This paper describes REGAL, a distributed genetic algorithm-based system, designed for learning first-order logic concept descriptions from examples. The system is a hybrid of the Pittsburgh and the Michigan approache...
详细信息
This paper describes REGAL, a distributed genetic algorithm-based system, designed for learning first-order logic concept descriptions from examples. The system is a hybrid of the Pittsburgh and the Michigan approaches, as the population constitutes a redundant set of partial concept descriptions, each evolved separately. In order to increase effectiveness, REGAL is specifically tailored to the concept learning task;hence, REGAL is tusk-dependent, but, on the other hand, domain-independent. The system proved particularly robust with respect to parameter setting across a variety of different application domains. REGAL is based on a selection operator, called Universal Suffrage operator, provably allowing the population to asymptotically converge, on the average, to an equilibrium state in which several species coexist. The system is presented in both a serial and a parallel version, and a new distributed computationul model is proposed and discussed. The system has been tested on a simple artificial domain for the sake of illustration, and on several complex real-world and artificial domains in order to show its power and to analyze its behavior under various conditions. The results obtained so far suggest that genetic search may be a valuable alternative to logic-based approaches to learning concepts, when no (or little) a priori knowledge is available and a very large hypothesis space has to be explored.
Security is an essential factor in wireless sensor networks especially for E-health applications. One of the common mechanisms to satisfy the security requirements is cryptography. Among the cryptographic methods, ell...
详细信息
ISBN:
(纸本)9781509020881
Security is an essential factor in wireless sensor networks especially for E-health applications. One of the common mechanisms to satisfy the security requirements is cryptography. Among the cryptographic methods, elliptic curve cryptography is well-known, as by having a small key length it provides the same security level in comparison with the other public key cryptosystems. The small key sizes make ECC very interesting for devices with limited processing power or memory such as wearable devices for E-health applications. It is vitally important that elliptic curves are protected against all kinds of attacks concerning the security of elliptic curve cryptography. Selection of a secure elliptic curve is a mathematically difficult problem. In this paper, an efficient elliptic curve selection framework, called SEECC, is proposed to select a secure and efficient curve front all the available elliptic curves. This method enhances the security and efficiency of elliptic curve cryptosystems by using a parallelgenetic algorithm.
作者:
Jones, Antonia J.Department of Computing
Imperial College of Science Technology and Medicine University of London London SW7 2BZ 180 Queen's Gate United Kingdom
This paper explores OpenCL implementations of a genetic algorithm used to optimize the features vector in periocular biometric recognition. Using a multi core platform the algorithm is tested for CPU and GPU, explorin...
详细信息
ISBN:
(纸本)9783642353796;9783642353802
This paper explores OpenCL implementations of a genetic algorithm used to optimize the features vector in periocular biometric recognition. Using a multi core platform the algorithm is tested for CPU and GPU, exploring different parallelization levels for each operator of the genetic algorithm. The results show that using the GPU platform it is possible to accelerate the algorithm by several orders of magnitude, with a recognition rate similar to the one obtained in the sequential version. The results also show that it is possible to use only a small portion of the features without any degradation of the classifier's recognition rate.
In this paper we propose a many-core implementation of evolutionary computation for GPGPU (General-Purpose Graphic Processing Unit) to solve non-convex Mixed Integer Non-Linear Programming (MINLP) and non-convex Non L...
详细信息
ISBN:
(纸本)9781424478354
In this paper we propose a many-core implementation of evolutionary computation for GPGPU (General-Purpose Graphic Processing Unit) to solve non-convex Mixed Integer Non-Linear Programming (MINLP) and non-convex Non Linear Programming (NLP) problems using a stochastic algorithm. Stochastic algorithms being random in their behavior are difficult to implement over GPU like architectures. In this paper we not only succeed in implementation of a stochastic algorithm over GPU but show considerable speedups over CPU implementations. The stochastic algorithm considered for this paper is an adaptive resolution approach to genetic algorithm (arGA), developed by the authors of this paper. The technique uses the entropy measure of each variable to adjust the intensity of the genetic search around promising individuals. Performance is further improved by hybridization with adaptive resolution local search (arLS) operator. In this paper, we describe the challenges and design choices involved in parallelization of this algorithm to solve complex MINLPs over a commodity GPU using Compute Unified Device Architecture (CUDA) programming model. Results section shows several numerical tests and performance measurements obtained by running the algorithm over an nVidia Fermi GPU. We show that for difficult problems we can obtain a speedup of up to 20x with double precision and up to 42x with single precision.
