Roulette Wheel Selection Research Articles

Performance Comparison of Roulette WheelSelection and Steady state Selection in GeneticNucleotide Sequence

In this paper the attempt has been made analyse the performance comparison of nucleotide sequence in DNA cells. The basic idea behind this proposed method is estimate the efficiency of roulette wheel selection and steady state selection with respect to memory and running time. Here this algorithm is applied to find the genetic operator such as mutation, crossover and selection in large dataset. In order to evaluate the proposed methodology, Comparisons are made based on the Execution time and memory efficiency in finding best fitness value in each generations and their distance estimation between each generations.. The extracted rules and analysed results are graphically demonstrated. The performance is analysed based on the different no of instances and confidence in DNA sequence data set. In genetic algorithms, the roulette wheel selection operator has spirit of utilization while steady state selection is influenced by exploration. The proposed solution is implemented in MATLAB using DNA Nucleotide Sequence of Cancer cells and the results were compared with roulette wheel selection and steady state selection with different problem sizes.

Genetic algorithm-based counter-flooding decision model for damaged warship

A good counter-flooding strategy is vital to the decision maker in case of emergency, but how to evaluate the scheme is still lack of a definite function. To establish a definite evaluation standard, this paper presents a counter-flooding decision model for scheme evaluation and decision support in shipboard flooding emergency. It adopts genetic algorithm to solve the proposed optimization model, which involves the combination of counter-flooding tanks that should be filled or evacuation in order to achieve an optimal response to a flooding accident. The genetic algorithm is developed with roulette wheel selection, one-point crossover, mutation, and iterative process continues until terminating condition is encountered. The stopping criterion proposed in this paper is the tilt angle, also the heeling angle is another terminate rule. The computational results validate the effectiveness of proposed optimization model and genetic algorithm.

A fixed-charge transportation problem in two-stage supply chain network in Gaussian type-2 fuzzy environments

This paper presents two mathematical models representing imprecise capacitated fixed-charge transportation problems for a two-stage supply chain network in Gaussian fuzzy type-2 environment. It is a two-stage transportation process from a manufacturing center to m potential distribution centers (DCs) and then from DCs to business centers of n retailers with particular demands. Retailers are situated at some distances apart. Here unit transportation costs, fixed charges, availabilities, and demands are imprecise and represented by Gaussian type-2 fuzzy numbers. The proposed models are formulated as profit maximization problems in such a way that some DCs are selected in order to satisfy the demands at all retailers. The type-2 fuzziness has been removed by using generalized credibility measure developed with the help of CV-based reduction method and hence the models are reduced to chance constrained programming problems with different credibility labels. The deterministic models are then solved using both genetic algorithm (GA) based on Roulette wheel selection, arithmetic crossover with uniform mutation and modified particle swarm optimization (PSO), where the position of each particle is adjusted according to its own experience and that of its neighbors. Finally models are illustrated with some numerical data. Some sensitivity analyses on the proposed models are presented.

Optimal Tuning of PI Controller for Full-Order Flux Observer of Induction Motor Using the Immune Genetic Algorithm

This paper presents a new method to tune the parameters of the adaptation PI controller of full-order flux observer. The method employs an Immune Genetic Algorithm (IGA) based optimization routine that can be implemented off-line. A novel fitness function is designed to assess both the estimation accuracy and the noise sensitivity of the rotor speed estimation system when each antibodys parameters are employed. The diversity of population is guaranteed by the evaluating of the antibody similarities function. The Roulette-wheel selection is used to choose the parents and large mutation probability is adopted to prevent the evolution from prematurity. The simulation results verify that the IGA has better performance in convergence speed and computation efficiency compared to the traditional GA.

