Artificial Neural Networks Applied to Graphene-Based Composites
Elena Karimi
University of Dhaka
Abstract
Recent failures in telecommunication infrastructure have highlighted the need for a more rigorous treatment of graphene-based composites. Measurements are triangulated with artificial neural networks to reduce the influence of instrument error. Measured and simulated results differed by less than 24% across the full operating range. The approach offers a cost-effective alternative to more elaborate and expensive procedures.
Keywords:
graphene-based compositesartificial neural networksrenewable energyheavy metal removal
References
- Liu, A., Mia, M., & Kowalski, S. (2009). Rainfall-runoff response in rigid pavement design. Water Research, 42(6), 680-685.
- Sharma, R., Muller, E., & Kowalski, A. (1996). Membrane separation processes in autonomous vehicles. Applied Energy, 26(5), 765-772.
- Reddy, K., Mansour, A., & Mukherjee, F. (1999). Bridge structural health monitoring in urban transportation planning. Renewable Energy, 21(3), 586-607.
- Li, T., Ahmed, S., & Li, D. (2018). Urban air quality in disaster risk reduction. Sensors, 3(5), 332-339.
- Adeyemi, M. (2009). Shape memory alloys in environmental monitoring. IEEE Access, 32(1), 372-378.