Khamron Sunat

Robust extreme learning machine

The output weights computing of extreme learning machine (ELM) encounters two problems, the computational and outlier robustness problems. The computational problem occurs when the hidden layer output matrix is a not full column rank matrix or an ill-conditioned matrix because of randomly generated input weights and biases. An existing solution to this problem is Singular Value Decomposition (SVD) method. However, the training speed is still affected by the large complexity of SVD when computing the Moore-Penrose (MP) pseudo inverse. The outlier robustness problem may occur when the training data set contaminated with outliers then the accuracy rate of ELM is extremely affected. This paper proposes the Extended Complete Orthogonal Decomposition (ECOD) method to solve the computational problem in ELM weights computing via ECODLS algorithm. And the paper also proposes the other three algorithms, i.e. the iteratively reweighted least squares (IRWLS-ELM), ELM based on the multivariate least-trimmed squares (MLTS-ELM), and ELM based on the one-step reweighted MLTS (RMLTS-ELM) to solve the outlier robustness problem. However, they also encounter the computational problem. Therefore, the ECOD via ECODLS algorithm is also used successfully in the three proposed algorithms. The experiments of regression problems were conducted on both toy and real-world data sets. The outlier types are one-sided and two-sided outliers. Each experiment was randomly contaminated with outliers, of one type only, with 10%, 20%, 30%, 40%, and 50% of the total training data size. Meta-metrics evaluation was used to measure the outlier robustness of the proposed algorithms compared to the existing algorithms, i.e. the minimax probability machine regression (MPMR) and the ordinary ELM. The experimental results showed that ECOD can effectively replace SVD. The ECOD is robust to the not full column rank or the ill-conditional problem. The speed of the ELM training using ECOD is also faster than the ordinary training algorithm. Moreover, the meta-metrics measure showed that the proposed algorithms are less affected by the increasing number of outliers than the existing algorithms.

An Improved Grey Wolf Optimizer for Training q-Gaussian Radial Basis Functional-link Nets

In this paper, a novel meta-heuristic technique an improved Grey Wolf Optimizer (IGWO) which is an improved version of Grey Wolf Optimizer (GWO) is proposed. The performance is evaluated by adopting the IGWO to training q-Gaussian Radial Basis Functional-link nets (qRBFLNs) neural networks. The function approximation problems in regression areas and the multiclass classification problem in classification areas are employed to test the algorithm. For instance, in order to overcome the multiclass classification problem, the dataset of the screening risk groups of the population age 15 years and over in Charoensin District, Sakon Nakhon Province, Thailand is used in the experiments. The results of the function approximation problems and real application in multiclass classification problem prove that the proposed algorithm is able to address the test problems. Moreover, the proposed algorithm obtains competitive performance compared to other meta-heuristic methods.

A Discrimination Analysis for Unsupervised Feature Selection via Optic Diffraction Principle

This paper proposes an unsupervised discrimination analysis for feature selection based on a property of the Fourier transform of the probability density distribution. Each feature is evaluated on the basis of a simple observation motivated by the concept of optical diffraction, which is invariant under feature scaling. The time complexity is O(mn), where m is number of features and n is number of instances when being applied directly to the given data. This approach is also extended to deal with data orientation, which is the direction of data alignment. Therefore, the discrimination score of any transformed space can be used for evaluating the original features. The experimental results on several real-world datasets demonstrate the effectiveness of the proposed method.

Improved differential evolution via cuckoo search operator

Differential Evolution (DE) is a very popular optimization algorithm for solving numerical optimization problems. It is simple yet powerful algorithm, which has shown effective performance in many optimization problems. In this paper, DECSO that uses the Abandon operator of Cuckoo search to improve the exploration ability of the original DE was proposed. The experimental studies on ten well-known benchmark functions have shown that the proposed approach has efficient search power and fast convergence.

Enhancing modified cuckoo search by using Mantegna Lévy flights and chaotic sequences

In this paper, we present an improvement of the modified cuckoo search (MCS) method. We focus on a new nest generation from the top nest group. This group of nests assists a better local search. We use Tent map chaotic sequences to replace the constant parameter, inverse golden ratio of MCS. This process aims to find a better solution in case of multi-modal problems. The Cauchy Lévy distribution is replaced by Mantegna Lévy distribution generation. This process assists in finding a better solution in case of uni-modal problems. To construct a more suitable with wider optimization problems and good convergence property, these two concepts are combined together as Improved MCS with Chaotic Sequences algorithm (ICMCS). The proposed algorithm is verified using nineteen constrained optimization problems. The performance of the proposed algorithm is compared with the original MCS algorithms. The optimal solutions obtained in this study are more superior to MCS.

