Genetic algorithm with dynamic variable number of individuals and accuracy

Magang merupakan proses yang penting dalam proses belajar mengajar di SMK. Secara spesifik magang di SMK disebut Prakerin (Praktek Kerja Industri). Penempatan magang harus memerhatikan kompetensi siswa, kuota dari perusahaan, kesesuaian jurusan dengan lowongan, dan penghasilan orang tua. Penempatan magang secara manual selama ini memakan waktu, sehingga kurang efisien. Oleh karena itu, penelitian ini fokus mengembangkan aplikasi dengan menerapkan pendekatan Algoritme Genetika untuk mempermudah dalam menentukan penempatan magang dengan menerapkan aturan yang berlaku. Algoritme Genetika dinilai sebagai algoritma yang relevan dan solutif untuk diterapkan dalam penyelesaian masalah optimasi kompleks. Masalah yang dimaksud umumnya adalah masalah yang sulit dilakukan dengan menerapkan metode konvensional. Algoritme Genetika memberikan hasil yang lebih baik untuk setiap iterasi pencarian solusi. Hasil fitness terbaik dengan nilai 0.0014286 diperoleh pada jumlah individu 200, jumlah generasi 200, persentase crossover 50% dan mutasi 10%. Hasil validasi dengan pihak SMK menyatakan bahwa sistem ini mudah untuk digunakan dan bermanfaat bagi pihak SMK, dengan rata-rata persentase kualitas sistem 82,5%. Algoritme Genetika efektif untuk diterapkan pada studi kasus penjadwalan atau penempatan magang yang memiliki karakteristik data yang kompleks. AbstractInternships are an important component of teaching and learning activities in vocational high schools (SMK). Specifically the internship in SMK is called Prakerin (Industrial Work Practice). The internship placement should considering student competence, number of vacancies, the suitability of majors with vacancy, and the income of the parent. During this time, manual internship placement takes more time, so less efficient. Therefore, this research tries to approach using Genetic Algorithm to make it easier in determining the internship placement by applying the applicable rules. The Genetic Algorithm is judged as the right algorithm used in solving complex optimization problems, which is difficult to do by conventional methods. The Genetic Algorithm provides better results for each iteration of the solution search. Best fitness results with value 0.0014286 obtained on the number of individuals 200, the number of generation 200, the percentage of crossover 50% and the mutation 10%. Validation results with the SMK stated that the system is easy to use and beneficial to the SMK, with an average percentage of system quality about 82.5%. Genetic Algorithms are effective to apply to scheduling case studies or internship placements that have complex data characteristics.

Download Full-text

A Variable-Number Genetic Algorithm for Growth of 1-Dimensional Nanostructures into Their Global Minimum Configuration Under Radial Confinement

Materials and Manufacturing Processes ◽

10.1080/10426910802678172 ◽

2009 ◽

Vol 24 (3) ◽

pp. 265-273 ◽

Cited By ~ 9

Author(s):

T. E. B. Davies ◽

D. P. Mehta ◽

J. L. Rodríguez-López ◽

G. H. Gilmer ◽

C. V. Ciobanu

Keyword(s):

Genetic Algorithm ◽

Global Minimum ◽

Variable Number

Download Full-text

The use of fuzzy sets to determine the parameters of genetic algorithms that provide approximately the same execution time on the CPU and GPU

Journal of Physics Conference Series ◽

10.1088/1742-6596/2131/3/032025 ◽

2021 ◽

Vol 2131 (3) ◽

pp. 032025

Author(s):

Oleg Agibalov ◽

Nikolay Ventsov

Keyword(s):

Genetic Algorithm ◽

Processing Time ◽

Fuzzy Numbers ◽

Subject Area ◽

Initial Information ◽

Hardware Architectures ◽

The Subject ◽

Gpu Architectures ◽

Number Of Individuals ◽

Gpu Architecture

Abstract The problem under consideration consists in choosing the number of k individuals, so that the time for processing k individuals by the genetic algorithm (GA) on the CPU architecture is close to the time for processing l individuals on the GPU architecture by the genetic algorithm. The initial information is data arrays containing information about the processing time of a given number of individuals by the genetic algorithm on the available hardware architectures. Fuzzy numbers are determined based on these arrays?~? and?~?, describing the processing time of a given number of individuals, respectively, on the CPU and GPU architectures. The peculiarities of the subject area do not allow considering the well-known methods of comparison based on the equalities of the membership functions and the nearest clear sets as adequate. Based on the known formula “close to Y (around Y)” the way to compare fuzzy numbers?~? and?~? was developed in order to determine the degree of closeness of the processing time of k and l individuals, respectively, on the hardware architectures of the CPU and GPU.

