Scholarlink

<p>Alzheimer’s disease is a gradually worsening neurological condition that severely affects cognitive abilities, making early detection essential for effective treatment and disease management. In this research article, we propose a novel predictive modeling approach that leverages Time-Partitioned Feature-Based Spectral Estimation (TP-FBSE) and Empirical Wavelet Transform (EWT) for advanced feature extraction from biomedical signals. To improve predictive accuracy, a hybrid optimization approach is utilized, combining Genetic Algorithm (GA) for effective feature selection with Particle Swarm Optimization (PSO) for optimal parameter tuning. The selected features are leveraged to train machine learning and deep learning models, enabling accurate detection and prediction of Alzheimer’s Disease (AD) progression. Our method effectively captures subtle neurophysiological changes associated with disease progression, improving classification reliability. Experimental validation on benchmark datasets demonstrates superior performance over traditional methods in terms of accuracy, sensitivity, and specificity. The findings highlight the potential of TP-FBSE-EWT in real-time AD diagnosis, paving the way for its integration into intelligent healthcare systems and wearable monitoring devices. Furthermore, this research provides a foundation for future advancements in non-invasive diagnostic technologies, facilitating early intervention and personalized treatment strategies for Alzheimer’s patients.</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

Predictive Modeling of Alzheimer’s Disease Progression Using TP-FBSE-EWT and Hybrid Optimization Techniques for Early Diagnosis and Monitoring

  • 期刊论文

  • 发表日期：

    2025年11月12日

查看全文
  • T. G. Ramabharathi,
  • Kamalraj Subramaniam,
  • K. Srihari,
  • C. Suresh

摘要

Alzheimer’s disease is a gradually worsening neurological condition that severely affects cognitive abilities, making early detection essential for effective treatment and disease management. In this research article, we propose a novel predictive modeling approach that leverages Time-Partitioned Feature-Based Spectral Estimation (TP-FBSE) and Empirical Wavelet Transform (EWT) for advanced feature extraction from biomedical signals. To improve predictive accuracy, a hybrid optimization approach is utilized, combining Genetic Algorithm (GA) for effective feature selection with Particle Swarm Optimization (PSO) for optimal parameter tuning. The selected features are leveraged to train machine learning and deep learning models, enabling accurate detection and prediction of Alzheimer’s Disease (AD) progression. Our method effectively captures subtle neurophysiological changes associated with disease progression, improving classification reliability. Experimental validation on benchmark datasets demonstrates superior performance over traditional methods in terms of accuracy, sensitivity, and specificity. The findings highlight the potential of TP-FBSE-EWT in real-time AD diagnosis, paving the way for its integration into intelligent healthcare systems and wearable monitoring devices. Furthermore, this research provides a foundation for future advancements in non-invasive diagnostic technologies, facilitating early intervention and personalized treatment strategies for Alzheimer’s patients.