Chaotic logic gate: A new approach in set and design by genetic algorithm

How to reconfigure a logic gate is an attractive subject for different applications. Chaotic systems can yield a wide variety of patterns and here we use this feature to produce a logic gate. This feature forms the basis for designing a dynamical computing device that can be rapidly reconfigured to become any wanted logical operator. This logic gate that can reconfigure to any logical operator when placed in its chaotic state is called chaotic logic gate. The reconfiguration realize by setting the parameter values of chaotic logic gate. In this paper we present mechanisms about how to produce a logic gate based on the logistic map in its chaotic state and genetic algorithm is used to set the parameter values. We use three well-known selection methods used in genetic algorithm: tournament selection, Roulette wheel selection and random selection. The results show the tournament selection method is the best method for set the parameter values. Further, genetic algorithm is a powerful tool to set the parameter values of chaotic logic gate.

A Paper on Multiple Objective Functions of Genetic Algorithm

or preparing Multi-objective formulations are a realistic models for many complex engineering, AI, mathematical and optimization problems etc. Customized genetic algorithms have been expressed as effective to determine best solutions to these problems. In many real-life problems, there are many conflicts to each other towards objective, and mainly by taking single objective to optimizing a particular solution can give unacceptable result with respective to other objective. An inevitable features of Genetic Algorithm are to generate set of solutions for multi objective problem with satisfying objective at acceptance level without dominating to any other solution. Genetic Algorithm is used in maximization as well as minimization of function. This paper tried to show an overview and tutorial is presented how Genetic Algorithm is best to solve the maximization of function for given function. This feature make Genetic Algorithm very unique from traditional genetic algorithms. Roulette-Wheel selection method is adopted to calculate fitness function and other functions. KeywordsAlgorithm, optimization and its techniques, Multi- objective functions, conclusion.

English

English

Fuzzy Goal Programming Approach to Solve Linear Multilevel Programming Problems using Genetic Algorithm

paper introduces a priority based fuzzy goal programming (FGP) method for modelling and solving multilevel programming problem (MLPP) through genetic algorithm (GA). In model formulation, the individual best solution of objectives of each of the decision makers (DMs) is determined by using the GA method for fuzzy description of the objectives. Then, tolerance membership functions of the defined fuzzy goals are constructed for measuring the degree of satisfaction of goal achievement and there by degree of optimality of the decision vectors controlled by the higher level DMs. In the executable FGP model, minimization of the under-deviational variables of the defined membership goals with highest membership value (unity) as the aspiration levels of them on the basis of pre- emptive priority is taken into consideration in the decision making context. In the solution process, sensitivity analysis with variations of priority structure of model goals is performed and then Euclidean distance function is used to identify the appropriate priority structure under which the most satisfactory decision can be reached in the decision making horizon. In the proposed GA scheme, roulette-wheel selection scheme, single point crossover and uniform mutation are adopted in the decision search process with regard to reach a satisfactory solution in the proposed hierarchical decision system. The effective use of the proposed approach is illustrated through a numerical example. Performance comparisons are also made to highlight the superiority of the proposed approach over the approaches studied previously.

A Modified Genetic Algorithm for solving uncertain Constrained Solid Travelling Salesman Problems

In this paper, a Modified Genetic Algorithm (MGA) is developed to solve Constrained Solid Travelling Salesman Problems (CSTSPs) in crisp, fuzzy, random, random-fuzzy, fuzzy-random and bi-random environments. In the proposed MGA, for the first time, a new ‘probabilistic selection’ technique and a ‘comparison crossover’ are used along with conventional random mutation. A Solid Travelling Salesman Problem (STSP) is a Travelling Salesman Problem (TSP) in which, at each station, there are a number of conveyances available to travel to another station. Thus STSP is a generalization of classical TSP and CSTSP is a STSP with constraints. In CSTSP, along each route, there may be some risk/discomfort in reaching the destination and the salesman desires to have the total risk/discomfort for the entire tour less than a desired value. Here we model the CSTSP with traveling costs and route risk/discomfort factors as crisp, fuzzy, random, random-fuzzy, fuzzy-random and bi-random in nature. A number of benchmark problems from standard data set, TSPLIB are tested against the existing Genetic Algorithm (with Roulette Wheel Selection (RWS), cyclic crossover and random mutation) and the proposed algorithm and hence the efficiency of the new algorithm is established. In this paper, CSTSPs are illustrated numerically by some empirical data using this algorithm. In each environment, some sensitivity studies due to different risk/discomfort factors and other system parameters are presented.

