Identification of the appropriate architecture of multilayer feed-forward neural network for estimation of NPPs parameters using the GA in combination with the LM and the BR learning algorithms

Moshkbar-Bakhshayesh, Khalil

doi:10.1016/j.anucene.2021.108222

Cited by 15 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen from the previous section that although the LM algorithm can speed up the training speed of the network, when the initial value is at the local optimal value, the convergence result will still fall into the local optimal solution, which reduces the reliability of the model. Therefore, this paper adds the GA algorithm [30,31] to the LM-BP network to optimize the search ability of the network.…”

Section: Bp Neural Network Algorithm Based On Ga-lm-bp Algorithmmentioning

confidence: 99%

Secure transmission of wireless energy-carrying communication systems for the Internet of Things

Zhou

Peng

et al. 2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

The Internet of Things, as an important part of important data aggregation, forwarding and control, is often subject to risks such as eavesdropping or data loss due to the huge amount of received data. Based on this, this paper introduces the GA-LM-BP algorithm, BP network, and LM-BP algorithm deep learning to optimize the data received by the Internet of Things, and selects the most suitable communication mode optimization algorithm. The experimental results show that the accuracy error of GA-LM-BP, BP and LM-BP algorithms shows a downward trend, from 0.029 to 0.011; the training time is reduced by 208 mins, and the training speed is increased to 74%, indicating that GA-LM-BP deep learning Excellent performance in the security and confidentiality of data transmission in the Internet of Things. In addition, we further analyzed GA-LM-BP from COP, SOP and STP to verify its reliability and safety.

show abstract

Section: Bp Neural Network Algorithm Based On Ga-lm-bp Algorithmmentioning

confidence: 99%