An effective gbest-guided gravitational search algorithm for real-parameter optimization and its application in training of feedforward neural networks

Bohat, Vijay Kumar; Arya, K. V.

doi:10.1016/j.knosys.2017.12.017

Cited by 45 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They demonstrated the superiority and success of the proposed algorithm by applying it to different classification problems. 50 Yang et al…”

Section: Mrfo Algorithm Applied To Feedforward Neural Networkmentioning

confidence: 99%

“…Bohat and Arya used the Gbest‐guided GSA in FFNN training. They demonstrated the superiority and success of the proposed algorithm by applying it to different classification problems 50 . Yang et al developed the Compact Teaching‐Learning‐Based Optimization algorithm for the training of FFNN and radial basis function neural network structures.…”

Section: Mrfo Algorithm Applied To Feedforward Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Manta ray foraging optimization algorithm–based feedforward neural network for electric energy consumption forecasting

Duman

Dalcalı

Özbay

2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…They demonstrated the superiority and success of the proposed algorithm by applying it to different classification problems. 50 Yang et al…”

Section: Mrfo Algorithm Applied To Feedforward Neural Networkmentioning

confidence: 99%

Section: Mrfo Algorithm Applied To Feedforward Neural Networkmentioning

confidence: 99%

Manta ray foraging optimization algorithm–based feedforward neural network for electric energy consumption forecasting

Duman

Dalcalı

Özbay

2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…ese models range from single to multiobjective and from direct to nonstraight forms. e optimization methods [29] used in the study range from conventional methods to computational intelligence (CI) techniques such as genetic/evolutionary algorithms [38,39].…”

Section: Proposed Optimization Techniquementioning

confidence: 99%

Optimal Crop Selection Using Gravitational Search Algorithm

Cheema

Singh

Gritli

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

For the economic growth of the crop, the optimal utilization of soil is found to be an open area of research. An efficient utilization includes various advantages such as watershed insurance, expanded biodiversity, and reduction of provincial destitution. Generally, soils present synthetic confinements for crop improvement. Therefore, in this paper, a novel diversified crop model is proposed to predict the suitable soil for good production of the crop. The proposed model utilizes a quantum value-based gravitational search algorithm (GSA) to optimize the best solution. Various features of soil are required to be investigated before crop selection. These features are refined further by applying quantum optimization. The crop selection based upon the soil requirement does not require any additional fertilizers which will reduce the production cost. Thus, the proposed model can select the optimal crop according to the soil components using the gravitational search algorithm. Therefore, the gravitational search algorithm is applied to the quantum values obtained from the crop and soil dataset. Extensive experiments show that the proposed model achieves an optimal selection of crops.

show abstract

“…Biogeography-based optimization [17] was introduced into the FNN weights optimization by Zhang et al, and they use the optimized FNN to solve fruit classification problems. In [18], Bohat and Arya studied the existing gravitational search algorithm (GSA) and further proposed a novel algorithm named gbest-guided gravitational search algorithm (GG-GSA). This algorithm is used to optimize the weights of FNN and also achieves a good performance on classification accuracy compared with GSA and some other EC methods.…”

mentioning

confidence: 99%

“…This algorithm is used to optimize the weights of FNN and also achieves a good performance on classification accuracy compared with GSA and some other EC methods. However, which is the same as the study of stochastic optimization problems in most literatures, the datasets chosen in [18] are all small-scale datasets, the biggest one of them only has 41 features while the corresponding number of weights (solution size of EC methods) is 3570. In other words, the researcher did not use GG-GSA to solve large-scale FNN weights optimization problems.…”

mentioning

confidence: 99%

Large-Scale Feedforward Neural Network Optimization by a Self-Adaptive Strategy and Parameter Based Particle Swarm Optimization

2019

View full text Add to dashboard Cite

Feedforward neural network (FNN) is one of the most widely used and fastest-developed artificial neural networks. Much evolutionary computation (EC) methods have been used to optimize the weights of FNN. However, as the dimension of datasets increases, the number of weights also increases dramatically. On high-dimensional datasets, if EC methods are used directly to optimize the weights of FNN, it is impossible to obtain the optimal weights of the FNN by EC methods in an acceptable time. Feature selection is a method that can effectively reduce the computational complexity of FNN by reducing irrelevant and redundant features. It may be practical to optimize the FNN by EC methods if we first employ the feature selection for the large-scale datasets. In this paper, we present a self-adaptive parameter and strategy-based particle swarm optimization (SPS-PSO) algorithm to optimize FNN with feature selection. First, we propose an optimization model for FNN by transforming the designing of FNN into a weights optimization problem. Simultaneously, we present a feature selection optimization model. Second, we present an SPS-PSO algorithm. In this algorithm, we use the parameter and strategy self-adaptive mechanism. In addition, five candidate solution generating strategies (CSGS) are used. The experiments are divided into two groups. In the first group, SPS-PSO and three other EC methods are used to directly optimize the weights of FNN on eight datasets without any modification. In the second group, we first employ SPS-PSO-based feature selection on the original datasets and obtain eight relatively smaller datasets with the k-nearest neighbor (KNN) which is used as the evaluation function for saving time. Then, we use the new datasets as the inputs for FNN. We optimize the weights of FNN again by SPS-PSO and three other EC methods to investigate whether we can get similar or even better classification accuracy by comparing the results with that of the first group. The experimental results show that SPS-PSO has the advantage in optimizing the weights of FNN compared with the other EC methods. Meanwhile, the SPS-PSO-based feature selection can reduce the solution size and computational complexity while ensuring the classification accuracy when it is used to preprocess the datasets for FNN. In this method, a solution with an originally higher than 700 000 dimensions can be even reduced to hundreds of dimensions. INDEX TERMS Classification, evolutionary computation, feature selection, feedforward neural networks, self-adaptive, parameter adaptation, particle swarm optimization. I. INTRODUCTION Artificial neural network (ANN) [1], [2] is a hot research topic in the field of artificial intelligence [3] since the 1980s The associate editor coordinating the review of this manuscript and approving it for publication was Yongming Li. and it has been widely used as an effective classification method. ANN is a nonlinear and adaptive information processing system composed of a large number of interconnected processing units. It abstra...

show abstract

An effective gbest-guided gravitational search algorithm for real-parameter optimization and its application in training of feedforward neural networks

Cited by 45 publications

References 33 publications

Manta ray foraging optimization algorithm–based feedforward neural network for electric energy consumption forecasting

Manta ray foraging optimization algorithm–based feedforward neural network for electric energy consumption forecasting

Optimal Crop Selection Using Gravitational Search Algorithm

Large-Scale Feedforward Neural Network Optimization by a Self-Adaptive Strategy and Parameter Based Particle Swarm Optimization

Contact Info

Product

Resources

About