Adaptive Strategies Based on Differential Evolutionary Algorithm for Many-Objective Optimization

The decomposition-based algorithm, for example, multiobjective evolutionary algorithm based on decomposition (MOEA/D), has been proved effective and useful in a variety of multiobjective optimization problems (MOPs). On the basis of MOEA/D, the MOEA/D-DE replaces the simulated binary crossover (SBX) operator with differential evolution (DE) operator, which is used to enhance the diversity of the solutions more effectively. However, the amplification factor and the crossover probability are fixed in MOEA/D-DE, which would lead to a low convergence rate and be more likely to fall into local optimum. To overcome such a prematurity problem, this paper proposes three different adaptive operators in DE with crossover probability and amplification factors to adjust the parameter settings adaptively. We incorporate these three adaptive operators in MOEA/D-DE and MOEA/D-PaS to solve MOPs and many-objective optimization problems (MaOPs), respectively. This paper also designs a sensitive experiment for the changeable parameter η in the proposed adaptive operators to explore how η would affect the convergence of the proposed algorithms. These adaptive algorithms are tested on many benchmark problems, including ZDT, DTLZ, WFG, and MaF test suites. The experimental results illustrate that the three proposed adaptive algorithms have better performance on most benchmark problems.

Metode SVM Untuk Klasifikasi Enam Tumbuhan Zingiberaceae Menggunakan Variabel Terpilih Hasil Algoritma Genetika

Ginger, red ginger, emprit ginger, elephant ginger, red galangal and white galangal are known to have similar shapes and uses, especially those that are packaged in powder form. In this study, UV-Vis spectrum 200nm-700nm were used as a source of data from chemical compound contain in those plants for classification of the six plants. In this research, the support vector machine (SVM) classification method was used to classify the six plants. Another goal of this study was to identify the wavelengths which give more information about the chemical compound of the plants. The preprocessing procedure was implemented by construction of a genetic algorithm. There were four parameters in the genetic algorithm were set namely population size, crossover probability, mutation, and generation probability. The mutation and the population size influenced significantly the results of SVM. The best result was given by probability of mutation was 10 and population size was 30. The SVM model was better than the SVM model without preprocessing procedure.

A hybrid differential evolution based on gaining‑sharing knowledge algorithm and harris hawks optimization

Differential evolution (DE) is favored by scholars for its simplicity and efficiency, but its ability to balance exploration and exploitation needs to be enhanced. In this paper, a hybrid differential evolution with gaining-sharing knowledge algorithm (GSK) and harris hawks optimization (HHO) is proposed, abbreviated as DEGH. Its main contribution lies are as follows. First, a hybrid mutation operator is constructed in DEGH, in which the two-phase strategy of GSK, the classical mutation operator “rand/1” of DE and the soft besiege rule of HHO are used and improved, forming a double-insurance mechanism for the balance between exploration and exploitation. Second, a novel crossover probability self-adaption strategy is proposed to strengthen the internal relation among mutation, crossover and selection of DE. On this basis, the crossover probability and scaling factor jointly affect the evolution of each individual, thus making the proposed algorithm can better adapt to various optimization problems. In addition, DEGH is compared with eight state-of-the-art DE algorithms on 32 benchmark functions. Experimental results show that the proposed DEGH algorithm is significantly superior to the compared algorithms.

Operator Control Parameters and Fine Tuning of Genetic Algorithms (GAs)

Genetic algorithms (GAs) are heuristic, blind (i.e., black box-based) search techniques. The internal working of GAs is complex and is opaque for the general practitioner. GAs are a set of interconnected procedures that consist of complex interconnected activity among parameters. When a naive GA practitioner tries to implement GA code, the first question that comes into the mind is what are the value of GA control parameters (i.e., various operators such as crossover probability, mutation probability, population size, number of generations, etc. will be set to run a GA code)? This chapter clears all the complexities about the internal interconnected working of GA control parameters. GA can have many variations in its implementation (i.e., mutation alone-based GA, crossover alone-based GA, GA with combination of mutation and crossover, etc.). In this chapter, the authors discuss how variation in GA control parameter settings affects the solution quality.

