The computer recognition systems are nowadays one of the most promising directions in artificial intelligence. This book is the most comprehensive study of this field. It contains a collection of 69 carefully selected...
ISBN:
(数字)9783540939054
ISBN:
(纸本)9783540939047
The computer recognition systems are nowadays one of the most promising directions in artificial intelligence. This book is the most comprehensive study of this field. It contains a collection of 69 carefully selected articles contributed by experts of pattern recognition. It reports on current research with respect to both methodology and applications. In particular, it includes the following sections: Features, learning and classifiers, Image processing and computer vision, Speech and word recognition, Medical applications, Miscellaneous applications. This book is a great reference tool for scientists who deal with the problems of designing computer pattern recognition systems. Its target readers can be the as well researchers as students of computer science, artificial intelligence or robotics.
In this study, a four-stage SVM-based multiagent ensemble learning approach is proposed for group decision making problem. In the first stage, the initial dataset is divided into training subset and testing subset for...
详细信息
ISBN:
(纸本)9783540896180
In this study, a four-stage SVM-based multiagent ensemble learning approach is proposed for group decision making problem. In the first stage, the initial dataset is divided into training subset and testing subset for training and testing purpose. In the second stage, different SVM learning paradigms with much dissimilarity are constructed as diverse agents for group decision making. In the third stage, multiple single SVM agents are trained using training subset and the corresponding decision resulcts are also obtained. In the final stage, all individual results produced by multiple single SVM agents are aggregated into a group decision result. Particularly, the effects of different diversity strategies and different ensemble strategies on multiagent ensemble learning system are tested. For illustration, one credit application approval dataset is used and empirical results demonstrated the impacts of different diversity strategies and ensemble strategies.
Optimizing the antecedent part of neuro-fuzzy system is investigated in a number of documents. Current approaches typically suffer from high computational complexity or lack of ability to extract knowledge from a give...
详细信息
ISBN:
(纸本)9783540896180
Optimizing the antecedent part of neuro-fuzzy system is investigated in a number of documents. Current approaches typically suffer from high computational complexity or lack of ability to extract knowledge from a given set of training data. In this paper, we introduce a novel incremental training algorithm for the class of neuro-fuzzy systems that are structured based on local linear classifiers. Linear discriminant analysis is utilized to transform the data into a space in which linear discriminancy of training samples is maximized. The neuro-fuzzy classifier is built in the transformed space, starting from the simplest form. In addition, rule consequent parameters are optimized using a local least square approach.
An information visualization framework is proposed that considers key human factors for effective complex data perception and. cognition. Virtual reality (VR) technology with data transformation heuristics are deploye...
详细信息
ISBN:
(纸本)9783642032011
An information visualization framework is proposed that considers key human factors for effective complex data perception and. cognition. Virtual reality (VR) technology with data transformation heuristics are deployed in building the framework where an interactive VR-based 3-D information visualization platform is developed. The framework is applied to develop a visualization system for an express cargo handling center where analysts are able to effectively perceive operation details and carry out timely decision making.
In this study, the disturbance and uncertainty on nonlinear and time varying systems as Active Queue Management (AQM) is analyzed. Many of AQM schemes have been proposed to regulate a queue size close to a reference l...
详细信息
ISBN:
(纸本)9783540896180
In this study, the disturbance and uncertainty on nonlinear and time varying systems as Active Queue Management (AQM) is analyzed. Many of AQM schemes have been proposed to regulate a queue size close to a reference level with the least variance. We apply a normal range of disturbances and uncertainty such as variable user numbers, variable link capacity, noise, and unresponsive flows, to the three AQM methods: Random Early Detection (RED), Proportional-Integral (PI) and Improved Neural Network (INN) AQM. Then we examine some important factors for TCP network congestion control such as queue size, drop probability, variance and throughput in NS-2 simulator, and then compare three AQM algorithms with these factors on congestion conditions. We present the performance of the INN controller in desired queue tracking and disturbance rejection is high.
Multi-agent systems have been employed for modeling dynamical and complex systems. In order to control these agent societies, the normative theory has arisen inside multi-agent system area as a coordination mechanism,...
详细信息
ISBN:
(纸本)9783642004865
Multi-agent systems have been employed for modeling dynamical and complex systems. In order to control these agent societies, the normative theory has arisen inside multi-agent system area as a coordination mechanism, being a key element in open systems. In this paper, a new normative reasoning process is presented. It allows agents to consider the existence of a dynamical normative context that regulates their behaviors.
