Functional Link Artificial Neural Network Research Articles

A multi-objective feature selection and classifier ensemble technique for microarray data analysis

Since last few years, microarray technology has got tremendous application in many biomedical researches. Many intelligent models have been developed with different biological interpretation. This work presents a multi-objective feature selection and classifier ensemble (MOFSCE) technique for microarray data. MOFSCE works in two phases. The first phase is a pre-processing step where bi-objective optimisation technique is used to identify the significant genes through Pareto front. Here seven feature ranking approaches are used to develop 21 bi-objective feature selection (BOFS) models. The performance of BOFS model varies with different datasets. Therefore, grading system is used to identify stable BOFS model. In the second phase a classifier ensemble is build up that receives selected features from the identified BOFS model. Output of the classifiers is presented to a harmony search based functional link artificial neural network (HSFLANN) for decision. Performance of MOFSCE is evaluated using seven publicly available microarray datasets.

Feature Selection Using Evolutionary Functional Link Neural Network for Classification

<p>Computational time is high for Multilayer perceptron (MLP) trained with back propagation learning algorithm (BP) also the complexity of the network increases with the number of layers and number of nodes in layers. In contrast to MLP, functional link artificial neural network (FLANN) has less architectural complexity, easier to train, and gives better result in the classification problems. The paper proposed an evolutionary functional link artificial neural network (EFLANN) using genetic algorithm (GA) by eliminating features having little or no predictive information. Particle swarm optimization (PSO) is used as learning tool for solving the problem of classification in data mining. EFLANN overcomes the non-linearity nature of problems by using the functionally expanded selected features, which is commonly encountered in single layer neural networks. The model is empirically compared to MLP, FLANN gradient descent learning algorithm, Radial Basis Function (RBF) and Hybrid Functional Link Neural Network (HFLANN) . The results proved that the proposed model outperforms the other models.</p>

Teaching learning based optimization-functional link artificial neural network filter for mixed noise reduction from magnetic resonance image

The clinical magnetic resonance imaging (MRI) images may get corrupted due to the presence of the mixture of different types of noises such as Rician, Gaussian, impulse, etc. Most of the available filtering algorithms are noise specific, linear, and non-adaptive. There is a need to develop a nonlinear adaptive filter that adapts itself according to the requirement and effectively applied for suppression of mixed noise from different MRI images. In view of this, a novel nonlinear neural network based adaptive filter i.e. functional link artificial neural network (FLANN) whose weights are trained by a recently developed derivative free meta-heuristic technique i.e. teaching learning based optimization (TLBO) is proposed and implemented. The performance of the proposed filter is compared with five other adaptive filters and analyzed by considering quantitative metrics and evaluating the nonparametric statistical test. The convergence curve and computational time are also included for investigating the efficiency of the proposed as well as competitive filters. The simulation outcomes of proposed filter outperform the other adaptive filters. The proposed filter can be hybridized with other evolutionary technique and utilized for removing different noise and artifacts from others medical images more competently.

Financial time series prediction using distributed machine learning techniques

The financial time series is inherently nonlinear and hence cannot be efficiently predicted by using linear statistical methods such as regression. Hence, intelligent predictor has been developed and reported which is suitable for nonlinear time series. But such predictors require that the past financial data are available at the location of the predictor which is not the case in many real-life situations. Hence, when the financial data are available at different places and a single intelligent predictor needs to be developed, the task becomes challenging. In the current work, this problem has been addressed and solved using a low-complexity artificial neural network and employing incremental and diffusion learning strategies. In the current study, distributed prediction of three different types of time series such as exchange rates, stock indices and net asset values has been carried using incremental and diffusion-based learning strategies. The results of different days ahead prediction of two proposed low computational complexity-based functional link artificial neural network are compared with those obtained by conventional intelligent method. The results of simulation-based experiments reveal similar or improved prediction performance of the proposed distributed predictors compared to conventional one. In addition, saving in band width, memory and power are achieved in this method.

