International Journal of Computational Intelligence Studies http://www.inderscience.com/browse/index.php?journalID=279&year=2010&vol=1&issue=3 Inderscience Publishers Ltd en-uk International Journal of Computational Intelligence Studies 1755-4977 1755-4985 © 2010 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijcistudies_scoverijcistudies.jpg http://www.inderscience.com/browse/index.php?journalID=279&year=2010&vol=1&issue=3 http://www.inderscience.com/link.php?id=34886 A hybrid computing scheme has been developed in the paper, which uses CFD softwares: Gambit for mesh generation, Fluent for carrying out hydrodynamic analysis, and employs a Genetic Algorithm (GA) for optimisation. It has been utilised to solve optimisation problems related to thermo-fluid field in a fully automated way by using specific system commands. In the developed hybrid computing scheme, the GA and CFD softwares combine each other seamlessly and data transfer takes places without any manual intervention. In this study, the main challenge lies in embedding highly structured commercial softwares, like Fluent and Gambit, inside an indigenously developed hybrid computing scheme. Using the said hybrid computing scheme, two different methodologies have been adopted to optimise the shapes of 2D symmetric nozzle. Corresponding to the optimised shapes of the nozzle, streamline patterns have been developed and variations in pressure loss (PL) factor values have been studied. A hybrid computing scheme for shape optimisation in thermo-fluid problems
Suman Ghosh, Dilip Kumar Pratihar, Biswajit Maiti, Prasanta Kumar Das
International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 207 - 226
A hybrid computing scheme has been developed in the paper, which uses CFD softwares: Gambit for mesh generation, Fluent for carrying out hydrodynamic analysis, and employs a Genetic Algorithm (GA) for optimisation. It has been utilised to solve optimisation problems related to thermo-fluid field in a fully automated way by using specific system commands. In the developed hybrid computing scheme, the GA and CFD softwares combine each other seamlessly and data transfer takes places without any manual intervention. In this study, the main challenge lies in embedding highly structured commercial softwares, like Fluent and Gambit, inside an indigenously developed hybrid computing scheme. Using the said hybrid computing scheme, two different methodologies have been adopted to optimise the shapes of 2D symmetric nozzle. Corresponding to the optimised shapes of the nozzle, streamline patterns have been developed and variations in pressure loss (PL) factor values have been studied.

]]> 10.1504/IJCISTUDIES.2010.034886 International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 207 - 226 Suman Ghosh Dilip Kumar Pratihar Biswajit Maiti Prasanta Kumar Das Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721302, West Bengal, India. ' Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721302, West Bengal, India. ' Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721302, West Bengal, India. ' Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721302, West Bengal, India hybrid computing Fluent software Gambit genetic algorithms GAs nozzles shape optimisation CFD computational fluid dynamics thermofluids streamline patterns pressure loss. 2010-08-26T23:20:50-05:00 1 3 207 226 2010-08-26T23:20:50-05:00 http://www.inderscience.com/link.php?id=34887 The speed of image denoising by adaptive thresholding approach in Wavelet Transform (WT) domain depends mainly upon the learning algorithm used for optimising the performance of adaptive thresholding function. In this context, in the literature, steepest gradient-based optimisation technique has been used in WT-based thresholding neural network (WT-TNN) approach, which has low learning speed. In this paper, a new computationally efficient approach, that is, Particle Swarm Optimisation (PSO)-based approach has been proposed in place of steepest gradient-based approach. The proposed hybrid computing approach utilises the features of WT-TNN approach and enhances the speed of optimisation by PSO technique. It also yields better performance of denoising as compared to WT-TNN approach. In the proposed approach, crucial problem of initialisation of thresholding parameters gets automatically sorted out besides learning time becoming independent of noise level of the image. The proposed approach also enhances edge preservation, when implemented with bior6.8 wavelet filters. Fast adaptive learning algorithm for sub-band adaptive thresholding function in image denoising
G.G. Bhutada, R.S. Anand, S.C. Saxena
International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 227 - 241
The speed of image denoising by adaptive thresholding approach in Wavelet Transform (WT) domain depends mainly upon the learning algorithm used for optimising the performance of adaptive thresholding function. In this context, in the literature, steepest gradient-based optimisation technique has been used in WT-based thresholding neural network (WT-TNN) approach, which has low learning speed. In this paper, a new computationally efficient approach, that is, Particle Swarm Optimisation (PSO)-based approach has been proposed in place of steepest gradient-based approach. The proposed hybrid computing approach utilises the features of WT-TNN approach and enhances the speed of optimisation by PSO technique. It also yields better performance of denoising as compared to WT-TNN approach. In the proposed approach, crucial problem of initialisation of thresholding parameters gets automatically sorted out besides learning time becoming independent of noise level of the image. The proposed approach also enhances edge preservation, when implemented with bior6.8 wavelet filters.

