Scholarlink

<p>Parkinson’s disease (PD) is a progressive neurological disorder primarily affecting motor functions and mobility. Early diagnosis is crucial for reducing disease progression and treatment costs. This paper proposes a bi-directional long short-term memory (BLSTM)-based system for PD diagnosis using electroencephalography (EEG) signals collected exclusively from the substantia nigra (SN) and ventral tegmental area (VTA), key brain regions associated with dopamine production. Mel-frequency cepstral coefficients (MFCC) features are extracted from the EEG data, and the BLSTM classifier is employed to differentiate PD subjects from healthy individuals. The performance of the proposed system is evaluated on three public datasets, namely, the University of Iowa (UI) dataset, Parkinson’s Disease Gait (PDG) dataset, and the UC San Diego Resting State (USDRS) dataset, demonstrating superior classification accuracy compared to existing methods.</p>

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

Parkinson’s disease diagnosis using deep learning model by analyzing the channels of electroencephalography signals from substansia niagra and ventral tegmental area regions of human brain

  • 期刊论文

  • 发表日期：

    2025年1月18日

查看全文
  • Kaushal Kumar,
  • Rajib Ghosh

摘要

Parkinson’s disease (PD) is a progressive neurological disorder primarily affecting motor functions and mobility. Early diagnosis is crucial for reducing disease progression and treatment costs. This paper proposes a bi-directional long short-term memory (BLSTM)-based system for PD diagnosis using electroencephalography (EEG) signals collected exclusively from the substantia nigra (SN) and ventral tegmental area (VTA), key brain regions associated with dopamine production. Mel-frequency cepstral coefficients (MFCC) features are extracted from the EEG data, and the BLSTM classifier is employed to differentiate PD subjects from healthy individuals. The performance of the proposed system is evaluated on three public datasets, namely, the University of Iowa (UI) dataset, Parkinson’s Disease Gait (PDG) dataset, and the UC San Diego Resting State (USDRS) dataset, demonstrating superior classification accuracy compared to existing methods.