Aplikasi Pertimbangan Wisata di Pulau Lombok dengan Metode Fuzzy Mamdani & Algoritma Genetika

<p class="Abstrak">Pulau Lombok memiliki pariwisata berupa keindahan alam dan kebudayaan yang menarik, sehingga juga mendapat tiga penghargaan pada <em>World Halal Tourism Awards</em> 2016 dengan faktor pertumbuhan kunjungan wisatawan sebesar 13% pada tahun tersebut. Adanya sebuah aplikasi yang dapat membantu wisatawan dalam menentukan keputusan perjalanan wisata mereka adalah wajib. Aplikasi ini dikembangkan dengan logika <em>Fuzzy</em> Mamdani dan Algoritma Genetika dengan tujuan memberikan rekomendasi pariwisata.Logika <em>Fuzzy</em> Mamdani memberikan pertimbangan wisata berdasarkan 5 parameter (anggaran, rencana perjalanan, akomodasi, makanan dan minuman, serta biaya transportasi) yang kemudian menjadi 5 fungsi keanggotaan untuk membangun kombinasi aturan pada fuzzy dan menghasilkan keluaran berupa pertimbangan wisata, yaitu: Tidak Memungkinkan, Cukup Memungkinkan, dan Memungkinkan. Kombinasi lima fungsi keanggotaan tersebut, menghasilkan 10.080 aturan, yang digunakan untuk mengetahui seseorang memungkinkan, atau tidak untuk berwisata ke pulau Lombok dengan <em>constrain</em> parameter yang dimiliki, yang dibangkitkan dengan menggunakan fungsi Defuzzifikasi <em>Mean of Max</em> (MOM). Algortima Genetika digunakan dalam memberikan alokasi penggunaan budget yang optimal dalam berwisata di Pulau Lombok.Hasil pengujian dengan perhitungan manual dan model defuzzifikasi yang berbeda memiliki akurasi 100%. Untuk implementasi Algoritma Genetika, aplikasi memperoleh alokasi anggaran optimal pada <em>probabilitas crossover</em> (pc) dan probabilitas mutasi (pm) dengan (pc) 0,7 dan (pm) 0,2.</p><p class="Abstrak"> </p><p class="Abstrak"><em><strong>Abstract</strong></em></p><p class="Abstract"><em>Tourism in Lombok has an interesting culture, it makes Lombok got three awards at the 2016 World Halal Tourism Awards and became a growth factor for tourist visits by 13% that year. An application that can help tourists in determining travel decision is mandatory.The application developed with Mamdani Fuzzy Logic and Genetic Algorithm to provide tourism recommendations. The Fuzzy Mamdani Logic Method provides tourism considerations based on 5 parameters (budget, travel plans, accommodation, food and drinks, and transportation costs) which then become 5 membership functions to build a combination of rules on fuzzy and produce output in the form of tourism's considerations: Not Enable, Enough Enable, and Enable. The combination of the 5 membership functions constructed 10.080 fuzzy rules, that's used to know wheater tourists enables them to go to Lombok with the limitation that they have. The defuzzification used is the Mean of Max (MOM). Genetic Algorithm (GA) is used in providing optimal budget allocation in traveling on Lombok IslandThe results of testing with manual calculations and different defuzzification models have 100% accurate, the application of GA obtained optimal budget allocation on crossover probability (pc) and mutation probability (pm) combination with (pc) 0.7 and (pm) 0.2.</em></p><p class="Abstrak"><em><strong><br /></strong></em></p>

