On Measuring the Attributes of Evolutionary Algorithms

2011 ◽  
pp. 281-302
Author(s):  
J.-L. Fernandez-Villacanas Martin ◽  
P. Marrow ◽  
M. Shackleton
Keyword(s):  
Genetic Algorithm ◽  
Information Retrieval ◽  
Evolutionary Algorithms ◽  
Genetic Programming ◽  
Selection Process ◽  
Relative Effectiveness ◽  
Evolutionary Process ◽  
Neutral Evolution ◽  
Adaptive Landscape ◽  
The Future

In this chapter we compare the performance of two contrasting evolutionary algorithms addressing a similar problem, of information retrieval. The first, BTGP, is based upon genetic programming, while the second, MGA, is a genetic algorithm. We analyze the performance of these evolutionary algorithms through aspects of the evolutionary process they undergo while filtering information. We measure aspects of the variation existing in the population undergoing evolution, as well as properties of the selection process. We also measure properties of the adaptive landscape in each algorithm, and quantify the importance of neutral evolution for each algorithm. We choose measures of these properties because they appear generally important in evolution. Our results indicate why each algorithm is effective at information retrieval, however they do not provide a means of quantifying the relative effectiveness of each algorithm. We attribute this difficulty to the lack of appropriate measures available to measure properties of evolutionary algorithms, and suggest some criteria for useful evolutionary measures to be developed in the future.

On Measuring the Attributes of Evolutionary Algorithms

2011 ◽  
pp. 332-348
Author(s):  
J. L. Fernandez-Villacanas Martin ◽  
P. Marrow ◽  
M. Shackleton
Keyword(s):  
Genetic Algorithm ◽  
Information Retrieval ◽  
Evolutionary Algorithms ◽  
Genetic Programming ◽  
Selection Process ◽  
Relative Effectiveness ◽  
Evolutionary Process ◽  
Neutral Evolution ◽  
Adaptive Landscape ◽  
The Future

In this chapter we compare the performance of two contrasting evolutionary algorithms addressing a similar problem, of information retrieval. The first, BTGP, is based upon genetic programming, while the second, MGA, is a genetic algorithm. We analyze the performance of these evolutionary algorithms through aspects of the evolutionary process they undergo while filtering information. We measure aspects of the variation existing in the population undergoing evolution, as well as properties of the selection process. We also measure properties of the adaptive landscape in each algorithm, and quantify the importance of neutral evolution for each algorithm. We choose measures of these properties because they appear generally important in evolution. Our results indicate why each algorithm is effective at information retrieval, however they do not provide a means of quantifying the relative effectiveness of each algorithm. We attribute this difficulty to the lack of appropriate measures available to measure properties of evolutionary algorithms, and suggest some criteria for useful evolutionary measures to be developed in the future.

Case Study

2019 ◽  
pp. 299-311
Author(s):  
Amit Verma ◽  
Iqbaldeep Kaur ◽  
Dolly Sharma ◽  
Inderjeet Singh
Keyword(s):  
Genetic Algorithm ◽  
Information Retrieval ◽  
Selection Process ◽  
Limiting Factors ◽  
Recruitment Process ◽  
Software Environment ◽  
Major Application ◽  
Limiting Values ◽  
Taking Care

Recruitment process takes place based on needed data while certain limiting factors are ignored. The objective of the chapter is to recruit best employees while taking care of limiting factors from the cluster for resource management and scheduling. Various parameters of the recruits have been selected to find the maximum score achieved by them. Recruitment process makes a database as cluster in the software environment perform the information retrieval on the database and then perform data mining using genetic algorithm while taking care of the positive values in contrast to limiting values received from the database. A bigger level recruitment process finds required values of a person, so negative points are ignored earlier in the recruitment process because there is no direct way to compare them. Genetic algorithm will create output in the form of chromosomal form. Again, apply information retrieval to get actual output. Major application of this process is that it will improve the selection process of candidates to a higher level of perfection in less time.

scholarly journals Optimalisasi Penyelesaian Knapsack Problem Dengan Algoritma Genetika

2016 ◽  
pp. 182
Author(s):  
I Wayan Supriana
Keyword(s):  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Everyday Life ◽  
Knapsack Problem ◽  
Selection Process ◽  
Optimization Algorithms ◽  
Evolutionary Process ◽  
Knapsack Problems ◽  
Theory Of Evolution ◽  
Selection Of

