Search

Surrogate-assisted evolutionary algorithms (SAEAs) are potential approaches to solve computationally expensive optimization problems. The critical idea of SAEAs is to combine the powerful searching capabilities of evolutionary algorithms with the predictive capabilities of surrogate models. In this study, an efficient surrogate-assisted hybrid optimization (SAHO) algorithm is proposed via combining two famous algorithms, namely, teaching–learning-based optimization (TLBO) and differential evolution (DE). The TLBO is focused on global exploration and the DE is concentrated on local exploitation. These two algorithms are carried out alternately when no better candidate solution can be found. Meanwhile, a new prescreening criterion based on the best and top collection information is introduced to choose promising candidates for real function evaluations. Besides, two evolution control (i.e., the generation-based and individual-based) strategies and a top-ranked restart strategy are integrated in the SAHO. Moreover, a local RBF surrogate which does not need too many training samples is employed to model the landscapes of the target function. Sixteen benchmark functions and the tension/compression spring design problem are adopted to compare the proposed SAHO with other state-of-the-art approaches. Extensive comparison results demonstrate that the proposed SAHO has superior performance for solving expensive optimization problems. [ABSTRACT FROM AUTHOR]

• A novel Kriging-assisted two-phase optimization framework is proposed based on TLBO's unique structure. • A data management approach is proposed to collect and organize the dynamically updated expensive samples. • Two prescreening operators are proposed in Kriging-assisted Teaching and Learning Phases to select elite individuals. • KTLBO performs efficient on 18 benchmark cases and can successfully solve actual engineering applications. In this paper, a novel algorithm KTLBO is presented to achieve computationally expensive constrained optimization. In KTLBO, Kriging is adopted to develop dynamically updated surrogate models for costly objective and inequality constraints. A data managing method aiming at solving expensive constrained problems is developed to archive, classify and update expensive samples, where a penalty function is set to adaptively select elite individuals. Moreover, based on the Teaching-Learning-based Optimization (TLBO), a Kriging-assisted two-phase optimization framework is presented to alternately conduct local and global searches. In Kriging-assisted Teaching and Learning Phases, two different prescreening operators considering the probability of feasibility are respectively proposed to select the high-quality samples around the present best solution and the samples exhibiting better space-filling performance, as an attempt to balance exploitation of surrogates and exploration of unknown area. In brief, KTLBO retains the meta -heuristic search mechanism of TLBO while adopting Kriging to accelerate its search, thereby acting as a novel idea for surrogate-assisted constrained optimization. Lastly, KTLBO is compared with 6 well-known methods on 27 benchmark cases, and then its significant advantages in expensive constrained optimization are verified. Furthermore, KTLBO is adopted to design the structure of a Blended-Wing-Body underwater glider, and the satisfactory solution is yielded. [ABSTRACT FROM AUTHOR]

• An ameliorated teaching–learning-based optimization algorithm is presented for multi-threshold image segmentation problem. • Two random numbers are utilized to determine the learning approaches of a learner in both teacher and learner phases of DI-TLBO, which further improves its global optimization ability. • Two new phases, self-feedback learning phase as well as mutation and crossover phase, are introduced in DI-TLBO algorithm. • DI-TLBO-based method possesses superior performance for multi-threshold image segmentation. In this paper, multi-threshold image segmentation approaches using an improved teaching–learning-based optimization algorithm (DI-TLBO) are presented and the proposed DI-TLBO-based methods obtain satisfactory segmentation results. This work is presented as follows. Firstly, two random numbers are introduced to determine the learning methods of the learner in the teacher phases and the learner phases of DI-TLBO. Randomness of the learning methods further improves global optimization ability of DI-TLBO. Self-feedback learning phase and mutation-crossover phase are also introduced into DI-TLBO algorithm, which makes DI-TLBO achieve better exploration ability. The comparative results of DI-TLBO with other evolutionary algorithms (EAs) on a set of benchmarks functions demonstrate that DI-TLBO acquires better solution accuracy than other EAs. Then the proposed DI-TLBO algorithm is applied to solve multi-level threshold image segmentation problems modeled by Otsu's between class variance function and Kapur's entropy function. Experiments comparing DI-TLBO-based methods with other EAs based approaches on standard test images show that DI-TLBO-based methods possess superior performance in terms of both solution accuracy and stability of segmentation results. Finally, the proposed DI-TLBO-based methods are successfully applied in casting X-ray image segmentation for multi-level threshold. Although the defects in high resolution X-ray image (3072 × 2400) are easy to be ignored and omitted when being detected artificially, all the defects are segmented perfectly using the proposed DI-TLBO-based methods. [ABSTRACT FROM AUTHOR]

The well-known optimization approach teaching-learning-based optimization (TLBO) is modified by using a confined TLBO (CTLBO) to eliminate the teaching factor. Different settings are suggested for various types of search factors, as they are used for different purposes. In addition, crossover frequencies are introduced into TLBO to prevent premature convergence. Furthermore, eight new mutation strategies are introduced to the teacher phase, and four new mutation strategies to the student phase to enhance the algorithm's exploitation and exploration capabilities. The experimental results show that the proposed versions, especially those that either adopted low crossover frequencies or implemented various mutation strategies, performed particularly well in achieving fast convergence speeds in the early stages, reaching convergence precision at lower cost, arriving at convergence plateaus at either lower cost or higher precision, handling tests of composition functions well, and achieving competitive performance on CEC2015 test problems. [ABSTRACT FROM AUTHOR]

