Shu-Mei Guo

Enhancing Differential Evolution Utilizing Eigenvector-Based Crossover Operator

Differential evolution has been shown to be an effective methodology for solving optimization problems over continuous space. In this paper, we propose an eigenvector-based crossover operator. The proposed operator utilizes eigenvectors of covariance matrix of individual solutions, which makes the crossover rotationally invariant. More specifically, the donor vectors during crossover are modified, by projecting each donor vector onto the eigenvector basis that provides an alternative coordinate system. The proposed operator can be applied to any crossover strategy with minimal changes. The experimental results show that the proposed operator significantly improves DE performance on a set of 54 test functions in CEC 2011, BBOB 2012, and CEC 2013 benchmark sets.

A boundary method for outlier detection based on support vector domain description

The support vector domain description (SVDD) is a popular kernel method for outlier detection, which tries to fit a class of data with a sphere and uses a few target objects to support its decision boundary. The problem is that even with a flexible Gaussian kernel function, the SVDD could sometimes generate such a loose decision boundary that the discrimination ability becomes poor. Therefore, a computationally intensive procedure called kernel whitening is often required to improve the performance. In this paper, we propose a simple post-processing method which tries to modify the SVDD boundary in order to achieve a tight data description with no need of kernel whitening. With the derivation of the distance between an object and its nearest boundary point in input space, the proposed method can efficiently construct a new decision boundary based on the SVDD boundary. The improvement from the proposed method is demonstrated with synthetic and real-world datasets. The results show that the proposed decision boundary can fit the shape of synthetic data distribution closely and achieves better or comparable classification performance on real-world datasets.

Improving Differential Evolution With a Successful-Parent-Selecting Framework

An effective and efficient successful-parent-selecting framework is proposed to improve the performance of differential evolution (DE) by providing an alternative for the selection of parents during mutation and crossover. The proposed method adapts the selection of parents by storing successful solutions into an archive, and the parents are selected from the archive when a solution is continuously not updated for an unacceptable amount of time. The proposed framework provides more promising solutions to guide the evolution and effectively helps DE escaping the situation of stagnation. The simulation results show that the proposed framework significantly improves the performance of two original DEs and six state-of-the-art algorithms in four real-world optimization problems and 30 benchmark functions.

Genetic-based fuzzy image filter and its application to image processing

In this paper, we propose a Genetic-based Fuzzy Image Filter (GFIF) to remove additive identical independent distribution (i.i.d.) impulse noise from highly corrupted images. The proposed filter consists of a fuzzy number construction process, a fuzz filtering process, a genetic learning process, and an image knowledge base. First, the fuzzy number construction process receives sample images or the noise-free image and then constructs an image knowledge base for the fuzzy filtering process. Second, the fuzzy filtering process contains a parallel fuzzy inference mechanism, a fuzzy mean process, and a fuzzy decision process to perform the task of noise removal. Finally, based on the genetic algorithm, the genetic learning process adjusts the parameters of the image knowledge base. By the experimental results, GFIF achieves a better performance than the state-of-the-art filters based on the criteria of Peak-Signal-to-Noise-Ratio (PSNR), Mean-Square-Error (MSE), and Mean-Absolute-Error (MAE). On the subjective evaluation of those filtered images, GFIF also results in a higher quality of global restoration.

A self-optimization approach for L-SHADE incorporated with eigenvector-based crossover and successful-parent-selecting framework on CEC 2015 benchmark set

A self-optimization approach and a new success-history based adaptive differential evolution with linear population size reduction (L-SHADE) which is incorporated with an eigenvector-based (EIG) crossover and a successful-parent-selecting (SPS) framework are proposed in this paper. The EIG crossover is a rotationally invariant operator which provides superior performance on numerical optimization problems with highly correlated variables. The SPS framework provides an alternative of the selection of parents to prevent the situation of stagnation. The proposed SPS-L-SHADE-EIG combines the L-SHADE with the EIG and SPS frameworks. To further improve the performance, the parameters of SPS-L-SHADE-EIG are self-optimized in terms of each function under IEEE Congress on Evolutionary Computation (CEC) benchmark set in 2015. The stochastic population search causes the performance of SPS-L-SHADE-EIG noisy, and therefore we deal with the noise by re-evaluating the parameters if the parameters are not updated for more than an unacceptable amount of times. The experiment evaluates the performance of the self-optimized SPS-L-SHADE-EIG in CEC 2015 real-parameter single objective optimization competition.