Research on X band extended cosecant squared beam synthesis of micro-strip antenna arrays using genetic algorithm

Synthesis of desired radiation patterns without an optimization algorithm is usually time consuming and inefficient. To achieve a desired radiation pattern such as cosecant squared beam and contoured beam, different evolutionary algorithms such as genetic algorithm (GA), particle swarm optimization algorithm, and invasive weed optimization algorithm have been used to find the excitation of radiation elements. Adaptive genetic algorithm (AGA) optimizer is a robust, stochastic search method, modeled on the principles and concepts of natural selection and evolution. As an optimizer, the powerful heuristic of the AGA is effective for solving complex and related problems. An improved AGA is proposed, in allusion to the characteristics of optimizing designs of antenna arrays which have many parameters and complicated structures. This algorithm constructs an adjustble formula to produce the crossover rate and mutation rate based on a logistic curve equation. In the way of combining roulette wheel selection and elitist strategy, this algorithm searches for the optimal solution in the global space, and is compared with the classical GA; the improved AGA has a better performance in seeking the solution. Taking the mutual coupling between the elements into account, we design the X band extended cosecant squared beam micro-strip antenna arrays based on the improved AGA. Specifications of the antenna are as follows:a -3 dB beam width in height is from 0° to 12°, a -10 dB beam width in height is from 12° to 65°, and a total height coverage is 65°; a frequency band ranges from 8.5 to 9.8 GHz and its center frequency is 9.05 GHz. Simulation results show that the fitness increases from 0.07 to 0.09, and the quality of the synthesized radiation pattern has a great improvement, which verifies the superiority of the improved AGA proposed in this paper. In addition, the prospect of the designed antenna which has an extended cosecant squared beam is promising in air-surveillance radar systems, where the radiation pattern of the antenna will compensate for the free-space loss.

REVERSED ROULETTE WHEEL SELECTION ALGORITHMS (RWSA) AND REINFORCEMENT LEARNING (RL) FOR PERSONALIZING AND IMPROVING E-LEARNING SYSTEM: THE CASE STUDY AND ITS IMPLEMENTATION

Various mechanisms to improve learning process with the objective of maximizing learning and dynamically selecting the best teaching operation to achieve learning goals have been done in the field of personalized learning. However, instructional strategists have failed to address the necessary corrective measures to remediate immediately learning difficulties. It is necessary that an alternative, more realistic, simpler and a real time multi-based performance for personalized learning sequence be developed and implemented. Three major contributions can be asserted by the study: it personalized the learning sequence using reversed roulette wheel selection algorithm and linear ranking; the fitness value is based on real time, multi-based performance system; and it implements the reinforcement and mastery learning to motivate students and to improve their learning output. Result shows that the personalized learning sequence (PLS) were dynamic and heuristic and considers the curriculum difficulty level and the curriculum continuity of successive curriculum while producing individualized and personalized learning sequence. Data collected during 18 weeks experimental sessions, from 34%, a 54% increased has been achieved, making the overall passing rate to 88%. Digital transcripts based on students’ perceptions and experiences in using the prototype positively correlates with theme analysis having a score of +.321 with positive attitude such as: very happy, friends, motivate, improve, understanding, knowledge and good were extracted from document analysis.

A modified genetic algorithm with fuzzy roulette wheel selection for job-shop scheduling problems

The job-shop scheduling problem is one of the most difficult production planning problems. Since it is in the NP-hard class, a recent trend in solving the job-shop scheduling problem is shifting towards the use of heuristic and metaheuristic algorithms. This paper proposes a novel metaheuristic algorithm, which is a modification of the genetic algorithm. This proposed algorithm introduces two new concepts to the standard genetic algorithm: (1) fuzzy roulette wheel selection and (2) the mutation operation with tabu list. The proposed algorithm has been evaluated and compared with several state-of-the-art algorithms in the literature. The experimental results on 53 JSSPs show that the proposed algorithm is very effective in solving the combinatorial optimization problems. It outperforms all state-of-the-art algorithms on all benchmark problems in terms of the ability to achieve the optimal solution and the computational time.

