The Experts below are selected from a list of 216 Experts worldwide ranked by ideXlab platform
Pawel Lichocki - One of the best experts on this subject based on the ideXlab platform.
-
approximating geometric crossover in semantic space
Genetic and Evolutionary Computation Conference, 2009Co-Authors: Krzysztof Krawiec, Pawel LichockiAbstract:We propose a crossover operator that works with genetic programming trees and is approximately geometric crossover in the semantic space. By defining semantic as program's evaluation profile with respect to a set of fitness cases and constraining to a specific class of metric-based fitness Functions, we cause the fitness landscape in the semantic space to have perfect fitness-distance correlation. The proposed approximately geometric semantic crossover exploits this property of the semantic fitness landscape by an appropriate sampling. We demonstrate also how the proposed method may be conveniently combined with hill climbing. We discuss the properties of the methods, and describe an extensive computational experiment concerning Logical Function synthesis and symbolic regression.
-
GECCO - Approximating geometric crossover in semantic space
Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09, 2009Co-Authors: Krzysztof Krawiec, Pawel LichockiAbstract:We propose a crossover operator that works with genetic programming trees and is approximately geometric crossover in the semantic space. By defining semantic as program's evaluation profile with respect to a set of fitness cases and constraining to a specific class of metric-based fitness Functions, we cause the fitness landscape in the semantic space to have perfect fitness-distance correlation. The proposed approximately geometric semantic crossover exploits this property of the semantic fitness landscape by an appropriate sampling. We demonstrate also how the proposed method may be conveniently combined with hill climbing. We discuss the properties of the methods, and describe an extensive computational experiment concerning Logical Function synthesis and symbolic regression.
Krzysztof Krawiec - One of the best experts on this subject based on the ideXlab platform.
-
approximating geometric crossover in semantic space
Genetic and Evolutionary Computation Conference, 2009Co-Authors: Krzysztof Krawiec, Pawel LichockiAbstract:We propose a crossover operator that works with genetic programming trees and is approximately geometric crossover in the semantic space. By defining semantic as program's evaluation profile with respect to a set of fitness cases and constraining to a specific class of metric-based fitness Functions, we cause the fitness landscape in the semantic space to have perfect fitness-distance correlation. The proposed approximately geometric semantic crossover exploits this property of the semantic fitness landscape by an appropriate sampling. We demonstrate also how the proposed method may be conveniently combined with hill climbing. We discuss the properties of the methods, and describe an extensive computational experiment concerning Logical Function synthesis and symbolic regression.
-
GECCO - Approximating geometric crossover in semantic space
Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09, 2009Co-Authors: Krzysztof Krawiec, Pawel LichockiAbstract:We propose a crossover operator that works with genetic programming trees and is approximately geometric crossover in the semantic space. By defining semantic as program's evaluation profile with respect to a set of fitness cases and constraining to a specific class of metric-based fitness Functions, we cause the fitness landscape in the semantic space to have perfect fitness-distance correlation. The proposed approximately geometric semantic crossover exploits this property of the semantic fitness landscape by an appropriate sampling. We demonstrate also how the proposed method may be conveniently combined with hill climbing. We discuss the properties of the methods, and describe an extensive computational experiment concerning Logical Function synthesis and symbolic regression.
Daniel Foito - One of the best experts on this subject based on the ideXlab platform.
-
A Sensorless Speed Control System for an Electric Vehicle without Mechanical Differential Gear
, 2006. MELECON 2006., 2006Co-Authors: Armando Cordeiro, Daniel FoitoAbstract:Two DC motors drive the two independent rear wheel of an electric vehicle with electric differential. The speed estimation of each wheel drive is based on the voltage equation which requires the voltage and armature current measures and a previous knowledge of the machine parameters. The current limitation and the speed control of the DC motors are determined by the result of a Logical Function, thus PI controllers are unnecessary. The overall control strategy is guaranteed by a single microcontroller, PIC18F452
-
A Sensolrless Speed Control System for an Electric Vehicle without Mechanical Differential Gear
Electrotechnical Conference, 2006. MELECON 2006. IEEE Mediterranean, 2006Co-Authors: Armando Cordeiro, Daniel Foito, Manuel GuerreiroAbstract:Two DC motors drive the two independent rear wheel of an electric vehicle with electric differential. The speed estimation of each wheel drive is based on the voltage equation which requires the voltage and armature current measures and a previous knowledge of the machine parameters. The current limitation and the speed control of the DC motors are determined by the result of a Logical Function, thus PI controllers are unnecessary. The overall control strategy is guaranteed by a single microcontroller, PIC18F452
Armando Cordeiro - One of the best experts on this subject based on the ideXlab platform.
