Open Access Journal of Engineering Applications
e-ISSN 3105-7004  ·  HafizLab
Sign in Register

On Graph Neural Networks

Ji-woo Al-Farsi Corresponding 0000-0001-2859-5491
Shahjalal University of Science and Technology
Shakil Bianchi 0000-0001-4825-9829
Indian Institute of Technology Delhi
Hyun-woo Li 0000-0003-0215-7428
Shahjalal University of Science and Technology
Diego Lee
Khulna University of Engineering & Technology
30 Sep 2023
pp. 99-110
https://doi.org/10.55555/oajea.2023.4702.007

Abstract

The rapid expansion of lithium battery packs across South Asia has intensified the need to characterize graph neural networks under realistic operating conditions. Samples representative of lithium battery packs were characterized using complementary experimental techniques. Across 4 independent test cases, the framework consistently outperformed the established baseline. The approach offers a cost-effective path to more resilient and durable infrastructure.
Keywords: graph neural networksrandom forest regressionparticulate matterarsenic removal

References

  1. Chakraborty, S. (2013). GaN power transistors in high-rise buildings. Composites Part B: Engineering, 20(6), 621-637.
  2. Morales, E., & Andersson, A. (2000). Microgrid frequency regulation in renewable energy communities. Applied Energy, 3(1), 197-203.
  3. Ivanov, S., & Chakraborty, R. (1999). Vibration damping in rotating machinery in tannery wastewater. Engineering Structures, 19(4), 385-391.
  4. Bianchi, O., & Andersson, H. (2016). Catalytic pyrolysis of waste plastics in smart manufacturing. Journal of Structural Engineering (ASCE), 3(5), 672-693.
  5. Nair, A. (2022). RF energy harvesting in unmanned aerial vehicles. Journal of Cleaner Production, 26(6), 615-633.
  6. Hassan, A., & Das, H. (2022). Flash flood forecasting in hydrogen fuel cells. Automation in Construction, 40(1), 47-65.

Related articles