PFP-PCA: Parallel Fixed Point PCA Face Recognition

With a high computational complexity of Eigenvector/Eigenvalue calculation, especially with a large database, of a traditional face recognition system, PCA, this paper proposes an alternative approach to utilize a fixed point algorithm for EVD stage optimization. We also proposed the optimization to reduce the complexity during the high computation stage, covariance matrix manipulation. In addition, the feasibility to enhance the speed-up over a single-core computation, parallelism, was investigated on the huge matrix calculation on both grayscale and RGB images. This mechanism, the so-called Parallel Fixed Point PCA (PFP-PCA), results in higher accuracy and lower complexity comparing to the traditional PCA leading to a high speed face recognition system.

Evolutionary Circular Extreme Learning Machine

Circular Extreme Learning Machine (C-ELM) is an extension of Extreme Learning Machine. Its power is mapping both linear and circular separation boundaries. However, C-ELM uses the random determination of the input weights and hidden biases, which may lead to local optimal. This paper proposes a hybrid learning algorithms based on the C-ELM and the Differential Evolution (DE) to select appropriate weights and hidden biases. It called Evolutionary circular extreme learning machine (EC-ELM). From experimental results show EC-ELM can slightly improve C-ELM and also reduce the number of nodes network.

R r-cr -IJADE: An efficient differential evolution algorithm for multilevel image thresholding

Abstract There is a need for a new method of segmentation to improve the efficiency of expert systems that need segmentation. Multilevel thresholding is a widely used technique that uses threshold values for image segmentation. However, from a computational stand point, the search for optimal threshold values presents a challenging task, especially when the number of thresholds is high. To get the optimal threshold values, a meta-heuristic or optimization algorithm is required. Our proposed algorithm is referred to as Rr-cr-IJADE, which is an improved version of Rcr-IJADE. Rr-cr-IJADE uses a newly proposed mutation strategy, “DE/rand-to-rank/1”, to improve the search success rate. The strategy uses the parameter F adaptation, crossover rate repairing, and the direction from a randomly selected individual to a ranking-based leader. The complexity of the proposed algorithm does not increase, compared to its ancestor. The performance of Rr-cr-IJADE, using Otsus function as the objective function, was evaluated and compared with other state-of-the-art evolutionary algorithms (EAs) and swarm intelligence algorithms (SIs), under both ‘low-level’ and ‘high-level’ experimental sets. Within the ‘low-level’ sets, the number of thresholds varied from 2 to 16, within 20 real images. For the ‘high-level’ sets, the threshold numbers chosen were 24, 32, 40, 48, 56 and 64, within 2 synthetic pseudo images, 7 satellite images, and three real images taken from the set of 20 real images. The proposed Rr-cr-IJADE achieved higher success rates with lower threshold value distortion (TVD) than the other state-of-the-art EA and SI algorithms.

Enhancement of online sequential extreme learning machine based on the householder block exact inverse QRD recursive least squares

The online sequential extreme learning machine (OS-ELM) has been used for training without retraining the ELM when a chunk of data is received. However, OS-ELM may be affected by an improper number of hidden nodes settings which reduces the generalization of OS-ELM. This paper addresses this problem in OS-ELM. A new structural tolerance OS-ELM (STOS-ELM), based on the Householder block exact inverse QRD recursive least squares algorithm having numerical robustness is proposed. Experimental results conducted on four regressions and five classification problems showed that STOS-ELM can handle the situation when the network is constructed with an improper number of hidden nodes. Accordingly, the proposed STOS-ELM can be easily applied; the size of the hidden layer of ELM can be roughly approximated. If a chunk of data is received, it can be updated in the existing network without having to worry about the proper number of given hidden nodes. Furthermore, the accuracy of the network trained by STOS-ELM is comparable to that of the batch ELM when the networks have the same configurations. STOS-ELM can also be applied in ensemble version (ESTOS-ELM). We found that the stability of STOS-ELM can be further improved using the ensemble technique. The results show that ESTOS-ELM is also more stable and accurate than both of the original OS-ELM and EOS-ELM, especially in the classification problems.

Multilevel thresholding selection based on chaotic multi-verse optimization for image segmentation

Multilevel thresholding is the most important method for image processing. Conventional multilevel thresholding methods have proven to be efficient in bi-level thresholding; however, when extended to multilevel thresholding, they prove to be computationally more costly, as they comprehensively search the optimal thresholds for the objective function. This paper presents a chaotic multi-verse optimizer (CMVO) algorithm using Kapurs objective function in order to determine the optimal multilevel thresholds for image segmentation. The proposed CMVO algorithm was applied to various standard test images, and evaluated by peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). The CMVO algorithm efficiently and accurately searched multilevel thresholds and reduced the required computational times.