A GA Mechanism for Optimizing the Design of attribute-double-sampling-plan

Size: px
Start display at page:

Download "A GA Mechanism for Optimizing the Design of attribute-double-sampling-plan"

Transcription

1 A GA Mechanism for Optimizing the Design of attribute-double-sampling-plan Tao-ming Cheng *, Yen-liang Chen Department of Construction Engineering, Chaoyang University of Technology, Taiwan, R.O.C. Abstract An attribute double sampling plan can be performed when the acceptance parameters are known. These include first sample size, second sample size, first acceptance number, first rejectable number, and second acceptance number. The acceptance parameters must match the predefined probability 1-α of accepting a lot if the lot proportion defective is at the acceptable quality level (AQL) and β of accepting a lot if the lot proportion defective is at the rejectable quality level (RQL). In addition, the parameters must be all nonnegative integers and thus the system can not be solved as a closed-form solution. As a result, the trial-and-error method is usually used to seek the solutions. This paper presents a genetic-algorithms-based mechanism for facilitating the ADSP design process. Objectives of minimizing both the deviations of fitting AQL-α and RQL-β and the total sample sizes are traded off in the optimization process. Case studies show that the new mechanism can effectively locate the acceptance parameters and therefore facilitate the task of ADSP design. Keywords: attribute double sampling plan, genetic algorithms 1. Introduction An acceptance-sampling (AS) plan is a statement of the sample size to be used and the associated acceptance for sentencing an individual lot. There are different ways for classifying AS plans. One major classification is by variables and attributes. Variables are quality characteristics that are measured on a numerical scale and attributes are quality characteristics that are expressed on go and no-go basis. Performing variables sampling plan (VSP) requires basic statistical knowledge such as the calculation of standard deviation and the decision parameter as well as checking the quality index table. Contrast to VSP, attributes sampling plan (ASP) is easy to be used and does not involve statistical calculation for processing data. Construction inspectors usually do not have statistical background necessary for data processing in VSP [1]. * Corresponding author. Address: 168 Gifeng E. Rd., Wufeng, Taichung County 413, Taiwan, Tel.: Ext. 438; Fax: address: tmcheng@mail.cyut.edu.tw 1

2 Hence, an ASP plays an important role in designing quality assurance specifications in construction. ASP can be categorized as single or double sampling depending on the number of samples taken. In a single sampling plan, the decision to accept or reject a lot is made based on one sample. However, in a double sampling plan, a second sample may be required before a lot can be sentenced. A lot would be accepted or rejected depending on whether the first sample conforms to the specified requirements. Otherwise, the second sample has to be taken before a decision is made. Since the sampling phase is divided into tow stages, as a result, performing an attribute double sampling plan (ADSP) usually (not always) uses a smaller sample size and is commonly used in designing quality assurance specifications [, 3]. To properly design an ADSP, the users first have to focus on certain points on the operation characteristics (OC) curve which plots the probability of accepting the lot versus the lot fraction defective. These points include the AQL-α and RQL-β. AQL (acceptable quality level) represents the poorest level of quality for the producer s process that the consumer would consider to accept the product. RQL (rejectable quality level) would lead the consumer to reject the product. The probability of accepting a lot at the acceptable quality level (AQL) is 1-α and that of accepting a lot at the rejectable quality level (RQL) is β. After the AQL-α and RQL-β points being decided, a proper combination of acceptance parameters including first sample size (N1), second sample size (N), first acceptance number, first rejectable number, and second acceptance number, then can be selected to match these two points on OC curve. In addition, the binominal distribution is applied to develop the sampling equations for solving the acceptance parameters. However, the parameters must be all nonnegative integers and thus the system does not have a closed-form solution. As a result, the trial-and-error method is usually used to seek the solutions [3]. In order to reduce the number of examining the possible parameter combinations when trial-and-error method is employed, Duncan presented two tables for determining ADSP with α = 0.05, β = 0.10, and N1 = N or N [4]. Then, Chow et al. implemented Duncan s tables by developing a computer program [5]. In addition, Soundararajan and Vijayaraghavan introduced the procedures for constructing ADSP with α = 0.05 and β = 0.10 [6]. Moreover, Olorunniwo and Salas developed a computer program for facilitating the ADSP deign with any value of α and β but limited to N = kn1 where k is an integer [7]. Exhaustive search of possible acceptance parameter could be extremely timeconsuming. Moreover, infeasible solution can be obtained if the fitting of OC curve is strictly limited by both the AQL-α and RQL-β. Hence, a more efficient mechanism is needed for facilitating the design of ADSP process. In this study, the genetic algorithm is applied for optimizing the design process. Objectives of minimizing both the deviations of fitting AQL-α and RQL-β and the total sample sizes are traded off in the optimization process. Details of this new mechanism,

3 the theory of developing ADSP, and the computer implementation are provided in the following sections.. Attribute Double Sampling Plans This section first describes the flow of performing ADSP, then introduces the theory of ADSP in brief and depicts how to design DASP in details..1 Procedure of performing ADSP The flow of performing ADSP is shown in Fig. 1. The notations of the parameters used in Fig. 1 are described in Table 1. The procedure begins at taking a random sample of N1 from the lot and being inspected. If X1 C1, the lot is accepted on the first sample but if X1 R1, the lot is rejected. However, if X1 is greater than C1 but less than R1, then a second sample with N item has to be taken for further inspection of the lot s quality. If the sum of X1 and X is less than or equal to C, the lot is accepted on the second sample. Otherwise, the lot should be rejected. Table 1 Description of notations used in Fig. 1 Notation Description N1 sample size of the first sample N sample size of the second sample C1 acceptance number of the first sample R1 rejected number of the first sample C acceptance number for both samples X1 the number of observed defective in the first sample X the number of observed defective in the second sample Inspect a random of N1 from the lot X1 = number of observed defective X1 = C1 Yes Accept the lot No X1 = R1 Yes Reject the lot No No Yes Inspect a random sample of N from the lot X = number of observed defective X1+X = C Fig. 1 Procedure of performing an ADSP 3

4 . Theory of ADSP When a lot size is finite, the hypergeometric distribution should be used to describe the probability of the sampling. However, if the lot size is much larger than the sample size, the binomial distribution would be more appropriate to be used to calculate the probability of sampling. In construction quality inspection, many measurements can be taken and therefore, the lot size is usually considered as much larger than the sample size [1]. As a result, the binomial distribution is used to develop the ADSP in this study. Assume that the lot fraction defective is P d, and then the probability of X defectives out of a random sample of N items can be obtained by using binomial distribution as shown in Eq. (1). In other words, the acceptance probability of a lot can be calculated by employing this equation when the specific P d is known. P N! X!( N X )! X N X ( X ) = P d (1 P ) d (1) In the ADSP, the acceptance probability (denoted as P a ) of a lot is decided from the combined samples. If P a1 and P a denote the probability of acceptance on the first and second samples, respectively, then the P a is the sum of P a1 and P a as indicated in Eq. (). The way of calculating P a1 is straightforward. The lot will be accepted in the first sampling only in the condition that the defective items (X1) are less to or equal to acceptance number (C1). However, to calculate the probability of acceptance on the second sample, two conditions should be met sequentially. The first is that the lot is neither accepted nor rejected in the first sampling and the other is that the lot is accepted in the second sampling. The calculation of P a1 and P a are listed in Eqs. (3) and (4), respectively. P = P + P () a a1 a P a 1 P X1 C ( 1) = (3) R1 = 1 a = P i C1+ 1 ( X1 = i) P[ X ( C i) ] P (4) For instance, if the acceptance parameters (N1, N, C1, R1, C) equal to (50, 100,, 4, 5) and the Pd = 0.1, the calculation of Pa1 and Pa, together with Pa are demonstrated from Eqs. (5) to (7). P a 1 = P( X1 C1 = ) = P( X = 0) + P( X = 1) + P( X 50! 0 = (0.1) (0.9) 0!50! ! 1!49! (0.1) 1 (0.9) ! (0.1)!48! = ) (0.9) 48 = 11.17% (5) 4