]]> 10.1504/IJCISTUDIES.2010.034887 International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 227 - 241 G.G. Bhutada R.S. Anand S.C. Saxena Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India. ' Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India. ' Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India adaptive thresholding computational intelligence image denoising hybrid computing particle swarm optimisation PSO fast adaptive learning wavelet transforms neural networks. 2010-08-26T23:20:50-05:00 1 3 227 241 2010-08-26T23:20:50-05:00 http://www.inderscience.com/link.php?id=34888 In this paper, design and stability analysis of neuro-fuzzy sliding mode controller is discussed. The controller has two parts: fuzzy logic system and neural network. They are used concurrently but each part is responsible for one phase of sliding mode controller. The fuzzy logic system is utilised to control reaching phase dynamics and the feed-forward neural network is employed to keep the system states on the sliding surface. The neural network is trained online using modified back-propagation algorithm. Initially, fuzzy logic system is dominant and as the system moves from reaching phase to sliding phase, neural network becomes more active and hence, a hybrid computing paradigm is achieved. The stability of the system is analysed using Lyapunov's direct method. The proposed controller is implemented to regulate a second-order nonlinear uncertain system and simulation results confirm that the proposed system reduces chattering and improves transient response. Neuro-fuzzy sliding mode controller: design and stability analysis
Dereje Shiferaw, R. Mitra
International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 242 - 255
In this paper, design and stability analysis of neuro-fuzzy sliding mode controller is discussed. The controller has two parts: fuzzy logic system and neural network. They are used concurrently but each part is responsible for one phase of sliding mode controller. The fuzzy logic system is utilised to control reaching phase dynamics and the feed-forward neural network is employed to keep the system states on the sliding surface. The neural network is trained online using modified back-propagation algorithm. Initially, fuzzy logic system is dominant and as the system moves from reaching phase to sliding phase, neural network becomes more active and hence, a hybrid computing paradigm is achieved. The stability of the system is analysed using Lyapunov's direct method. The proposed controller is implemented to regulate a second-order nonlinear uncertain system and simulation results confirm that the proposed system reduces chattering and improves transient response.

]]> 10.1504/IJCISTUDIES.2010.034888 International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 242 - 255 Dereje Shiferaw R. Mitra Department of Electrical Engineering, Adama University, P.O. Box 1888, Adama, Ethiopia. ' Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India fuzzy logic hybrid computing neuro-fuzzy control sliding mode control computational intelligence neural networks stability analysis controller design simulation. 2010-08-26T23:20:50-05:00 1 3 242 255 2010-08-26T23:20:50-05:00 http://www.inderscience.com/link.php?id=34889 A hybrid computing scheme has been developed for carrying out forward and reverse mappings of metal inert gas welding process. As the input-output relationships of this process may not be the same over the entire range of the variables, the mappings have been done using the clusters made by the data points. Optimisation has been carried out to improve the performances of both fuzzy clustering techniques as well as radial basis function neural network used for the clustering and reasoning, respectively. Two approaches of hybrid computing scheme have been proposed, in which a binary-coded genetic algorithm has been utilised to decide the optimal structure of the network (through clustering of the data using two different approaches separately) and a back-propagation algorithm has been employed to determine the optimised parameters of the network. The hybrid scheme has yielded better performance compared to that developed using the genetic algorithm only. A hybrid computing scheme for forward and reverse mappings of metal inert gas welding process
Somak Datta, Dilip Kumar Pratihar
International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 256 - 272
A hybrid computing scheme has been developed for carrying out forward and reverse mappings of metal inert gas welding process. As the input-output relationships of this process may not be the same over the entire range of the variables, the mappings have been done using the clusters made by the data points. Optimisation has been carried out to improve the performances of both fuzzy clustering techniques as well as radial basis function neural network used for the clustering and reasoning, respectively. Two approaches of hybrid computing scheme have been proposed, in which a binary-coded genetic algorithm has been utilised to decide the optimal structure of the network (through clustering of the data using two different approaches separately) and a back-propagation algorithm has been employed to determine the optimised parameters of the network. The hybrid scheme has yielded better performance compared to that developed using the genetic algorithm only.

