Scholarlink

This work mainly focuses on the need for collaborative learning framework that allows for early prediction of disease detection in patients. Principal component analysis comes out as a very effective approach for classifying the target classes. PCA successfully combines related qualities and creates a dispersed exhibition of its constituents. The number of principle components to be retained is determined by examining the screen plot. With a small amount of data, Support Vector Machines (SVM) beats other classification algorithms. The components obtained will be sent to the SVM which classifies the cancer based on Multi-Level and helps in prediction of malignancy of cancer, the early dangerous stage will urge clinical specialists to offer those patients extra attention. The results obtained through the proposed framework have achieved accurate results in terms of various performance parameters like accuracy. Precision, recall and F-measure and then confusion matrix is drawn to validate the proposed model and helps in detecting various stages of malignancy at an early stage.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Efficient Framework for Multi-level Lung Cancer Prediction Using Support Vector Machine Classifier

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ashok K. Patil,
  • Siddanagouda S. Patil,
  • M. Prabhakar,
  • Vineet Kumar

摘要

This work mainly focuses on the need for collaborative learning framework that allows for early prediction of disease detection in patients. Principal component analysis comes out as a very effective approach for classifying the target classes. PCA successfully combines related qualities and creates a dispersed exhibition of its constituents. The number of principle components to be retained is determined by examining the screen plot. With a small amount of data, Support Vector Machines (SVM) beats other classification algorithms. The components obtained will be sent to the SVM which classifies the cancer based on Multi-Level and helps in prediction of malignancy of cancer, the early dangerous stage will urge clinical specialists to offer those patients extra attention. The results obtained through the proposed framework have achieved accurate results in terms of various performance parameters like accuracy. Precision, recall and F-measure and then confusion matrix is drawn to validate the proposed model and helps in detecting various stages of malignancy at an early stage.