Knapsack problems is a problem that often we encounter in everyday life. Knapsack problem itself is a problem where a person faced with the problems of optimization on the selection of objects that can be inserted into the container which has limited space or capacity. Problems knapsack problem can be solved by various optimization algorithms, one of which uses a genetic algorithm. Genetic algorithms in solving problems mimicking the theory of evolution of living creatures. The components of the genetic algorithm is composed of a population consisting of a collection of individuals who are candidates for the solution of problems knapsack. The process of evolution goes dimulasi of the selection process, crossovers and mutations in each individual in order to obtain a new population. The evolutionary process will be repeated until it meets the criteria o f an optimum of the resulting solution. The problems highlighted in this research is how to resolve the problem by applying a genetic algorithm knapsack. The results obtained by the testing of the system is built, that the knapsack problem can optimize the placement of goods in containers or capacity available. Optimizing the knapsack problem can be maximized with the appropriate input parameters.

scholarly journals RankGPES: learning to rank for information retrieval using a hybrid genetic programming with evolutionary strategies

2021 ◽  
Author(s):  
Mohammad A. Islam
Keyword(s):  
Information Retrieval ◽  
Evolutionary Algorithms ◽  
Genetic Programming ◽  
Large Volume ◽  
Learning To Rank ◽  
Hybrid Approach ◽  
Industrial Applications ◽  
Evolutionary Strategies ◽  
Optimal Result ◽  
Approach To Learning

In recent years, Learning to Rank has not only shown effectiveness and better suitability for modern Web Era needs, but also has proved that it outperforms traditional ranking in terms of accuracy and efficiency. Evolutionary approach to Learning to Rank such as RankGP [37] and RankDE [3] have shown further improvement over non-evolutionary algorithms. However when Evolutionary algorithms have been applied to a large volume of data, often they showed they required so much computational efforts that they were not worth applying to industrial applications. In this thesis, we present RankGPES: a Learning to Rank algorithm based on a hybrid approach combining Genetic Programming with Evolution Strategies. Our results not only showed that it outperformed both RankGP [37] by 20% and RankDE [3] by 6% in terms of accuracy but also it showed it required significant less amount of time to converge to a near-optimal result.

CHAOS SYNTHESIS BY MEANS OF EVOLUTIONARY ALGORITHMS

2008 ◽  
Vol 18 (04) ◽  
pp. 911-942 ◽  
Author(s):  
IVAN ZELINKA ◽  
GUANRONG CHEN ◽  
SERGEJ CELIKOVSKY
Keyword(s):  
Genetic Algorithm ◽  
Evolutionary Algorithms ◽  
Genetic Programming ◽  
Differential Evolution ◽  
Cost Function ◽  
Case Studies ◽  
Chaotic System ◽  
Chaotic Systems ◽  
Reliability And Robustness ◽  
Eleven Case

This paper introduces the notion of chaos synthesis by means of evolutionary algorithms and develops a new method for chaotic systems synthesis. This method is similar to genetic programming and grammatical evolution and is being applied along with three evolutionary algorithms: differential evolution, self-organizing migration and genetic algorithm. The aim of this investigation is to synthesize new and "simple" chaotic systems based on some elements contained in a prechosen existing chaotic system and a properly defined cost function. The investigation consists of eleven case studies: the aforementioned three evolutionary algorithms in eleven versions. For all algorithms, 100 simulations of chaos synthesis were repeated and then averaged to guarantee the reliability and robustness of the proposed method. The most significant results were carefully selected, visualized and commented in this report.

scholarly journals RankGPES: learning to rank for information retrieval using a hybrid genetic programming with evolutionary strategies

2021 ◽  
Author(s):  
Mohammad A. Islam
Keyword(s):  
Information Retrieval ◽  
Evolutionary Algorithms ◽  
Genetic Programming ◽  
Large Volume ◽  
Learning To Rank ◽  
Hybrid Approach ◽  
Industrial Applications ◽  
Evolutionary Strategies ◽  
Optimal Result ◽  
Approach To Learning

In recent years, Learning to Rank has not only shown effectiveness and better suitability for modern Web Era needs, but also has proved that it outperforms traditional ranking in terms of accuracy and efficiency. Evolutionary approach to Learning to Rank such as RankGP [37] and RankDE [3] have shown further improvement over non-evolutionary algorithms. However when Evolutionary algorithms have been applied to a large volume of data, often they showed they required so much computational efforts that they were not worth applying to industrial applications. In this thesis, we present RankGPES: a Learning to Rank algorithm based on a hybrid approach combining Genetic Programming with Evolution Strategies. Our results not only showed that it outperformed both RankGP [37] by 20% and RankDE [3] by 6% in terms of accuracy but also it showed it required significant less amount of time to converge to a near-optimal result.

