Hybrid Genetic Algorithm Neural Network Research Articles

Enhanced prediction intervals of tunnel-induced settlement using the genetic algorithm and neural network

This paper constructs the prediction intervals (PIs) of the tunnels’ settlement caused by the shielding steering process. The hybrid genetic algorithm -neural network (GA-NN) is developed to obtain the upper and lower bound of the settlement based on a series of shield operating parameters, geological condition parameters, tunnel geometric parameters, and anomalous conditions. An improved prediction interval-based cost function is proposed to enable the consideration of the uncertainty from model misspecification and noise variance. The genetic algorithm optimizes the weighted parameters in the neural network by minimizing the cost function value. This study adopts a metro tunnel construction case in China to verify the effectiveness of the proposed hybrid genetic algorithm-neural network approach. The results based on the study case illustrate the superiority of the proposed hybrid approach in (1) overcoming the limitations of the conventional prediction interval indicator; (2) achieving comparative results with the deterministic estimation based on the least squares support vector machine; (3) providing a probability prediction of the settlement only based on deterministic input multivariables. Overall, this study contributes to (1) the uncertainty assessment of tunnel settlement based on the deterministic variables, (2) developing a new PIs based cost function which is stable and reliable, (3) the engineering practice for a safer assessment based on the prediction intervals.

A hybrid genetic algorithm-neural network model for power spectral density compatible ground motion prediction

In this paper, the utility of power spectral density (PSD) in ground motion prediction for hazard analysis is examined. The main advantage of PSD is that the area under PSD of excitation gives the energy of the excitation and it is structure independent. The PSD of ground motion from past earthquakes and properties of PSD in terms of spectral moments are studied. 1487 accelerograms from 25 major past earthquakes with magnitude ranging from 4.9 to 7.9 taken from the ‘Pacific Earthquake Engineering Research Centre – Next Generation Attenuation’ database are considered. PSD of past ground motion data is used to form a hybrid genetic algorithm-neural network based attenuation relationship with magnitude of earthquake, Joyner-Boore distance and shear-wave velocity. PSD compatible time histories are generated using the proposed model. An application of the proposed model is demonstrated by developing a uniform hazard power spectral density for Delhi with a return period of 2500 years.

Multi-output Hybrid GA-NN with Adaptive Mechanism

This research presents a hybrid Genetic Algorithm Neural Network (GA-NN) model to simulate the physical tests procedures of Medium Density Fiberboard (MDF). Data included in the model are related to MDF properties and its fiber characteristics. Multilayer Perceptron NN is a reliable supervised machine learning model. The model learns from seven inputs fed to the network to produce prediction of three targets. In order to avoid result from local optimum scenario, GA optimizes synaptic weights of the network towards reducing prediction error. The research used a fixed probability rates for crossover and mutation for hybrid GA-NN model. GA-NN model is further improved using adaptive mechanism to help identify the best probability rates for crossover and mutation. Fitness value refers to Sum of Squared Error, which is the accumulation of network error in the Output Layer. The population fitness distribution will guide best rates for each epoch. Performance comparisons are among three models; namely NN with Back Propagation (BP), hybrid GA-NN and hybrid GA-NN with adaptive mechanism. Results show the hybrid GA-NN model perform much better than NN model with back propagation optimizer. Adaptive mechanism in GA helps increase capability to converge at zero sooner than the ordinary GA.

Optimization of genetic algorithm parameter in hybrid genetic algorithm-neural network modelling: Application to spray drying of coconut milk

Application of Artificial Neural Network (ANN) and Genetic Algorithm (GA) are to provide an accurate model of the spray drying system. In this study, a comparative study is performed between ANN and GA enhanced ANN to estimate their abilities in emulating the spray drying process of coconut milk powder under restricted parameters. The GA parameter is optimized through response surface methodology (RSM). Through RSM, GA parameter such as population size, mutation and crossover are optimized and is used for the development of GA-ANN network. The optimized GA parameters values are at maximum population size (100), minimum crossover rate (0.2) and maximum mutation rate (1.0). The optimized GA parameters is then applied in the development of the GA-ANN network as the networks applied genetic algorithm to determine the initial weights in its neural network. Both models are then compared by placing importance of highest correlation of determination (R2) and lowest mean square error (MSE) values. The results have shown GA-ANN’s MSE (0.033396) is lower than ANN’s MSE value (0.082263), which the GA-ANN’s R2 value (0.88245) is higher than ANN (0.8499). This have shown that GA as a global search technique can be integrated in the development of the ANN.

