Orthogonal Learning Particle Swarm Optimization Research Articles

Multi-objective energy aware task scheduling using Orthogonal Learning Particle Swarm Optimization on cloud environment

Multi-objective energy aware task scheduling using Orthogonal Learning Particle Swarm Optimization on cloud environment

A novel particle swarm optimization algorithm with Lévy flight and orthogonal learning

• In LOPSO, the there major highlights are described below. • First, a novel PSO based on Lévy flight and orthogonal learning with enhanced exploitation ability and faster search efficiency is proposed. The jumping ability of Lévy flights is utilized to enhance the exploration, while the orthogonal learning process aims to strengthen the exploitation;. • Second, an orthogonal learning process for particle swarms is developed. In the orthogonal learning process, the inclusion of the Lévy flights term in the levels of the Taguchi method is determined based on the flight probability value. Besides, parallel computation is easier to perform during orthogonal learning, which greatly improves efficiency. • Third, each particle in the proposed LOPSO learns from the only best experience generated by a new search strategy instead of the history best experience of each particle and the global best experience that used in the classical PSO variants, thus avoiding the conflict between above two guides. Taguchi method This paper presents a novel particle swarm optimization algorithm (PSO) variant to tackle single-objective numerical optimization, named “Lévy flight orthogonal learning particle swarm optimization” (LOPSO). There are three contributions mentioned in the paper: First, a novel PSO based on Lévy flight and orthogonal learning with enhanced exploitation ability and faster search efficiency is proposed. The jumping ability of Lévy flight is utilized to enhance the exploration, while the orthogonal learning process aims to strengthen the exploitation; Second, an orthogonal learning process for particle swarms is developed. In the orthogonal learning process, the Lévy flight term's inclusion in the Taguchi method levels is determined based on the flight probability value. Besides, parallel computation is easier to perform during orthogonal learning, which greatly improves efficiency. Third, each particle in the proposed LOPSO learns from the only best experience generated by a new search strategy instead of the historical best experience of each particle and the global best experience that is used in the classical PSO variants, thus avoiding the conflict between the above two guides. A large test suite containing benchmarks from the CEC2013 and the CEC2015 test suites on real-parameter single-objective optimization is employed in the algorithm validation, and extensive experiments demonstrate that the comprehensive performance of LOPSO ranks first in terms of accuracy and Wilcoxon signed-rank test in most cases with the same population size and iteration steps and similar time consumption, when compared with the canonical PSO and 13 state-of-the-art PSO variants.

An Efficient Handwritten Digit Recognition Based on Convolutional Neural Networks with Orthogonal Learning Strategies

The predictions of characters/text/digits from the handwritten images have made the research community spotlight towards recognition. There are enormous applications and ambiguity that made prediction possible with Deep Learning (DL) approaches. Primarily, there are four necessary steps to be carried out with handwriting prediction. First, consideration of a dataset that is more appropriate for DL validation an inefficient manner. Here, Special Database 1 and Special Database 2 are used, which are combined and modified by the National Institute of Standards and Technology (NIST). Next is pre-processing of input handwritten digit recognition data by data normalization, extraction of efficient features which provides better prediction accuracy. The proposed idea uses pixel values as features with the analysis of hyper-parameters to enhance near-human performance. With SVM, non-linear and linear models are built to extract the appropriate features for further processing. The features are separate and placed over the Bag of Features (BoF), which is used by the next processing stage. Finally, a novel Convolutional Neural Network (CNN) is by built modifying the network structure with Orthogonal Learning Particle Swarm Optimization (CNN-OLPSO). This modification is adopted for evolutionarily optimizing the number of hyper-parameters. This proposed optimizer predicts the optimal values from the fitness computation and shows better efficiency when compared to various other conventional approaches. The novelty which relies on CNN adoption is to endeavor a suitable path towards digitalization and preserve the handwritten structure and help automatic feature extraction using CNN by offering better computation accuracy. The optimization approach helps to avoid over-fitting and under-fitting issues. Here, metrics like accuracy, elapsed time, recall, precision, and [Formula: see text]-measure are evaluated. The results of CNN-OLPSO give better accuracy, reduced error rate and better execution time (s) compared to other existing methods. Thus, the proposed model shows better tradeoff in the recognition rate of handwritten digits.