A bilinear functional link artificial neural network filter for nonlinear active noise control and its stability condition

Since the functional link artificial neural network (FLANN) filter using trigonometric expansions do not exploit cross-terms (products of input samples and /or past output samples with different time shifts), its performance for nonlinear active noise control (ANC) can be considerably degraded, especially in strong nonlinearity environment. In order to overcome this drawback, a novel bilinear FLANN (BFLANN) filter for the nonlinear ANC is proposed in this paper. In addition, a sufficient condition that guarantees the stability of the BFLANN filter is also presented. Simulation results demonstrate that the proposed BFLANN filter based nonlinear ANC can achieve better performance than the FLANN and generalized FLANN (GFLANN) filters based nonlinear ANC in the presence of strong nonlinearity.

A hybridized ELM-Jaya forecasting model for currency exchange prediction

This paper establishes a hybridized intelligent machine learning based currency exchange forecasting model using Extreme Learning Machines (ELMs) and the Jaya optimization technique. This model can very well forecast the exchange price of USD (US Dollar) to INR (Indian Rupee) and USD to EURO based on statistical measures, technical indicators and combination of both measures over a time frame varying from 1day to 1month ahead. The proposed ELM-Jaya model has been compared with existing optimized Neural Network and Functional Link Artificial Neural Network based predictive models. Finally, the model has been validated using various performance measures such as; MAPE, Theil'sU, ARV and MAE. The comparison of different features demonstrates that the technical indicators outperform both the statistical measures and a combination of statistical measures and technical indicators in ELM-Jaya forecasting model.

DABE: Differential evolution in analogy-based software development effort estimation

Abstract Several feature weight optimization techniques have been proposed for similarity functions in analogy-based estimation (ABE); however, no consensus regarding the method and settings suitable for producing accurate estimates has been reached. We investigate the effectiveness of differential evolution (DE) algorithm, for optimizing the feature weights of similarity functions of ABE by applying five successful mutation strategies. We have named this empirical analysis as DE in analogy-based software development effort estimation (DABE). We have conducted extensive simulation study on the PROMISE repository test suite to estimate the effectiveness of our proposed DABE technique. We find significant improvements in predictive performance of our DABE technique over ABE, particle swarm optimization-based feature weight optimization in ABE, genetic algorithm-based feature weight optimization in ABE, self-adaptive DE-based feature weight optimization ABE, adaptive differential evolution with optional external archive-based feature weight optimization ABE, functional link artificial neural network,artificial neural network with back propagation learning based software development effort estimation (SDEE), and radial basis function-based SDEE.

Noise Removal using Chebyshev Functional Link Artificial Neural Network with Backpropagation

In this proposed work, we have used an alternate ANN structure called Functional link ANN for image denoising. In contrast to other feed forward neural networks, the FLANN is a single layer structure, which never contain any hidden layer and non-linearity is introduced by enhancing the input pattern with a nonlinear function expansion called Chebyshev functional expansion. With the Chebyshev functional expansion, the network shows very good result in denoising the image corrupted by four different noise called Salt and Pepper noise, Gaussian noise, Speckle noise and Poisson noise. In this paper Gaussian noise is added to the speckle noise to give better result. In particular FLANN structure with Chebyshev functional expansion works best for Poisson noise suppression from an image. Here Back Propagation network is used to train the Chebyshev expanded image. BP network can be used to learn and store a great deal of mapping relations of input-output models, and no need to disclose in advance the mathematical equation that describes these mapping relations. Feed Forward Back Propagation (FFBP) algorithm performs quite well in the presence of different noise while preserving the image features satisfactorily

Odia Handwritten Vowel Recognition System using Slantlet Transform and Differential Evolution based Functional Link Artificial Neural Network Classifier

One of the challenging problems in optical character recognition (OCR) is the identification of handwritten characters. It has several complexities like missing part, size variation, added noise, media devices used, slant variation etc. The goal of this paper is to develop an effective system for recognition of Odia handwritten vowels using functional link artificial neural network (FLANN) classifier and differential evolution (DE) optimization technique. In this paper the emphasis is on preprocessing, feature extraction, feature reduction and classification with optimization technique. Various preprocessing operations like size normalization mean filtering and canny edge detection methods are carried out on the vowel images to enhance the quality. Slantlet transform (SLT) is applied for feature extraction and the extracted features are further reduced by principal component analysis (PCA) method. FLANN classifier is applied on the reduced feature vector and the weights of the FLANN are optimized with DE evolutionary technique. The system has achieved a good classification accuracy of 91.32% on the dataset.

