An improved artificial neural network based on human-behaviour particle swarm optimization and cellular automata

Wang, Yue; Líu, Hao; Yu, ZhongXin; Tu, Liangping

doi:10.1016/j.eswa.2019.112862

Cited by 27 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In that study, the performance of the MLPNN-ChOA algorithm was compared with the performance of IMA, GWO and a hybrid algorithm on the underwater acoustic dataset classification problem, which showed the superiority of the MLPNN-ChOA. Wang et al [ 160 ] used the PSO and CA algorithms to optimize the neural network weights. The combined particle swarm optimization (HPSO) algorithm was first developed in that research.…”

Section: Review Of the Training DL And Aans By Mh Algorithmsmentioning

confidence: 99%

Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review

Kaveh

Mesgari

2022

Neural Process Lett

View full text Add to dashboard Cite

The learning process and hyper-parameter optimization of artificial neural networks (ANNs) and deep learning (DL) architectures is considered one of the most challenging machine learning problems. Several past studies have used gradient-based back propagation methods to train DL architectures. However, gradient-based methods have major drawbacks such as stucking at local minimums in multi-objective cost functions, expensive execution time due to calculating gradient information with thousands of iterations and needing the cost functions to be continuous. Since training the ANNs and DLs is an NP-hard optimization problem, their structure and parameters optimization using the meta-heuristic (MH) algorithms has been considerably raised. MH algorithms can accurately formulate the optimal estimation of DL components (such as hyper-parameter, weights, number of layers, number of neurons, learning rate, etc.). This paper provides a comprehensive review of the optimization of ANNs and DLs using MH algorithms. In this paper, we have reviewed the latest developments in the use of MH algorithms in the DL and ANN methods, presented their disadvantages and advantages, and pointed out some research directions to fill the gaps between MHs and DL methods. Moreover, it has been explained that the evolutionary hybrid architecture still has limited applicability in the literature. Also, this paper classifies the latest MH algorithms in the literature to demonstrate their effectiveness in DL and ANN training for various applications. Most researchers tend to extend novel hybrid algorithms by combining MHs to optimize the hyper-parameters of DLs and ANNs. The development of hybrid MHs helps improving algorithms performance and capable of solving complex optimization problems. In general, the optimal performance of the MHs should be able to achieve a suitable trade-off between exploration and exploitation features. Hence, this paper tries to summarize various MH algorithms in terms of the convergence trend, exploration, exploitation, and the ability to avoid local minima. The integration of MH with DLs is expected to accelerate the training process in the coming few years. However, relevant publications in this way are still rare.

show abstract

Section: Review Of the Training DL And Aans By Mh Algorithmsmentioning

confidence: 99%

Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review

Kaveh

Mesgari

2022

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…Parwez et al [ 11 ] trained a neural network prediction model with anomalous and nonanomalous data to highlight the influence of anomalies in data while constructing the intelligent model; this can greatly improve the accuracy of neural networks. Wang et al [ 12 ] have used evolutionary algorithms to improve traditional BP neural network algorithms to prevent particles from falling into locally optimal solutions. Researchers such as Ai and Yang [ 13 ] have proposed a machine learning method based on a support vector machine optimized by a particle swarm optimization algorithm and applied it to cost prediction of environmental governance.…”

Section: Introductionmentioning

confidence: 99%

Safety Risk Assessment of Tourism Management System Based on PSO-BP Neural Network

Guo

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the development of science and technology, system management is gradually applied to tourism management. How to correctly assess the security risks of the tourism management system has become an important means to maintain passenger information. The security risk index of the travel management system is input into the PSO-BP network as a sample, and the corresponding risk value of the index is used as the network output. The results show that the error results, accuracy (96.53%), training time (216 s), number of iterations (275 times), and convergence speed are all better than traditional BP network. The relative error of PSO-BP network (0.32%) is better than that of BP network, with 300 iterations, and the error is close to 10–5. The average evaluation accuracy of S based on PSO-BP network is 99.72%, and the average time consumed is 2.512 s. It is superior to the evaluation model based on fuzzy set and entropy weight theory and the evaluation model based on gray correlation analysis and radial basis function neural network. In conclusion, the security risk assessment of the tourism management system based on PSO-BP network can effectively assess the security risk of the tourism management system.

show abstract

“…where xi is an input variable, wij is the weight between the input i and the hidden neuron j, βj is the bias of the hidden neuron j, ϕ1 the activation sigmoid function, wjk is the weight of connection of neuron j in the hidden layer to unique neuron k in the output layer, β0 is the bias of the output neuron k (Wang et al 2020;)…”

Section: Multilayer Perceptron Artificial Neural Network (Mlpnn)mentioning

confidence: 99%

Modelling Reference Evapotranspiration using a Novel Regression-based Method: Radial basis M5 Model Tree

Kişi

Keshtegar

Zounemat‐Kermani

et al. 2021

Preprint

View full text Add to dashboard Cite

In the current study, an ability of a novel regression-based method is evaluated in modelling daily reference evapotranspiration (ET0), which is an important issue in water resources management plans and helps farmers in irrigation planning. The method was developed by hybridizing radial basis function and M5 model tree and called as radial basis M5 model tree (RM5Tree). The radial-based kernel function was used to control the input variables in modelling process of M5 model tree. The new model results were compared with traditional M5 model tree (M5Tree), response surface method (RSM) and two neural networks (multi-layer perceptron neural networks, MLPNN & radial basis function neural network, RBFNN) with respect to several statistical indices. Daily climatic data (relative humidity, RH, solar radiation, SR, wind speed, air temperature, T) recorded at three stations in Turkey, Mediterranean Region, were used. The effect of each weather data on ET0 was also investigated by utilizing three different input scenarios with various combinations of input variables. On the whole, the RM5Tree provided the best results (NSE > 0.997) followed by the MLPNN (NSE > 0.990), and M5Tree (NSE > 0.945) in modelling daily ET0. The SR was observed as the most effective input parameter on ET0 which was followed by the T and RH. However, the findings of the third modelling scenario revealed that taking into account of all variables would considerably increase models’ accuracies for the three stations.

show abstract

An improved artificial neural network based on human-behaviour particle swarm optimization and cellular automata

Cited by 27 publications

References 21 publications

Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review

Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review

Safety Risk Assessment of Tourism Management System Based on PSO-BP Neural Network

Modelling Reference Evapotranspiration using a Novel Regression-based Method: Radial basis M5 Model Tree

Contact Info

Product

Resources

About