Community detection has been an active field of study in complex network analysis in recent years. It can be modeled as a seriously nonlinear optimization problem. Many intelligent optimization techniques have shown promising results for this problem. The teaching–learning-based optimization (TLBO) algorithm is a recently proposed swarm intelligent algorithm. In this paper, a discrete variant of TLBO (DTLBO) is proposed to address discrete optimization problems. In the proposed method, the learner representation scheme is redefined, and the updating rules for learners are also redesigned. Moreover, based on the proposed discrete variant DTLBO, a multi-objective discrete method (MODTLBO/D) is proposed to solve community detection problems for complex networks. The multi-objective decomposition mechanism is adopted and neighbor-based mutation is introduced to maintain the diversity of the population and avoid being trapped in the local optima. Finally, to verify the performance of the proposed algorithm, real-world networks are examined. The experimental results indicate that MODTLBO/D is effective compared with other algorithms used for community detection in complex networks. [ABSTRACT FROM AUTHOR]

This paper proposes an improved constrained teaching–learning-based optimization (ICTLBO) method to efficiently solve constrained optimization problems (COPs). In the teacher phase of ICTLBO, the population is partitioned into several subpopulations, and the direction information between the mean position of each subpopulation and the best position of population guide the corresponding subpopulation to the promising region promptly. Information exchange between different subpopulations is used to discourage premature convergence of each subpopulation. Furthermore, in the learner phase, a new learning strategy is introduced to improve the population diversity and enhance the global search ability. Three different constraint handling methods are adopted for three situations, which are infeasible, semi-feasible, and feasible situations, during the evolution process. To evaluate the performance of ICTLBO, 22 benchmark functions presented in CEC2006 and 18 benchmark functions introduced in CEC2010 are chosen as the test suite. Moreover, four widely used engineering design problems are selected to test the performance of ICTLBO for real-world problems. Experimental results indicate that ICTLBO can obtain a highly competitive performance compared with other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Abstract: Global optimization remains one of the most challenging tasks for evolutionary computation and swarm intelligence. In recent years, there have been some significant developments in these areas regarding the solution of global optimization problems. In this paper, we propose an improved teaching–learning-based optimization (TLBO) algorithm with dynamic group strategy (DGS) for global optimization problems. Different to the original TLBO algorithm, DGSTLBO enables each learner to learn from the mean of his corresponding group, rather than the mean of the class, in the teacher phase. Furthermore, each learner employs the random learning strategy or the quantum-behaved learning strategy in his corresponding group in the learner phase. Regrouping occurs dynamically after a certain number of generations, helping to maintain the diversity of the population and discourage premature convergence. To verify the feasibility and effectiveness of the proposed algorithm, experiments are conducted on 18 numerical benchmark functions in 10, 30, and 50 dimensions. The results show that the proposed DGSTLBO algorithm is an effective method for global optimization problems. [Copyright &y& Elsevier]

Abstract: A note published by Črepinšek et al. [3] (A note on teaching–learning-based optimization algorithm, Information Sciences 212 (2012) 79–93) reported three “important mistakes” regarding teaching–learning-based optimization (TLBO) algorithm. Furthermore, the authors had presented some experimental results for constrained and unconstrained benchmark functions and tried to invalidate the performance supremacy of the TLBO algorithm. However, the authors had not reviewed the latest research literature on TLBO algorithm and their observations about TLBO algorithm were based only on two papers that were published initially. The views and the experimental results presented by Črepinšek et al. [3] are questionable and this paper re-examines the experimental results and corrects the understanding about the TLBO algorithm in an objective manner. The latest literature on TLBO algorithm is also presented and the algorithm-specific parameter-less concept of TLBO is explained. The results of the present work demonstrate that the TLBO algorithm performs well on the problems where the fitness-distance correlations are low by proper tuning of the common control parameters of the algorithm. [Copyright &y& Elsevier]

Abstract: Teaching–Learning-Based Optimization (TLBO) seems to be a rising star from amongst a number of metaheuristics with relatively competitive performances. It is reported that it outperforms some of the well-known metaheuristics regarding constrained benchmark functions, constrained mechanical design, and continuous non-linear numerical optimization problems. Such a breakthrough has steered us towards investigating the secrets of TLBO’s dominance. This paper reports our findings on TLBO qualitatively and quantitatively through code-reviews and experiments, respectively. Our findings have revealed three important mistakes regarding TLBO: (1) at least one unreported but important step; (2) incorrect formulae on a number of fitness function evaluations; and (3) misconceptions about parameter-less control. Additionally, unfair experimental settings/conditions were used to conduct experimental comparisons (e.g., different stopping criteria). The experimental results for constrained and unconstrained benchmark functions under fairly equal conditions failed to validate its performance supremacy. The ultimate goal of this paper is to provide reminders for metaheuristics’ researchers and practitioners in order to avoid similar mistakes regarding both the qualitative and quantitative aspects, and to allow fair comparisons of the TLBO algorithm to be made with other metaheuristic algorithms. [Copyright &y& Elsevier]

Abstract: An efficient optimization method called ‘Teaching–Learning-Based Optimization (TLBO)’ is proposed in this paper for large scale non-linear optimization problems for finding the global solutions. The proposed method is based on the effect of the influence of a teacher on the output of learners in a class. The basic philosophy of the method is explained in detail. The effectiveness of the method is tested on many benchmark problems with different characteristics and the results are compared with other population based methods. [Copyright &y& Elsevier]