Grefenstette, J.J., "GENESIS: A System for Using genetic search procedures," In Proceedings of the Conference on Intelligent Systems and Machines, 1984, pp. 161-165.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....survey has been reported by Coello[2] Vector Evaluated Genetic Algorithm (VEGA) is the earliest example of an evolutionary algorithm designed for finding an approximation to the Pareto optimal solution set of a multiobjective problem. Shaffer[28] proposed VEGA as an extension of Grefenstette s[12] (GENESIS) program for simple genetic algorithm. It is based on the use of multiple populations and selective migration of individuals from one population to another. The methodology is simple to understand and implement but requires a large number of subpopulations with sufficient number of ....

Grefenstette, J.J.: GENESIS: A system for using genetic search procedure, Proceedings of the

....entry. ffl When classifying new examples, look up the projected example in the decision table using the Euclidean distance measure. To determine the classification, find the majority class entry with the minimum Euclidean distance between the entry and the unseen case. 2. 2 GENESIS GENESIS [Grefenstette, 1984] is a genetic algorithm that has been used as a search engine by many researchers [Turney, 1997] Bala et al. 1997] Bala et al. 1995] because of its simplicity and its availability. GENESIS is a public domain software based on a simple GA. GENESIS uses crossover and mutation according to ....

Grefenstette, J. J. (1984). GENESIS: A System for Using Genetic Search Procedures. In Proceedings of a Conference on Intelligent Systems and Machines, pages 161--165.

....et al. 1993] C was f0; 1g 100 . If x 2 C (x = x 1 ; x 2 ; x 100 ) then let P (x) P 100 i=1 x i w i , and then f(x) a(M P (x) 1 a)P (x) where a = 1 when x is feasible (i.e. M P (e) 0) and a = 0 otherwise. 3. 2 WAVE ANALYSIS The experiments were performed with GENESIS [Grefenstette 1984]. The selection type was ranking selection. The operators were 1 point crossover and traditional mutation. The probabilities of the operators are 1 and 0:003 if not otherwise stated. The population size was 100 and the number of evaluations was 5000 in every experiment. The initial populations ....

J.J. Grefenstette (1984) GENESIS: A System for Using Genetic Search Procedures, in Proceedings of the 1984 Conference on Intelligent Systems and Machines, (pp161165) .

....fixed representation space, namely that of binary strings. A common perception is that to employ such an algorithm for a new problem, one need only define a fitness function. Indeed, standard software packages exist which literally require only computer code for a fitness function, e.g. GENESIS; Grefenstette, 1984. For problems defined explicitly over binary strings (one counting, royal road, etc. this does not present any difficulty. For others, such as real parameter optimisation, some encoding from the problem variables into binary strings must be formulated, in order that the fitness of binary ....

J. J. Grefenstette, 1984. GENESIS: A system for using genetic search procedures. In Proceedings of the 1984 Conference on Intelligent Systems and Machines, pages 161-- 165.

....of the objectives [Powell and Skolnick 1993] Some of the most popular approaches that fall into this category will be examined in this section. An Updated Survey of GA Based Multiobjective Optimization Techniques Delta 17 5. 1 VEGA David Schaffer [1985] extended Grefenstette s GENESIS program [Grefenstette 1984] to include multiple objective functions. Schaffer s approach was to use an extension of the Simple Genetic Algorithm (SGA) that he called the Vector Evaluated Genetic Algorithm (VEGA) and that differed of the first only in the way in which selection was performed. This operator was modified so ....

Grefenstette, J. J. 1984. GENESIS: A system for using genetic search procedures. In Proceedings of the 1984 Conference on Intelligent Systems and Machines (1984), pp. 161-- 165.

....of the coefficients of the combining function, additional runs may be required until a suitable solution is found. Some of the main approaches proposed in the literature will be summarized in the remainder of this section. 5. 1 VEGA David Schaffer [53] extended Grefenstette s GENESIS program [26] to include multiple objective functions. Schaffer s approach was to use an extension of the Simple Genetic Algorithm (SGA) that he called the Vector Evaluated Genetic Algorithm (VEGA) and that differed of the first only in the way in which selection was performed. This operator was modified so ....

J. J. Grefenstette. GENESIS: A system for using genetic search procedures. In Proceedings of the 1984 Conference on Intelligent Systems and Machines, pages 161--165, 1984.

....M . Almost equivalent, because of the asymmetric construction of the objective function. and then Gammaf (x) a(M Gamma P (x) 1 Gamma a)P (x) where a = 1 when x is feasible (i.e. M Gamma P (e) 0) and a = 0 otherwise. 3. 2 WAVE ANALYSIS The experiments were performed with genesis [Grefenstette 1984]. The selection type was ranking selection. The operators were 1 point crossover and traditional mutation. The probabilities of the operators are 1 and 0:003 if not otherwise stated. The population size was 100 and the number of evaluations was 5000 in every experiment. The initial populations ....

J.J. Grefenstette (1984) GENESIS: A System for Using Genetic Search Procedures, in Proceedings of the 1984 Conference on Intelligent Systems and Machines, (pp161-165).

