Efficient Artificial neural networks based on a hybrid metaheuristic optimization algorithm for damage detection in laminated composite structures

Artificial neural network (ANN) has been commonly used to deal with many problems. However, since this algorithm applies backpropagation algorithms based on gradient descent (GD) technique to look for the best solution, the network may face major risks of being entrapped in local minima. To overcome those drawbacks of ANN, in this work, we propose a novel ANN working parallel with metaheuristic algorithms (MAs) to train the network. The core idea is that first, (1) GD is applied to increase the convergence speed. (2) If the network is stuck in local minima, the capacity of the global search technique of MAs is employed. (3) After escaping from local minima, the GD technique is applied again. This process is applied until the target is achieved. Additionally, to increase the efficiency of the global search capacity, a hybrid of particle swarm optimization and genetic algorithm (PSOGA) is employed. The effectiveness of ANNPSOGA is assessed using both numerical models and measurement. The results demonstrate that ANNPSOGA provides higher accuracy than traditional ANN, PSO, and other hybrid ANNs (even a higher level of noise is employed) and also considerably decreases calculational cost compared with PSO.

With the rapid development of sequencing technology, the application of genomic prediction has become more and more common in breeding schemes of livestocks and crops. Selecting an appropriate statistical model is of central importance to achieve high prediction accuracy. Recently, machine learning models have been expected to upgrade genomic prediction into a new era. However, the perspective still suffers from lack of evidence that machine learning models can generally outperform the traditional ones on empirical data sets. In this study, we compared two machine learning models based on artificial neural network (ANN) and convolutional neural network (CNN) with four traditional models, including genomic best linear unbiased prediction (GBLUP), Bayesian ridge regression (BRR), BayesA and BayesB, using three published data sets for grain yield in wheat. For each model, we considered two variants: modeling and ignoring the genotype-by-environment ([Formula: see text]) interaction. In the comparison, we considered two strategies of cross-validation: predicting genotypes that have not been evaluated in any environment (CV1) and predicting genotypes that have been tested in other environments (CV2). Our results showed that traditional Bayesian models (BayesA, BayesB, and BRR) outperformed GBLUP, ANN and CNN when considering [Formula: see text] interaction. The accuracies of ANN and CNN were higher than traditional models only in CV1 and when [Formula: see text] interaction was ignored. It was also found that the performance of the two machine learning models was significantly affected by the interaction between the CV strategy and the way of treating the [Formula: see text] interaction, while that of the four traditional models was only influenced by whether the [Formula: see text] interaction was considered or not. Thus, machine learning models can be a powerful complementary to the traditional ones and their superiority may depend on the prediction scenario. Among the two machine learning models, we observed that the accuracy of ANN was higher than CNN in most cases, indicating that it is still challenging to adapt complex machine learning models such as CNN to genomic prediction.