Applied Genetic Algorithm for Solving Rich VRP

In this article, we present a study of the effectiveness of a genetic algorithm (GA) to solve a combinatorial problem, that is, a vehicle routing problem (VRP). We propose a new selection method, called “rank and select,” based on selection rate, and we compare it with roulette wheel selection. In this article, we use two types of crossover method and two types of mutation method. These are applied for comparing the best fitness at the end of a generation. The problem solved in this study is how to generate feasible route combinations for a rich VRP and meet all the requirements with an optimum solution. Initial test results show that the route produced by the GA was effectively used for solving rich VRP and especially for a large number of customers, depots, and vehicles. Fuel consumption by proposed routes was lower by about 20.38% compared to that of an existing route.

Controlling maximum evaluation duration in on-line and on-board evolutionary robotics

On-line evolution of robot controllers allows robots to adapt while they perform their proper tasks. In our investigations, robots contain their own self-sufficient evolutionary algorithm (known as the encapsulated approach) where individual solutions are evaluated by means of a time sharing scheme: an individual controller is given the run of the robot for some amount of time and fitness corresponds to the robot’s task performance during that period. In this paper, we propose and provide a detailed analysis of two on-the-fly control schemes to set the evaluation time in highly dynamic scenarios with completely different tasks. One scheme, called the roulette-wheel selection scheme, stochastically selects evaluation time from promising intervals similar to multi-armed bandit schemes. The other scheme, named Heuristic-Rule (H-Rule), tweaks the evaluation time using specific heuristics. Our experiments show that H-Rule gives stable performance in different scenarios and can serve as a viable alternative to pre-selected optimal evaluation time.

Study on the Soft Time Windows Vehicle Synthesis Algorithm Based on Genetic

This paper designed a mathematical model of vehicle synthetising and proposed a solution to solve the vehicle carpool problem by using genetic algorithm. The solution encoded the nodes of station and start, end point. Arranged randomly to generate multiple chromosome, initial population and calculate the fitness value obtained from the objective function by the matching node of each vehicle. Generated a new individual by mutation and crossover through Roulette Wheel Selection method.Repeat the above operation to reach the maximun number of iteration and got the optimal solution path. The experimental result shows that the algorithm is valid.

Hybrid bee colony optimization for examination timetabling problems

Swarm intelligence is a branch of artificial intelligence that focuses on the actions of agents in self-organized systems. Researchers have proposed a bee colony optimization (BCO) algorithm as part of swarm intelligence. BCO is a meta-heuristic algorithm based on the foraging behavior of bees. This study presents a hybrid BCO algorithm for examination timetabling problems. Bees in the BCO algorithm perform two main actions: forward pass and backward pass. Each bee explores the search space in forward pass and then shares information with other bees in the hive in backward pass. This study found that a bee decides to be either a recruiter that searches for a food source or a follower that selects a recruiter bee to follow on the basis of roulette wheel selection. In forward pass, BCO is supported along with other local searches, including the Late Acceptance Hill Climbing and Simulated Annealing algorithms. We introduce three selection strategies (tournament, rank and disruptive selection strategies) for the follower bees to select a recruiter to maintain population diversity in backward pass. The disruptive selection strategy outperforms tournament and rank selections. We also introduce a self-adaptive mechanism to select a neighborhood structure to enhance the neighborhood search. The proposed algorithm is evaluated against the latest methodologies in the literature with respect to two standard examination timetabling problems, namely, uncapacitated and competition datasets. We demonstrate that the proposed algorithm produces one new best result on uncapacitated datasets and comparable results on competition datasets.

A self-adaptive genetic algorithm to estimate JA model parameters considering minor loops

Abstract A self-adaptive genetic algorithm for estimating Jiles–Atherton (JA) magnetic hysteresis model parameters is presented. The fitness function is established based on the distances between equidistant key points of normalized hysteresis loops. Linearity function and logarithm function are both adopted to code the five parameters of JA model. Roulette wheel selection is used and the selection pressure is adjusted adaptively by deducting a proportional which depends on current generation common value. The Crossover operator is established by combining arithmetic crossover and multipoint crossover. Nonuniform mutation is improved by adjusting the mutation ratio adaptively. The algorithm is used to estimate the parameters of one kind of silicon-steel sheet’s hysteresis loops, and the results are in good agreement with published data.

