| Authors | G.P. Dawange1, T.D. Diwan2, P. William3 , P. Kumar4, B.A. Tingare5, N. Yogeesh6 , A. Badholia7, M.V. Kulkarni1 |
| Affiliations |
1Engineering Science and Humanities, Sanjivani College of Engineering, Kopargaon, India 2Controller of Examination (COE), Atal Bihari Vajpayee University, Bilaspur, India 3Department of Information Technology, Sanjivani College of Engineering, Kopargaon, MH, India 4Swami Rama Himalayan University Dehradun, Uttarakhand, India 5Department of Artificial Intelligence and Data Science, D Y Patil College of Engineering, Akurdi, Pune, India 6Department of Mathematics, Government First Grade College, Tumkur, Karnataka, India 7Department of Data Science, Shri Shankaracharya Institute of Professional Management and Technology, Raipur, India |
| Е-mail | abhibad@gmail.com |
| Issue | Volume 17, Year 2025, Number 5 |
| Dates | Received 15 August 2025; revised manuscript received 22 October 2025; published online 30 October 2025 |
| Citation | G.P. Dawange, T.D. Diwan, P. William, et al., J. Nano- Electron. Phys. 17 No 5, 05015 (2025) |
| DOI | https://doi.org/10.21272/jnep.17(5).05015 |
| PACS Number(s) | 07.05.Mh, 07.05.Tp |
| Keywords | Vanadium Dioxide (VO2), Thermochromic Films, Artificial Intelligence (AI), Machine Learning (ML). |
| Annotation |
The study focuses on optimizing the synthesis process of Vanadium Dioxide (VO2) films through advanced machine learning (ML) algorithms, enabling precise control over key parameters such as temperature, pressure, and deposition techniques. By utilizing Artificial Intelligence AI-driven predictive modeling aim to achieve improved film quality, uniformity, and thermochromic (TC) performance. This study suggested a novel Tabu Search Optimized Adaptive Long Short-Term Memory (TSO-ALSTM) for the integration of AI to facilitate real-time monitoring and adjustment of production conditions, reducing defects and minimizing waste. The data was preprocessed using Min-max normalization. The proposed method is implemented using Python software. Compared the suggested method with other existing methods. Experimental results demonstrate that AI-enhanced processes lead to VO2 films with larger optical switching characteristics, broadening their potential applications in smart windows, advanced thermal management systems, and energy-efficient buildings. The outcomes demonstrate that the suggested approach outperforms the other method in terms of accuracy (90.74 %), recall (76 %), F1 score (81 %), and specificity (99.1 %). This work highlights the transformative impact of AI technologies in materials science, paving the way for the next generation of smart materials. |
|
List of References |