Objective: The main objective of this paper is to improve the intrusion detection accuracy of neural networks by hybridized with Jordan network, applying novel Lyapunov function and changing input values as fuzzy values using fuzzy logic. Methods: In this research, the intrusion detection of NSL KDD dataset is carry out by neural network first . The performance of neural networks mainly depends on the parameters like number of hidden layer, no of node in the hidden layer and the no of epoch. Selecting the proper parameters values and weight initialization are the main difficulty in neural network. To overcome this issue a hybrid network by combining neural network with Jordan network is proposed which is highly sensitive to weight convergence. In hybrid network Lyapunov function is used to achieve the stability of equilibrium between two networks. But in this work a novel Lyapunov function is proposed to achieve global robust stability in hybrid network. A novel Lyapunov function uses a class of general activation functions which are not to be differentiable, bounded or monotonically nondecreasing. A set of criteria are derived to guarantee the existence, uniqueness and global robust stability of the equilibrium of hybrid networks with time delays. Then the learning ability of hybrid network is improved by using fuzzy logic. The hybrid network improved by a novel Lyapunov and fuzzy logic is called as Improved Fuzzy Hybrid Jordan network and Artificial Neural Network (IHFJANN). Findings: Artificial Neural Network (ANN), Hybrid Jordan network and Artificial Neural Network (HJANN) and Improved Hybrid Fuzzy Jordan network and Artificial Neural Network (IHFJ ANN) are applied on NSL KDD training dataset to lean the type of available attacks. NSL training dataset contains 2500 instances and 38 attributes where as testing dataset contains 995 instances and 38 attributes. The learned model of three classifiers is used to predict the classes in test dataset. The performance measures are evaluated in terms of accuracy, precision, recall and f-measure values. Improvement: The classification accuracy of Artificial Neural Network (ANN), Hybrid Jordan network and Artificial Neural Network (HJANN) and Improved Hybrid Fuzzy Jordan network and Artificial Neural Network (IHFJANN) are 72%, 80% and 84% respectively. Accuracy is increased by 12% in IHFJANN than the ANN and 4% than the HJANN. The precision value of ANN, HJANN and IHFJANN are 0.46, 0.54 and 0.57 respectively. Precision value is increased by 0.9 in IHFJANN than the ANN and 0.3 than the HJANN. The recall value of ANN, HJANN and IHFJANN are 0.73, 0.81 and 0.84 respectively. Recall value is increased by 0.9 in IHFJANN than the ANN and 0.3 than the HJANN. The F-measure value of ANN, HJANN and IHFJANN are 0.58, 0.65 and 0.68 respectively. F-measure value is increased by 0.10 in IHFJANN than the ANN and 0.3 than the HJANN. The results proved that the proposed IHFJANN provides better performance than ANN and HJANN.

Under harsh geographical conditions where manned flight is not possible, the ability of the unmanned aerial vehicle (UAV) to successfully carry out the payload hold–release mission by avoiding obstacles depends on the optimal path planning and tracking performance of the UAV. The ability of the UAV to plan and track the path with minimum energy and time consumption is possible by using the flight parameters. This study performs the optimum path planning and tracking using Harris hawk optimization (HHO)–grey wolf optimization (GWO), a hybrid metaheuristic optimization algorithm, to enable the UAV to actualize the payload hold–release mission avoiding obstacles. In the study, the hybrid HHO–GWO algorithm, which stands out with its avoidance of local minima and speed convergence, is used to successfully obtain the feasible and effective path. In addition, the effect of the mass change uncertainty of the UAV on optimal path planning and tracking performance is determined. The effectiveness of the proposed approach is tested by comparing it with the metaheuristic swarm optimization algorithms such as particle swarm optimization (PSO) and GWO. The experimental results obtained indicate that the proposed algorithm generates a fast and safe optimal path without becoming stuck with local minima, and the quadcopter tracks the generated path with minimum energy and time consumption.

Artificial neural networks have a wide use in the prediction and classification of different variables, but their application in the area of educational psychology is still relatively rare. The aim of this study was to examine the accuracy of artificial neural networks in predicting students’ general giftedness. The participants were 221 fourth grade students from one Croatian elementary school. The input variables for artificial neural networks were teachers’ and peers’ nominations, school grades, earlier school readiness assessment and parents’ education. The output variable was the result on the Standard Progressive Matrices (Raven, 1994), according to which students were classified as gifted or non-gifted. We tested two artificial neural networks’ algorithms: multilayer perceptron and radial basis function. Within each algorithm, a number of different types of activation functions were tested. 80% of the sample was used for training the network and the remaining 20% to test the network. For a criterion according to which students were classified as gifted if their result on the Standard Progressive Matrices was in the 95th centile or above, the best model was obtained by the hyperbolic tangent multilayer perceptron, which had a high accuracy of 100% of correctly classified non-gifted students and 75% correctly classified gifted students in the test sample. When the criterion was the 90th centile or above, the best model was also obtained by the hyperbolic tangent multilayer perceptron, but the accuracy was lower: 94.7% in the classification of non-gifted students and 66.7% in the classification of gifted students. The study has shown artificial neural networks’ potential in this area, which should be further explored. Keywords: gifted students, identification of gifted students, artificial neural networks