On Development and Performance Evaluation of Novel Odia Handwritten Digit Recognition Methods

Odia is an old and recognized regional language of India and is spoken, read and written by almost 90% people of Odisha state and an appreciable part of the population of neighbouring states. Unfortunately, very little work on Odia language processing (OLP) has been carried out and reported in standard literature. Accordingly, in this paper, a sincere attempt has been made on the recognition of handwritten Odia numerals, as a part of OLP, by using a standard database (Bhowmik et al. in Proceedings of 9th international conference on information technology (ICIT’06), Bhubaneswar, 18–21 December, pp 105–110, 2006) of ISI Kolkata. In this investigation, we have chosen six different transforms like the discrete Fourier transform (DFT), short-time Fourier transform, discrete cosine transform, discrete wavelet transform, S-transform (ST) and curvelet transform (CT) for feature extraction from handwritten numerals and principal component analysis for feature reduction. The standard four adaptive classifiers such as multilayered perceptron (MLP), four types of functional link artificial neural network (FLANN), radial basis function network and probabilistic neural network (PNN) are used to classify the handwritten Odia digits using the reduced extracted features from transform as inputs. The investigation made in this paper reveals that the RBF network with CT-based features and the power series FLANN with DFT features provide the best and the worst recognition performance for handwritten Odia numerals, respectively. Further, the first five best accuracy-based combined recognition systems are RBF-CT, RBF-ST, RBF-WT, PNN-CT and MLP-CT which offers percentage classification accuracy of 98.70, 96.22, 95.12, 95.10 and 93.60, respectively.

An improved shuffled frog leaping algorithm based evolutionary framework for currency exchange rate prediction

Forecasting purchasing power of one currency with respect to another currency is always an interesting topic in the field of financial time series prediction. Despite the existence of several traditional and computational models for currency exchange rate forecasting, there is always a need for developing simpler and more efficient model, which will produce better prediction capability. In this paper, an evolutionary framework is proposed by using an improved shuffled frog leaping (ISFL) algorithm with a computationally efficient functional link artificial neural network (CEFLANN) for prediction of currency exchange rate. The model is validated by observing the monthly prediction measures obtained for three currency exchange data sets such as USD/CAD, USD/CHF, and USD/JPY accumulated within same period of time. The model performance is also compared with two other evolutionary learning techniques such as Shuffled frog leaping algorithm and Particle Swarm optimization algorithm. Practical analysis of results suggest that, the proposed model developed using the ISFL algorithm with CEFLANN network is a promising predictor model for currency exchange rate prediction compared to other models included in the study.

Chebyshev Functional Link Artificial Neural Network Based on Correntropy Induced Metric

In this paper, the Correntropy Induced Metric (CIM) as an alternative to the well-known mean square error (MSE) is employed in Chebyshev functional link artificial neural network (CFLANN) to deal with the noisy training data set and enhance the generalization performance. The MSE performs well under Gaussian noise but it is sensitive to large outliers. The CIM as a local similarity measure, however, can improve significantly the anti-noise ability of CFLANN. The convergence of the proposed algorithm, namely the CFLANN based on CIM (CFLANNCIM), has been analyzed. Simulation results on nonlinear channel identification show that CFLANNCIM can perform much better than the traditional CFLANN and multiple-layer perceptron (MLP) neural networks trained under MSE criterion.

