Pauline Ong

Reliable multiclass cancer classification of microarray gene expression profiles using an improved wavelet neural network

Abstract Properly designing a wavelet neural network (WNN) is crucial for achieving the optimal generalization performance. In this paper, two different approaches were proposed for improving the predictive capability of WNNs. First, the types of activation functions used in the hidden layer of the WNN were varied. Second, the proposed enhanced fuzzy c-means clustering algorithm—specifically, the modified point symmetry-based fuzzy c-means (MSFCM) algorithm—was employed in selecting the locations of the translation vectors of the WNN. The modified WNN was then applied to heterogeneous cancer classification using four different microarray benchmark datasets. The comparative experimental results showed that the proposed methodology achieved an almost 100% classification accuracy in multiclass cancer prediction, leading to superior performance with respect to other clustering algorithms. Subsequently, performance comparisons with other classifiers were made. An assessment analysis showed that this proposed approach outperformed most of the other classifiers.

Adaptive Cuckoo Search Algorithm for Unconstrained Optimization

Modification of the intensification and diversification approaches in the recently developed cuckoo search algorithm (CSA) is performed. The alteration involves the implementation of adaptive step size adjustment strategy, and thus enabling faster convergence to the global optimal solutions. The feasibility of the proposed algorithm is validated against benchmark optimization functions, where the obtained results demonstrate a marked improvement over the standard CSA, in all the cases.

An efficient cuckoo search algorithm for numerical function optimization

Cuckoo search algorithm which reproduces the breeding strategy of the best known brood parasitic bird, the cuckoos has demonstrated its superiority in obtaining the global solution for numerical optimization problems. However, the involvement of fixed step approach in its exploration and exploitation behavior might slow down the search process considerably. In this regards, an improved cuckoo search algorithm with adaptive step size adjustment is introduced and its feasibility on a variety of benchmarks is validated. The obtained results show that the proposed scheme outperforms the standard cuckoo search algorithm in terms of convergence characteristic while preserving the fascinating features of the original method.

AN EFFECTIVE AND NOVEL WAVELET NEURAL NETWORK APPROACH IN CLASSIFYING TYPE 2 DIABETICS

Designing a wavelet neural network (WNN) needs to be done judiciously in attaining the optimal generalization performance. Its prediction competence relies highly on the initial value of translation vectors. However, there is no established solution in determining the appropriate initial value for the translation vectors at this moment. In this paper, we propose a novel enhanced fuzzy c-means clustering algorithm – specifically, the modified point symmetry-based fuzzy c-means (MPSDFCM) algorithm – in initializing the translation vectors of the WNNs. The effectiveness of embedding different activation functions in WNNs will be investigated as well. The categorization effectiveness of the proposed WNNs model was then evaluated in classifying the type 2 diabetics, and was compared with the multilayer perceptrons (MLPs) and radial basis function neural networks (RBFNNs) models. Performance assessment shows that our proposed model outperforms the rest, since a 100% superior classification rate was achieved.

An enhanced harmony search based algorithm for feature selection

A feature selection approach is proposed using the harmony search algorithm.A new harmony memory initialization is adopted and dynamic parameters are used.The proposed method and other metaheuristic algorithms give comparable performance.The enhanced harmony search algorithm outperforms the standard algorithm. Feature selection is a well-studied problem in the areas of pattern recognition and artificial intelligence. Apart from reducing computational cost and time, a good feature subset is also imperative in improving the classification accuracy of automated classifiers. In this work, a wrapper-based feature selection approach is proposed using the evolutionary harmony search algorithm, whereas the classifiers used are the wavelet neural networks. The metaheuristic algorithm is able to find near-optimal solutions within a reasonable amount of iterations. The modifications are accomplished in two ways-initialization of harmony memory and improvisation of solutions. The proposed algorithm is tested and verified using UCI benchmark data sets, as well as two real life binary classification problems, namely epileptic seizure detection and prediction. The simulation results show that the standard harmony search algorithm and other similar metaheuristic algorithms give comparable performance. In addition, the enhanced harmony search algorithm outperforms the standard harmony search algorithm. Display Omitted

Design of wavelet neural networks based on symmetry fuzzy C-means for function approximation

Specifying the number and locations of the translation vectors for wavelet neural networks (WNNs) is of paramount significance as the quality of approximation may be drastically reduced if initialization of WNNs parameters was not done judiciously. In this paper, an enhanced fuzzy C-means algorithm, specifically the modified point symmetry–based fuzzy C-means algorithm (MPSDFCM), was proposed, in order to determine the optimal initial locations for the translation vectors. The proposed neural network models were then employed in approximating five different nonlinear continuous functions. Assessment analysis showed that integration of the MPSDFCM in the learning phase of WNNs would lead to a significant improvement in WNNs prediction accuracy. Performance comparison with the approaches reported in the literature in approximating the same benchmark piecewise function verified the superiority of the proposed strategy.

