“…Seeking improved performance of conventional neural networks, researchers [11,12] have turned to GA. Three evolutionary operations are required to implement a GA: selection, crossover, and mutation. It has been found in experiments that, with large training samples, the convergence speed for the GA would be significantly reduced [13].…”
Section: Journal Of Nanomaterialsmentioning
confidence: 99%
“…Relying on multipoint search and algorithmic features, the chance of convergence to the universal optimal solution is much higher than the chance of falling into a local optimal solution. GA has a positive track record successfully having dealt with problems in a variety of fields, including but not limited to optimization, fuzzy logic, NN, expert systems, and scheduling [11].…”
By combining particle swarm optimization (PSO) and genetic algorithms (GA) this paper offers an innovative algorithm to train artificial neural networks (ANNs) for the purpose of calculating the experimental growth parameters of CNTs. The paper explores experimentally obtaining data to train ANNs, as a method to reduce simulation time while ensuring the precision of formal physics models. The results are compared with conventional particle swarm optimization based neural network (CPSONN) and Levenberg-Marquardt (LM) techniques. The results show that PSOGANN can be successfully utilized for modeling the experimental parameters that are critical for the growth of CNTs.
“…Seeking improved performance of conventional neural networks, researchers [11,12] have turned to GA. Three evolutionary operations are required to implement a GA: selection, crossover, and mutation. It has been found in experiments that, with large training samples, the convergence speed for the GA would be significantly reduced [13].…”
Section: Journal Of Nanomaterialsmentioning
confidence: 99%
“…Relying on multipoint search and algorithmic features, the chance of convergence to the universal optimal solution is much higher than the chance of falling into a local optimal solution. GA has a positive track record successfully having dealt with problems in a variety of fields, including but not limited to optimization, fuzzy logic, NN, expert systems, and scheduling [11].…”
By combining particle swarm optimization (PSO) and genetic algorithms (GA) this paper offers an innovative algorithm to train artificial neural networks (ANNs) for the purpose of calculating the experimental growth parameters of CNTs. The paper explores experimentally obtaining data to train ANNs, as a method to reduce simulation time while ensuring the precision of formal physics models. The results are compared with conventional particle swarm optimization based neural network (CPSONN) and Levenberg-Marquardt (LM) techniques. The results show that PSOGANN can be successfully utilized for modeling the experimental parameters that are critical for the growth of CNTs.
“…A decision problem is NP-complete when it is both in NP and NP-hard [62]. Evolutionary algorithms are effective means of solving NP problems [63,64]. These algorithms simulate the mechanism of biological evolution.…”
Section: Genetic Algorithm For Farmland Full-coverage Monitoring Wmentioning
Wireless sensor networks (WSNs) are suitable for the continuous monitoring of crop information in large-scale farmland. The information obtained is great for regulation of crop growth and achieving high yields in precision agriculture (PA). In order to realize full coverage and k-connectivity WSN deployment for monitoring crop growth information of farmland on a large scale and to ensure the accuracy of the monitored data, a new WSN deployment method using a genetic algorithm (GA) is here proposed. The fitness function of GA was constructed based on the following WSN deployment criteria: (1) nodes must be located in the corresponding plots; (2) WSN must have k-connectivity; (3) WSN must have no communication silos; (4) the minimum distance between node and plot boundary must be greater than a specific value to prevent each node from being affected by the farmland edge effect. The deployment experiments were performed on natural farmland and on irregular farmland divided based on spatial differences of soil nutrients. Results showed that both WSNs gave full coverage, there were no communication silos, and the minimum connectivity of nodes was equal to k. The deployment was tested for different values of k and transmission distance (d) to the node. The results showed that, when d was set to 200 m, as k increased from 2 to 4 the minimum connectivity of nodes increases and is equal to k. When k was set to 2, the average connectivity of all nodes increased in a linear manner with the increase of d from 140 m to 250 m, and the minimum connectivity does not change.
“…According to real situation of attack and defense decision of network security, the improved genetic algorithm is applied in optimization of parameters of fuzzy neutral network, the chaos optimization is introduced into the genetic algorithm, and the original population can be expressed by chaos sequence, the searching precision can be regulated in real time according to genetic procedure of population in optimization of parameters, then searching precision can be improved effectively [7].…”
Section: Training Algorithm Of Fuzzy Neutral Network Based On Improvementioning
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.