In patternrecognition, feature selection is a quite important process for constructing practical systems. However, because there are many features as candidates to recognize object, it is difficult to select appropri...
详细信息
ISBN:
(纸本)9780769547633;9781467321389
In patternrecognition, feature selection is a quite important process for constructing practical systems. However, because there are many features as candidates to recognize object, it is difficult to select appropriate features for patternrecognition systematically. The previous research proposed a patternrecognition method using the ensemble system based on fuzzy classifier for multiple feature selection. However, this method can not apply for the problems with many input vectors because it takes a lot of time for learning when the number of the input vector increases. In this study, an attempt is made to overcome the problem by introducing ID3 (Iterative Dichotomizer 3) with classifiers consisting of many feature vectors. ID3 constructs a decision tree for multiple feature selection with the results obtained from classifiers based on each feature. Therefore, it is possible to select appropriate features applied many input vectors. Several benchmark problems are presented to demonstrate the efficiency and applicability of the proposed method.
This paper presents speaker recognition system possessing very good generalization properties. Relatively low equal error rate for speaker verification and high identification rate for identification are achieved for ...
详细信息
ISBN:
(纸本)9781479938247
This paper presents speaker recognition system possessing very good generalization properties. Relatively low equal error rate for speaker verification and high identification rate for identification are achieved for very short training and testing sequences. This behaviour is achieved for the kernel modification of a classic Ho-Kashyap linear classifier. Achieved results for the new approach are compared with results for the classic GMM and VQ techniques. Speech of a moderately good quality from the Polish speech corpus was used for development of recognition system.
softcomputing admits approximate reasoning, imprecision, uncertainty and partial truth in order to mimic aspects of the remarkable human capabilityof making decisions in real-life and ambiguous environments. "So...
ISBN:
(数字)9783540707066
ISBN:
(纸本)9783540707042
softcomputing admits approximate reasoning, imprecision, uncertainty and partial truth in order to mimic aspects of the remarkable human capabilityof making decisions in real-life and ambiguous environments. "softcomputing in Industrial Applications" contains a collection of papers that were presented at the 11th On-line World conference on softcomputing in Industrial Applications, held in September-October 2006. This carefully edited book provides a comprehensive overview of the recent advances in the industrial applications of softcomputing and covers a wide range of application areas, including data analysis and data mining, computer graphics, intelligent control, systems, patternrecognition, classifiers, as well as modeling optimization. The book is aimed at researchers and practitioners who are engaged in developing and applying intelligent systems principles to solving real-world problems. It is also suitable as wider reading for science and engineering postgraduate students.
This article presents the use of Customized Multi-Layer ANN based patternrecognition Technique for the numerical differential protection of a power transformer. An efficient Resilient Back Propagation trained neural ...
详细信息
Edge detection has been used in many applications such as image analysis, patternrecognition and computer vision. Various edge detection techniques are used in images to filter out less relevant information while pre...
详细信息
ISBN:
(纸本)9781467379182
Edge detection has been used in many applications such as image analysis, patternrecognition and computer vision. Various edge detection techniques are used in images to filter out less relevant information while preserving the basic structural properties in different domains. In this paper a critical evaluation of various edges detection techniques with softcomputing techniques has been examined.
Work is in on line Arabic character recognition and the principal motivation is to study the Arab manuscript with on line technology. This system is a Markovien system which one can see as like a Dynamic Bayesian Netw...
详细信息
ISBN:
(纸本)9781467315203
Work is in on line Arabic character recognition and the principal motivation is to study the Arab manuscript with on line technology. This system is a Markovien system which one can see as like a Dynamic Bayesian Network (DBN). One of the major interests of these systems resides in the complete models training (topology and parameters) starting from training data. Our approach is based on the dynamic Bayesian Networks formalism. The DBNs theory is a Bayesiens networks generalization to the dynamic processes. Among our objective, amounts finding better parameters which represent the links (dependences) between dynamic network variables. In applications in patternrecognition, one will carry out the fixing structure which obliges us to admit some strong assumptions (for example independence between some variables). Our application will relate to the Arabic isolated characters on line recognition using our laboratory data base: NOUN. A neural tester proposed for DBN external optimization.
