Artificial Immune System in Doing 2-Satisfiability Based Reverse Analysis Method via a Radial Basis Function Neural Network

Abstract

A radial basis function neural network-based 2-satisfiability reverse analysis (RBFNN-2SATRA) primarily depends on adequately obtaining the linear optimal output weights, alongside the lowest iteration error. This study aims to investigate the effectiveness, as well as the capability of the artificial immune system (AIS) algorithm in RBFNN-2SATRA. Moreover, it aims to improve the output linearity to obtain the optimal output weights. In this paper, the artificial immune system (AIS) algorithm will be introduced and implemented to enhance the effectiveness of the connection weights throughout the RBFNN-2SATRA training. To prove that the introduced method functions efficiently, five well-established datasets were solved. Moreover, the use of AIS for the RBFNN-2SATRA training is compared with the genetic algorithm (GA), differential evolution (DE), particle swarm optimization (PSO), and artificial bee colony (ABC) algorithms. In terms of measurements and accuracy, the simulation results showed that the proposed method outperformed in the terms of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Schwarz Bayesian Criterion (SBC), and Central Process Unit time (CPU time). The introduced method outperformed the existing four algorithms in the aspect of robustness, accuracy, and sensitivity throughout the simulation process. Therefore, it has been proven that the proposed AIS algorithm effectively conformed to the RBFNN-2SATRA in relation to (or in terms of) the average value of training of RMSE rose up to 97.5%, SBC rose up to 99.9%, and CPU time by 99.8%. Moreover, the average value of testing in MAE was rose up to 78.5%, MAPE—rose up to 71.4%, and was capable of classifying a higher percentage (81.6%) of the test samples compared with the results for the GA, DE, PSO, and ABC algorithms.

Examining the Forecasting Movement of Palm Oil Price Using RBFNN-2SATRA Metaheuristic Algorithms for Logic Mining

“…where pa refers to the center's number, widths, as well as output weights. Concerning the values of SBC, lower values designate the better values [16].…”

“…In [15], a logic mining method in ANN has been presented by applying the 3 Satisfiability Reverse Analysis method. To improve the method, [16] proposed a logic mining method by implementing in RBFNN and 2 Satisfiability. The proposed model showed its capability of extracting the logical rule between neurons.…”

An optimal representation of Random Maximum kSatisfiability on a Hopfield Neural Network for High order logic(k 3)

“…the RANMAXkSAT with large number of neurons as the input may achieve good results based on the training data used in this study; however, this could lead to a bad generalization (Alzaeemi and Sathasivam, 2020). In our experiments, we assess the performance of the proposed logical rule model on In our experiments, different evaluate matric were used based on the logical rules.…”

“…the neuronal oscillations of the Hopfield Neural Network during the recovery phase. Some studies have been conducted on the feasibility of Radial basis function neural to be incorporated with symbolic logic as a single network model studies such as propsoed in (Hamadneh et al 2012;Alzaeemi et al 2020). The Maximum random k-Satisfiability problem (MAXRANkSAT) is a vital generalization of Satisfiability problem.…”

Simulation Study on Modified Weibull Distribution for Modelling of Investment Return

“…However, there are a plethora of studies on the application of applications and uses of metaheuristics algorithm (MA) and artificial intelligence (AI) based techniques. These studies include a simulated algorithm (Abbasi et al 2006), genetic algorithm (Alzaeemi & Sathasivam 2020) and election algorithm (EA) (Sathasivam et al, 2020;Abubakar et al, 2020a;Abubakar Danrimi, 2021) and artificial dragonfly algorithm (Abubakar et al, 2020b). One of the purposes of incorporating MA was to maximise the fitness function for optimal representation.…”