Scholarlink

<p>Conventional procedures in field of structural health monitoring (SHM) are typically time-consuming, complex, and harmful. To properly assess and track the structural integrity, a wide range of sensors is also required. Thus, machine learning techniques are giving SHM systems the tools they need to improve their skills and offer clever answers to historical problems. This research proposes novel technique in scalability enhancement in SHM for smart healthcare development using machine learning model. Here the data processing with damage detection is carried put using probabilistic Bayesian perceptron basis function with convolutional Gabor component regression (PBPBF-CBCR) model. Then the processed data segmentation is carried out using stacked quadratic finite element decision tree discriminant analysis. The experimental analysis is carried out in terms of Detection accuracy, Correlation coefficient, reliability, Scalability, Processing time. Proposed technique attained Correlation coefficient of 97%, Detection accuracy of 95%, RELIABILITY of 94%, processing time of 58%, SCALABILITY of 95%.</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

Probabilistic Bayesian perceptron basis function with convolutional Gabor component regression in scalability analysis for structure health monitoring system: a machine learning algorithms

  • 期刊论文

  • 发表日期：

    2026年1月18日

查看全文
  • Perumalla Naga Padmavathi,
  • Dinesh Kumar Anguraj

摘要

Conventional procedures in field of structural health monitoring (SHM) are typically time-consuming, complex, and harmful. To properly assess and track the structural integrity, a wide range of sensors is also required. Thus, machine learning techniques are giving SHM systems the tools they need to improve their skills and offer clever answers to historical problems. This research proposes novel technique in scalability enhancement in SHM for smart healthcare development using machine learning model. Here the data processing with damage detection is carried put using probabilistic Bayesian perceptron basis function with convolutional Gabor component regression (PBPBF-CBCR) model. Then the processed data segmentation is carried out using stacked quadratic finite element decision tree discriminant analysis. The experimental analysis is carried out in terms of Detection accuracy, Correlation coefficient, reliability, Scalability, Processing time. Proposed technique attained Correlation coefficient of 97%, Detection accuracy of 95%, RELIABILITY of 94%, processing time of 58%, SCALABILITY of 95%.