Taguchi design and flower pollination algorithm application to optimize the shrinkage of triaxial porcelain containing palm oil fuel ash

In the preparation of triaxial porcelain from Palm Oil Fuel Ash (POFA), a new parameter variable must be determined. The parameters involved are the particle size of POFA, percentage of POFA in triaxial porcelain composition, moulding pressure, sintering temperature and soaking time. Meanwhile, the shrinkage is the dependent variable. The optimization process was investigated using a hybrid Taguchi design and flower pollination algorithm (FPA). The interaction model of shrinkage was derived from regression analysis and found that the shrinkage is highly dependent on the sintering temperature followed by POFA composition, moulding pressure, POFA particle size and soaking time. The interaction between sintering temperature and soaking time highly affects the shrinkage. From the FPA process, targeted shrinkage approaching zero values were predicted for 142 μm particle sizes of POFA, 22.5 wt% of POFA, 3.4 tonne moulding pressure, 948.5 °C sintering temperature and 264 minutes soaking time.

Calibrating wavelet neural networks by distance orientation similarity fuzzy C-means for approximation problems

We propose a novel fuzzy C-means algorithm.Its effectiveness is tested in optimizing wavelet neural networks.Performance comparison in function approximation is made.The proposed model shows higher generalization capability. Improperly tuned wavelet neural network (WNN) has been shown to exhibit unsatisfactory generalization performance. In this study, the tuning is done by an improved fuzzy C-means algorithm, that utilizes a novel similarity measure. This similarity measure takes the orientation as well as the distance into account. The modified WNN was first applied to a benchmark problem. Performance assessments with other approaches were made subsequently. Next, the feasibility of the proposed WNN in forecasting the chaotic Mackey-Glass time series and a real world application problem, i.e., blood glucose level prediction, were studied. An assessment analysis demonstrated that this presented WNN was superior in terms of prediction accuracy.

Modeling and optimization of cold extrusion process by using response surface methodology and metaheuristic approaches

Obtaining the optimal extrusion process parameters by integration of optimization techniques was crucial and continuous engineering task in which it attempted to minimize the tool load. The tool load should be minimized as higher extrusion forces required greater capacity and energy. It may lead to increase the chance of part defects, die wear and die breakage. Besides, optimization may help to save the time and cost of producing the final product, in addition to produce better formability of work material and better quality of the finishing product. In this regard, this study aimed to determine the optimal extrusion process parameters. The minimization of punch load was the main concern, in such a way that the structurally sound product at minimum load can be achieved. Minimization of punch load during the extrusion process was first formulated as a nonlinear programming model using response surface methodology in this study. The established extrusion force model was then taken as the fitness function. Subsequently, the analytical approach and metaheuristic algorithms, specifically the particle swarm optimization, cuckoo search algorithm (CSA) and flower pollination algorithm, were applied to optimize the extrusion process parameters. Performance assessment demonstrated the promising results of all presented techniques in minimizing the tool loading. The CSA, however, gave more persistent optimization results, which was validated through statistical analysis.

Optimization of wavelet neural networks with the firefly algorithm for approximation problems

The effectiveness of swarm intelligence has been proven to be at the heart of various optimization problems. In this study, a recently developed nature-inspired algorithm, specifically the firefly algorithm (FA), is integrated in the learning strategy of wavelet neural networks (WNNs). The FA, which systematically optimizes the initial location of the translation parameters for WNNs, has reduced the number of hidden nodes while simultaneously improved the generalization capability of WNNs significantly. The applicability of the proposed model was demonstrated through empirical simulations for function approximation study, with both synthetic and real-world data. Performance assessment demonstrated its enhancement over the K-means clustering and random initialization approaches, as well as to the other neural network models reported in the literature, whereby a noteworthy decrease in the approximation error was observed.