Scholarlink

<p>The most common kind of Dementia that affects social and cognitive abilities is Alzheimer’s disease (AD). In order to prevent brain damage and prolong daily functioning, early detection is essential for medical intervention. The current research has developed a novel Termite Cat Boost Prediction Framework (TCBPF) technique to detect Alzheimer’s disease using electroencephalogram (EEG) signals. The chief processes, like filtering, feature selection, prediction, and severity analysis, have been performed. The primary phase executes the filtering process to obtain a noise-free EEG signal. Here, the required features were extracted for the prediction process, and then the severity level of Alzheimer’s disease was finally determined. Subsequently, the performance of the proposed methods is compared with that of existing methods. The suggested model achieves the following metrics: 96.23% Matthew’s Correlation Coefficient (MCC), 99.47% Recall, 96.57% Negative Predictive Value (NPV), 0.031% False Positive Rate (FPR), 0.006% False Negative Rate (FNR), 99.10% Accuracy, 99.30% Precision, and 99.50% F1score. As a result, with accurate identification, ensemble learning has the potential to reduce the annual death rates from Alzheimer’s disease significantly.</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

Optimal boosted ensemble system for Alzheimer’s disease forecasting

  • 期刊论文

  • 发表日期：

    2026年4月9日

查看全文
  • Shashi Rekha Diddi,
  • A. Vani Vathsala

摘要

The most common kind of Dementia that affects social and cognitive abilities is Alzheimer’s disease (AD). In order to prevent brain damage and prolong daily functioning, early detection is essential for medical intervention. The current research has developed a novel Termite Cat Boost Prediction Framework (TCBPF) technique to detect Alzheimer’s disease using electroencephalogram (EEG) signals. The chief processes, like filtering, feature selection, prediction, and severity analysis, have been performed. The primary phase executes the filtering process to obtain a noise-free EEG signal. Here, the required features were extracted for the prediction process, and then the severity level of Alzheimer’s disease was finally determined. Subsequently, the performance of the proposed methods is compared with that of existing methods. The suggested model achieves the following metrics: 96.23% Matthew’s Correlation Coefficient (MCC), 99.47% Recall, 96.57% Negative Predictive Value (NPV), 0.031% False Positive Rate (FPR), 0.006% False Negative Rate (FNR), 99.10% Accuracy, 99.30% Precision, and 99.50% F1score. As a result, with accurate identification, ensemble learning has the potential to reduce the annual death rates from Alzheimer’s disease significantly.