An Optimal Deep Learning based Computer-aided Diagnosis System for Diabetic Retinopathy

Diabetic Retinopathy (DR) is a significant blinding disease that poses serious threat to human vision rapidly. Classification and severity grading of DR are difficult processes to accomplish. Traditionally, it depends on ophthalmoscopically-visible symptoms of growing severity, which is then ranked in a stepwise scale from no retinopathy to various levels of DR severity. This paper presents an ensemble of Orthogonal Learning Particle Swarm Optimization (OPSO) algorithm-based Convolutional Neural Network (CNN) Model EOPSO-CNN in order to perform DR detection and grading. The proposed EOPSO-CNN model involves three main processes such as preprocessing, feature extraction, and classification. The proposed model initially involves preprocessing stage which removes the presence of noise in the input image. Then, the watershed algorithm is applied to segment the preprocessed images. Followed by, feature extraction takes place by leveraging EOPSO-CNN model. Finally, the extracted feature vectors are provided to a Decision Tree (DT) classifier to classify the DR images. The study experiments were carried out using Messidor DR Dataset and the results showed an extraordinary performance by the proposed method over compared methods in a considerable way. The simulation outcome offered the maximum classification with accuracy, sensitivity, and specificity values being 98.47%, 96.43%, and 99.02% respectively.

Stability-enhanced prestack seismic inversion using hybrid orthogonal learning particle swarm optimization

Prestack seismic inversion quantitatively translates seismic data into multiple elastic properties, supporting the exploration of subsurface reservoirs in detail. Whereas, nonlinearity existing in the physical model causes the ill-posed inverse problem. Although global optimization algorithms own the advantages of achieving better results for highly nonlinear problems compared to linear/local optimization algorithms, such algorithms may suffer from stochastic instabilities or premature convergence when applied to prestack seismic inversion involving multiparameter and multimodal results, especially under complex geological conditions. In this paper, the Metropolis-based probabilistic acceptance criterion is incorporated into orthogonal learning particle swarm optimization (OLPSO), which leads to the proposed hybrid OLPSO (HOLPSO) algorithm. The HOLPSO is introduced to solve prestack seismic inversion problem with special intention of mitigating the instability of the results and the premature convergence of the algorithm. In specific, the stability of multiple results is enhanced by the orthogonal learning (dimensional combination) during model update/perturbation. In addition, the searching capability of the algorithm is improved by selecting guidance particle based on probabilistic acceptance mechanism. Synthetic tests demonstrate the stability and accuracy of the proposed method. Field application shows the method is capable of obtaining fine description of subsurface properties for better identifying potential reservoirs under complex geological conditions.

Evolutionary computing approach to optimize superframe scheduling on industrial wireless sensor networks

The industrial wireless sensor domain has undergone a shift in paradigm as a consequence of Internet of Things (IoT), a thriving technology that has been leading the way in short-range and fixed wireless sensing. One of the problems associated with industrial wireless sensor networks (IWSNs) is finding the optimal solution for minimizing defect time in superframe scheduling. This paper proposed a method based on the use of evolutionary algorithms, namely particle swarm optimization (PSO), orthogonal learning PSO, genetic algorithm (GA), and modified GA for optimizing the superframe scheduling. Additionally, we evaluated a contemporary method, deadline monotonic scheduling, on the ISA 100.11a protocol. The use of this standard as a case study means that the presented 72 simulations are object-oriented, with numerous variations in the number of timeslots and wireless sensor nodes. The simulation results show that the use of GA and modified GA can improve the performance in terms of idle, missed deadlines, memory consumption, and processing time comparing to other metaheuristic algorithms. A comprehensive analysis and detailed performance evaluation are provided in the paper.

