Nazri Mohd Nawi | Universiti Tun Hussein Onn Malaysia (original) (raw)
Books by Nazri Mohd Nawi
Artificial Higher Order Neural Networks for Computer Science and Engineering: Trends for Emerging... more Artificial Higher Order Neural Networks for Computer Science and Engineering: Trends for Emerging Applications introduces Higher Order Neural Networks (HONNs) to computer scientists and computer engineers as an open box neural networks tool when compared to traditional artificial neural networks. Since HONNs are open box models, they can be easily used in information science, information technology, management, economics, and business. This book details the techniques, theory and applications essential to engaging and capitalizing on this developing technology.
Papers by Nazri Mohd Nawi
arXiv preprint arXiv:1112.4628, Dec 20, 2011
Abstract: Nowadays, computer scientists have shown the interest in the study of social insect... more Abstract: Nowadays, computer scientists have shown the interest in the study of social insect's behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm. Multilayer Perceptron (MLP) trained with the standard back propagation algorithm normally utilises computationally intensive training algorithms. One of the crucial ...
Lecture Notes in Computer Science, 2012
Learning problems for Neural Networks (NNs) has widely been explored from last two decades. Popul... more Learning problems for Neural Networks (NNs) has widely been explored from last two decades. Population based algorithms become more focus by researchers because of its nature behavior processing with optimal solution. The population-based algorithms are Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), and recently Hybrid Ant Bee Colony (HABC) Algorithms produced easy way for training NNs. These social based techniques mostly used for finding optimal weight values and over trapping local minima in NNs ...
Lecture Notes in Computer Science, 2013
This paper proposed Global Artificial Bee Colony algorithm for training Neural Network (NN), whic... more This paper proposed Global Artificial Bee Colony algorithm for training Neural Network (NN), which is a globalised form of standard Artificial Bee Colony algorithm. NN trained with the standard backpropagation (BP) algorithm normally utilizes computationally intensive training algorithms. One of the crucial problems with the BP algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome, GABC algorithm used in this work to train MLP learning for classification problem, the performance of GABC is benchmarked against MLP training with the typical BP, ABC and Particle swarm optimization. The experimental result shows that MLP-GABC performs better than that standard BP, ABC and PSO for the classification task.
International Journal of Applied Evolutionary Computation, 2000
The performance of Neural Networks (NN) depends on network structure, activation function and sui... more The performance of Neural Networks (NN) depends on network structure, activation function and suitable weight values. For finding optimal weight values, freshly, computer scientists show the interest in the study of social insect's behavior learning algorithms. Chief among these are, Ant Colony Optimzation (ACO), Artificial Bee Colony (ABC) algorithm, Hybrid Ant Bee Colony (HABC) algorithm and Global Artificial Bee Colony Algorithm train Multilayer Perceptron (MLP). This paper investigates the new hybrid technique called Global Artificial Bee Colony-Levenberq-Marquardt (GABC-LM) algorithm. One of the crucial problems with the BP algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome GABC-LM algorithm used in this work to train MLP for the boolean function classification task, the performance of GABC-LM is benchmarked against MLP training with the typical LM, PSO, ABC and GABC. The experimental result shows that GABC-LM performs better than that standard BP, ABC, PSO and GABC for the classification task.
From Last ten years, computer scientists show the interest in the study of social insect's behavi... more From Last ten years, computer scientists show the interest in the study of social insect's behavior algorithms like, Artificial Bee Colony (ABC), Ant Colony Optimization. Chief among of them, Standard ABC is well-known and new swarm optimization technique used for solving different combinatorial problems; however, it is often trapped in local optima in global optimization. This study investigates the new hybrid technique called Global Artificial Bee Colony-Backpropagation (GABC-BP) algorithm. This new technique shows great advantages of convergence property and excellent solution. To hybrid technique, GABC-BP algorithm used to this work for classification and prediction task. The performance of GABC-BP is benchmarked against BP, ABC and GABC. The experimental result shows that GABC-BP performs better than that standard BP, ABC and GABC for Boolean function classification and heat wave's temperature time series prediction.