5 P a = = 0.008% ( X1 = 3) P( X ) = P( X1 = 3) [ P( X = 0) + P( X = 1) + P( = ) ] = P X 50! 3 (0.1) (0.9) 3!47! ! (0.1) 0! 100! 0 (0.9) ! 1 + (0.1) (0.9) 1!99! ! + (0.1)!98! (0.9) 98 (6) P P + P = % % % (7) a = a1 a = The performance of an ADSP can be conveniently summarized by means of its operating characteristic (OC) curve. The OC curve is the curve that shows the acceptance probability of a lot based on the various quality levels. Fig. shows the OC curve for ADSP when N1=50, N=100, C1=, R1=4, C=5. It can be predicted that the lot will be accepted with the chance of 11.18% when the quality level of the lot is 10% defective with the specified requirement (i.e., AQL=10%) on OC curve. Probability of acceptance, Pa Lot fraction defective, Pd Fig. OC curve for an ADSP with N1=50, N=100, C1=, R1=4, C=5.3 Design of ADSP If the acceptance parameters (N1, N, C1, R1, C) are known, the probability of accepting a lot can be given in any required quality level, however, the way of designing ADSP is opposite. In designing an ADSP, first the AQL, RQL, and the risk levels of α and β have to be considered. Then a proper combination of acceptance parameters (N1, N, C1, R1, C) have to be found to fit the predefined AQL-α and RQL-β on OC curve. The relations between AQL-α and RQL-β and acceptance parameters (N1, N, C1, R1, C) are listed in Eqs. (8) and (9). R1 = i C1+ 1 ( 1 ) = P ( X1 C1) + P ( X1 = i) P [ X ( C i) ] α (8) 5

6 R1 = i C1+ 1 ( X1 C1) + P ( X1 = i) P [ X ( C i) ] β = P (9) where N1! X X ( N 1 X ) P1 ( X ) = AQL (1 AQL ) X!( N1 X )! (10) N! X X ( N X ) P ( X ) = AQL (1 AQL ) X!( N X )! (11) N 1! X X ( N 1 X ) P3 ( X ) = RQL (1 RQL ) X!( N 1 X )! (1) N! X X ( N X ) P4 ( X ) = RQL (1 RQL ) X!( N X )! (13) Since the acceptance parameters (N1, N, C1, R1, C) must be nonnegative integers, the system does not have a closed-form solution. As a result, the trial-and-error method is usually used to seek solutions. Trial-and-error method is not only time consuming in terms of computation effort but does not guarantee that the minimum sample size can be reached. Moreover, infeasible solution can be obtained if the fitting of OC curve is strictly limited by both the AQL-α and RQL-β. Hence, a more efficient mechanism is needed to facilitate the design of ADSP process. Genetic algorithms are suitable in solving the optimal problems when potential solutions are tremendously large or even are not obvious known. Thus, it is adopted in this study to build up the mechanism. 3. Genetic algorithms for optimizing ADSP 3.1 Background Genetic algorithms (GA) is the search algorithm developed by Holland [8], which is based on the mechanics of natural selection and genetics to search through decision space for optimal solutions. The metaphor underlying GA is natural selection. In evolution, the problem that each species faces is to search for beneficial adaptations to the complicated and changing environment. In other words, each species has to change its chromosome combination to survive in the living world. In GA, a string represents a set of decisions (chromosome combination), that is a potential solution to a problem. Each string is evaluated on its performance with respect to the fitness function (objective function). The ones with better performance (fitness value) are more likely to survive than the ones with worse performance. Then the genetic information is exchanged between strings by crossover and perturbed by mutation. The result is a new generation with (usually) better survival abilities. This process is repeated until the strings in the new generation are identical, or certain termination conditions are met. A generic flow of GA operation is given in Fig. 3. Readers can find more details of GAs in [9]. 6

7 Crossover Strings Encoding Initial Population Solution New Population Selection Roulette Wheel Mutation Evaluation Offspring Decoding Solution Fitness Computation Fig. 3 Generic procedure of GA operations [9] 3. Components and process This section introduces how GA is applied in the design of ADSP. Topics include chromosome structure, fitness value, mechanism of selection, crossover, and mutation, and termination condition Chromosome structure The chromosome structure used in this study is designed so that all permutations can be represented and evaluated. The length of the chromosome is defined as the total number of parameters. For example, as shown in Fig. 4, the two strings represent that (N1=5, N=10, C1=0, R1=1, C=1) and (N1=6, N=14, C1=0, R1=3, C=3), respectively. 7

8 P N1 N C1 R1 C P N1 N C1 R1 C Fig. 4 Chromosome structure 3.. Fitness value The purpose of using GA is to decide the acceptance parameters for the sake of minimizing the sample size in ADSP and, in addition, the resulted OC curve could meet the AQL-α and RQL-β requirements as much as possible. Two objectives of minimizing both total sample size and deviation of fitting α and β risk for specific lot fraction defective are considered in the optimization process. The Pareto front approach is usually used for solving multiobjective optimization problem is thus applied in this study [6]. Pareto front are a set of solutions for the multiobjective case which cannot simply be compared with each other. In other words, no improvement can be reached in any objective function without sacrificing at least one of the other objective functions for any Pareto solution which is a solution belonging to Pareto front. The functions representing the objectives of minimizing both the total sample size and deviation of fitting α and β risk for specific lot fraction defective are described in Eqs. (14) and (15). In addition, the fitness value is defined in Eq. (16). min Z 1 = N (14) ' ' min Z = 100α 100α + 100β 100β (15) where α ' and β ' are the calculated risks (which are contrast to α and β) with required AQL and RQL when particular acceptance parameters are generated. Fi = d max d i (16) where dmax: maximal distance between di in the generation (i.e., di=min(dij, for all j) dij: distance between parent i and each of the point j of the pareto front, where d ij = ( iz j ) ( 1 Z + i 1 Z j Z ) (see Fig. 5) 8

9 d = min ( d ) i j ij Z Parent i d ij Pareto front Pareto solution j Fig. 5 Evaluate fitness of member of population Z 1 The principle behind Eq. (16) is that the closer to Pareto front for each individual solution in a generation, the more fit. However, Pareto solutions are identified in each generation and thus, a Pareto solution in a generation may disappear in the next generation. In order to maintain a tendency that the new Pareto front always move toward to the coordinate axes, each solution at Pareto front in a generation will be kept for the next generation Selection The proportional selection is used to select the strings that have better fitness value in this study. According to the fitness value generated by the previous step, the selection probability can be determined by using Eq. (17). i i = Pop _ size P F i= 1 F i where P i : the selection probability of the parent i F i : the fitness value of string i Pop_size: The population size (17) 3..4 Crossover and mutation The one-point crossover mechanism is applied to the chromosomes used in this study. The process of the one-point crossover, shown in Fig. 6, is described as follows: At first, two parent strings, P1 and P, are selected randomly. Then one randomly chosen point is used as the separator that cuts the each selected parent string into two sections. 9

10 Combine section 1 of P1 to form the head of the first offspring (O1) and use section of P to form the tail of O1. In addition, the section 1 of P and the section of P1 are used as the head and the tail of the second offspring (O), respectively. Point cut Point cut P P Section 1 Section Section 1 Section O O Section 1 of P1 Section of P Section 1 of P Fig. 6 Example of the one-point crossover Section of P1 Self-mutation [6] is used in this study. If a chromosome is selected for mutation, one gene is randomly selected for changing their values by chance. An example of selfmutation is shown in Fig. 7. P is the selected chromosome and O is the chromosome after self-mutation. Mutation Point Mutation Point P P O O Fig. 7 Example of the self-mutation Termination condition The number of iterations is usually set as the termination criterion for stopping the evolution process while performing GA operation. Ideally, the final Pareto front obtained should move toward the coordinate axes as close as possible. Therefore, it will be more suitable to determine whether the final Pareto front is reached by checking if the area below Pareto front is decreased continuously. In this study, the convergence of evolution process will be examined by the rate of decreasing the area below Pareto front. 10