Human-competitive evolved antennas

2008 ◽  
Vol 22 (3) ◽  
pp. 235-247 ◽  
Author(s):  
Jason D. Lohn ◽  
Gregory S. Hornby ◽  
Derek S. Linden
Keyword(s):  
Genetic Algorithm ◽  
Evolutionary Algorithms ◽  
Genetic Programming ◽  
Development Process ◽  
Space Technology ◽  
Circularly Polarized ◽  
Similar Performance ◽  
Traditional Design ◽  
Structured Representation

AbstractWe present a case study showing a human-competitive design of an evolved antenna that was deployed on a NASA spacecraft in 2006. We were fortunate to develop our antennas in parallel with another group using traditional design methodologies. This allowed us to demonstrate that our techniques were human-competitive because our automatically designed antenna could be directly compared to a human-designed antenna. The antennas described below were evolved to meet a challenging set of mission requirements, most notably the combination of wide beamwidth for a circularly polarized wave and wide bandwidth. Two evolutionary algorithms were used in the development process: one used a genetic algorithm style representation that did not allow branching in the antenna arms; the second used a genetic programming style tree-structured representation that allowed branching in the antenna arms. The highest performance antennas from both algorithms were fabricated and tested, and both yielded very similar performance. Both antennas were comparable in performance to a hand-designed antenna produced by the antenna contractor for the mission, and so we consider them examples of human-competitive performance by evolutionary algorithms. Our design was approved for flight, and three copies of it were successfully flown on NASA's Space Technology 5 mission between March 22 and June 30, 2006. These evolved antennas represent the first evolved hardware in space and the first evolved antennas to be deployed.

scholarly journals An Improved MOEA/D Based on Reference Distance for Software Project Portfolio Optimization

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-16 ◽  
Author(s):  
Jing Xiao ◽  
Jing-Jing Li ◽  
Xi-Xi Hong ◽  
Min-Mei Huang ◽  
Xiao-Min Hu ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Evolutionary Algorithms ◽  
Portfolio Optimization ◽  
Optimization Problem ◽  
Experimental Comparison ◽  
Software Project ◽  
Project Portfolio ◽  
Multiobjective Evolutionary Algorithms ◽  
Reference Distance ◽  
Nondominated Sorting

As it is becoming extremely competitive in software industry, large software companies have to select their project portfolio to gain maximum return with limited resources under many constraints. Project portfolio optimization using multiobjective evolutionary algorithms is promising because they can provide solutions on the Pareto-optimal front that are difficult to be obtained by manual approaches. In this paper, we propose an improved MOEA/D (multiobjective evolutionary algorithm based on decomposition) based on reference distance (MOEA/D_RD) to solve the software project portfolio optimization problems with optimizing 2, 3, and 4 objectives. MOEA/D_RD replaces solutions based on reference distance during evolution process. Experimental comparison and analysis are performed among MOEA/D_RD and several state-of-the-art multiobjective evolutionary algorithms, that is, MOEA/D, nondominated sorting genetic algorithm II (NSGA2), and nondominated sorting genetic algorithm III (NSGA3). The results show that MOEA/D_RD and NSGA2 can solve the software project portfolio optimization problem more effectively. For 4-objective optimization problem, MOEA/D_RD is the most efficient algorithm compared with MOEA/D, NSGA2, and NSGA3 in terms of coverage, distribution, and stability of solutions.

An efficient intelligent decision method for bionic motion unmanned system

2021 ◽  
pp. 095965182110655
Author(s):  
Haipeng Chen ◽  
Wenxing Fu ◽  
Yuze Feng ◽  
Jia Long ◽  
Kang Chen
Keyword(s):  
Genetic Algorithm ◽  
Evolutionary Algorithms ◽  
Path Planning ◽  
Motion Control ◽  
Control Method ◽  
Improved Genetic Algorithm ◽  
Decision Method ◽  
Multiple Traveling Salesman Problem ◽  
Intelligent Decision ◽  
Unmanned System

In this article, we propose an efficient intelligent decision method for a bionic motion unmanned system to simulate the formation change during the hunting process of the wolves. Path planning is a burning research focus for the unmanned system to realize the formation change, and some traditional techniques are designed to solve it. The intelligent decision based on evolutionary algorithms is one of the famous path planning approaches. However, time consumption remains to be a problem in the intelligent decisions of the unmanned system. To solve the time-consuming problem, we simplify the multi-objective optimization as the single-objective optimization, which was regarded as a multiple traveling salesman problem in the traditional methods. Besides, we present the improved genetic algorithm instead of evolutionary algorithms to solve the intelligent decision problem. As the unmanned system’s intelligent decision is solved, the bionic motion control, especially collision avoidance when the system moves, should be guaranteed. Accordingly, we project a novel unmanned system bionic motion control of complex nonlinear dynamics. The control method can effectively avoid collision in the process of system motion. Simulation results show that the proposed simplification, improved genetic algorithm, and bionic motion control method are stable and effective.

Sign in / Sign up

Export Citation Format

Share Document