Communications in Computer and Information Science, 2012
A social insect's techniques become more focus by researchers because of its nature behavior proc... more A social insect's techniques become more focus by researchers because of its nature behavior processing and by training neural networks through agents. Chief among them are Swarm Intelligence (SI), Ant Colony Optimization (ACO), and recently Artificial Bee Colony algorithm, which produced easy way for solving combinatorial problems and for training NNs. These social based techniques mostly used for finding optimal weight values in NNs learning. Usually, NNs trained by a standard and well known algorithm called Backpropagation (BP) have difficulties such as trapping in local minima, slow convergence or might fail sometimes. For recovering the above cracks the population or social insects based algorithms used for training NNs for minimizing network output error. Here, the hybrid of nature behavior agents' ant and bees combine's techniques used for training ANNs. The simulation result of a hybrid algorithm compared with, ABC and BP training algorithms. From the experimental results, the proposed Hybrid Ant Bee Colony (HABC) algorithm did improve the classification accuracy for prediction of a volcano time-series data.
A social insect's techniques become more focus by researchers because of its nature behavior proc... more A social insect's techniques become more focus by researchers because of its nature behavior processing and by training neural networks through agents. Chief among them are Swarm Intelligence (SI), Ant Colony Optimization (ACO), and recently Artificial Bee Colony algorithm, which produced easy way for solving combinatorial problems and for training NNs. These social based techniques mostly used for finding optimal weight values in NNs learning. Usually, NNs trained by a standard and well known algorithm called Backpropagation (BP) have difficulties such as trapping in local minima, slow convergence or might fail sometimes. For recovering the above cracks the population or social insects based algorithms used for training NNs for minimizing network output error. Here, the hybrid of nature behavior agents' ant and bees combine's techniques used for training ANNs. The simulation result of a hybrid algorithm compared with, ABC and BP training algorithms. From the experimental results, the proposed Hybrid Ant Bee Colony (HABC) algorithm did improve the classification accuracy for prediction of a volcano time-series data.
From Last ten years, computer scientists show the interest in the study of social insect’s behavi... more From Last ten years, computer scientists show the interest in the study of social insect’s behavior algorithms like, Artificial Bee Colony (ABC), Ant Colony Optimization. Chief among of them, Standard ABC is well-known and new swarm optimization technique used for solving different combinatorial problems; however, it is often trapped in local optima in global optimization. This study investigates the new hybrid technique called Global Artificial Bee Colony-Backpropagation (GABC-BP) algorithm. This new technique shows great advantages of convergence property and excellent solution. To hybrid technique, GABC-BP algorithm used to this work for classification and prediction task. The performance of GABC-BP is benchmarked against BP, ABC and GABC. The experimental result shows that GABC-BP performs better than that standard BP, ABC and GABC for Boolean function classification and heat wave's temperature time series prediction.
Prediction of tsunami was focused by researchers due to its devastating intensity among other dis... more Prediction of tsunami was focused by researchers due to its devastating intensity among other disasters in the world, especially after the Indian Ocean tsunami in December 2004. For natural disaster events scientists take an interest in social insects for classification, analyses and prediction to get optimal solution. Artificial bee colony (ABC) algorithm based on the natural behaviour of artificial bee is proposed here for prediction of tsunami parameters caused by undersea earthquakes. An artificial bee colony algorithm is used ...
Nowadays, computer scientists have shown the interest in the study of social insect's behaviour i... more Nowadays, computer scientists have shown the interest in the study of social insect's behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm. Multilayer Perceptron (MLP) trained with the standard back propagation algorithm normally utilises computationally intensive training algorithms. One of the crucial problems with the backpropagation (BP) algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome ABC algorithm used in this work to train MLP learning the complex behaviour of earthquake time series data trained by BP, the performance of MLP-ABC is benchmarked against MLP training with the standard BP. The experimental result shows that MLP-ABC performance is better than MLP-BP for time series data.
Journal of Computer Science & Computational Mathematics, 2012
Prediction of tsunami was focused by researchers due to its devastating intensity among other dis... more Prediction of tsunami was focused by researchers due to its devastating intensity among other disasters in the world, especially after the Indian Ocean tsunami in December 2004. For natural disaster events scientists take an interest in social insects for classification, analyses and prediction to get optimal solution. Artificial bee colony (ABC) algorithm based on the natural behaviour of artificial bee is proposed here for prediction of tsunami parameters caused by undersea earthquakes. An artificial bee colony algorithm is used ...