Mining Medical Opinions Using Hybrid Genetic Algorithm—Neural Network

Mining Medical Opinions Using Hybrid Genetic Algorithm—Neural Network

Adaptive GA-NN for MDF Prediction Model

This research presents a hybrid Genetic Algorithm Neural Network (GA-NN) model to replace the physical tests procedures of Medium Density Fiberboard (MDF). Data included in the model is MDF properties and its fiber characteristics. Multilayer Perceptron (MLP) NN model is reliable to learn from seven inputs fed to the network to produce prediction of three targets. In order to avoid result from local optimum scenario, GA optimizes synaptic weights of the network towards reducing prediction error. The research used a fixed probability rates for crossover and mutation for hybrid GA-NN model. GA-NN model is further improved using adaptive mechanism to help identify the best probability rates. The fitness value refers to Sum of Squared Error. Performance comparisons are among three models; namely NN with Back Propagation (BP), hybrid GA-NN and hybrid GA-NN with adaptive mechanism. Results show the hybrid GA-NN model perform much better than NN model used with back propagation optimizer. Adaptive mechanism in GA helps increase capability to converge at zero sooner than the ordinary GA.

Hybrid genetic algorithm-neural network: Feature extraction for unpreprocessed microarray data

Suitable techniques for microarray analysis have been widely researched, particularly for the study of marker genes expressed to a specific type of cancer. Most of the machine learning methods that have been applied to significant gene selection focus on the classification ability rather than the selection ability of the method. These methods also require the microarray data to be preprocessed before analysis takes place. The objective of this study is to develop a hybrid genetic algorithm-neural network (GANN) model that emphasises feature selection and can operate on unpreprocessed microarray data. The GANN is a hybrid model where the fitness value of the genetic algorithm (GA) is based upon the number of samples correctly labelled by a standard feedforward artificial neural network (ANN). The model is evaluated by using two benchmark microarray datasets with different array platforms and differing number of classes (a 2-class oligonucleotide microarray data for acute leukaemia and a 4-class complementary DNA (cDNA) microarray dataset for SRBCTs (small round blue cell tumours)). The underlying concept of the GANN algorithm is to select highly informative genes by co-evolving both the GA fitness function and the ANN weights at the same time. The novel GANN selected approximately 50% of the same genes as the original studies. This may indicate that these common genes are more biologically significant than other genes in the datasets. The remaining 50% of the significant genes identified were used to build predictive models and for both datasets, the models based on the set of genes extracted by the GANN method produced more accurate results. The results also suggest that the GANN method not only can detect genes that are exclusively associated with a single cancer type but can also explore the genes that are differentially expressed in multiple cancer types. The results show that the GANN model has successfully extracted statistically significant genes from the unpreprocessed microarray data as well as extracting known biologically significant genes. We also show that assessing the biological significance of genes based on classification accuracy may be misleading and though the GANN's set of extra genes prove to be more statistically significant than those selected by other methods, a biological assessment of these genes is highly recommended to confirm their functionality.

Evolving neural network using real coded genetic algorithm for permeability estimation of the reservoir

In this work we investigate how artificial neural network (ANN) evolution with genetic algorithm (GA) improves the reliability and predictability of artificial neural network. This strategy is applied to predict permeability of Mansuri Bangestan reservoir located in Ahwaz, Iran utilizing available geophysical well log data. Our methodology utilizes a hybrid genetic algorithm–neural network strategy (GA–ANN). The proposed algorithm combines the local searching ability of the gradient–based back-propagation (BP) strategy with the global searching ability of genetic algorithms. Genetic algorithms are used to decide the initial weights of the gradient decent methods so that all the initial weights can be searched intelligently. The genetic operators and parameters are carefully designed and set avoiding premature convergence and permutation problems. For an evaluation purpose, the performance and generalization capabilities of GA–ANN are compared with those of models developed with the common technique of BP. The results demonstrate that carefully designed genetic algorithm-based neural network outperforms the gradient descent-based neural network.

A hybrid genetic algorithm–neural network strategy for simulation optimization

Abstract Simulation optimization aims at determining the best values of input parameters, while the analytical objective function and constraints are not explicitly known in terms of design variables and their values only can be estimated by complicated analysis or time-consuming simulation. In this paper, a hybrid genetic algorithm–neural network strategy (GA–NN) is proposed for such kind of optimization problems. The good approximation performance of neural network (NN) and the effective and robust evolutionary searching ability of genetic algorithm (GA) are applied in hybrid sense, where NNs are employed in predicting the objective value, and GA is adopted in searching optimal designs based on the predicted fitness values. Numerical simulation results and comparisons based on a well-known pressure vessel design problem demonstrate the feasibility and effectiveness of the framework, and much better results are achieved than some existed literature results.