11 4. The computer program A user-friendly computer implementation named attribute-double-sampling-planoptimizer (ADSPO) is developed to facilitate the task of optimizing the design of ADSP and its interface is shown in Fig. 8. There are two areas requiring users to input data. The first area is the section of Sampling Parameters including AQL, RQL, α Risk, and β Risk, which contains the data related to design ADSP parameters. In addition, users can limit the generated total sample size not exceeding to their expectation through typing data in Upper limit of sample size. The second area is the section of GA parameters, which includes Population Size, Generation, Crossover Rate, and Mutation Rate. After the data needed for these two areas are entered, the ADSPO will be ready to optimize the design of ADSP. In addition, there are three areas that report the results generated by ADSPO. Population Status indicates the performance of GA operation. Moreover, the Pareto front obtained for current generation can be observed schematically in this area. Pareto front for Current Generation shows the detailed information for each Pareto solution of the current generation during the GA operation. The information includes the acceptance parameters (N1, N, C1, R1, C) and related α and β risk. Furthermore, Population for Current Generation lists all solutions generated in current generation. Fig. 8 Interface of ADSPO 11

12 5. Results Many tests have been done to verify the accuracy and efficiency of ADSPO. Three examples are presented in this paper. The test platform is a Pentium GHz PC with 51 MB RAM. The first example, with the population of 100, generations of 00, and total sample size limited to 50, it takes ADSPO around 4 hours to complete the evolution process. In addition, the requested AQL-α and RQL-β are set to 5%-5% and 0%-10%, respectively. The final Pareto front containing 7 solutions are indicated in Table. Among them, decision maker can select the solution 1 with the least total sample size of 10 but β risk is very undesirable. On other hand, if the required α and β risks is strictly demanded, solution 7 with total sample size of 38 meets the requirement. However, solution 6 with less sample size of 37 whose β risk is only slightly higher than the requested may worth to be adopted if inspection cost could increase substantially when even one more sample is examined. Moreover, there are 789,168 possible acceptance parameters if total sample size is limited to not exceeding 50. However, as shown in Fig. 9, ADSPO searches through about 1% (100*75/789,168) of the solution space by taking 75 generations to converge to the optimal solutions Area below Pareto Front Number of Generation Fig. 9 Convergent curve of example 1 1

13 Table Pareto solutions of example 1 Pareto Solutions Sample Size α (%) β (%) N1 N C1 R1 C

14 The second example examined with the population of 50, generations of 100, and total sample size limited to 50, it takes the ADSPO 44 minutes to complete the evolution process. The requested AQL-α and RQL-β are designed as 5%-5% and 0%- 3%, respectively. The results are listed in Table. Among the Pareto solutions, solutions 1 and whose obtained α and β risks meet the requirement. Solution 0 could be appropriate to be selected if β risk is allowed to be slightly higher than the required. In addition, as indicated in Fig. 10, about 0.1% (50*18/789,168) of the solution space is searched by ADSPO that took 18 generations to converge to the optimal solutions. Table 3 Pareto solutions of example Pareto Solutions Sample Size α (%) β (%) N1 N C1 R1 C

15 15000 Area below Pareto Front Number of Generation Fig. 10 Convergent curve of example The third example has been tested by Chow et al. and Olorunniwo and Salas. This example is tested with the population of 100, generations of 00, and total sample size limited to 150. In addition, the requested AQL-α and RQL-β are 1%-5% and 9%-10%. The results are shown in Table 3. There are four solutions (i.e., 5, 6, 7, and 8) whose α and β risks are accepted. Compared to the minimum sample size of 66 with accepted risks found in the plans presented in Olorunniwo s and Salas s work, three solutions searched by ADSPO have smaller total sample sizes. In addition, several solutions such as 3 and 4 are almost qualified for the requested risks. Moreover, as indicated in Fig. 11, about 5.9*10-6 (0*50/168,961,870) of the solution space is searched by ADSPO that took about 50 generations to converge to the Pareto solutions Area below Pareto Front Number of Generation Fig. 11 Convergent curve of example 3 15

16 Table 4 Pareto solutions of example 3 Pareto Solutions Sample Size α (%) β (%) N1 N C1 R1 C

17 6. Summary Attribute double sampling plans play an important role in constructing the quality assurance system. In designing an ADSP, the AQL, RQL, and α and β risks have to be predefined. Then a proper combination of acceptance parameters (N1, N, C1, R1, C) can be explored to fit the AQL-α and RQL-β on OC curve. In addition, the parameters must be all nonnegative integers and thus the system does not have a closed-form solution. As a result, the trial-and-error method is usually used to seek the solutions. The less the total sample sizes, the less cost and time for the quality inspection process. This is true both from the producer s and the consumer s point of view. However, the trial-and-error method not only does not guarantee that the minimum sample sizes can be reached but infeasible solution can be obtained if the fitting of OC curve is strictly limited by both the AQL-α and RQL-β. This study applied GA to optimize the design process such that the ADSP can be conveniently used for construction quality control. Objectives of minimizing both the deviations of fitting AQL-α and RQL-β and the total sample sizes are concerned in the optimization process. A computer program named ADSPO for facilitating the ADSP design process is developed. The verified results show the ADSPO can locate the optimal solutions more efficiently and accurately. References [1] L.-M. Chang and M. Hsie, Developing acceptance-sampling methods for quality construction, Journal of Construction Engineering and Management, 11(), 46-53, [] M. Hsie and L.-M. Chang, Attribute-double-sampling method for infrastructure quality assurance, Journal of Infrastructure Systems, 1(), , [3] D. C. Montgomery, Introduction to statistical quality control, John Wiley & Sons, Inc., New York, N. Y., [4] A. J. Duncan, Quality Control and Industrial Statistics, Irwin, Homewood, Illinois, [5] B. Chow, P. E. Dickinson, and H. Hughes, A computer program for the solution of double sampling plans, Journal of Quality Technology, 4(4), 05-09, 197. [6] V. Soundararajan and R. Vijayaraghavan, Procedures and tables for the construction and selection of conditional double sampling plans, Journal of Applies Statistics, 19(3), , 199. [7] F. O. Olorunniwo and J. R. Salas, An algorithm for determining double attribute sampling plans, Journal of Quality Technology, 14(3), , 198. [8] J. Holland, Adaptation in Natural and Artificial System, University of Michigan Press, Ann Arbor, Michigan, [9] M. Gen, R. Cheng, Genetic Algorithms and Engineering Optimization, Wiley, New York,

Determination of Optimal Tightened Normal Tightened Plan Using a Genetic Algorithm

Determination of Optimal Tightened Normal Tightened Plan Using a Genetic Algorithm Journal of Modern Applied Statistical Methods Volume 15 Issue 1 Article 47 5-1-2016 Determination of Optimal Tightened Normal Tightened Plan Using a Genetic Algorithm Sampath Sundaram University of Madras,

More information

Lecture 9 Evolutionary Computation: Genetic algorithms

Lecture 9 Evolutionary Computation: Genetic algorithms Lecture 9 Evolutionary Computation: Genetic algorithms Introduction, or can evolution be intelligent? Simulation of natural evolution Genetic algorithms Case study: maintenance scheduling with genetic

More information

CSC 4510 Machine Learning

CSC 4510 Machine Learning 10: Gene(c Algorithms CSC 4510 Machine Learning Dr. Mary Angela Papalaskari Department of CompuBng Sciences Villanova University Course website: www.csc.villanova.edu/~map/4510/ Slides of this presenta(on

More information

Shortening Picking Distance by using Rank-Order Clustering and Genetic Algorithm for Distribution Centers

Shortening Picking Distance by using Rank-Order Clustering and Genetic Algorithm for Distribution Centers Shortening Picking Distance by using Rank-Order Clustering and Genetic Algorithm for Distribution Centers Rong-Chang Chen, Yi-Ru Liao, Ting-Yao Lin, Chia-Hsin Chuang, Department of Distribution Management,

More information

GENETIC ALGORITHM FOR CELL DESIGN UNDER SINGLE AND MULTIPLE PERIODS

GENETIC ALGORITHM FOR CELL DESIGN UNDER SINGLE AND MULTIPLE PERIODS GENETIC ALGORITHM FOR CELL DESIGN UNDER SINGLE AND MULTIPLE PERIODS A genetic algorithm is a random search technique for global optimisation in a complex search space. It was originally inspired by an

More information

An artificial chemical reaction optimization algorithm for. multiple-choice; knapsack problem.

