Scholarlink

One of the main causes of dementia in the elderly population is Alzheimer’s disease (AD)—furthermore, a sizeable segment of the global populace experiences metabolic disorders including diabetes and Alzheimer’s disease. Patients with AD can recover from it more successfully and with less damage if they receive early diagnosis and therapy. This research uses a combination of Principal Component Analysis (PCA), Genetic Algorithm (GA), and Hybrid Kernel Support Vector Machine (HKSVM) for feature extraction and feature selection to recommend and predict the AD. The selected subset is then fed into SVM. Accuracy, precision, recall, and F1-score are the four performance indicators that are compared. The outcomes demonstrate that the proposed strategy performs better in terms of executing time performance metrics, accuracy, precision, and F1-score. Secondly, the experiment demonstrates a notable improvement in running time over the k-nearest neighbor technique that is conventional. With an accuracy of 98.75%, the suggested model outperforms existing state-of-the-art methods for the OASIS dataset. Performance-wise, it was shown that the proposed algorithm outperformed the single kernel SVM. The current approach is also used in categorizing thyroid illness detection to provide a deeper knowledge of it.

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

PCA-GA-HKSVM: An Efficient Hybrid Kernel SVM Integrated GA-PCA Model for Early Diagnosis of Disease

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Pijush Dutta,
  • Shobhandeb Paul,
  • Arindam Sadhu,
  • Gour Gopal Jana

摘要

One of the main causes of dementia in the elderly population is Alzheimer’s disease (AD)—furthermore, a sizeable segment of the global populace experiences metabolic disorders including diabetes and Alzheimer’s disease. Patients with AD can recover from it more successfully and with less damage if they receive early diagnosis and therapy. This research uses a combination of Principal Component Analysis (PCA), Genetic Algorithm (GA), and Hybrid Kernel Support Vector Machine (HKSVM) for feature extraction and feature selection to recommend and predict the AD. The selected subset is then fed into SVM. Accuracy, precision, recall, and F1-score are the four performance indicators that are compared. The outcomes demonstrate that the proposed strategy performs better in terms of executing time performance metrics, accuracy, precision, and F1-score. Secondly, the experiment demonstrates a notable improvement in running time over the k-nearest neighbor technique that is conventional. With an accuracy of 98.75%, the suggested model outperforms existing state-of-the-art methods for the OASIS dataset. Performance-wise, it was shown that the proposed algorithm outperformed the single kernel SVM. The current approach is also used in categorizing thyroid illness detection to provide a deeper knowledge of it.