2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2014
ABSTRACT In this paper, Cauchy criterion, the necessary and sufficient conditions for Henstock in... more ABSTRACT In this paper, Cauchy criterion, the necessary and sufficient conditions for Henstock integrability of fuzzy number-valued functions defined on a compact interval in the real line is presented. The results can be used to characterize the integrability of a fuzzy number valued function without calculation the value of the integral. In addition, the notion, the elementary properties and the relation of R and R* integrals of fuzzy number-valued function defined on a compact interval in the real line are also presented.
Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the gr... more Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt Back propagation (LMBP) still it is not able to avoid local minimum. To deal with this problem, global search optimization technique has the ability to adjust the weight for NN (Neural Network) to avoid the local minima problem. This paper proposes an accelerated particle swarm optimization (APSO) is implemented in conjunction with Levenberg Marquardt back propagation (LMBP) algorithms to achieve faster convergence rate and to avoid local minima problem. The performances of the proposed Accelerated Particle Swarm Optimization Levenberg Marquardt (APSO_LM) algorithms compared by means of simulations on 7-Bit Parity and six UCI benchmark classification datasets. The simulation results show that the APSO-LM algorithm shows better performance than baseline algorithms in terms of convergence speed and Mean Squared Error (MSE).
An improved Bat algorithm with Gaussian distribution random walk (BAGD) is introduced in this pap... more An improved Bat algorithm with Gaussian distribution random walk (BAGD) is introduced in this paper. The original Bat algorithm has a problem of random large step length that leads to sub-optimal solutions in the search space and it cannot solve higher dimensional problems. To solve higher dimensional problems and to decrease the step length size, this research focuses on using a Gaussian distribution in Bat algorithm which provide shorter step lengths during the search. The proposed BAGD was compared with six popular metaheuristic algorithms on ten benchmark functions. Comparative results indicated that the proposed BAGD perform better than the state-of-the-art algorithms in most cases. The proposed BAGD solution used small step lengths in the search space and it was able to solve high dimensional problems.
Artificial Higher Order Neural Networks for Computer Science and Engineering: Trends for Emerging... more Artificial Higher Order Neural Networks for Computer Science and Engineering: Trends for Emerging Applications introduces Higher Order Neural Networks (HONNs) to computer scientists and computer engineers as an open box neural networks tool when compared to traditional artificial neural networks. Since HONNs are open box models, they can be easily used in information science, information technology, management, economics, and business. This book details the techniques, theory and applications essential to engaging and capitalizing on this developing technology.
arXiv preprint arXiv:1112.4628, Dec 20, 2011
Abstract: Nowadays, computer scientists have shown the interest in the study of social insect... more Abstract: Nowadays, computer scientists have shown the interest in the study of social insect's behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm. Multilayer Perceptron (MLP) trained with the standard back propagation algorithm normally utilises computationally intensive training algorithms. One of the crucial ...
Lecture Notes in Computer Science, 2012
Learning problems for Neural Networks (NNs) has widely been explored from last two decades. Popul... more Learning problems for Neural Networks (NNs) has widely been explored from last two decades. Population based algorithms become more focus by researchers because of its nature behavior processing with optimal solution. The population-based algorithms are Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), and recently Hybrid Ant Bee Colony (HABC) Algorithms produced easy way for training NNs. These social based techniques mostly used for finding optimal weight values and over trapping local minima in NNs ...
Lecture Notes in Computer Science, 2013
This paper proposed Global Artificial Bee Colony algorithm for training Neural Network (NN), whic... more This paper proposed Global Artificial Bee Colony algorithm for training Neural Network (NN), which is a globalised form of standard Artificial Bee Colony algorithm. NN trained with the standard backpropagation (BP) algorithm normally utilizes computationally intensive training algorithms. One of the crucial problems with the BP algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome, GABC algorithm used in this work to train MLP learning for classification problem, the performance of GABC is benchmarked against MLP training with the typical BP, ABC and Particle swarm optimization. The experimental result shows that MLP-GABC performs better than that standard BP, ABC and PSO for the classification task.
International Journal of Applied Evolutionary Computation, 2000
The performance of Neural Networks (NN) depends on network structure, activation function and sui... more The performance of Neural Networks (NN) depends on network structure, activation function and suitable weight values. For finding optimal weight values, freshly, computer scientists show the interest in the study of social insect's behavior learning algorithms. Chief among these are, Ant Colony Optimzation (ACO), Artificial Bee Colony (ABC) algorithm, Hybrid Ant Bee Colony (HABC) algorithm and Global Artificial Bee Colony Algorithm train Multilayer Perceptron (MLP). This paper investigates the new hybrid technique called Global Artificial Bee Colony-Levenberq-Marquardt (GABC-LM) algorithm. One of the crucial problems with the BP algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome GABC-LM algorithm used in this work to train MLP for the boolean function classification task, the performance of GABC-LM is benchmarked against MLP training with the typical LM, PSO, ABC and GABC. The experimental result shows that GABC-LM performs better than that standard BP, ABC, PSO and GABC for the classification task.