An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis

Abstract The plant disease classification based on using digital images is very challenging. In the last decade, machine learning techniques and plant images classification tools such as deep learning can be used for recognizing, detecting and diagnosing plant diseases. Currently, deep learning technology has been used for plant disease detection and classification. In this paper, an ensemble model of two pre-trained convolutional neural networks (CNNs) namely VGG16 and VGG19 have been developed for the task plant disease diagnosis by classifying the leaves images of healthy and unhealthy. In this context, CNNs are used due to its capability of overcoming the technical problems which are associated with the classification problem of plant diseases. However, CNNs suffer from a great variety of hyperparameters with specific architectures which is considered as a challenge to identify manually the optimal hyperparameters. Therefore, orthogonal learning particle swarm optimization (OLPSO) algorithm is utilized in this paper to optimize a number of these hyperparameters by finding optimal values for these hyperparameters rather than using traditional methods such as the manual trial and error method. In this paper, to prevent CNNs from falling into the local minimum and to train efficiently, an exponentially decaying learning rate (EDLR) schema is used. In this paper, the problem of the imbalanced used dataset has been solved by using random minority oversampling and random majority undersampling methods, and some restrictions in terms of both the number and diversity of samples have been overcome. The obtained results of this work show that the accuracy of the proposed model is very competitive. The experimental results are compared with the performance of other pre-trained CNN models namely InceptionV3 and Xception, whose hyperparameters were selected using a non-evolutionary method. The comparison results demonstrated that the proposed diagnostic approach has achieved higher performance than the other models.

A hybrid method for power system state estimation using Cellular Computational Network

Several heuristic optimization methods including Particle Swarm Optimization (PSO) have been studied for power system state estimation and these perform quite well for small systems. However, in case of larger systems with hundreds of states, these suffer from the curse of dimensionality. To overcome this problem, a hybrid state estimator that consists of a Cellular Computational Network (CCN) and the Genetic Algorithm (GA) is proposed in this study. CCN is a framework that distributes the whole computation to computation cells and the cells execute local estimation. The result of CCN is further improved using GA. To compare the performance of the proposed estimator, two acclaimed variants of PSO, Comprehensive Learning PSO, and Orthogonal Learning PSO, which are specialized in multimodal high dimensional systems, are also implemented both individually and in conjunction with CCN. Through simulation, it is shown that the proposed CCN-GA outperform all direct and hybrid methods in terms of accuracy. Typical results on an IEEE 16-machine 68-bus power system are presented to illustrate the effectiveness of the CCN-GA over other methods.

Robust optimal position detection scheme for relational database watermarking through HOLPSOFA algorithm

Nowadays, relational database watermarking is a challenging problem in many content distribution applications and internet-based application environments. The watermarking scheme for relational databases based on a hybrid algorithm, named as HOLPSOFA is proposed. In HOLPSOFA, the combination of Orthogonal Learning Particle Swarm Optimization and Firefly Algorithm is used. This new approach combines the advantages of Orthogonal Learning particle swarm optimization (OLPSO) and Firefly algorithm (FA), which can find the time-optimal solutions simultaneously. The overall relational database watermarking scheme consists of three stages, (1) Optimal location identification through HOLPSOFA algorithm, (2) Watermark embedding and (3) watermark extraction. The proposed HOLPSOFA algorithm is also compared with OLPSO and Firefly algorithm. The performance of the proposed watermarking method is analyzed through Mean Square Error (MSE) and normalized correlation (NC). Our extensive analysis illustrates that the proposed method is robust against various forms of database attacks, including insertion, deletion and alteration. Computer simulations show that the hybrid algorithm is very effective in diminishing different kind of attacks in terms of MSE and NC than existing algorithms.