....be a function of such weights. Still more important is the fact that this approach does not generate proper Pareto optimal solutions in the presence of non convex search spaces regardless of the weights used [15] 4. 2 Schaffer s VEGA David Schaffer [16] extended Grefenstette s GENESIS program [17] to include multiple objective functions. Schaffer s F 2 f f 1 Figure 1: An example of a problem with two objective functions. The Pareto front is marked with a bold line. approach was to use an extension of the Simple Genetic Algorithm (SGA) that he called the Vector Evaluated Genetic ....

J. J. Grefenstette. GENESIS: A system for using genetic search procedures. In Proceedings of the 1984 Conference on Intelligent Systems and Machines, pages 161-- 165, 1984.

....use of a graded penalty term incorporated in the fitness function to penalize infeasible solutions. The fitness function itself is quite simple and needs to be added to GENEsYs, the genetic algorithm software package we use in this work. This package is based on Grefenstette s widely used GENESIS [4]. Following the formal introduction of the mvcp, the best known heuristic algorithm for that problem is introduced. The study then focuses on the genetic based heuristic. Several problem instances are used with both algorithms and the results are compared. Our work concludes with some observations ....

J. J. Grefenstette. Genesis: A system for using genetic search procedures. In Proceedings of the 1984 Conference on Intelligent Systems and Machines, pages 161--165, 1984.

....the closely related physical map GENETIC ALGORITHMS FOR DNA SEQUENCING ping problem [Goldstein and Waterman, 1987) Here we describe a genetic algorithm approach to the fragment assembly problem. The genetic algorithm is implemented within the context of the Genesis genetic algorithm package [Grefenstette, 1984)] Our modifications to Genesis to support the new operators are all written in the C programming language, as is the Genesis package itself. Genesis is available on the Internet; our modifications are available on request. We use five realistically sized data sets, referred to as POBF, AMCG, ....

John J. Grefenstette. Genesis: A system for using genetic search procedures. In Proceedings of a Conference on Intelligent Systems and Machines, pages 161--165, Rochester, Minnesota, USA.

....strategies is better tested on large problems. This paper uses the LandSat data set (36 features) the DNA data set (180 features) and the Cloud data set (204 features) For standard crossover operators, Guerra Salcedo Whitely [GW98] have shown that CHC [Esh91] performs better than GENESIS [Gre84], and that the performance difference is most pronounced for the largest (Cloud) data set. 1 The best feature subset during training can over fit the initial training data, and thus it may not be the best during final testing. The offspring of standard crossover operators inherit all of the ....

J. Grefenstette. (1984) "GENESIS: A System for Using Genetic Search Procedures." In Proceedings of a Conference on Intelligent Systems and Machines.

....on infeasible solutions with greater excessive load and or more overloaded concentrators, thus differentiating the degrees of infeasibility among strings. As mentioned earlier, the two software packages we use for our experimental runs are GENEsYs [2] which was based on Grefenstette s GENESIS [5], and LibGA [3] Both are implemented in C under the UNIX platform. In the next section, we introduce the third heuristic technique used in this research grouping genetic algorithms. We discuss the implementation issues and why and when the grouping genetic algorithms should be considered. 5 ....

Grefenstette, J. (1984). GENESIS: A System for Using Genetic Search Procedures. Proceedings of the Conference on Intelligent Systems and Machines, pp. 161--165.

....entire population Individuals are now mixed Apply genetic operators Generation (t 1) Start all over again Fig. 2. Schematic of VEGA selection. It is assumed that the population size is N and that there are M objective functions. 4. 1 VEGA David Schaffer [83] extended Grefenstette s GENESIS program [31] to include multiple objective functions. Schaffer s approach was to use an extension of the Simple Genetic Algorithm (SGA) that he called the Vector Evaluated Genetic Algorithm (VEGA) and that differed of the first only in the way in which selection was performed. This operator was modified so ....

J. J. Grefenstette. GENESIS: A system for using genetic search procedures. In Proceedings of the 1984 Conference on Intelligent Systems and Machines, pages 161--165, 1984.

....in the paper was conducted earlier under the supports of NSF Young Investigator Awards IRI 92 57293 and BCS 9257351. The software package for model simulation DDASAC was originated from M. Caracotsios and W. E. Stewart. The GENESIS implementation of GA was developed by John J. Grefenstette [42]. 0 200 400 600 800 1000 1200 1400 1600 0 2000 4000 6000 8000 10000 12000 Accumulated # of operations Trials Reflection Contraction (a) 0 200 400 600 800 1000 0 2000 4000 6000 8000 10000 12000 Accumulated # of operations Trials Contraction Reflection Contraction to the Best Expansion (b) ....

J. Grefenstette, "GENESIS: A system for using genetic search procedures," In Proceedings of the 1984 Conference of Intelligent Systems and Machines, pp. 161--165, 1984.