From Last ten years, computer scientists show the interest in the study of social insect's behavi... more From Last ten years, computer scientists show the interest in the study of social insect's behavior algorithms like, Artificial Bee Colony (ABC), Ant Colony Optimization. Chief among of them, Standard ABC is well-known and new swarm optimization technique used for solving different combinatorial problems; however, it is often trapped in local optima in global optimization. This study investigates the new hybrid technique called Global Artificial Bee Colony-Backpropagation (GABC-BP) algorithm. This new technique shows great advantages of convergence property and excellent solution. To hybrid technique, GABC-BP algorithm used to this work for classification and prediction task. The performance of GABC-BP is benchmarked against BP, ABC and GABC. The experimental result shows that GABC-BP performs better than that standard BP, ABC and GABC for Boolean function classification and heat wave's temperature time series prediction.
Communications in Computer and Information Science, 2012
A social insect's techniques become more focus by researchers because of its nature behavior proc... more A social insect's techniques become more focus by researchers because of its nature behavior processing and by training neural networks through agents. Chief among them are Swarm Intelligence (SI), Ant Colony Optimization (ACO), and recently Artificial Bee Colony algorithm, which produced easy way for solving combinatorial problems and for training NNs. These social based techniques mostly used for finding optimal weight values in NNs learning. Usually, NNs trained by a standard and well known algorithm called Backpropagation (BP) have difficulties such as trapping in local minima, slow convergence or might fail sometimes. For recovering the above cracks the population or social insects based algorithms used for training NNs for minimizing network output error. Here, the hybrid of nature behavior agents' ant and bees combine's techniques used for training ANNs. The simulation result of a hybrid algorithm compared with, ABC and BP training algorithms. From the experimental results, the proposed Hybrid Ant Bee Colony (HABC) algorithm did improve the classification accuracy for prediction of a volcano time-series data.
A social insect's techniques become more focus by researchers because of its nature behavior proc... more A social insect's techniques become more focus by researchers because of its nature behavior processing and by training neural networks through agents. Chief among them are Swarm Intelligence (SI), Ant Colony Optimization (ACO), and recently Artificial Bee Colony algorithm, which produced easy way for solving combinatorial problems and for training NNs. These social based techniques mostly used for finding optimal weight values in NNs learning. Usually, NNs trained by a standard and well known algorithm called Backpropagation (BP) have difficulties such as trapping in local minima, slow convergence or might fail sometimes. For recovering the above cracks the population or social insects based algorithms used for training NNs for minimizing network output error. Here, the hybrid of nature behavior agents' ant and bees combine's techniques used for training ANNs. The simulation result of a hybrid algorithm compared with, ABC and BP training algorithms. From the experimental results, the proposed Hybrid Ant Bee Colony (HABC) algorithm did improve the classification accuracy for prediction of a volcano time-series data.
From Last ten years, computer scientists show the interest in the study of social insect’s behavi... more From Last ten years, computer scientists show the interest in the study of social insect’s behavior algorithms like, Artificial Bee Colony (ABC), Ant Colony Optimization. Chief among of them, Standard ABC is well-known and new swarm optimization technique used for solving different combinatorial problems; however, it is often trapped in local optima in global optimization. This study investigates the new hybrid technique called Global Artificial Bee Colony-Backpropagation (GABC-BP) algorithm. This new technique shows great advantages of convergence property and excellent solution. To hybrid technique, GABC-BP algorithm used to this work for classification and prediction task. The performance of GABC-BP is benchmarked against BP, ABC and GABC. The experimental result shows that GABC-BP performs better than that standard BP, ABC and GABC for Boolean function classification and heat wave's temperature time series prediction.
Prediction of tsunami was focused by researchers due to its devastating intensity among other dis... more Prediction of tsunami was focused by researchers due to its devastating intensity among other disasters in the world, especially after the Indian Ocean tsunami in December 2004. For natural disaster events scientists take an interest in social insects for classification, analyses and prediction to get optimal solution. Artificial bee colony (ABC) algorithm based on the natural behaviour of artificial bee is proposed here for prediction of tsunami parameters caused by undersea earthquakes. An artificial bee colony algorithm is used ...
Nowadays, computer scientists have shown the interest in the study of social insect's behaviour i... more Nowadays, computer scientists have shown the interest in the study of social insect's behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm. Multilayer Perceptron (MLP) trained with the standard back propagation algorithm normally utilises computationally intensive training algorithms. One of the crucial problems with the backpropagation (BP) algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome ABC algorithm used in this work to train MLP learning the complex behaviour of earthquake time series data trained by BP, the performance of MLP-ABC is benchmarked against MLP training with the standard BP. The experimental result shows that MLP-ABC performance is better than MLP-BP for time series data.
Journal of Computer Science & Computational Mathematics, 2012
Prediction of tsunami was focused by researchers due to its devastating intensity among other dis... more Prediction of tsunami was focused by researchers due to its devastating intensity among other disasters in the world, especially after the Indian Ocean tsunami in December 2004. For natural disaster events scientists take an interest in social insects for classification, analyses and prediction to get optimal solution. Artificial bee colony (ABC) algorithm based on the natural behaviour of artificial bee is proposed here for prediction of tsunami parameters caused by undersea earthquakes. An artificial bee colony algorithm is used ...
2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2014
ABSTRACT In this paper, Cauchy criterion, the necessary and sufficient conditions for Henstock in... more ABSTRACT In this paper, Cauchy criterion, the necessary and sufficient conditions for Henstock integrability of fuzzy number-valued functions defined on a compact interval in the real line is presented. The results can be used to characterize the integrability of a fuzzy number valued function without calculation the value of the integral. In addition, the notion, the elementary properties and the relation of R and R* integrals of fuzzy number-valued function defined on a compact interval in the real line are also presented.
Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the gr... more Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt Back propagation (LMBP) still it is not able to avoid local minimum. To deal with this problem, global search optimization technique has the ability to adjust the weight for NN (Neural Network) to avoid the local minima problem. This paper proposes an accelerated particle swarm optimization (APSO) is implemented in conjunction with Levenberg Marquardt back propagation (LMBP) algorithms to achieve faster convergence rate and to avoid local minima problem. The performances of the proposed Accelerated Particle Swarm Optimization Levenberg Marquardt (APSO_LM) algorithms compared by means of simulations on 7-Bit Parity and six UCI benchmark classification datasets. The simulation results show that the APSO-LM algorithm shows better performance than baseline algorithms in terms of convergence speed and Mean Squared Error (MSE).
An improved Bat algorithm with Gaussian distribution random walk (BAGD) is introduced in this pap... more An improved Bat algorithm with Gaussian distribution random walk (BAGD) is introduced in this paper. The original Bat algorithm has a problem of random large step length that leads to sub-optimal solutions in the search space and it cannot solve higher dimensional problems. To solve higher dimensional problems and to decrease the step length size, this research focuses on using a Gaussian distribution in Bat algorithm which provide shorter step lengths during the search. The proposed BAGD was compared with six popular metaheuristic algorithms on ten benchmark functions. Comparative results indicated that the proposed BAGD perform better than the state-of-the-art algorithms in most cases. The proposed BAGD solution used small step lengths in the search space and it was able to solve high dimensional problems.
The Levenberg-Marquardt (LM) gradient descent algorithm is used extensively for the training of A... more The Levenberg-Marquardt (LM) gradient descent algorithm is used extensively for the training of Artificial Neural Networks (ANN) in the literature, despite its limitations, such as susceptibility to the local minima that undermine its robustness. In this paper, a bio-inspired algorithm referring to the Bat algorithm was proposed for training the ANN, to deviate from the limitations of the LM. The proposed Bat algorithm-based LM (BALM) was simulated on 10 benchmark datasets. For evaluation of the proposed BALM, comparative simulation experiments were conducted. The experimental results indicated that the BALM was found to deviate from the limitations of the LM to advance the accuracy and convergence speed of the ANN. Also, the BALM performs better than the back-propagation algorithm, artificial bee colony trained back-propagation ANN, and artificial bee colony trained LM ANN. The results of this research provide an alternative ANN training algorithm that can be used by researchers and industries to solve complex real-world problems across numerous domains of applications.
