The article shows how rough sets can be applied to improve the classification ability of a hybrid pattern recognition system. The system presented here consists of a feature extractor based on a computer-generated hologram (CGH) playing the role of a ring-wedge detector. Features extracted by it are shift, rotation, and scale invariant. Although they can be optimized, no method has been proposed in the literature. This article presents an original method of optimizing the feature extraction abilities of a CGH. The method uses rough set theory (RST) to measure the amount of essential information contained in the feature vector. This measure is used to define an objective function in the optimization process. Since RST-based factors are not differentiable, we use a nongradient approach for a search in the space of possible solutions. Finally, RST is used to determine decision rules for the classification of feature vectors. The alternative method of classification based on neural networks is also discussed. The whole method is illustrated by a system recognizing the class of speckle pattern images indicating the class of distortion of optical fibers. © 2001 John Wiley & Sons, Inc.

Many papers describe hybrid methods used for pattern recognition. Such systems consist of an optical part, performing fast signal preprocessing, and a computer, analyzing preprocessed data. Here we present the method which uses for feature extraction the ring-wedge detectors (RWD) or computer generated holograms (CGH) serving as RWD. Features obtained in this way are shift, rotation, and scale invariant, but papers suggest that they can be still subject for further optimization. This article presents an original method for optimizing feature extraction abilities of CGH. This method uses rough set theory (RST) to measure the amount of essential information for the classification, preserved in feature vector. As there is no gradient direction information in factors defined by RST, we use for a space search a stochastic evolutionary approach. Finally, we use RST to determine decision rules for the feature vector classification. The whole method is illustrated by a system recognizing the speckle pattern images obtained as a result of interference of light going through a quasi-monomode optical fiber. As the conditions of interference differ when some kind of distortion of the optical fiber is produced, such a system can be used as a sensor of the pressure causing this distortion. © 2000 John Wiley & Sons, Inc.

Alternative approaches to data processing, e.g., fuzzy set theory, rough set theory and neural networks, known collectively as ‘soft computing,’ have drawn significant interest from the scientific community. They have already found numerous applicati

The inverted pendulum poses serious problems for qualitative modeling methods, so it is a good benchmark to lest their performance. This paper shows how a new data analysis method known as rough set theory can be utilized to swing up and stabilize the pendulum. Our approach to this task consists of deriving control rules from the actions of a human operator stabilizing the pendulum and subsequently using them for automatic control. Rule derivation is based on the “learning from examples” principle and does not require knowledge of a quantitative model of the system.