....data. Acknowledgements This research is partially supported by NSF Young Investigator Awards IRI 92 57293 and BCS9257351. The software package for model simulation DDASAC was originated from M. Caracotsios and W. E. Stewart. The GENESIS implementation of GA was developed by John J. Grefenstette [36]. ....

J. Grefenstette, "GENESIS: A system for using genetic search procedures," In Proceedings of the 1984 Conference of Intelligent Systems and Machines, pp. 161--165, 1984.

....amount of evolutionary progress after a fixed amount of time has passed. This is more similar to the experiments of Keesing and Stork [3] than the Hinton and Nowlan experiment [2] Before looking at the results, we detail the genetic algorithm portion of the experiment. Grefenstette s GENESIS [6] was used as the genetic algorithm, with default settings for mutation and crossover probabilities. The population size was set at fifty. The GA experiments all ran for exactly one thousand generations. Individuals are initially set to all zero bits for the first generation 2 . An individual in ....

J. J. Grefenstette. GENESIS: A System for Using Genetic Search Procedures. In Proceedings of a Conference on Intelligent Systems and Machines. 161--165, 1984.

....of two individuals into a new individual, whereas mutation changes the bits of an individual with some small probability. A discussion of genetic algorithm methodology is found in [6] The experiments reported here were conducted with Genesis 1. 2ucsd, which is a genetic algorithm tool written in C [11]. 3 Previous Results In earlier experiments the artificial immune system was used to test whether the genetic algorithm could evolve the gene libraries effectively [9] 10] Preliminary experiments showed that the genetic algorithm could easily evolve an immune system (one using gene libraries) ....

J. J. Grefenstette. GENESIS: A System for Using Genetic Search Procedures. In Proceedings of a Conference on Intelligent Systems and Machines. 161--165, 1984.

....training data, the procedural representation is inherently embedded in the decision tree. This procedural descriptiveness of the evaluation process is the main motivation to use decision trees. In order to implement the Genetic Module and ID3 we use GENESIS (GENEtic Search Implementation System [12], and C4.5, respectively. 4.Eye Detection Experimental Results This section describes the data used, the original list of possible features, and the detection architectures used to train and test the eye detection routine. The facial images are of 64x64 resolution Fig. 2 shows examples of ....

Grefenstette, J.J. (1984), Genesis: A system for using genetic search procedures, Proc. Conf. Intelligent Systems and Machines, pp.161-165.

.... component [3] Holland s goal was two fold: firstly, to explain the adaptive process of natural systems [3] and secondly, to design computing systems capable of embodying the important mechanisms of natural systems [3] Pioneering work of Holland [8] Goldberg [3] De Jong [2] Grefenstette [5], Davis [1] M hlenbein [10] and others is fuelling the spectacular growth of GAs. GAs are particularly suitable for the solution of complex optimisation problems, and consequently are good for applications that require adaptive problem solving strategies 1 . In addition, GAs are inherently ....

....others focus on a specific domain, such as finance (as with OMEGA) Algorithm oriented systems are programming systems which support specific genetic algorithms. They sub divide into: Algorithm specific systems which contain a single genetic algorithm; the classic example being GENESIS [5]. Algorithm Libraries where a variety of genetic algorithms and operators are grouped in library; as in Lawrence Davis OOGA[1] Algorithm oriented systems are often supplied in source code and can be easily incorporated into user applications. Tool Kits are programming systems that ....

[Article contains additional citation context not shown here]

J. J. Grefenstette "GENESIS: A System for Using Genetic Search Procedures" in Proceedings of the 1984 Conference on Intelligent Systems and Machines, pp. 161-165 -- 1984.

....for infeasible solutions on the mscp. More precisely, the traditional one and two point crossover, uniform crossover, and the recently suggested fusion crossover [5] are incorporated in the genetic algorithm GENEsYs. This package is based on Grefenstette s popular software package GENESIS [11]. The fitness function uses a graded penalty term to penalize infeasibly bred strings. Unlike other works, such as Beasley et al. 7] that use a tailor made fitness function, a variable mutation rate, or Huang et al. 12] whose custom made algorithm targets specific instances of the mcsp, ....

J. J. Grefenstette. Genesis: A system for using genetic search procedures. In Proceedings of the 1984 Conference on Intelligent Systems and Machines, pages 161--165, 1984.

No context found.

Grefenstette, J.J., "GENESIS: A System for Using genetic search procedures," In Proceedings of the Conference on Intelligent Systems and Machines, 1984, pp. 161-165.

No context found.

Grefenstette, J., 1984, `Genesis: A System For Using Genetic Search Procedures', Proceedings of a Conference on Intelligent Systems and Machines, 161-165.

No context found.

J. Grefenstette. Genesis: A system for using genetic search procedures. In Proceedings of the 1984.

No context found.

Grefenstette, J. J. (1984). Genesis: A system for using genetic search procedures, Proc. Conf. Intelligent Systems and Machines, 161-165.

No context found.

Grefenstette, John J. (1984). GENESIS: A system for using genetic search procedures. Proceedings of the 1984 Conference on Intelligent Systems and Machines, 161165.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC