Scholarlink

There are an alarming number of people on the planet who are suffering from neurological problems. The EEG signal is a chaotic time series signal that changes fast depending on the patient’s condition. The nature of the signals changes dramatically from normal to severe situations, with changes in amplitude and frequency. Early detection and prediction of these signals is a very difficult task. The target of this research is to forecast individual state signals. The work is carried out by using the Generalized Regression Neural Networks (GRNN) variation of the Radial basis Function Neural Network (RBFNN), but it requires careful selection of the spread factor. Selecting an exact spread factor is not an easy task, it necessitates time-consuming and painstaking experiments. The spread factor for GRNN is determined by searching the particles in the swarm. Implémentation of Particle Swarm optimization (PSO) in conjunction with GRNN dramatically improved GRNN’s prediction accuracy for a variety of neurological illnesses.

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

Optimized Neural Network for Prediction of Neurological Disorders

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Swagat Karve,
  • Siddheshwar Gangonda,
  • Ganesh Birajadar,
  • Vaibhav Godase,
  • Rahul Ghodake,
  • Altaf O. Mulani

摘要

There are an alarming number of people on the planet who are suffering from neurological problems. The EEG signal is a chaotic time series signal that changes fast depending on the patient’s condition. The nature of the signals changes dramatically from normal to severe situations, with changes in amplitude and frequency. Early detection and prediction of these signals is a very difficult task. The target of this research is to forecast individual state signals. The work is carried out by using the Generalized Regression Neural Networks (GRNN) variation of the Radial basis Function Neural Network (RBFNN), but it requires careful selection of the spread factor. Selecting an exact spread factor is not an easy task, it necessitates time-consuming and painstaking experiments. The spread factor for GRNN is determined by searching the particles in the swarm. Implémentation of Particle Swarm optimization (PSO) in conjunction with GRNN dramatically improved GRNN’s prediction accuracy for a variety of neurological illnesses.