Enhancing Engineering Design through Topological Data Analysis (TDA) and Adaptive Clustering Algorithms

 Ochieng Dembe H.

Faculty of Engineering Kampala International University Uganda

  ABSTRACT

This paper explores advanced methodologies for component analysis and clustering in engineering design processes, focusing on generalized Principal Component Analysis (g-PCA) and topological data analysis (TDA). We discuss deep-learning-based methods that minimize information loss (MIL) and adaptive clustering algorithms for equal variance circles and g-circles. Additionally, we review traditional and modern approaches to component analysis, highlighting TDA’s role in extracting topological features such as Betti numbers. TDA’s integration into engineering design is examined through various applications, demonstrating its ability to manage high-dimensional data and optimize complex systems. Future research directions are proposed to further leverage TDA and machine learning for robust and efficient engineering design optimization.

Keywords: Topological Data Analysis, Generalized Principal Component Analysis, Adaptive Clustering, Information Loss Minimization and Engineering Design

CITE AS: Ochieng Dembe H. (2024). Enhancing Engineering Design through Topological Data Analysis (TDA) and Adaptive Clustering Algorithms. RESEARCH INVENTION JOURNAL OF ENGINEERING AND PHYSICAL SCIENCES 3(1):16-22.