An artificial chemical reaction optimization algorithm for. multiple-choice; knapsack problem. An artificial chemical reaction optimization algorithm for multiple-choice knapsack problem Tung Khac Truong 1,2, Kenli Li 1, Yuming Xu 1, Aijia Ouyang 1, and Xiaoyong Tang 1 1 College of Information Science

More information

Statistical Quality Control - Stat 3081

Statistical Quality Control - Stat 3081 Statistical Quality Control - Stat 3081 Awol S. Department of Statistics College of Computing & Informatics Haramaya University Dire Dawa, Ethiopia March 2015 Introduction Lot Disposition One aspect of

More information

Zebo Peng Embedded Systems Laboratory IDA, Linköping University

Zebo Peng Embedded Systems Laboratory IDA, Linköping University TDTS 01 Lecture 8 Optimization Heuristics for Synthesis Zebo Peng Embedded Systems Laboratory IDA, Linköping University Lecture 8 Optimization problems Heuristic techniques Simulated annealing Genetic

More information

Genetic Algorithms: Basic Principles and Applications

Genetic Algorithms: Basic Principles and Applications Genetic Algorithms: Basic Principles and Applications C. A. MURTHY MACHINE INTELLIGENCE UNIT INDIAN STATISTICAL INSTITUTE 203, B.T.ROAD KOLKATA-700108 e-mail: murthy@isical.ac.in Genetic algorithms (GAs)

More information

Determination of cumulative Poisson probabilities for double sampling plan

Determination of cumulative Poisson probabilities for double sampling plan 2017; 3(3): 241-246 ISSN Print: 2394-7500 ISSN Online: 2394-5869 Impact Factor: 5.2 IJAR 2017; 3(3): 241-246 www.allresearchjournal.com Received: 25-01-2017 Accepted: 27-02-2017 G Uma Assistant Professor,

More information

Genetic Algorithm. Outline

Genetic Algorithm. Outline Genetic Algorithm 056: 166 Production Systems Shital Shah SPRING 2004 Outline Genetic Algorithm (GA) Applications Search space Step-by-step GA Mechanism Examples GA performance Other GA examples 1 Genetic

More information

Data Warehousing & Data Mining

Data Warehousing & Data Mining 13. Meta-Algorithms for Classification Data Warehousing & Data Mining Wolf-Tilo Balke Silviu Homoceanu Institut für Informationssysteme Technische Universität Braunschweig http://www.ifis.cs.tu-bs.de 13.

More information

Fundamentals of Genetic Algorithms

Fundamentals of Genetic Algorithms Fundamentals of Genetic Algorithms : AI Course Lecture 39 40, notes, slides www.myreaders.info/, RC Chakraborty, e-mail rcchak@gmail.com, June 01, 2010 www.myreaders.info/html/artificial_intelligence.html

More information

Evolutionary computation

Evolutionary computation Evolutionary computation Andrea Roli andrea.roli@unibo.it DEIS Alma Mater Studiorum Università di Bologna Evolutionary computation p. 1 Evolutionary Computation Evolutionary computation p. 2 Evolutionary

More information

Approximating the step change point of the process fraction nonconforming using genetic algorithm to optimize the likelihood function

Approximating the step change point of the process fraction nonconforming using genetic algorithm to optimize the likelihood function Journal of Industrial and Systems Engineering Vol. 7, No., pp 8-28 Autumn 204 Approximating the step change point of the process fraction nonconforming using genetic algorithm to optimize the likelihood

More information

OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd Basic Statistics Sample size?

OHSU OGI Class ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Brainerd Basic Statistics Sample size? ECE-580-DOE :Statistical Process Control and Design of Experiments Steve Basic Statistics Sample size? Sample size determination: text section 2-4-2 Page 41 section 3-7 Page 107 Website::http://www.stat.uiowa.edu/~rlenth/Power/

More information

Chapter 8: Introduction to Evolutionary Computation

Chapter 8: Introduction to Evolutionary Computation Computational Intelligence: Second Edition Contents Some Theories about Evolution Evolution is an optimization process: the aim is to improve the ability of an organism to survive in dynamically changing

More information

Computational statistics

Computational statistics Computational statistics Combinatorial optimization Thierry Denœux February 2017 Thierry Denœux Computational statistics February 2017 1 / 37 Combinatorial optimization Assume we seek the maximum of f

More information

Selection Procedures for SKSP-2 Skip-Lot Plans through Relative Slopes

Selection Procedures for SKSP-2 Skip-Lot Plans through Relative Slopes Global Journal of Mathematical Sciences: Theory and Practical. ISSN 0974-3200 Volume 4, Number 3 (2012), pp. 263-270 International Research Publication House http://www.irphouse.com Selection Procedures

More information

Generalization of Dominance Relation-Based Replacement Rules for Memetic EMO Algorithms

Generalization of Dominance Relation-Based Replacement Rules for Memetic EMO Algorithms Generalization of Dominance Relation-Based Replacement Rules for Memetic EMO Algorithms Tadahiko Murata 1, Shiori Kaige 2, and Hisao Ishibuchi 2 1 Department of Informatics, Kansai University 2-1-1 Ryozenji-cho,

More information

Learning Objectives 15.1 The Acceptance-Sampling Problem

Learning Objectives 15.1 The Acceptance-Sampling Problem Learning Objectives 5. The Acceptance-Sampling Problem Acceptance sampling plan (ASP): ASP is a specific plan that clearly states the rules for sampling and the associated criteria for acceptance or otherwise.

More information

Modified Procedure for Construction and Selection of Sampling Plans for Variable Inspection Scheme

Modified Procedure for Construction and Selection of Sampling Plans for Variable Inspection Scheme International OPEN ACCESS Journal Of Modern Engineering Research (IJMER) Modified Procedure for Construction and Selection of Sampling Plans for Variable Inspection Scheme V. Satish Kumar, M. V. Ramanaiah,

More information

Multi-objective approaches in a single-objective optimization environment

Multi-objective approaches in a single-objective optimization environment Multi-objective approaches in a single-objective optimization environment Shinya Watanabe College of Information Science & Engineering, Ritsumeikan Univ. -- Nojihigashi, Kusatsu Shiga 55-8577, Japan sin@sys.ci.ritsumei.ac.jp

More information

Genetic Learning of Firms in a Competitive Market

Genetic Learning of Firms in a Competitive Market FH-Kiel, Germany University of Applied Sciences Andreas Thiemer, e-mail: andreas.thiemer@fh-kiel.de Genetic Learning of Firms in a Competitive Market Summary: This worksheet deals with the adaptive learning

More information

Matt Heavner CSE710 Fall 2009

Matt Heavner CSE710 Fall 2009 Matt Heavner mheavner@buffalo.edu CSE710 Fall 2009 Problem Statement: Given a set of cities and corresponding locations, what is the shortest closed circuit that visits all cities without loops?? Fitness