In this paper we investigate the applicability of geneticalgorithms (GAs) for solving Constraint Satisfaction Problems (CSPs). Despite some success of GAs when tackling CSPs, they generally suffer from poor crossover...
详细信息
ISBN:
(数字)9783642371981
ISBN:
(纸本)9783642371981
In this paper we investigate the applicability of geneticalgorithms (GAs) for solving Constraint Satisfaction Problems (CSPs). Despite some success of GAs when tackling CSPs, they generally suffer from poor crossover operators. In order to overcome this limitation in practice, we propose a novel crossover specifically designed for solving CSPs. Together with a variable ordering heuristic and an integration into a parallel architecture, this proposed crossover enables the solving of large and hard problem instances as demonstrated by the experimental tests conducted on randomly generated CSPs based on the model RB. We will indeed demonstrate, through these tests, that our proposed method is superior to the known GA based techniques for CSPs. In addition, we will show that we are able to compete with the efficient MAC-based Abscon 109 solver for random problem instances.
geneticalgorithms have worked fairly well for the VLSI cell placement problem, albeit with significant run times. Two parallel models for GA are presented for VLSI cell placement where the objectives axe optimizing p...
详细信息
ISBN:
(纸本)1595930108
geneticalgorithms have worked fairly well for the VLSI cell placement problem, albeit with significant run times. Two parallel models for GA are presented for VLSI cell placement where the objectives axe optimizing power dissipation, timing performance and interconnect wirelength, while layout width is a constraint. A Master-Slave approach is mentioned wherein both fitness calculation and crossover mechanism are distributed among slaves. A Multi-Deme parallel GA is also presented in which each processor works independently on an allocated subpopulation followed by information exchange through migration of chromosomes. A pseudo-diversity approach is taken, wherein similar solutions with the same overall cost values are not permitted in the population at any given time. A series of experiments are performed on ISCAS-85/89 benchmarks to show the performance of the Multi-Deme approach.
This work deals with a global model of PGA. A short overview of the model is introduced. Our research is concentrated on a master-slave algorithm (somewhere also called global). The complexity analysis of the algorith...
详细信息
ISBN:
(纸本)9780889866294
This work deals with a global model of PGA. A short overview of the model is introduced. Our research is concentrated on a master-slave algorithm (somewhere also called global). The complexity analysis of the algorithm is created and the processor optimality is derived from the analysis. Based on the optimality derivation, theoretical results with results from the real implementation are compared and the limitations of the algorithm are stated.
This paper addresses the problem of computing the three-dimensional motions of objects and proposes a robust approach to position estimation of moving objects by exploiting the only available geometric constraint, nam...
详细信息
ISBN:
(纸本)0964345692
This paper addresses the problem of computing the three-dimensional motions of objects and proposes a robust approach to position estimation of moving objects by exploiting the only available geometric constraint, namely, the epipolar constraint. The extrinsic parameters of the camera and the motion of the stereo rig is unknown. If we make an exhaustive search for the epipolar geometry, the complexity is prohibitively high. The idea underlying our approach is to use a parallel fine-grain GA as an optimizer. Since the constraint on the rotation matrix is not fully exploited in the analytical method, nonlinear minimization can be used to improve the result.
This paper shows the computational benefits of a game theoretic approach to optimization of high dimensional control problems. A dynamic noncooperative game framework is adopted to partition the control space and to s...
详细信息
This paper shows the computational benefits of a game theoretic approach to optimization of high dimensional control problems. A dynamic noncooperative game framework is adopted to partition the control space and to search the optimum as the equilibrium of a k-person dynamic game played by k-parallel genetic algorithms. When there are multiple inputs, we delegate control authority over a set of control variables exclusively to one player so that k artificially intelligent players explore and communicate to learn the global optimum as the Nash equilibrium. In the case of a single input, each player's decision authority becomes active on exclusive sets of dates-so that k GAs construct the optimal control trajectory as the equilibrium of evolving best-to-date responses. Sample problems are provided to demonstrate the gains in computational speed and accuracy. (C) 2000 Elsevier Science B.V. All rights reserved.
暂无评论