Data fusion using Tabu crossover genetic algorithm in information retrieval

This article explores the odd and even point crossover based Tabu Genetic Algorithm. The search optimization tools equipped with exploration and exploitation operators. Those operators assist the optimization tools for finding the optimal solution. Few problems demand vigorous exploration and minimal exploitation. The vigorous exploration needs some specialized operators, which is capable of carrying out the task. In this article, we explore one such possible operator using odd and even point (OEP) crossover. The resultant hybrid GA namely OEP crossover based Tabu GA has two tuning factors namely tenure period and OEP crossover probability (Podd). The tenure period may be a single entity or a group of entities. However, Podd is single, as the tenure period is involved with group of entities, it demands some fine tuning. The fine tuning may alter the proportion of exploration and exploitation. Hence, we proposed a method for selecting the tenure period. The proposed exploration operator and the method for fixing the tenure period has been tested over the data fusion problem in information retrieval. The results look promising.

Synthesis of Sparse Concentric Ring Arrays Based on Fitness-Associated Differential Evolution Algorithm

In this paper, fitness-associated differential evolution (FITDE) algorithm is proposed and applied to the synthesis of sparse concentric ring arrays under constraint conditions, whose goal is to reduce peak sidelobe level. In unmodified differential evolution (DE) algorithm, crossover probability is constant and remains unchanged during the whole optimization process, resulting in the negative effect on the population diversity and convergence speed. Therefore, FITDE is proposed where crossover probability can change according to certain information. Firstly, the population fitness variance is introduced to the traditional differential evolution algorithm to adjust the constant crossover probability dynamically. The fitness variance in the earlier iterations is relatively large. Under this circumstance, the corresponding crossover probability shall be small to speed up the exploration process. As the iteration progresses, the fitness variance becomes small on the whole and the crossover probability should be set large to enrich population diversity. Thereby, we construct three variation strategies of crossover probability according to the above changing trend. Secondly, FITDE is tested on benchmark functions, and the best one of the three strategies is determined according to the test results. Finally, sparse concentric ring arrays are optimized using FITDE, of which the results are compared with reference algorithms. The optimization results manifest the advantageous effectiveness of FITDE.

Shared Aperture Multibeam Forming of Time-Modulated Linear Array

A novel technique is proposed in this paper for shared aperture multibeam forming in a complex time-modulated linear array. First, a uniform line array is interleaved randomly to form two sparse array subarrays. Subsequently, the theory of time modulation for linear arrays is applied in the constructed subarrays. In the meantime, the switch-on time sequences for each element of the two subarrays are optimized by an optimized differential evolution (DE) algorithm, i.e., the scaling factor of the sinusoidal iterative chaotic system and the adaptive crossover probability factor are used to enhance the diversity of the population. Lastly, the feasibility of the new technique is verified by the comparison between this technique and the basic multibeam algorithm in a shared aperture and the algorithm of iterative FFT. The results of simulations confirm that the proposed algorithm can form more desired beams, and it is superior to other similar approaches.

Effect of Crossover Probability on Performance of Genetic Algorithm in Scheduling of Parallel Machines for BI- Criteria Objectives

Optimization of multi objective function gain the importance in the scheduling process. Many classical techniques are available to address the multi objective functions but the solutions yield the unsatisfactory results when the problem becomes complex and large. Evolutionary algorithm would be the solution for such problems. Genetic algorithm is adaptive heuristic search algorithms and optimization techniques that mimic the process of natural evolution. Genetic algorithms are a very effective way of obtaining a reasonable solution quickly to a complex problem. The genetic algorithm operators such as selection method, crossover method, crossover probability, mutation operators and stopping criteria have an effect on obtaining the reasonably good solution and the computational time. Partially mapped crossover operators are used to solve the problem of the traveling salesman, planning and scheduling of the machines, etc., which are having a wide range of solutions. This paper presents the effect of crossover probability on the performance of the genetic algorithm for the bi-criteria objective function to obtain the best solution in a reasonable time. The simulation on a designed genetic algorithm was conducted with a crossover probability of 0.4 to 0.95 (with a step of 0.05) and 0.97, found that results were converging for the crossover probability of 0.6 with the computational time of 3.41 seconds.