More information

Evolutionary Computation. DEIS-Cesena Alma Mater Studiorum Università di Bologna Cesena (Italia)

Evolutionary Computation. DEIS-Cesena Alma Mater Studiorum Università di Bologna Cesena (Italia) Evolutionary Computation DEIS-Cesena Alma Mater Studiorum Università di Bologna Cesena (Italia) andrea.roli@unibo.it Evolutionary Computation Inspiring principle: theory of natural selection Species face

More information

The Role of Crossover in Genetic Algorithms to Solve Optimization of a Function Problem Falih Hassan

The Role of Crossover in Genetic Algorithms to Solve Optimization of a Function Problem Falih Hassan The Role of Crossover in Genetic Algorithms to Solve Optimization of a Function Problem Falih Hassan ABSTRACT The genetic algorithm is an adaptive search method that has the ability for a smart search

More information

Set-based Min-max and Min-min Robustness for Multi-objective Robust Optimization

Set-based Min-max and Min-min Robustness for Multi-objective Robust Optimization Proceedings of the 2017 Industrial and Systems Engineering Research Conference K. Coperich, E. Cudney, H. Nembhard, eds. Set-based Min-max and Min-min Robustness for Multi-objective Robust Optimization

More information

Exploiting Machine Learning Techniques for the Enhancement of Acceptance Sampling

Exploiting Machine Learning Techniques for the Enhancement of Acceptance Sampling Exploiting Machine Learning Techniques for the Enhancement of Acceptance Sampling Aikaterini Fountoulaki, Nikos Karacapilidis, and Manolis Manatakis International Science Index, Industrial and Manufacturing

More information

Department of Mathematics, Graphic Era University, Dehradun, Uttarakhand, India

Department of Mathematics, Graphic Era University, Dehradun, Uttarakhand, India Genetic Algorithm for Minimization of Total Cost Including Customer s Waiting Cost and Machine Setup Cost for Sequence Dependent Jobs on a Single Processor Neelam Tyagi #1, Mehdi Abedi *2 Ram Gopal Varshney

More information

Effect of repair cost on the rework decision-making in an economic production quantity model

Effect of repair cost on the rework decision-making in an economic production quantity model Effect of repair cost on the rework decision-making in an economic production quantity model Singa Wang Chiu Department of Business Administration Chaoyang University of Technology 68, Gifeng E. Rd. Wufeng,

More information

Parallel Genetic Algorithms

Parallel Genetic Algorithms Parallel Genetic Algorithms for the Calibration of Financial Models Riccardo Gismondi June 13, 2008 High Performance Computing in Finance and Insurance Research Institute for Computational Methods Vienna

More information

Interplanetary Trajectory Optimization using a Genetic Algorithm

Interplanetary Trajectory Optimization using a Genetic Algorithm Interplanetary Trajectory Optimization using a Genetic Algorithm Abby Weeks Aerospace Engineering Dept Pennsylvania State University State College, PA 16801 Abstract Minimizing the cost of a space mission

More information

Representation and Hidden Bias II: Eliminating Defining Length Bias in Genetic Search via Shuffle Crossover

Representation and Hidden Bias II: Eliminating Defining Length Bias in Genetic Search via Shuffle Crossover Representation and Hidden Bias II: Eliminating Defining Length Bias in Genetic Search via Shuffle Crossover Abstract The traditional crossover operator used in genetic search exhibits a position-dependent

More information

ARTIFICIAL NEURAL NETWORK WITH HYBRID TAGUCHI-GENETIC ALGORITHM FOR NONLINEAR MIMO MODEL OF MACHINING PROCESSES

ARTIFICIAL NEURAL NETWORK WITH HYBRID TAGUCHI-GENETIC ALGORITHM FOR NONLINEAR MIMO MODEL OF MACHINING PROCESSES International Journal of Innovative Computing, Information and Control ICIC International c 2013 ISSN 1349-4198 Volume 9, Number 4, April 2013 pp. 1455 1475 ARTIFICIAL NEURAL NETWORK WITH HYBRID TAGUCHI-GENETIC

More information

Evolutionary computation in high-energy physics

Evolutionary computation in high-energy physics Evolutionary computation in high-energy physics Liliana Teodorescu Brunel University, United Kingdom Abstract Evolutionary computation is a branch of computer science with which, traditionally, high-energy

More information

Research Article A Novel Differential Evolution Invasive Weed Optimization Algorithm for Solving Nonlinear Equations Systems

Research Article A Novel Differential Evolution Invasive Weed Optimization Algorithm for Solving Nonlinear Equations Systems Journal of Applied Mathematics Volume 2013, Article ID 757391, 18 pages http://dx.doi.org/10.1155/2013/757391 Research Article A Novel Differential Evolution Invasive Weed Optimization for Solving Nonlinear

More information

DETECTING THE FAULT FROM SPECTROGRAMS BY USING GENETIC ALGORITHM TECHNIQUES

DETECTING THE FAULT FROM SPECTROGRAMS BY USING GENETIC ALGORITHM TECHNIQUES DETECTING THE FAULT FROM SPECTROGRAMS BY USING GENETIC ALGORITHM TECHNIQUES Amin A. E. 1, El-Geheni A. S. 2, and El-Hawary I. A **. El-Beali R. A. 3 1 Mansoura University, Textile Department 2 Prof. Dr.

More information

Construction of a Tightened-Normal-Tightened Sampling Scheme by Variables Inspection. Abstract

Construction of a Tightened-Normal-Tightened Sampling Scheme by Variables Inspection. Abstract onstruction of a ightened-ormal-ightened Sampling Scheme by Variables Inspection Alexander A ugroho a,, hien-wei Wu b, and ani Kurniati a a Department of Industrial Management, ational aiwan University

More information

Construction and Evalution of Performance Measures for One Plan Suspension System

Construction and Evalution of Performance Measures for One Plan Suspension System International Journal of Computational Science and Mathematics. ISSN 0974-3189 Volume 2, Number 3 (2010), pp. 225--235 International Research Publication House http://www.irphouse.com Construction and

More information

Intelligens Számítási Módszerek Genetikus algoritmusok, gradiens mentes optimálási módszerek

Intelligens Számítási Módszerek Genetikus algoritmusok, gradiens mentes optimálási módszerek Intelligens Számítási Módszerek Genetikus algoritmusok, gradiens mentes optimálási módszerek 2005/2006. tanév, II. félév Dr. Kovács Szilveszter E-mail: szkovacs@iit.uni-miskolc.hu Informatikai Intézet

More information

Crossover Techniques in GAs

Crossover Techniques in GAs Crossover Techniques in GAs Debasis Samanta Indian Institute of Technology Kharagpur dsamanta@iitkgp.ac.in 16.03.2018 Debasis Samanta (IIT Kharagpur) Soft Computing Applications 16.03.2018 1 / 1 Important

More information

Multi-Objective Optimization Methods for Optimal Funding Allocations to Mitigate Chemical and Biological Attacks

Multi-Objective Optimization Methods for Optimal Funding Allocations to Mitigate Chemical and Biological Attacks Multi-Objective Optimization Methods for Optimal Funding Allocations to Mitigate Chemical and Biological Attacks Roshan Rammohan, Ryan Schnalzer Mahmoud Reda Taha, Tim Ross and Frank Gilfeather University

More information

Statistical quality control (SQC)

Statistical quality control (SQC) Statistical quality control (SQC) The application of statistical techniques to measure and evaluate the quality of a product, service, or process. Two basic categories: I. Statistical process control (SPC):

More information

An Effective Chromosome Representation for Evolving Flexible Job Shop Schedules

An Effective Chromosome Representation for Evolving Flexible Job Shop Schedules An Effective Chromosome Representation for Evolving Flexible Job Shop Schedules Joc Cing Tay and Djoko Wibowo Intelligent Systems Lab Nanyang Technological University asjctay@ntuedusg Abstract As the Flexible

