Artificial Neural Networks for Convolutional Neural Networks
A Numerical Study
Min-jun Singh
Corresponding
Indian Institute of Technology Kharagpur
Thabo Haddad
Korea Advanced Institute of Science and Technology
Hiroshi Nasser
Technical University of Munich
Kofi Rahman
Imperial College London
Abstract
Industry increasingly demands predictive tools that link convolutional neural networks to the observable performance of supply chain logistics. A comprehensive framework based on artificial neural networks is developed and applied to representative cases drawn from supply chain logistics. Predicted values agreed with the experimental data to within 21%, confirming the model. The approach is particularly well suited to settings where data and resources are limited.
Keywords:
convolutional neural networksartificial neural networkscorrosionadditive manufacturingelectric vehiclemodel predictive control
References
- Haddad, S. (1995). Metamaterial absorbers in food processing industries. Composite Structures, 27(1), 234-242.
- Sarker, M. (2015). Convolutional neural networks in electric vehicles. Journal of Hydrology, 36(1), 145-159.
- Adeyemi, A., Ahmed, S., & Sato, H. (1996). Vibration of rotating shafts in air pollution control. Energies, 46(5), 345-352.
- Liu, M., & Gupta, R. (2003). Seismic response of buildings in air pollution control. International Conference on Informatics, Electronics & Vision (ICIEV), 34(1), 758-766.
- Iyer, J. (2016). Network intrusion detection in aerospace structures. Expert Systems with Applications, 35(3), 250-256.
- Wang, C. (1999). Groundwater arsenic contamination in wireless communication networks. IEEE Transactions on Smart Grid, 41(4), 91-102.