The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The single biometric identification technology has the inherent and difficult overcoming shortcomings, so multi-modal biometric fusion and identification techniques were proposed to improve the performance and accurate rate of identification system. This paper proposed a model combined with 2-dimensional Fisher linear discriminant analysis for face and iris feature fusion and recognition. First face...
Data classification has been studied widely in the fields of Artificial Intelligence, Machine Learning, Data Mining and Pattern Recognition. Up to the present, the development of classification has made great achievements, and many kinds of classified technology and theory will continue to emerge. This paper discusses a great deal of classification algorithms based on the Artificial Neural Networks,...
The posterior union decision-based neural network (PUD-BNN) has been proposed in our previous work for dealing with face recognition task subject to partial occlusion and distortion. However, one difficult of this method is inaccurate to model classes with only a single, or a small number of training samples. In this paper, we proposed an extern approach to tackle above problem by two strategies....
To locate the object accurately in a scene for further vision processing, a novel approach for figure-ground segmentation is proposed, which combines the normalized-cut method (Ncut) and top-down method inspired by the trickle-up and trickle-down processing in primate visual pathways. Firstly, as the trickle-up stage, the Ncut method groups the pixels into multiple partitions based on the global criterion,...
Web document classification is the process of grouping web documents into one or more predefined categories based on their content. It is an important component of web monitor system that can assist people to reduce the dissemination of harmful information. This paper proposes a combined approach for building a decision tree with the multilayer neural network as its categorically value function, and...
A face recognition method similar to human cognitive mechanism has been proposed. Motivated by the continuity rule of a same class samples, face recognition can be regarded as face pattern cognition. Compared with traditional statistical pattern based face recognition, it has a kind of relationship with human's cognitive mechanism. When face coverage of different people overlap, a person's face distribution...
Effects of farmer field school (FFS) and the conventional (classroom lectures) training on acquisition of pest management knowledge and skills by small vegetable farmers were studied in Yunnan province, China from 2003 to 2007. There were significant gains of knowledge about vegetable pests, natural enemies, insect and disease ecology and pest management among the FFS farmers, but were no significant...
This paper presents a new wrapper-based feature selection method for multi-layer perceptrons (MLP) neural networks. It uses a feature ranking criterion to measure the importance of a feature by computing the aggregate difference, over the feature space, of the probabilistic outputs of the MLP with and without the feature. Thus, a score of importance with respect to every feature can be provided using...
Novel feature-selection methods are proposed for multi-class support-vector-machine (SVM) learning. They are based on two new feature-ranking criteria. Both criteria, collectively termed multi-class feature-based sensitivity of posterior probabilities (MFSPP), evaluate the importance of a feature by computing the aggregate value, over the feature space, of the absolute difference of the probabilistic...
The paper provides a new idea on improving the calculating speed of the complex economic system evaluation by adopting the LM algorithms based on BP artificial neural network. It deeply discusses the concrete implementation process of LM and BP algorithms by using the comprehensive economic performance evaluation on fixed assets invest economic performance module as the example, and carries on the...
An accurate friction model is necessary for friction compensation in radar servo systems or industrial robots. In order to obtain an accurate friction model, a method of friction modelling is proposed, based on support vector regression machines (SVRM) and real genetic algorithms (RGA). Three optimization problem formulations are proposed to realize the automatic optimal parameter selection of SVMR...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.