Bearing fault diagnosis plays a pivotal role in the realm of condition-based maintenance, with vibration spectra analysis standing out as a highly effective method for discerning issues in rotating machinery. Various signal processing tools, including wavelet analysis, empirical mode decomposition, and Hilbert-Huang transform, have been employed to scrutinize vibration spectra. However, these methodologies often necessitate human expertise to ensure optimal outcomes. In the pursuit of automated fault diagnosis, machine learning tools such as Artificial Neural Networks (ANN) and support vector machines (SVM) have emerged as viable alternatives. Over recent decades, considerable research efforts have been devoted to exploring the viability of employing Artificial Neural Networks (ANN) for automatic fault diagnosis, resulting in predominantly positive findings. Nevertheless, the accuracy of Artificial Neural Networks (ANN) is intricately linked to factors such as the neural network structure, encompassing considerations like the number of nodes, hidden layers, and the choice of activation function. Addressing this challenge, the present study introduces an innovative hybrid algorithm for automated bearing fault diagnosis, integrating Artificial Neural Networks (ANN) with the Bayes’ Theorem (BT) theory. The hybrid algorithm exploits Bayes’ Theorem (BT) theory to augment fault diagnosis results derived from Artificial Neural Networks (ANN), specifically by alleviating conflicting outcomes generated within the neural network. The study focuses on characterizing four conditions of bearings, namely a healthy state and three distinct fault types: rolling element, inner race, and outer race faults. Through the proposed hybrid algorithm, working in tandem with artificial neural networks, a demonstrated superiority is established, surpassing the results obtained by Artificial Neural Networks (ANN) in isolation. This pioneering approach not only underscores the potential for heightened accuracy but also underscores the enhanced reliability achievable in automated bearing fault diagnosis.

Hybrid adaptive simplified human learning optimization algorithms for supply chain network design problem with possibility of direct shipment

Artificial neural networks (ANN) and evolutionary algorithms are two relatively young research areas that were subject to a steadily growing interest during the past years. This paper examines the use of different evolutionary algorithms, imperialist competitive algorithm (ICA), genetic algorithm (GA), ICA-GA and recursive ICA-GA (R-ICA-GA) to train a classification problem on a multi layer perceptron (MLP) neural network. All of named evolutionary training algorithms are compared together in this paper. The first goal of the paper is to apply new evolutionary optimization algorithms ICA-GA and R-ICA-GA for training the ANN and the second goal of the paper is to compare different evolutionary algorithms. It is shown that the ICA-GA has the best performance, in number of epochs, compared to the other algorithms. For this purpose, learning algorithms are applied on six known datasets (WINE, PIMA, WDBC, IRIS, SONAR and GLASS) which are used for classification problems.

Predicting postoperative nausea and vomiting with the application of an artificial neural network

In this paper, cell loading and shipment method optimisation problem in a cellular manufacturing system are studied. A hierarchical methodology that consists of mathematical optimisation model, genetic algorithms (GAs) and artificial neural networks (ANNs) were proposed. The mathematical model is compared with the GA in terms of the optimisation performance. Next, ANN model was developed as decision support tool to study the impact of GA parameters on the solution quality. Several problem sizes were experimented with the proposed GA and the mathematical model, and compared. GA was run to make a total of 648 sample solutions for the 20-job problem. Next, ANN model was built based on the sample solutions' data and the optimal ANN model is identified out of 1,000 networks. The results were also coupled with sensitivity and statistical analyses, which indicated that type of crossover and mutation operators, had the greatest impact on the solution quality.


 
 
 
 One of the weakness in backpropagation Artificial neural network(ANN) is being stuck in local minima. Learning rate parameter is an important parameter in order to determine how fast the ANN Learning. This research is conducted to determine a method of finding the value of learning rate parameter using a genetic algorithm when neural network learning stops and the error value is not reached the stopping criteria or has not reached the convergence. Genetic algorithm is used to determine the value of learning rate used is based on the calculation of the fitness function with the input of the ANN weights, gradient error, and bias. The calculation of the fitness function will produce an error value of each learning rate which represents each candidate solutions or individual genetic algorithms. Each individual is determined by sum of squared error value. One with the smallest SSE is the best individual. The value of learning rate has chosen will be used to continue learning so that it can lower the value of the error or speed up the learning towards convergence.
 