-
A Sensorless Speed Control System for an Electric Vehicle without Mechanical Differential Gear
, 2006. MELECON 2006., 2006Co-Authors: Armando Cordeiro, Daniel FoitoAbstract:Two DC motors drive the two independent rear wheel of an electric vehicle with electric differential. The speed estimation of each wheel drive is based on the voltage equation which requires the voltage and armature current measures and a previous knowledge of the machine parameters. The current limitation and the speed control of the DC motors are determined by the result of a Logical Function, thus PI controllers are unnecessary. The overall control strategy is guaranteed by a single microcontroller, PIC18F452
-
A Sensolrless Speed Control System for an Electric Vehicle without Mechanical Differential Gear
Electrotechnical Conference, 2006. MELECON 2006. IEEE Mediterranean, 2006Co-Authors: Armando Cordeiro, Daniel Foito, Manuel GuerreiroAbstract:Two DC motors drive the two independent rear wheel of an electric vehicle with electric differential. The speed estimation of each wheel drive is based on the voltage equation which requires the voltage and armature current measures and a previous knowledge of the machine parameters. The current limitation and the speed control of the DC motors are determined by the result of a Logical Function, thus PI controllers are unnecessary. The overall control strategy is guaranteed by a single microcontroller, PIC18F452
Pla Information - One of the best experts on this subject based on the ideXlab platform.
-
Chrestenson Spectrum and Auto-correlation Function of m-value “Composition” Logical Function and Applications
Journal of Electronics Information & Technology, 2006Co-Authors: Pla InformationAbstract:This paper presents the formula of Chrestenson spectrum of m-value “composition” Logical Function by using inversion formula, and gives the formula of auto-correlation Function of m-value “composition” Logical Function. Furthermore, this paper gives some conditions under which m-value “composition” Logical Function is separate balanced or correlation-immune, and analyzes the auto-correlation Function of m-value “composition” Logical Function and its charateristic. Moreover, this paper gets the Chrestenson spectrum formular of nonzero linear combination of several m-value “composition” Logical Functions.
-
The Strict Avalanche Criterion of Order k Spectral Properties of m-Valued Logical Functions
2005Co-Authors: Pla InformationAbstract:Many cryptographic properties of m-valued Logical Functions are often described by their Chrestenson cyclic spectrums and auto-correlation Functions,so Chrestenson cyclic spectrums and auto-correlation Functions play important roles in properties and constructions for m-valued Logical Functions.In this paper,in residue class ring Z_m,the concept of the strict avalanche criterion of order k of m-valued Logical Functions is presented. Then,by applying probabilistic thought and methods,the rule that a m-valued Logical Function fulfills the SAC of lower order if it fulfills the SAC of higher order is proved.Finally,by Chrestenson cyclic spectrums,a necessary and sufficient condition on a mvalued Logical Function is given,which fulfills the strict avalanche criterion of order k.
-
Multiple Block Affine Approximation of m valued Logical Function
Operations Research and Management Science, 1999Co-Authors: Pla InformationAbstract:This paper defines the Chrestenson transformations of m valued Logical Functions over a nonempty subset D of z n m and gives some properties of such Chrestenson transformations. Based on it,the methods of multiple block affine approximation of m valued Logical Functions are proposed. And the superiority of the methods is simultaneously considered. We put a special emphasis on the multiple block affine approximation of Boolean Functions. As an application of the results concerned,we obtain the maximum correlators of Boolean Functions with the set of all Boolean combinations of a subset of its variables.