A competitive functional link artificial neural network as a universal approximator

In this article, a competitive functional link artificial neural network (C-FLANN) is proposed for function approximation and classification problems. In contrast to the traditional functional link artificial neural networks (FLANNs), the novel structure is a universal approximator and can be used for various applications. C-FLANN is a single-layered feed-forward neural network that enjoys from the concepts of expanded inputs, information capacity units (ICUs) and a winner-take-all competition among the ICUs. These features increase the information capacity of the model without adding the hidden neurons. In the experimental studies, the proposed method is tested on function approximation problems as well as classification applications. Various comparisons with related algorithms such as improved swarm optimization-based FLANN, random vector FLANN and a multilayer perceptron indicate the superiority of the approach in terms of higher accuracy.

Application of functional link artificial neural network for mitigating nonlinear effects in coherent optical OFDM

Artificial Neural Networks are developed as an important technique for equalization and have been widely used to mitigate the nonlinear effects in coherent optical systems. For the compensation of nonlinearities in coherent optical orthogonal frequency division multiplexing technique, the most popular artificial neural network model is a multilayer perceptron (MLP), as it is able to perform complex mapping between input and output spaces with significant success. However due to the complexity of multilayer perceptron nonlinear equalizer (MLP-NLE) model training of neural network is difficult. To overcome computational complexity issues of MLP-NLE, a single neuron based functional link artificial neural network nonlinear equalizer (FLANN-NLE) has been developed in this paper. Better performance of an equalizer is attributed to the usage of aPSO-BP algorithm for training the FLANN-NLE. The proposed FLANN-NLE surpasses the existing works both in terms of Q-Factor and computational complexity. For a fiber length of 1000 km and at launch power of −6 dBm, the improvement in Q-Factor is approximately equal to 3.3 and 1 dB in contrast to the previously reported values of approximately 3 and 0.7 dB at bit rate of 40 and 80 Gbps respectively.

Generalized spline nonlinear adaptive filters

A new spline based generalized non-linear filter.Adaptive spline function is used as basis function.Provides improved classification accuracy.Successfully applied in dynamic system identification. A new nonlinear filter, which employs an adaptive spline function as the basis function is designed in this paper. The input signal to this filter is used to generate suitable parameters to update the control points in a spline function. The update rule for updating the control points have been derived and a mean square analysis has been carried out. The output of the spline functions are suitably combined together to obtain the filter response. This filter is called the generalized spline nonlinear adaptive filter (GSNAF). The proposed GSNAF is similar to a functional link artificial neural network (FLANN), considering a functional expansion using spline basis functions. GSNAF has been shown to offer improved accuracy in benchmark classification scenarios and provide enhanced modeling accuracy in single input single output as well as in multiple input multiple output dynamic system identification cases.

Robust nonlinear channel equalization using WNN trained by symbiotic organism search algorithm

In the present world of ‘Big Data,’ the communication channels are always remaining busy and overloaded to transfer quintillion bytes of information. To design an effective equalizer to prevent the inter-symbol interference in such scenario is a challenging task. In this paper, we develop equalizers based on a nonlinear neural structure (wavelet neural network (WNN)) and train it's weighted by a recently developed meta-heuristic (symbiotic organisms search algorithm). The performance of the proposed equalizer is compared with WNN trained by cat swarm optimization (CSO) and clonal selection algorithm (CLONAL), particle swarm optimization (PSO) and least mean square algorithm (LMS). The performance is also compared with other equalizers with structure based on functional link artificial neural network (trigonometric FLANN), radial basis function network (RBF) and finite impulse response filter (FIR). The superior performance is demonstrated on equalization of two non-linear three taps channels and a linear twenty-three taps telephonic channel. It is observed that the performance of the gradient algorithm based equalizers fails in the presence of burst error. The robustness in the performance of the proposed equalizers to handle the burst error conditions is also demonstrated.