Optimizing Power Electronic Circuit Design with Uniform Search Range

Power electronic circuit (PEC) design is a complicated optimization problem that calls for evolutionary computation (EC) algorithm. The existing EC algorithms for optimizing PEC have difficulty in practical applications because they demand users to carefully define very narrow search ranges for different circuit components. Aiming at this problem, this paper models PEC with uniform search range (USR), where the components' search ranges are set uniformly according to the commonly used ranges in industrial applications. In order to solve the complex PEC problem with USR, an efficient orthogonal learning particle swarm optimization with predictive solution (OLPSO/PS) is proposed. Firstly, OLPSO/PS uses an orthogonal learning strategy to construct a more promising and efficient exemplar to guide particles to fly towards better searching areas dynamically. Secondly OLPSO/PS utilizes the predictive solution (PS) strategy to help save computational burden. OLPSO/PS is compared not only with the well-studied genetic algorithm and PSO for optimizing PEC in the literature, but also with OLPSO without PS and some other well-performed EC algorithms. Results show that OLPSO/PS is more promising in the optimization of PEC with USR, outperforming other algorithms in terms of higher fitness quality, faster optimization speed, stronger reliability, and better simulation results on both voltage and current. Moreover, the effectiveness of OLPSO/PS is further validated on the experiments in a practical circuit.

Quadratic interpolation based orthogonal learning particle swarm optimization algorithm

Particle swarm optimization (PSO) is a population based algorithm for solving global optimization problems. Owing to its efficiency and simplicity, PSO has attracted many researchers' attention and developed many variants. Orthogonal learning particle swarm optimization (OLPSO) is proposed as a new variant of PSO that relies on a new learning strategy called orthogonal learning strategy. The OLPSO differs in the utilization of the information of experience from the standard PSO, in which each particle utilizes its historical best experience and globally best experience through linear summation. In OLPSO, particles can fly in better directions by constructing an efficient exemplar through orthogonal experimental design. However, the global version based orthogonal learning PSO (OLPSO-G) still have some drawbacks in solving some complex multimodal function optimization. In this paper, we proposed a quadratic interpolation based OLPSO-G (QIOLPSO-G), in which, a quadratic interpolation based construction strategy for the personal historical best experience is applied. Meanwhile, opposition-based learning, and Gaussian mutation are also introduced into this paper to increase the diversity of the population and discourage the premature convergence. Experiments are conducted on 16 benchmark problems to validate the effectiveness of the QIOLPSO-G, and comparisons are made with four typical PSO algorithms. The results show that the introduction of the three strategies does enhance the effectiveness of the algorithm.

Orthogonal Learning Particle Swarm Optimization

Particle swarm optimization (PSO) relies on its learning strategy to guide its search direction. Traditionally, each particle utilizes its historical best experience and its neighborhood's best experience through linear summation. Such a learning strategy is easy to use, but is inefficient when searching in complex problem spaces. Hence, designing learning strategies that can utilize previous search information (experience) more efficiently has become one of the most salient and active PSO research topics. In this paper, we proposes an orthogonal learning (OL) strategy for PSO to discover more useful information that lies in the above two experiences via orthogonal experimental design. We name this PSO as orthogonal learning particle swarm optimization (OLPSO). The OL strategy can guide particles to fly in better directions by constructing a much promising and efficient exemplar. The OL strategy can be applied to PSO with any topological structure. In this paper, it is applied to both global and local versions of PSO, yielding the OLPSO-G and OLPSO-L algorithms, respectively. This new learning strategy and the new algorithms are tested on a set of 16 benchmark functions, and are compared with other PSO algorithms and some state of the art evolutionary algorithms. The experimental results illustrate the effectiveness and efficiency of the proposed learning strategy and algorithms. The comparisons show that OLPSO significantly improves the performance of PSO, offering faster global convergence, higher solution quality, and stronger robustness.