More information

SkSP-V Acceptance Sampling Plan based on Process Capability Index

SkSP-V Acceptance Sampling Plan based on Process Capability Index 258 Chiang Mai J. Sci. 2015; 42(1) Chiang Mai J. Sci. 2015; 42(1) : 258-267 http://epg.science.cmu.ac.th/ejournal/ Contributed Paper SkSP-V Acceptance Sampling Plan based on Process Capability Index Muhammad

More information

DESIGN OF OPTIMUM CROSS-SECTIONS FOR LOAD-CARRYING MEMBERS USING MULTI-OBJECTIVE EVOLUTIONARY ALGORITHMS

DESIGN OF OPTIMUM CROSS-SECTIONS FOR LOAD-CARRYING MEMBERS USING MULTI-OBJECTIVE EVOLUTIONARY ALGORITHMS DESIGN OF OPTIMUM CROSS-SECTIONS FOR LOAD-CARRING MEMBERS USING MULTI-OBJECTIVE EVOLUTIONAR ALGORITHMS Dilip Datta Kanpur Genetic Algorithms Laboratory (KanGAL) Deptt. of Mechanical Engg. IIT Kanpur, Kanpur,

More information

On Detecting Multiple Faults in Baseline Interconnection Networks

On Detecting Multiple Faults in Baseline Interconnection Networks On Detecting Multiple Faults in Baseline Interconnection Networks SHUN-SHII LIN 1 AND SHAN-TAI CHEN 2 1 National Taiwan Normal University, Taipei, Taiwan, ROC 2 Chung Cheng Institute of Technology, Tao-Yuan,

More information

Optimal SPRT and CUSUM Procedures using Compressed Limit Gauges

Optimal SPRT and CUSUM Procedures using Compressed Limit Gauges Optimal SPRT and CUSUM Procedures using Compressed Limit Gauges P. Lee Geyer Stefan H. Steiner 1 Faculty of Business McMaster University Hamilton, Ontario L8S 4M4 Canada Dept. of Statistics and Actuarial

More information

Multiobjective Optimization of Cement-bonded Sand Mould System with Differential Evolution

Multiobjective Optimization of Cement-bonded Sand Mould System with Differential Evolution DOI: 10.7763/IPEDR. 013. V63. 0 Multiobjective Optimization of Cement-bonded Sand Mould System with Differential Evolution T. Ganesan 1, I. Elamvazuthi, Ku Zilati Ku Shaari 3, and P. Vasant + 1, 3 Department

More information

CERTAIN RESULTS ON MULTI DIMENSIONAL SAMPLING PLANS. The mixed sampling plans are two stage sampling plans in which variable

CERTAIN RESULTS ON MULTI DIMENSIONAL SAMPLING PLANS. The mixed sampling plans are two stage sampling plans in which variable CHAPTER III CERTAIN RESULTS ON MULTI DIMENSIONAL SAMPLING PLANS Focus The mixed sampling plans are two stage sampling plans in which variable and attribute quality characteristics are used in deciding

More information

Evolutionary Functional Link Interval Type-2 Fuzzy Neural System for Exchange Rate Prediction

Evolutionary Functional Link Interval Type-2 Fuzzy Neural System for Exchange Rate Prediction Evolutionary Functional Link Interval Type-2 Fuzzy Neural System for Exchange Rate Prediction 3. Introduction Currency exchange rate is an important element in international finance. It is one of the chaotic,

More information

Adaptive Generalized Crowding for Genetic Algorithms

Adaptive Generalized Crowding for Genetic Algorithms Carnegie Mellon University From the SelectedWorks of Ole J Mengshoel Fall 24 Adaptive Generalized Crowding for Genetic Algorithms Ole J Mengshoel, Carnegie Mellon University Severinio Galan Antonio de

More information

An optimization model for designing acceptance sampling plan based on cumulative count of conforming run length using minimum angle method

An optimization model for designing acceptance sampling plan based on cumulative count of conforming run length using minimum angle method Hacettepe Journal of Mathematics and Statistics Volume 44 (5) (2015), 1271 1281 An optimization model for designing acceptance sampling plan based on cumulative count of conforming run length using minimum

More information

Designing of Special Type of Double Sampling Plan for Compliance Testing through Generalized Poisson Distribution

Designing of Special Type of Double Sampling Plan for Compliance Testing through Generalized Poisson Distribution Volume 117 No. 12 2017, 7-17 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu ijpam.eu Designing of Special Type of Double Sampling Plan for Compliance Testing

More information

An easy approach to derive EOQ and EPQ models with shortage and. defective items

An easy approach to derive EOQ and EPQ models with shortage and. defective items An easy approach to derive EOQ and EPQ models with shortage and defective items Hsin-Fan Chen 1, Yung-Fu Huang,*, Yu-Cheng Tu 3 and Ming-Hon Hwang 4 1,,3,4 Department of Mareting and Logistics Management,

More information

Havrda and Charvat Entropy Based Genetic Algorithm for Traveling Salesman Problem

Havrda and Charvat Entropy Based Genetic Algorithm for Traveling Salesman Problem 3 IJCSNS International Journal of Computer Science and Network Security, VOL.8 No.5, May 008 Havrda and Charvat Entropy Based Genetic Algorithm for Traveling Salesman Problem Baljit Singh, Arjan Singh

More information

Better AOQL Formulas -- copyright 2016 by John Zorich; all rights reserved. Better AOQ Formulas

Better AOQL Formulas -- copyright 2016 by John Zorich; all rights reserved. Better AOQ Formulas Better AOQ Formulas John N. Zorich, Jr. Independent Consultant in Applied Statistics Houston, Texas, USA July 22, 2016 JOHNZORICH@YAHOO.COM WWW.JOHNZORICH.COM ABSTRACT: The classic formula for AOQ calculates

More information

ME 418 Quality in Manufacturing ISE Quality Control and Industrial Statistics CHAPTER 07 ACCEPTANCE SAMPLING PLANS.

ME 418 Quality in Manufacturing ISE Quality Control and Industrial Statistics CHAPTER 07 ACCEPTANCE SAMPLING PLANS. University of Hail College of Engineering ME 418 Quality in Manufacturing ISE 320 - Quality Control and Industrial Statistics CHAPTER 07 ACCEPTANCE SAMPLING PLANS Professor Mohamed Aichouni http://cutt.us/maichouni

More information

SELECTING THE LAST RECORD WITH RECALL IN A SEQUENCE OF INDEPENDENT BERNOULLI TRIALS

SELECTING THE LAST RECORD WITH RECALL IN A SEQUENCE OF INDEPENDENT BERNOULLI TRIALS Statistica Sinica 19 (2009), 355-361 SELECTING THE LAST RECORD WITH RECALL IN A SEQUENCE OF INDEPENDENT BERNOULLI TRIALS Jiing-Ru Yang Diwan College of Management Abstract: Given a sequence of N independent

More information

Evolutionary Design I

Evolutionary Design I Evolutionary Design I Jason Noble jasonn@comp.leeds.ac.uk Biosystems group, School of Computing Evolutionary Design I p.1/29 This lecture Harnessing evolution in a computer program How to construct a genetic

More information

Efficient Non-domination Level Update Method for Steady-State Evolutionary Multi-objective. optimization

Efficient Non-domination Level Update Method for Steady-State Evolutionary Multi-objective. optimization Efficient Non-domination Level Update Method for Steady-State Evolutionary Multi-objective Optimization Ke Li, Kalyanmoy Deb, Fellow, IEEE, Qingfu Zhang, Senior Member, IEEE, and Qiang Zhang COIN Report

More information

Superiority by a Margin Tests for One Proportion

Superiority by a Margin Tests for One Proportion Chapter 103 Superiority by a Margin Tests for One Proportion Introduction This module provides power analysis and sample size calculation for one-sample proportion tests in which the researcher is testing

