Novel AI-Based Methodology for Predicting Superconducting Films' Resistance-Temperature Properties with Nanomaterials

Authors Gaurav Kumar1, Komal Parashar2, Prashant Sharma3, Durgeshwar Pratap Singh4, Anurag Shrivastava5, Arun Pratap Srivastava6, Amit Srivastava7 , P. William8
Affiliations

1Chitkara Centre for Research and Development, Chitkara University, 174103 Himachal Pradesh, India

2Centre of Research Impact and Outcome, Chitkara University, Rajpura-140417 Punjab, India

3Department of Civil Engineering, GLA University, Mathura-281406, Uttar Pradesh, India

4Department of Mechanical Engineering, Graphic Era Deemed to be University, Dehradun, Uttarakhand

5Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, TN, India

6Lloyd Institute of Engineering & Technology, Greater Noida, Uttar Pradesh 201306, India

7Lloyd Law College, Greater Noida, Uttar Pradesh 201306, India

8Department of Information Technology, Sanjivani College of Engineering, Kopargaon, MH, India

Е-mail gauravcivilengg714@gmail.com
Issue Volume 16, Year 2024, Number 4
Dates Received 18 April 2024; revised manuscript received 21 August 2024; published online 27 August 2024
Citation Gaurav Kumar, Komal Parashar, et al., J. Nano- Electron. Phys. 16 No 4, 04018 (2024)
DOI https://doi.org/10.21272/jnep.16(4).04018
PACS Number(s) 73.40.Cg, 84.37.+q
Keywords Nanomaterial (4) , Superconductivity (2) , Nanotechnology (6) , Resistivity (11) , Film resistance.
Annotation

Integrating state-of-the-art nanostructures into prediction models enhances our understanding of superconductivity properties. Using artificial intelligence techniques and modeling, the mathematical method leverages the unique characteristics of nanoparticles to improve resistance-temperature projections. This paper proposes a novel artificial intelligence (AI) approach for predicting the resistance-temperature aspects of nanomaterial-infused superconducting films. In this paper, we offer a novel AI method called Progressive Red Fox Optimized Adaptive Decision Tree (PRFO-ADT) to predict the super conductiveness of film coatings. A sufficient information pretreatment step that addresses issues like feature creation and normalizing is part of the study's technique. A diversified dataset is employed, including synthesis factors, nanomaterial properties, and resistance-temperature patterns of several superconducting films. Next, the gathered data undergo the preprocessing stage using a min-max normalization. Our proposed method opens the door to a sophisticated comprehension of the resistance-temperature landscapes of their superconductivity films by investigating several nanotechnologies and their different effects on the prediction algorithm. Compared to other existing approaches, PRFO-ADT is efficient and produces a lower rate of errors, with a total of 1.2 RMSE, 1.25 MSE, 1.1 MAPE, and 4.8s of computing time.

List of References