samples and changing treatment protocols, accurate diagnosis of breast cancer is extremely challenging. Better diagnostic procedures are critical for tailored care and treatment, as well as reducing and controlling cancer recurrence. This study investigates the early identification of breast cancer using a variety of ensemble methodologies. The dataset that has been utilized in this work is chosen to forecast breast cancer based on nine individual variables, including BMI, age, insulin, glucose and a homeostasis model evaluation. This research provides a suggested strategy based on feature selection that uses Principal Component Analysis (PCA) as well as the ensemble technique for dramatically lessening the dimensionality of features and enhance breast cancer classification. The suggested method is tested using the Wisconsin Breast Cancer Dataset, which is open to the public (WBCD dataset). This study focuses on evaluating and comparing the efficacy of several ensemble approaches based on PCA feature selection in early diagnosis of BC. LogitBoost is the most precise model amongst all the ensemble approaches, according to the findings. The LogitBoost algorithm beats the other ensemble methods, with an accuracy of 72.46 percent. The findings of data analysis show that ensemble classifiers outperform state-of-the-art approaches in detecting BC.