More information

Multi-objective genetic algorithm

Multi-objective genetic algorithm Multi-objective genetic algorithm Robin Devooght 31 March 2010 Abstract Real world problems often present multiple, frequently conflicting, objectives. The research for optimal solutions of multi-objective

More information

Evolutionary computation

Evolutionary computation Evolutionary computation Andrea Roli andrea.roli@unibo.it Dept. of Computer Science and Engineering (DISI) Campus of Cesena Alma Mater Studiorum Università di Bologna Outline 1 Basic principles 2 Genetic

More information

Trade Of Analysis For Helical Gear Reduction Units

Trade Of Analysis For Helical Gear Reduction Units Trade Of Analysis For Helical Gear Reduction Units V.Vara Prasad1, G.Satish2, K.Ashok Kumar3 Assistant Professor, Mechanical Engineering Department, Shri Vishnu Engineering College For Women, Andhra Pradesh,

More information

Mohammad Saidi-Mehrabad a, Samira Bairamzadeh b,*

Mohammad Saidi-Mehrabad a, Samira Bairamzadeh b,* Journal of Optimization in Industrial Engineering, Vol. 11, Issue 1,Winter and Spring 2018, 3-0 DOI:10.22094/JOIE.2018.272 Design of a Hybrid Genetic Algorithm for Parallel Machines Scheduling to Minimize

More information

Performance Evaluation and Comparison

Performance Evaluation and Comparison Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Cross Validation and Resampling 3 Interval Estimation

More information

Repeated Occurrences of the Baldwin Effect Can Guide Evolution on Rugged Fitness Landscapes

Repeated Occurrences of the Baldwin Effect Can Guide Evolution on Rugged Fitness Landscapes Repeated Occurrences of the Baldwin Effect Can Guide Evolution on Rugged Fitness Landscapes Reiji Suzuki and Takaya Arita Graduate School of Information Science, Nagoya University Furo-cho, Chikusa-ku,

More information

Search. Search is a key component of intelligent problem solving. Get closer to the goal if time is not enough

Search. Search is a key component of intelligent problem solving. Get closer to the goal if time is not enough Search Search is a key component of intelligent problem solving Search can be used to Find a desired goal if time allows Get closer to the goal if time is not enough section 11 page 1 The size of the search

More information

The European Applied Business Research Conference Rothenburg, Germany 2002

The European Applied Business Research Conference Rothenburg, Germany 2002 The European Applied Business Research Conference Rothenburg, Germany 00 Using Genetic Algorithms To Optimise Kanban-Based Production System M Al-Tahat, (E-mail: mohammadal-tahat@mailinguniboit), University

More information

OPTIMIZED RESOURCE IN SATELLITE NETWORK BASED ON GENETIC ALGORITHM. Received June 2011; revised December 2011

OPTIMIZED RESOURCE IN SATELLITE NETWORK BASED ON GENETIC ALGORITHM. Received June 2011; revised December 2011 International Journal of Innovative Computing, Information and Control ICIC International c 2012 ISSN 1349-4198 Volume 8, Number 12, December 2012 pp. 8249 8256 OPTIMIZED RESOURCE IN SATELLITE NETWORK

More information

Design of Repetitive Acceptance Sampling Plan for Truncated Life Test using Inverse Weibull Distribution

Design of Repetitive Acceptance Sampling Plan for Truncated Life Test using Inverse Weibull Distribution Design of Repetitive Acceptance Sampling Plan for Truncated Life Test using Inverse Weibull Distribution Navjeet Singh 1, Navyodh Singh 2, Harpreet Kaur 3 1 Department of Mathematics, Sant Baba Bhag Singh

More information

Design Optimization of an Electronic Component with an Evolutionary Algorithm Using the COMSOL-MATLAB LiveLink

Design Optimization of an Electronic Component with an Evolutionary Algorithm Using the COMSOL-MATLAB LiveLink Design Optimization of an Electronic Component with an Evolutionary Algorithm Using the COMSOL-MATLAB LiveLink Eva Pelster 1,David Wenger,1 1 Wenger Engineering GmbH, Einsteinstr. 55, 8977 Ulm, mail@wenger-engineering.com

More information

Chapter 1 Statistical Inference

Chapter 1 Statistical Inference Chapter 1 Statistical Inference causal inference To infer causality, you need a randomized experiment (or a huge observational study and lots of outside information). inference to populations Generalizations

More information

Benders' Method Paul A Jensen

Benders' Method Paul A Jensen Benders' Method Paul A Jensen The mixed integer programming model has some variables, x, identified as real variables and some variables, y, identified as integer variables. Except for the integrality

More information

DESINGING DSP (0, 1) ACCEPTANCE SAMPLING PLANS BASED ON TRUNCATED LIFE TESTS UNDER VARIOUS DISTRIBUTIONS USING MINIMUM ANGLE METHOD

DESINGING DSP (0, 1) ACCEPTANCE SAMPLING PLANS BASED ON TRUNCATED LIFE TESTS UNDER VARIOUS DISTRIBUTIONS USING MINIMUM ANGLE METHOD DESINGING DSP (0, 1) ACCEPTANCE SAMPLING PLANS BASED ON TRUNCATED LIFE TESTS UNDER VARIOUS DISTRIBUTIONS USING MINIMUM ANGLE METHOD A. R. Sudamani Ramaswamy 1, R. Sutharani 2 1 Associate Professor, Department

More information

Behavior of EMO Algorithms on Many-Objective Optimization Problems with Correlated Objectives

Behavior of EMO Algorithms on Many-Objective Optimization Problems with Correlated Objectives H. Ishibuchi N. Akedo H. Ohyanagi and Y. Nojima Behavior of EMO algorithms on many-objective optimization problems with correlated objectives Proc. of 211 IEEE Congress on Evolutionary Computation pp.

More information

Computational Complexity and Genetic Algorithms

Computational Complexity and Genetic Algorithms Computational Complexity and Genetic Algorithms BART RYLANDER JAMES FOSTER School of Engineering Department of Computer Science University of Portland University of Idaho Portland, Or 97203 Moscow, Idaho

More information

CHAPTER 4 INTRODUCTION TO DISCRETE VARIABLE OPTIMIZATION

CHAPTER 4 INTRODUCTION TO DISCRETE VARIABLE OPTIMIZATION CHAPTER 4 INTRODUCTION TO DISCRETE VARIABLE OPTIMIZATION. Introduction.. Examples of Discrete Variables One often encounters problems in which design variables must be selected from among a set of discrete

More information

Evolutionary Multiobjective. Optimization Methods for the Shape Design of Industrial Electromagnetic Devices. P. Di Barba, University of Pavia, Italy

Evolutionary Multiobjective. Optimization Methods for the Shape Design of Industrial Electromagnetic Devices. P. Di Barba, University of Pavia, Italy Evolutionary Multiobjective Optimization Methods for the Shape Design of Industrial Electromagnetic Devices P. Di Barba, University of Pavia, Italy INTRODUCTION Evolutionary Multiobjective Optimization

More information

Bayesian Decision Theory

Bayesian Decision Theory Bayesian Decision Theory Dr. Shuang LIANG School of Software Engineering TongJi University Fall, 2012 Today s Topics Bayesian Decision Theory Bayesian classification for normal distributions Error Probabilities

More information

Genetic Algorithms & Modeling

Genetic Algorithms & Modeling Genetic Algorithms & Modeling : Soft Computing Course Lecture 37 40, notes, slides www.myreaders.info/, RC Chakraborty, e-mail rcchak@gmail.com, Aug. 10, 2010 http://www.myreaders.info/html/soft_computing.html

More information

University of Groningen. Statistical Auditing and the AOQL-method Talens, Erik

University of Groningen. Statistical Auditing and the AOQL-method Talens, Erik University of Groningen Statistical Auditing and the AOQL-method Talens, Erik IMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check

