An Improved Grey Wolf Optimization-Based Learning of Artificial Neural Network for Medical Data Classification

Abstract

Grey wolf optimization (GWO) is a recent and popular swarm-based metaheuristic approach. It has been used in numerous fields such as numerical optimization, engineering problems, and machine learning. The different variants of GWO have been developed in the last 5 years for solving optimization problems in diverse fields. Like other metaheuristic algorithms, GWO also suffers from local optima and slow convergence problems, resulted in degraded performance. An adequate equilibrium among exploration and exploitation is a key factor to the success of meta-heuristic algorithms especially for optimization task. In this paper, a new variant of GWO, called inertia motivated GWO (IMGWO) is proposed. The aim of IMGWO is to establish better balance between exploration and exploitation. Traditionally, artificial neural network (ANN) with backpropagation (BP) depends on initial values and in turn, attains poor convergence. The metaheuristic approaches are better alternative instead of BP. The proposed IMGWO is used to train the ANN to prove its competency in terms of prediction. The proposed IMGWO-ANN is used for medical diagnosis task. Some benchmark medical datasets including heart disease, breast cancer, hepatitis, and parkinson's diseases are used for assessing the performance of IMGWO-ANN. The performance measures are described in terms of mean squared errors (MSEs), classification accuracies, sensitivities, specificities, the area under the curve (AUC), and receiver operating characteristic (ROC) curve. It is found that IMGWO outperforms than three popular metaheuristic approaches including GWO, genetic algorithm (GA), and particle swarm optimization (PSO). Results confirmed the potency of IMGWO as a viable learning technique for an ANN.

Imgwo Based Ann: A New Heart Disease Diagnosis Model to Classify Real World Dataset

“…In this study, the weights and biases are optimized with a variant of grey wolf optimization (GWO) [54]. This variant is named inertia motivated grey wolf optimization (IMGWO) and proposed by Kumar et al in 2021 [22].IMGWO was proposed to increase the exploration and exploitation capabilities of GWO since it is usually entrapped in local minima and slow convergence during the later part of evolution [55].IMGWO is explained in Algorithm1.…”

“…ANNs performed better as compared to other classifiers while diagnosing a heart problem [17], [18] however, ANN often entrapped in local minima and poor convergence [19], [20]. The poor convergence and local minima entrapment may be handled by hybridizing ANN with suitable metaheuristic optimization methods [21], [22].In this paper, classification via ANN-IMGWO model is performed preceded by feature selection on a real-world heart diseases dataset. Other contemporary metaheuristic optimization methods viz.…”

“…FS(the second contribution), is a naturally demanded issue while dealing with a new dataset with many dimensions. IMGWO has been proposed recently by the authors in 2021 [22]. IMGWO improved the exploration and exploitation capabilities of GWO by combing the memory retention property of PSO and avoiding local optima and slow convergence of classic GWO.…”

“…The position of the alpha search agent is the optimal solution. The details of the IMGWO algorithm is given in [22]. The current research study investigated the performance of IMGWO in terms of better convergence by avoiding the local minima entrapment in a large search space of weights and biases for an ANN.…”

Media Information Dissemination Model of Wireless Networks Using Deep Residual Network

“…In the network training process, for the output results of each layer, the degree of classification error needs to be measured by loss function calculation. e weight of each layer is updated by gradient descent [13].…”