Developing a Machine Learning Algorithm to Determine COVID-19 Contamination in Different Age Groups and Comparing Statistical Algorithms and Learning Data

Savas Ilgi G., Etikan I., Kirsal Ever Y.

IEEE ACCESS, vol.12, pp.117461-117470, 2024 (SCI-Expanded, Scopus) identifier identifier

  • Publication Type: Article / Article
  • Volume: 12
  • Publication Date: 2024
  • Doi Number: 10.1109/access.2024.3447835
  • Journal Name: IEEE ACCESS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.117461-117470
  • Middle East Technical University Northern Cyprus Campus Affiliated: No

Abstract

The development of machine learning algorithms for the correction checking of statistical method theorems is a significant advancement in statistical research and analysis. These algorithms are designed to automatically detect and rectify errors and inconsistencies in applying statistical theorems, improving the overall reliability and accuracy of statistical analyses. These algorithms can identify issues in interpreting and applying statistical theorems by leveraging machine learning techniques, such as natural language processing, pattern recognition, and data validation. As a result, they help researchers and analysts avoid potential pitfalls, enhance the quality of statistical results, and streamline the peer-review process in scientific publications. This innovative approach combines the power of automation with the intricacies of statistical theory, promising more robust and error-free statistical analyses in various research domains.