More information

V. Evolutionary Computing. Read Flake, ch. 20. Genetic Algorithms. Part 5A: Genetic Algorithms 4/10/17. A. Genetic Algorithms

V. Evolutionary Computing. Read Flake, ch. 20. Genetic Algorithms. Part 5A: Genetic Algorithms 4/10/17. A. Genetic Algorithms V. Evolutionary Computing A. Genetic Algorithms 4/10/17 1 Read Flake, ch. 20 4/10/17 2 Genetic Algorithms Developed by John Holland in 60s Did not become popular until late 80s A simplified model of genetics

More information

Feature selection and classifier performance in computer-aided diagnosis: The effect of finite sample size

Feature selection and classifier performance in computer-aided diagnosis: The effect of finite sample size Feature selection and classifier performance in computer-aided diagnosis: The effect of finite sample size Berkman Sahiner, a) Heang-Ping Chan, Nicholas Petrick, Robert F. Wagner, b) and Lubomir Hadjiiski

More information

Optimal Sequencing of Inspection of Dependent Characteristics 1

Optimal Sequencing of Inspection of Dependent Characteristics 1 JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS: Vol. 103, No. 3, pp. 557-565, DECEMBER 1999 Optimal Sequencing of Inspection of Dependent Characteristics 1 S. O. DUFFUUA 2 AND S. M. POLLOCK 3 Communicated

More information

An-Najah National University Faculty of Engineering Industrial Engineering Department. Course : Quantitative Methods (65211)

An-Najah National University Faculty of Engineering Industrial Engineering Department. Course : Quantitative Methods (65211) An-Najah National University Faculty of Engineering Industrial Engineering Department Course : Quantitative Methods (65211) Instructor: Eng. Tamer Haddad 2 nd Semester 2009/2010 Chapter 3 Discrete Random

More information

Design Of Optimal Pid Controller Using Genetic Algorithm

Design Of Optimal Pid Controller Using Genetic Algorithm Australian Journal of Basic and Applied Sciences, 5(10): 996-1001, 2011 ISSN 1991-8178 Design Of Optimal Pid Controller Using Genetic Algorithm 1 Mohammad Reza Dastranj, 1 Kazem Esmaeili Khoshmardan, 2

More information

INFORMATION-THEORETIC BOUNDS OF EVOLUTIONARY PROCESSES MODELED AS A PROTEIN COMMUNICATION SYSTEM. Liuling Gong, Nidhal Bouaynaya and Dan Schonfeld

INFORMATION-THEORETIC BOUNDS OF EVOLUTIONARY PROCESSES MODELED AS A PROTEIN COMMUNICATION SYSTEM. Liuling Gong, Nidhal Bouaynaya and Dan Schonfeld INFORMATION-THEORETIC BOUNDS OF EVOLUTIONARY PROCESSES MODELED AS A PROTEIN COMMUNICATION SYSTEM Liuling Gong, Nidhal Bouaynaya and Dan Schonfeld University of Illinois at Chicago, Dept. of Electrical

More information

MEAN-ABSOLUTE DEVIATION PORTFOLIO SELECTION MODEL WITH FUZZY RETURNS. 1. Introduction

MEAN-ABSOLUTE DEVIATION PORTFOLIO SELECTION MODEL WITH FUZZY RETURNS. 1. Introduction Iranian Journal of Fuzzy Systems Vol. 8, No. 4, (2011) pp. 61-75 61 MEAN-ABSOLUTE DEVIATION PORTFOLIO SELECTION MODEL WITH FUZZY RETURNS Z. QIN, M. WEN AND C. GU Abstract. In this paper, we consider portfolio

More information

Energy Minimization of Protein Tertiary Structure by Parallel Simulated Annealing using Genetic Crossover

Energy Minimization of Protein Tertiary Structure by Parallel Simulated Annealing using Genetic Crossover Minimization of Protein Tertiary Structure by Parallel Simulated Annealing using Genetic Crossover Tomoyuki Hiroyasu, Mitsunori Miki, Shinya Ogura, Keiko Aoi, Takeshi Yoshida, Yuko Okamoto Jack Dongarra

More information

RESOLUTION OF NONLINEAR OPTIMIZATION PROBLEMS SUBJECT TO BIPOLAR MAX-MIN FUZZY RELATION EQUATION CONSTRAINTS USING GENETIC ALGORITHM

RESOLUTION OF NONLINEAR OPTIMIZATION PROBLEMS SUBJECT TO BIPOLAR MAX-MIN FUZZY RELATION EQUATION CONSTRAINTS USING GENETIC ALGORITHM Iranian Journal of Fuzzy Systems Vol. 15, No. 2, (2018) pp. 109-131 109 RESOLUTION OF NONLINEAR OPTIMIZATION PROBLEMS SUBJECT TO BIPOLAR MAX-MIN FUZZY RELATION EQUATION CONSTRAINTS USING GENETIC ALGORITHM

More information

Package nsga2r. February 20, 2015

Package nsga2r. February 20, 2015 Type Package Package nsga2r February 20, 2015 Title Elitist Non-dominated Sorting Genetic Algorithm based on R Version 1.0 Date 2013-06-12 Author Maintainer Ming-Chang (Alan) Lee

More information

A genetic algorithm for robust berth allocation and quay crane assignment

A genetic algorithm for robust berth allocation and quay crane assignment Prog Artif Intell (2014) 2:177 192 DOI 10.1007/s13748-014-0056-3 REGULAR PAPER A genetic algorithm for robust berth allocation and quay crane assignment Mario Rodriguez-Molins Laura Ingolotti Federico

More information

THE EXISTENCE AND USEFULNESS OF EQUALITY CUTS IN THE MULTI-DEMAND MULTIDIMENSIONAL KNAPSACK PROBLEM LEVI DELISSA. B.S., Kansas State University, 2014

THE EXISTENCE AND USEFULNESS OF EQUALITY CUTS IN THE MULTI-DEMAND MULTIDIMENSIONAL KNAPSACK PROBLEM LEVI DELISSA. B.S., Kansas State University, 2014 THE EXISTENCE AND USEFULNESS OF EQUALITY CUTS IN THE MULTI-DEMAND MULTIDIMENSIONAL KNAPSACK PROBLEM by LEVI DELISSA B.S., Kansas State University, 2014 A THESIS submitted in partial fulfillment of the

More information

Genetic Algorithm for Solving the Economic Load Dispatch

Genetic Algorithm for Solving the Economic Load Dispatch International Journal of Electronic and Electrical Engineering. ISSN 0974-2174, Volume 7, Number 5 (2014), pp. 523-528 International Research Publication House http://www.irphouse.com Genetic Algorithm

More information

Efficiency Improvement of PM Disc Motor Using Genetic Algorithm

Efficiency Improvement of PM Disc Motor Using Genetic Algorithm Efficiency Improvement of PM Disc Motor Using Genetic Algorithm Goga Cvetkovski 1, Lidija Petkovska 1 and inclair Gair 2 1 s. Cyril & Methodius University, Faculty of Electrical Engineering, P.O. Box 574,

More information

Nonparametric Predictive Inference for Acceptance Decisions. Mohamed A. Elsaeiti. A thesis presented for the degree of Doctor of Philosophy

Nonparametric Predictive Inference for Acceptance Decisions. Mohamed A. Elsaeiti. A thesis presented for the degree of Doctor of Philosophy Nonparametric Predictive Inference for Acceptance Decisions Mohamed A. Elsaeiti A thesis presented for the degree of Doctor of Philosophy Department of Mathematical Sciences University of Durham England

More information

Evolutionary Computation

Evolutionary Computation Evolutionary Computation - Computational procedures patterned after biological evolution. - Search procedure that probabilistically applies search operators to set of points in the search space. - Lamarck

More information