Scholarlink

Parkinson’s disease is a neurological condition that leads to involuntary movements, including tremors, muscle cramps, and problems with balance. The signs of a patient suffering from Parkinson’s disease increase with age, and with the development of information technology, diagnosis can be made using machine learning. This study aims to compare the Decision Tree and K-Nearest Neighbor classification algorithms in producing maximum accuracy values ​​from the Parkinson’s disease dataset. This study was conducted to determine whether the Binary Particle Swarm Optimization algorithm can be used to optimize the Accuracy, Precision, Recall and F1-Score values ​​in the classification algorithm in predicting Parkinson’s disease. The Decision Tree Classification Algorithm produces 97.65% Accuracy, 95.30% Precision, 100% Recall and 97.59% F1-Score compared to the K-Nearest Neighbor (K-NN) classification algorithm whose value is below the Decision Tree classification algorithm.

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

Comparison of Decision Tree with K-Nearest Neighbor in Binary Particle Swarm Optimization Algorithms for Diagnosis of Parkinson’s Disease

  • 章节

  • 发表日期：

    2026年

查看全文
  • Andi Nugroho,
  • Ratna Mutu Manikam,
  • Sarwati Rahayu,
  • Yustika Erliani,
  • Agill Prasetyo Nugroho,
  • Siti Dairini,
  • Zikri Nur Iman

摘要

Parkinson’s disease is a neurological condition that leads to involuntary movements, including tremors, muscle cramps, and problems with balance. The signs of a patient suffering from Parkinson’s disease increase with age, and with the development of information technology, diagnosis can be made using machine learning. This study aims to compare the Decision Tree and K-Nearest Neighbor classification algorithms in producing maximum accuracy values ​​from the Parkinson’s disease dataset. This study was conducted to determine whether the Binary Particle Swarm Optimization algorithm can be used to optimize the Accuracy, Precision, Recall and F1-Score values ​​in the classification algorithm in predicting Parkinson’s disease. The Decision Tree Classification Algorithm produces 97.65% Accuracy, 95.30% Precision, 100% Recall and 97.59% F1-Score compared to the K-Nearest Neighbor (K-NN) classification algorithm whose value is below the Decision Tree classification algorithm.