Download Full-text

Intraclass and interclass correlations of allele sizes within and between loci in DNA typing data.

Genetics ◽

10.1093/genetics/133.2.411 ◽

1993 ◽

Vol 133 (2) ◽

pp. 411-419

Author(s):

R Chakraborty ◽

M R Srinivasan ◽

M de Andrade

Keyword(s):

Fragment Size ◽

Dna Typing ◽

Population Data ◽

Variable Number ◽

Population Subdivision ◽

The Us ◽

Correlation Measures ◽

Computer Simulation Studies ◽

Nonparametric Correlation ◽

Number Of Individuals

Abstract Nonparametric measures of correlations of DNA fragment lengths within and between variable number of tandem repeat (VNTR) loci are proposed to test the hypothesis of random association of allele sizes at VNTR loci. Transformations of these nonparametric correlation measures are suggested to detect deviations of their null expectations caused by population subdivision and errors of measurement of VNTR fragment lengths. Analytic and permutation-based computer simulation studies are performed to show that under the hypothesis of independence of allele sizes the transformed correlation measures are normally distributed, irrespective of the VNTR fragment size distribution in the population even when the number of individuals samples is as low as 100. Power calculations are performed to establish that the current population data on six VNTR loci in the US Hispanic sample are in accordance with the hypothesis of random association of allele sizes within and between loci. Implications of these results in the context of forensic use of DNA typing are also discussed.

Download Full-text

CROSS-POLLINATING PARALLEL GENETIC ALGORITHMS FOR MULTI-OBJECTIVE SEARCH AND OPTIMIZATION

International Journal of Foundations of Computer Science ◽

10.1142/s012905410500298x ◽

2005 ◽

Vol 16 (02) ◽

pp. 261-280 ◽

Cited By ~ 4

Author(s):

LUCAS A. WILSON ◽

MICHELLE D. MOORE

Keyword(s):

Genetic Algorithm ◽

Empirical Studies ◽

Path Generation ◽

Parallel Genetic Algorithm ◽

Optimization Criteria ◽

Parallel Genetic Algorithms ◽

Multi Objective ◽

Hard Constraints ◽

Future Work ◽

Number Of Individuals

This paper discusses the design of a parallel genetic algorithm to generate solutions to multi-objective problems. The algorithm uses multiple optimization criteria, independent cross-pollinating populations, and handles multiple hard constraints. Individuals in the population consist of multiple chromosomes. The complexity of the algorithm is the number of generations processed times O(N2) where N is the total number of individuals used for path generation on any of the optimizations. The results of initial empirical studies on the effects of pollination and recommendations for possible future work are presented.

Download Full-text

Genetic algorithm efficiency improvement in the course of set cover problem solution

Vestnik of Don State Technical University ◽

10.23947/1992-5980-2019-19-4-389-397 ◽

2020 ◽

Vol 19 (4) ◽

pp. 389-397

Author(s):

I. S. Konovalov ◽

V. A. Fatkhi ◽

V. G. Kobak

Keyword(s):