An intelligent image agent based on soft-computing techniques for color image processing

An intelligent image agent based on soft-computing techniques for color image processing is proposed in this paper. The intelligent image agent consists of a parallel fuzzy composition mechanism, a fuzzy mean related matrix process and a fuzzy adjustment process to remove impulse noise from highly corrupted images. The fuzzy mechanism embedded in the filter aims at removing impulse noise without destroying fine details and textures. A learning method based on the genetic algorithm is adopted to adjust the parameters of the filter from a set of training data. By the experimental results, the intelligent image agent achieves better performance than the state-of-the-art filters based on the criteria of Peak-Signal-to-Noise-Ratio (PSNR) and Mean-Absolute-Error (MAE). On the subjective evaluation of those filtered images, the intelligent image agent also results in a higher quality of global restoration.

State-space self-tuning control for nonlinear stochastic and chaotic hybrid systems

This paper presents a new state-space self-tuning control scheme for adaptive digital control of continuous-time multivariable nonlinear stochastic and chaotic systems, which have unknown system parameters, system and measurement noises, and inaccessible system states. Instead of using the moving average (MA)-based noise model commonly used for adaptive digital control of linear discrete-time stochastic systems in the literature, an adjustable auto-regressive moving average (ARMA)-based noise model with estimated states is constructed for state-space self-tuning control of nonlinear continuous-time stochastic systems. By taking advantage of a digital redesign methodology, which converts a predesigned high-gain analog tracker/observer into a practically implementable low-gain digital tracker/observer, and by taking the non-negligible computation time delay and a relatively longer sampling period into consideration, a digitally redesigned predictive tracker/observer has been newly developed in this paper for adaptive chaotic orbit tracking. The proposed method enables the development of a digitally implementable advanced control algorithm for nonlinear stochastic and chaotic hybrid systems.

Actuator fault detection and performance recovery with Kalman filter-based adaptive observer

A novel Kalman filter-based adaptive observer for the sampled-data nonlinear time-varying system is proposed in this paper. With the high gain property of Kalman filter, it is applicable to a large variation of unknown parameters, which can be estimated optimally. Then a method of actuator fault detection is proposed. With the estimated faults, one can use the proposed input compensation method to solve actuator faults. Additionally, the optimal linearization technique is used to obtain the locally optimal linear model for a nonlinear system at each sampled state, so that the actuator fault detection and performance recovery of a sampled-data nonlinear time-varying system is accomplished. In this paper, we also introduce a prediction-based digital redesign method to develop the corresponding sampled-data controller.

State-Space Self-Tuning Control for Stochastic Fractional-Order Chaotic Systems

Based on the modified state-space self-tuning control (STC), a novel low-order tuner via the modified observer/Kalman filter identification (OKID) is proposed for stochastic fractional-order chaotic systems. The OKID method is a time-domain technique that identifies a discrete input-output map by using known input-output sampled data in the general coordinate form, through an extension of the eigensystem realization algorithm (ERA). First, the estimated system in the general coordinate based on the conventional OKID method is transformed to the one in an observer form to fit the state-space innovation form for the STC. Then, in stead of the conventional recursive least squares (RLS) identification algorithm used for STC, the Kalman filter as a parameter estimator with the state-space innovation form is presented for effectively estimating the time-varying parameters. Besides, taking the advantage of the digital redesign approach, the derivation of the current-output-based observer is proposed for the modified STC. As a result, the low-order state-space self-tuner with the high-gain controller property is then proposed for stochastic fractional-order chaotic systems, which the fractional operators are well approximated using the standard high integer-order operators. Finally, the fractional-order Chen and Roumlssler systems with stochastic system process and measurement noises are used as illustrative examples to demonstrate the effectiveness of the proposed methodology

EP-based adaptive tracker with observer and fault estimator for nonlinear time-varying sampled-data systems against actuator failures

An evolutionary programming-based adaptive observer is presented in this paper to improve the performance of state estimation of nonlinear time-varying sampled-data systems. Also, this paper presents a novel state-space adaptive tracker together with the proposed observer and estimation schemes for nonlinear time-varying sampled-data systems having actuator failures. For the class of slowly varying nonlinear time-varying systems, the proposed methodology is able to achieve the desired fault detection and performance recovery for the originally well-designed systems, as long as the controller having the high-gain property. For practical implementation, we utilize the advantages of digital redesign methodology to convert a well-designed high-gain analog controller/observer into its corresponding low-gain digital controller/observer. Illustrative examples are given to demonstrate the effectiveness of the proposed method. The developed digitally redesigned adaptive tracker with the proposed observer and estimator is suitable for implementation by using microprocessors.