This paper proposes a dynamic structured interaction among members of population in a Quantum Evolutionary Algorithms (QEA). The structured population is allowed to expand/collapse based on a functional population siz...
详细信息
ISBN:
(纸本)9783540896180
This paper proposes a dynamic structured interaction among members of population in a Quantum Evolutionary Algorithms (QEA). The structured population is allowed to expand/collapse based on a functional population size and partial reinitialization of new members in the population. Several structures are compared here and the study shows that the best structure for QEA is the cellular structure which can be an efficient architecture for an effective Exploration/Exploitation tradeoff, and the partial re-initialization of the proposed algorithm can improve the diversity of the algorithm. The proposed approach is tested on Knapsack Problem, Trap Problem as well as 14 numerical optimization functions. Experimental results show that the proposed Structure consistently improves the performance of QEA.
It is important to discover hierarchical decision rules from databases because much of the world's knowledge is best expressed in the form of hierarchies. Mining of decision rules at multiple concept levels leads ...
详细信息
ISBN:
(纸本)9783540896180
It is important to discover hierarchical decision rules from databases because much of the world's knowledge is best expressed in the form of hierarchies. Mining of decision rules at multiple concept levels leads to discovery of more informative and comprehensible knowledge. This paper proposes automated discovery of Hierarchical Production Rules (HPR) using a parallel genetic algorithm approach. A combination of degree of subsumption and coefficient of similarity has been used as a quantitative measure of hierarchical relationship among the classes. An island/detne GA is designed to evolve HPRs for the classes of the dataset being mined. The island model exploits control as well as data parallelism. The model is applied to a synthetic dataset on means of transport and results are presented.
作者：
Borrego, CarlosRobles, SergiIFAE
Inst High Energy Phys Fac Ciencies Campus UAB Edifici Cn E-08193 Bellaterra Spain DEIC
E-08193 Barcelona Spain
Grid computing is consolidated as a technology capable of solving scientific projects of our century. These projects' needs include complex computational and large data storage resources. The goal of grid Computin...
详细信息
ISBN:
(纸本)9783642004865
Grid computing is consolidated as a technology capable of solving scientific projects of our century. These projects' needs include complex computational and large data storage resources. The goal of grid computing is to share these resources among different institutes and virtual organizations across high-speed networks. The more resources there are the more difficult it gets to monitor them and to assure users find the best resources they are looking for. We introduce the concept of relative information to enhance grid information and grid monitoring services. Resource relative information is information that is not only gathered from the resource itself but also that takes into account other resources of the same type. The resource is not described in terms of the resource local information but also relative to other resources. We present a framework based on mobile agents that enables to publish relative information in the grid information service and another framework to monitor grid resources using relative criteria.
Spread spectrum audio watermarking (SSW) is one of the most secure techniques of audio watermarking. SSW hides information by spreading their spectrum which is called watermark and adds it to a host signal as a waterm...
详细信息
ISBN:
(纸本)9783540896180
Spread spectrum audio watermarking (SSW) is one of the most secure techniques of audio watermarking. SSW hides information by spreading their spectrum which is called watermark and adds it to a host signal as a watermarked signal. Spreading spectrum is done by a pseudo-noise (PN) sequence. In conventional SSW approaches, the receiver must know the PN sequence used at the transmitter as well as the location of the watermark in watermarked signal for detecting hidden information. This method is attributed high security features, since any unauthorized user who does not access this information cannot detect any hidden information. Detection of the PN sequence is the key factor for detection of hidden information from SSW. Although PN sequence detection is possible by using heuristic approaches such as evolutionary algorithms, due to the high computational cost of this task, such heuristic tends to become too expensive (computationally speaking), which can turn it impractical. Much of the computational complexity involved in the use of evolutionary algorithms as an optimization tool is due to the fitness function evaluation that may either be very difficult to define or be computationally very expensive. This paper proposes the use of fitness granulation to recover a PN sequence with a chip period equal to 63, 127, 255 bits. This is a new application of authors' earlier work on adaptive fitness function approximation with fuzzy supervisory. With the proposed approach, the expensive fitness evaluation step is replaced by an approximate model. The approach is then compared with standard application of evolutionary algorithms;statistical analysis confirms that the proposed approach demonstrates an ability to reduce the computational complexity of the design problem without sacrificing performance.
暂无评论