Process Sequencing Modeled as TSP with Precedence Constraints – A Genetic Algorithm Approach

This study addresses process sequencing subject to precedence constraints which arises as a sub-problem in scheduling, planning and routing problems. The process sequencing problem can be modeled as the travelling salesman problem with precedence constraints (TSPPC). In this study a new genetic algorithm (GA) procedure is developed which includes chromosome’s repairing strategy based topological sort to handle the precedence constraints and to generate only feasible solution during the evolutionary process. The procedure to select the task in sequence is based on “earliest position” techniques. This procedure is combined with roulette wheel selection, linear order crossover and inversion mutation. The effectiveness and the stability of the proposed GA are then evaluated against benchmark problems and the solutions are compared with the results obtained from research results published in the relevant literature. The developed GA procedure improved the performance of the algorithm with less number of generations and less convergence time in achieving optimal solutions. This result will greatly help to solve many real world sequencing problems especially in the field of assembly line design and management.

A modified Intelligent Water Drops algorithm and its application to optimization problems

The Intelligent Water Drop (IWD) algorithm is a recent stochastic swarm-based method that is useful for solving combinatorial and function optimization problems. In this paper, we investigate the effectiveness of the selection method in the solution construction phase of the IWD algorithm. Instead of the fitness proportionate selection method in the original IWD algorithm, two ranking-based selection methods, namely linear ranking and exponential ranking, are proposed. Both ranking-based selection methods aim to solve the identified limitations of the fitness proportionate selection method as well as to enable the IWD algorithm to escape from local optima and ensure its search diversity. To evaluate the usefulness of the proposed ranking-based selection methods, a series of experiments pertaining to three combinatorial optimization problems, i.e., rough set feature subset selection, multiple knapsack and travelling salesman problems, is conducted. The results demonstrate that the exponential ranking selection method is able to preserve the search diversity, therefore improving the performance of the IWD algorithm.

A modified genetic algorithm for UAV trajectory tracking control laws optimization

Purpose – The purpose of this paper is to gain trajectory-tracking controllers for autonomous aircraft are optimized using a modified evolutionary, or genetic algorithm (GA). Design/methodology/approach – The GA design utilizes real representation for the individual consisting of the collection of all controller gains subject to tuning. The initial population is generated randomly over pre-specified ranges. Alternatively, initial individuals are produced as random variations from a heuristically tuned set of gains to increase convergence time. A two-point crossover mechanism and a probabilistic mutation mechanism represent the genetic alterations performed on the population. The environment is represented by a performance index (PI) composed of a set of metrics based on tracking error and control activity in response to a commanded trajectory. Roulette-wheel selection with elitist strategy are implemented. A PI normalization scheme is also implemented to increase the speed of convergence. A flexible control laws design environment is developed, which can be used to easily optimize the gains for a variety of unmanned aerial vehicle (UAV) control laws architectures. Findings – The performance of the aircraft trajectory-tracking controllers was shown to improve significantly through the GA optimization. Additionally, the novel normalization modification was shown to encourage more rapid convergence to an optimal solution. Research limitations/implications – The GA paradigm shows much promise in the optimization of highly non-linear aircraft trajectory-tracking controllers. The proposed optimization tool facilitates the investigation of novel control architectures regardless of complexity and dimensionality. Practical implications – The addition of the evolutionary optimization to the WVU UAV simulation environment enhances significantly its capabilities for autonomous flight algorithm development, testing, and evaluation. The normalization methodology proposed in this paper has been shown to appreciably speed up the convergence of GAs. Originality/value – The paper provides a flexible generalized framework for UAV control system evolutionary optimization. It includes specific novel structural elements and mechanisms for improved convergence as well as a comprehensive PI for trajectory tracking.