In order to maximize the available performance of the Li-ion batteries, a searching algorithm for an optimal fast charging pattern using particle swarm optimization (PSO) with an evaluation index based on the fuzzy-de...
详细信息
ISBN:
(纸本)9781467327435;9781467327428
In order to maximize the available performance of the Li-ion batteries, a searching algorithm for an optimal fast charging pattern using particle swarm optimization (PSO) with an evaluation index based on the fuzzy-deduced cost function is proposed in this paper. An optimal five-stage charging strategy is obtained by the PSO searching according to the decision-making in the fitness evaluation index that is computed from the cost function. The cost function formulated by two paramount parameters, charge time and discharge capacity, is employed to assess the cost benefit of the applied charging pattern. Regulating rules of weighting within the cost function are derived from the fuzzy logic inference to attain the best fitness evaluation. The proposed searching methodology for optimal multistage charging pattern features characteristics of fast convergence, effectiveness and easy to implement. Experimental results show that the obtained rapid charging pattern is capable of charging the batteries to 90% available capacity within 51 minutes and also provides 22% more cycle life than the conventional constant current-constant voltage (CC-CV) method.
In disaster areas, rescue work by humans is extremely difficult. Therefore, rescue work using rescue robots in place of humans is attracting attention. This study specifically examines peristaltic crawling, the moveme...
详细信息
ISBN:
(纸本)9781467327435;9781467327428
In disaster areas, rescue work by humans is extremely difficult. Therefore, rescue work using rescue robots in place of humans is attracting attention. This study specifically examines peristaltic crawling, the movement mechanism of an earthworm, because it can enable movement through narrow spaces and because it can provide stable movement according to various difficult environments. We develop a robot using peristalsis characteristics and derive a robot motion pattern using Q-learning, a mode of reinforcement learning. Additionally, we confirmed the convergence to the most suitable solution by coordinating Q-learning parameters.
The representations of outer world in the brain are considered to be undertaken by spatiotemporal activity patterns of neuronal circuits. In this study, we analyzed the transition of the internal states of the circuit...
详细信息
ISBN:
(纸本)9781509049172
The representations of outer world in the brain are considered to be undertaken by spatiotemporal activity patterns of neuronal circuits. In this study, we analyzed the transition of the internal states of the circuit of rat hippocampal neurons cultured on a multi-electrodes-array-dish. We analyzed transition of center of gravity and 64-dimensional feature-vectors of electrical activity patterns. Electrical activity pattern at a certain 5-ms-width-time-window was represented as a 64 dimensional "0-1" feature vector, and analyzed the stability. We confirmed that the reproducibility of the neuronal network activity increased during culture days. In addition, we applied similarity analysis to 64-dimensional feature vectors of neuronal activity. Using X-means algorithm, feature vectors were classified into "pattern repertories" based on the spatial distribution of activity.
Today in data mining research we are daily confronted with large amount of data. Most of the time, these data contain redundant and irrelevant data that it is important to extract before a learning task in order to ge...
详细信息
ISBN:
(纸本)9781467369619
Today in data mining research we are daily confronted with large amount of data. Most of the time, these data contain redundant and irrelevant data that it is important to extract before a learning task in order to get good accuracy. The fact that today's computers are more powerful does not solves the problems of this ever-growing data. It is therefore crucial to find techniques which allow handling these large databases often too big to be processed. Data reduction techniques are therefore a very important step to prepare the data before data mining and knowledge discovery. In this paper we present a comparative study on original and reduced data to see the role data reduction in a learning task. For this purpose, we used a medical dataset;especially a vertebral column pathologies database.
暂无评论