EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CLASSIFICATION APPROACHES FOR MULTI-LEVEL BREAST CANCER PREDICTION: A MACHINE LEARNING PERSPECTIVE

Hujun Sun, Ling Weay Ang

Journal of Applied Research and Multidisciplinary Studies · 2022

DOI: 10.32350/jarms.31.03 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Research and Multidisciplinary Studies, 2022. Verfasst von Hujun Sun und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research compares the performance of machine learning and deep learning algorithms for breast cancer prediction in order to identify the most effective strategy for handling large data sets while maintaining high prediction accuracy. The study focuses on the use of machine intelligence techniques, such as machine learning and deep learning, for breast cancer prediction and classification. The paper reviews previous research on machine learning algorithms, segmentation techniques, and classification approaches used for multi-level breast cancer prediction. The results of the comparison show that using Long Short-Term Memory (LSTM) Recurrent Neural Networks for multi-disease prediction results in improved classification performance for breast cancer predictions.

Zitieren

APA

Sun, H., & Ang, L. W. (2022). CLASSIFICATION APPROACHES FOR MULTI-LEVEL BREAST CANCER PREDICTION: A MACHINE LEARNING PERSPECTIVE. Journal of Applied Research and Multidisciplinary Studies. https://doi.org/10.32350/jarms.31.03

Vancouver

Sun H, Ang LW. CLASSIFICATION APPROACHES FOR MULTI-LEVEL BREAST CANCER PREDICTION: A MACHINE LEARNING PERSPECTIVE. Journal of Applied Research and Multidisciplinary Studies. 2022. doi:10.32350/jarms.31.03

BibTeX
@article{Sun2022,
  author = {Sun, Hujun and Ang, Ling Weay},
  title = {CLASSIFICATION APPROACHES FOR MULTI-LEVEL BREAST CANCER PREDICTION: A MACHINE LEARNING PERSPECTIVE},
  journal = {Journal of Applied Research and Multidisciplinary Studies},
  year = {2022},
  doi = {10.32350/jarms.31.03}
}
Kostenlos starten →