 
 
 
 The final result of this study is to provide a new solution to resolve the problem in the backpropagation learning that often have problems in determining the learning parameters. These results indicate that the method of genetic algorithms can provide a solution for backpropagation learning in order to decrease the value of SSE when learning of ANN has been static in large error conditions, or stuck in local minima

Corporate bankruptcy prediction is an important task in the determination of corporate solvency, that is, whether a company can meet up to its financial obligations or not. It is widely studied as it has a significant effect on employees, customers, management, stockholders, bank lending assessments, and profitability. In recent years, machine learning techniques, particularly Artificial Neural Network (ANN), have widely been studied for bankruptcy prediction since they have proven to be a good predictor, especially in financial applications. A critical process in learning a network is weight training. Although the ANN is mathematically efficient, it has a complex weight training process, especially in computation time when involving a large training data. Many studies improved ANN’s weight training using metaheuristic algorithms such as Evolutionary Algorithms (EA), and Swarm Intelligence (SI) approaches for bankruptcy prediction. In this study, two metaheuristics algorithms, Magnetic Optimization Algorithm (MOA) and Particle Swarm Optimization (PSO), have been enhanced through hybridization to propose a new method MOA-PSO. Hybrid algorithms have been proven to be capable of solving optimization problems faster, with better accuracy. The MOA-PSO was used in training ANN to improve the performance of the ANN in bankruptcy prediction. The performance of the hybrid MOA-PSO was compared with that of four existing algorithms. The proposed hybrid MOA-PSO algorithm exhibits promising results with a faster and more accurate prediction, with 99.7% accuracy.

The Brain Emotional Learning (BEL) is a novel bio-inspired machine learning approach mentioned as a new class of artificial neural network (ANN). The artificial emotional neural network (AENN) is one of the BEL methods which used the genetic algorithm (GA) to compute proper weights, weights of the amygdala (AMYG), orbitofrontal cortex (OFC) weights and a bias value. AENN trained by GA has been reported that it could produce low error rates. However, AENN still has more rooms to enhance its prediction of performance, especially generalization and the prediction of performance. Therefore, this paper aims to propose a new training method for AENN. The JAYA optimization algorithm optimized the weights and the biases of AENN. Two new proposed models are named as AENN-Max-JAYA and AENN-Mean-JAYA. Their names are according to the way of selecting the additional expanded feature which obtained through either the max or the average of input patterns, respectively. From the experimental results for wind power forecasting dataset, the proposed methods proved that the results are better in generalization performance and give lower error rates which compared to the comparative AENN models and traditional ANNs.

Experimental evaluation, sensitivity analyzation and ANN modeling of thermal conductivity of ZnO-MWCNT/EG-water hybrid nanofluid for engineering applications

The test- day model is a method of choice for the study of milk yield traits and this method is very important in countries like India where herd size is generally smaller and lacking well-established milk recording system. The present study was aimed to predict first lactation milk yield on the basis of test day yield in Gir cows and comparison was made between the relative efficiency of Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) models. First lactation records of 513Gir cows sired by 75 bulls spread over a period of 34 years (1981to 2014), maintained at Cattle Breeding Farm, Junagadh were used for the study. The data of monthly test-day milk yield (MTMY)was divided into seven sets. ANN was used with backpropagation Bayesian regularization (BR) algorithm and MLR was used with backward elimination method. The accuracy of prediction of first lactation milk yield in MLR was lower than the accuracy of ANN in all the test data sets. The Root Mean Square Errors (RMSE) of prediction were lower in ANN as compared to MLR. The optimum equation had total four variables (test days)viz. TD2 to TD5 for prediction of First Lactation 305-Days Milk Yield (FL305DMY). This equation gave an accuracy of prediction of 76.02% by MLR and 87.69% by ANN model till 125th days of lactation i.e. 5th monthly test day.