Noise-Induced Hearing Loss (NIHL) has become a major source of health problem in industrial worke... more Noise-Induced Hearing Loss (NIHL) has become a major source of health problem in industrial workers due to continuous exposure to high frequency sounds emitting from the machines. In the past, several studies have been carried-out to identify NIHL in industrial workers. Unfortunately, these studies neglected some important factors that directly affect hearing ability in human. Artificial Neural Network (ANN) provides very effective way to predict hearing loss in humans. However, the training process for an ANN required the designers to arbitrarily select parameters such as network topology, initial weights and biases, learning rate value, the activation function, value for gain in activation function and momentum. An improper choice of any of these parameters can result in slow convergence or even network paralysis, where the training process comes to a standstill or get stuck at local minima.Therefore, this current study focuses on proposing a new framework on using Gradient Descent Back Propagation Neural Network model with an improvement on the momentum value to identify the important factors that directly affect the hearing ability of industrial workers. Results from the prediction will be used in determining the environmental health hazards which affect the workers health.
The traditional Gradient Descent Back-propagation Neural Network Algorithm is widely used in solv... more The traditional Gradient Descent Back-propagation Neural Network Algorithm is widely used in solving many practical applications around the globe. Despite providing successful solutions, it possesses a problem of slow convergence and sometimes getting stuck at local minima. Several modifications are suggested to improve the convergence rate of Gradient Descent Back-propagation algorithm such as careful selection of initial weights and biases, learning rate, momentum, network topology, activation function and ‘gain’ value in the activation function. In a certain variation, the previous researchers demonstrated that in “feed-forward algorithm”, the slope of activation function is directly influenced by ‘gain’ parameter. This research proposed an algorithm for improving the current working performance of Backpropagation algorithm by adaptively changing the momentum value and at the same time keeping the ‘gain’ parameter fixed for all nodes in the neural network. The performance of the proposed method known as ‘Gradient Descent Method with Adaptive Momentum (GDAM)’is compared with the performances of ‘Gradient Descent Method with Adaptive Gain (GDM-AG)’ and ‘Gradient Descent with Simple Momentum (GDM)’. The learning rate is kept fixed while sigmoid activation function is used throughout the experiments. The efficiency of the proposed method is demonstrated by simulations on three classification problems. Results show that GDAM is far better than previous methods with an accuracy ratio of 1.0 for classification problems and can be used as an alternative approach of BPNN.
Back propagation training algorithm is widely used techniques in artificial neural network and is... more Back propagation training algorithm is widely used techniques in artificial neural network and is also very popular optimization task in finding an optimal weight sets during the training process. However, traditional back propagation algorithms have some drawbacks such as getting stuck in local minimum and slow speed of convergence. This research proposed an improved Levenberg Marquardt (LM) based back propagation (BP) trained with Cuckoo search algorithm for fast and improved convergence speed of the hybrid neural networks learning method. The performance of the proposed algorithm is compared with Artificial Bee Colony (ABC) and the other hybridized procedure of its kind. The simulation outcomes show that the proposed algorithm performed better than other algorithm used in this study in term of convergence speed and rate.
Recently, the popularity of artificial neural networks (ANN) is increasing since its capacity to ... more Recently, the popularity of artificial neural networks (ANN) is increasing since its capacity to model very complex problems in the area of Machine Learning, Data Mining and Pattern Recognition. Improving training efficacy of ANN based algorithm is a dynamic area of research and several papers have been reviewed in the literature. The performance of Multi-layer Perceptrons (MLP) trained with Back Propagation Artificial Neural Network (BP-ANN) method is highly influenced by the size of the datasets and the datapreprocessing techniques used. This work analyses the benefits of using pre-processing datasets using different techniques in-order to improve the ANN convergence. Specifically Min-Max, Z-Score and Decimal Scaling Normalization preprocessing techniques were evaluated. The simulation results show that the computational efficiency of ANN training process is highly enhanced when coupled with different preprocessing techniques.
22-23 January, 2020
The 4th International Conference on Soft Computing and Data Mining 2020 (SCDM 2020) will be held ... more The 4th International Conference on Soft Computing and Data Mining 2020 (SCDM 2020) will be held from 22nd to 23rd January 2020 at Langkawi, Malaysia. The previous SCDM (SCDM 2018) has been successfully held at the Le Grandeur Palm Resort, Senai, Johor, Malaysia and all presented papers has been published in Springer: Advances in Intelligent Systems and Computing volume 700.