2026-09-22T18:46:25Zhttps://ubir.buffalo.edu/oai/request

oai:ubir.buffalo.edu:10477/838382025-07-16T19:37:17Zcom_10477_77914col_10477_81567

Boon of Hybrid Approaches over the Bane of Model Based and Machine Learning Approaches in Modelling Cyber-Physical Systems Sahu, Chandan Kumar; 0000-0001-5893-4031 Rai, Rahul Mechanical and Aerospace Engineering mechanical engineering electrical engineering computer science M.S. Physics-based models (MB) and machine learning models (ML) have emerged as two paradigms for modeling any system. They represent the two opposite ends of the spectrum of system knowledge/data. Interpretability, tractability, and composability provided the thrust for MB. Genericity and accuracy drove ML. Interestingly, the drivers of physics models are the deterrents of machine learning models and vice versa. Even with their inherent boons and banes, they have evolved and practiced independently of each other for computing. Recently, several works attempted to merge MB and ML models for the complete exploitation of their combined potential. However, the research is scattered and unorganized. So, we make a meticulous attempt at organizing and standardizing the methods of combining ML and MB models. In addition to that, we prepared a five-faceted generic framework for the comprehensive evaluation of hybrid learning models (MB + ML). Finally, we conclude by shedding some light on the challenges of hybrid models, which we as a research community should focus for expediting the research and harnessing the full potential of hybrid learning models. All of these have been discussed with a clear focus on modeling cyber-physical systems (CPS) and overcoming the limitations of the existing models of CPS. 2022-06-17T19:54:37Z 2022-06-17T19:54:37Z 2020 Text Thesis http://hdl.handle.net/10477/83838 eng Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions. Copyright retained by author. application/pdf State University of New York at Buffalo