An improved harmony search-based functional link higher order ANN for nonlinear data classification

To obtain the optimal set of weights in any higher order artificial neural network, it is often laborious to adjust the set of weights by using appropriate learning algorithm. In this paper, an improved variant of harmony search (HS), called improved harmony search (IHS) along with gradient descent learning (GDL) is used with functional link artificial neural network (FLANN) for the task of classification in data mining. IHS performs better than HS by eliminating constant parameters [bandwidth (bw), pitch adjustment rate (PAR)] in HS algorithm and incorporating changes dynamically in PAR and bw with iteration. The searching capability of IHS to obtain optimal harmony is used along with GDL to discover optimal set of weights for FLANN model. The proposed IHS-GDL-FLANN is implemented in MATLAB and compared with other alternatives. In order to get statistical correctness of results, the proposed method is analysed by using various statistical analysis under null-hypothesis.

Mining of electricity prices in energy markets using a hybrid linear ARMA and nonlinear functional link neural network trained by evolutionary unscented H-infinity filter

This paper presents a hybrid autoregressive moving average (ARMA) and a nonlinear functional link neural network for electricity price forecasting in an Energy market. The functional neural block helps to introduce nonlinearity by expanding the input space to higher dimensional space through a basis function without using any hidden layers like MLP structure. Unlike the conventional functional link artificial neural network (FLANN), the input layer comprises the inputs and tangent hyperbolic functions of the linear combination of the inputs known as the basis functions. The proposed hybrid neural network is trained by an unscented H-infinity filter to provide an accurate forecasting of day ahead electricity prices. The noise covariance parameters of the unscented H-infinity filter are further optimised with an adaptive differential evolution strategy. The studies on PJM, Spanish and Australian energy markets exhibit excellent forecasting results over different seasonal horizons for one day ahead of time.

A novel nonlinear functional expansion based PLS (FEPLS) and its soft sensor application

A novel robust nonlinear partial least square model is proposed to handle the nonlinearity and collinearity problems of process data. The proposed model integrates a nonlinear functional link artificial neural network (FLANN) with a traditional partial least square (PLS). There are two parts in the proposed model: a nonlinear mapping part and a linear regression part. In the nonlinear mapping part, the input space is effectively extended to nonlinear space through the functional expansion block of FLANN. The PLS regression (PLSR) is adopted in the linear part. Thus, a novel robust nonlinear PLS integrated with functional expansion (FEPLS) is built. The proposed FEPLS model is very easy to construct. First, a traditional FLANN is selected. Second, the input space is expanded to nonlinear space using the functional expansion block. Third, the collinearity among the expanded variables and the expected outputs is eliminated by extracting input latent variables and output latent variables through PLS projection, respectively. Finally, an optimal regression model between the expanded variables and the expected outputs is established by using PLSR. To evaluate the performance of the proposed model, case studies of modeling two complex chemical processes are provided. Four more models of FLANN, extreme learning machine based PLS (ELM-PLS), kernel PLS (KPLS), and PLSR are also developed for comparisons. Simulation results illustrated that the proposed FEPLS model could improve the prediction performance.

Spectrum occupancy prediction based on functional link artificial neural network (FLANN) in ISM band

Recent advancements in artificial neural networks (ANNs) motivated us to design a simple and faster spectrum prediction model termed the functional link artificial neural network (FLANN). The main objective of this paper is to gather realistic data to obtain utilization statistics for the industrial, scientific and medical band of 2.4–2.5 GHz. To present the occupancy statistics, we conducted measurement in indoors at the Swearingen Engineering Center, University of South Carolina. Further, we introduce different threshold-based spectrum prediction schemes to show the impact of threshold on occupancy, and propose a spectrum prediction algorithm based on FLANN to forecast a future spectrum usage profile from historical occupancy statistics. Spectrum occupancy is estimated and predicted by employing different ANN models including the Feed-forward multilayer perceptron (MLP), Recurrent MLP, Chebyshev FLANN and Trigonometric FLANN. It is observed that the absence of a hidden layer in FLANN makes it more efficient than the MLP model in predicting the occupancy faster and with less complexity. A set of illustrative results are presented to validate the performance of our proposed learning scheme.