]]> 10.1504/IJCISTUDIES.2010.034889 International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 256 - 272 Somak Datta Dilip Kumar Pratihar Soft Computing Laboratory, Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721302, West Bengal, India. ' Soft Computing Laboratory, Department of Mechanical Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721302, West Bengal, India hybrid computing forward mapping reverse mapping metal inert gas welding fuzzy clustering radial basis function RBF neural network genetic algorithms back-propagation algorithms MIG welding. 2010-08-26T23:20:50-05:00 1 3 256 272 2010-08-26T23:20:50-05:00 http://www.inderscience.com/link.php?id=34890 The method of processing two algorithms within a single workflow, and hence the combined method, is called as hybrid computing. We propose a data mining framework comprising of two stages, namely clustering and classification. The first stage employs k-means algorithm on data and generates two clusters, namely cluster-0 and cluster-1. Instances in cluster-0 do not have disease symptoms and cluster-1 consists of instances with disease symptoms. The verification of valid grouping is then carried out by referring to the association of class labels in original datasets. Incorrectly classified instances are removed and remaining instances are used to build the classifier using C4.5 decision-tree algorithm with k-fold cross validation method. The framework was tested using eight datasets from the machine learning repository of the UCI. The proposed framework was evaluated for accuracy, sensitivity and specificity measures. Our framework obtained promising classification accuracy as compared to other methods found in the literature. Effective framework for prediction of disease outcome using medical datasets: clustering and classification
B.M. Patil, Ramesh C. Joshi, Durga Toshniwal
International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 273 - 290
The method of processing two algorithms within a single workflow, and hence the combined method, is called as hybrid computing. We propose a data mining framework comprising of two stages, namely clustering and classification. The first stage employs k-means algorithm on data and generates two clusters, namely cluster-0 and cluster-1. Instances in cluster-0 do not have disease symptoms and cluster-1 consists of instances with disease symptoms. The verification of valid grouping is then carried out by referring to the association of class labels in original datasets. Incorrectly classified instances are removed and remaining instances are used to build the classifier using C4.5 decision-tree algorithm with k-fold cross validation method. The framework was tested using eight datasets from the machine learning repository of the UCI. The proposed framework was evaluated for accuracy, sensitivity and specificity measures. Our framework obtained promising classification accuracy as compared to other methods found in the literature.

]]> 10.1504/IJCISTUDIES.2010.034890 International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 273 - 290 B.M. Patil Ramesh C. Joshi Durga Toshniwal Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India. ' Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India. ' Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India clustering classification effective framework hybrid computing disease outcomes computational intelligence medical datasets data mining machine learning disease outcome prediction. 2010-08-26T23:20:50-05:00 1 3 273 290 2010-08-26T23:20:50-05:00 http://www.inderscience.com/link.php?id=34891 Automatic speech recognition has been a subject of active research interest since last few decades. In the present paper, spoken Hindi (Indian national language) Paired Word Recognition (HPWR) has been examined with the help of intelligent hybrid computing scheme based on wavelet transform and Probabilistic Neural Network (PNN). This type of network is a combination of radial basis layer and a competitive transfer function layer, which picks up the maximum probabilities as a final result. For the experimental purpose, six hundred and fifty Hindi paired word samples from individuals with different gender and age groups have been recorded. Pre-processing procedure has been performed on the samples using accurate endpoint detection algorithm. For feature extraction of samples, wavelet transform has been used. PNN algorithm is used as a classifier. The proposed intelligent hybrid computing scheme based on wavelet-probabilistic neural network has produced practically good recognition rate. Hindi paired word recognition using probabilistic neural network
Dinesh Kumar Rajoriya, R.S. Anand, R.P. Maheshwari
International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 291 - 308
Automatic speech recognition has been a subject of active research interest since last few decades. In the present paper, spoken Hindi (Indian national language) Paired Word Recognition (HPWR) has been examined with the help of intelligent hybrid computing scheme based on wavelet transform and Probabilistic Neural Network (PNN). This type of network is a combination of radial basis layer and a competitive transfer function layer, which picks up the maximum probabilities as a final result. For the experimental purpose, six hundred and fifty Hindi paired word samples from individuals with different gender and age groups have been recorded. Pre-processing procedure has been performed on the samples using accurate endpoint detection algorithm. For feature extraction of samples, wavelet transform has been used. PNN algorithm is used as a classifier. The proposed intelligent hybrid computing scheme based on wavelet-probabilistic neural network has produced practically good recognition rate.

]]> 10.1504/IJCISTUDIES.2010.034891 International Journal of Computational Intelligence Studies, Vol. 1, No. 3 (2010) pp. 291 - 308 Dinesh Kumar Rajoriya R.S. Anand R.P. Maheshwari Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India. ' Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India. ' Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee 247667, Uttarakhand, India PNN probabilistic neural networks HPWR Hindi paired word recognition broad acoustic classes wavelet transforms classification pattern recognition hybrid computing automatic speech recognition. 2010-08-26T23:20:50-05:00 1 3 291 308 2010-08-26T23:20:50-05:00