Genetic Algorithm ◽

Single Point ◽

Set Cover ◽

Covering Problem ◽

Problem Solution ◽

Crossover Operator ◽

Deletion Mutations ◽

Set Cover Problem ◽

Cover Problem ◽

Number Of Individuals

Introduction. Practical tasks (location of service points, creation of microcircuits, scheduling, etc.) often require an exact or approximate to exact solution at a large dimension. In this case, achieving an acceptable result requires solving a set cover problem, fundamental for combinatorics and the set theory. An exact solution can be obtained using exhaustive methods; but in this case, when the dimension of the problem is increased, the time taken by an exact algorithm rises exponentially. For this reason, the precision of approximate methods should be increased: they give a solution that is only approximate to the exact one, but they take much less time to search for an answer at a large dimension.Materials and Methods. One of the ways to solve the covering problem is described, it is a genetic algorithm. The authors use a modification of the Goldberg model and try to increase its efficiency through various types of mutation and crossover operators. We are talking about gene mutations, two-point mutations, addition and deletion mutations, insertion and deletion mutations, saltation, mutations based on inversion. The following types of crossover operator are noted: single-point, two-point, three-point and their versions with restrictions, uniform, triad. The effect of the stopping condition and the probability values of genetic operators on the accuracy of the solutions is investigated. It is shown how an increase in the number of individuals in a generation affects the efficiency of a solution. Research Results. The experiment results allow us to draw three conclusions. 1) It is recommended to use a combination of gene mutation and single-point crossing. 2) With an increase in the number of individuals, the accuracy of the result and the time to obtain it increases. The average deviation from the exact result at a task size of 25 × 25 was 0%, at 50 × 50 – 0%, at 75 × 75 – 0.013%, at 100 × 100 – 0%, at 110 × 110 – 0% (the number of individuals was 500).3) It is advisable to use the probabilities of the mutation and crossover operator 100% and 100%, respectively. Discussion and Conclusions. Recommendations are given to improve the efficiency of covering problem solution. To this end, a preferred combination of the genetic algorithm parameters, of types of crossover and mutation operators is indicated.

Download Full-text

Advances in data-driven analyses and modelling using EPR-MOGA

Journal of Hydroinformatics ◽

10.2166/hydro.2009.017 ◽

2009 ◽

Vol 11 (3-4) ◽

pp. 225-236 ◽

Cited By ~ 98

Author(s):

O. Giustolisi ◽

D. A. Savic

Keyword(s):

Genetic Algorithm ◽

Polynomial Regression ◽

Variable Number ◽

Sequential Search ◽

Multi Objective ◽

Polynomial Coefficients ◽

Evolutionary Polynomial Regression ◽

Multi Objective Genetic Algorithm ◽

Regression Techniques

Evolutionary Polynomial Regression (EPR) is a recently developed hybrid regression method that combines the best features of conventional numerical regression techniques with the genetic programming/symbolic regression technique. The original version of EPR works with formulae based on true or pseudo-polynomial expressions using a single-objective genetic algorithm. Therefore, to obtain a set of formulae with a variable number of pseudo-polynomial coefficients, the sequential search is performed in the formulae space. This article presents an improved EPR strategy that uses a multi-objective genetic algorithm instead. We demonstrate that multi-objective approach is a more feasible instrument for data analysis and model selection. Moreover, we show that EPR can also allow for simple uncertainty analysis (since it returns polynomial structures that are linear with respect to the estimated coefficients). The methodology is tested and the results are reported in a case study relating groundwater level predictions to total monthly rainfall.

Download Full-text

On the issue of fuzzy timing estimations of the algorithms running at GPU and CPU architectures

E3S Web of Conferences ◽

10.1051/e3sconf/201913501082 ◽

2019 ◽

Vol 135 ◽

pp. 01082 ◽

Cited By ~ 1

Author(s):

Oleg Agibalov ◽

Nikolay Ventsov

Keyword(s):

Genetic Algorithm ◽

Genetic Algorithms ◽

Graphics Processing Unit ◽

Processing Unit ◽

Running Time ◽

Average Value ◽

Central Processing ◽

Graphics Processing ◽

Number Of Individuals ◽

Gpu Architecture

We consider the task of comparing fuzzy estimates of the execution parameters of genetic algorithms implemented at GPU (graphics processing unit’ GPU) and CPU (central processing unit) architectures. Fuzzy estimates are calculated based on the averaged dependencies of the genetic algorithms running time at GPU and CPU architectures from the number of individuals in the populations processed by the algorithm. The analysis of the averaged dependences of the genetic algorithms running time at GPU and CPU-architectures showed that it is possible to process 10’000 chromosomes at GPU-architecture or 5’000 chromosomes at CPUarchitecture by genetic algorithm in approximately 2’500 ms. The following is correct for the cases under consideration: “Genetic algorithms (GA) are performed in approximately 2, 500 ms (on average), ” and a sections of fuzzy sets, with a = 0.5, correspond to the intervals [2, 000.2399] for GA performed at the GPU-architecture, and [1, 400.1799] for GA performed at the CPU-architecture. Thereby, it can be said that in this case, the actual execution time of the algorithm at the GPU architecture deviates in a lesser extent from the average value than at the CPU.

Download Full-text