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 following topics are dealt with: computational intelligence; natural computing; intelligent computing; Web intelligence; information processing; business intelligence; wireless computing; intelligent control; image processing; coal mine industry; grid computing; data mining; and neural network.
As a key technology of intelligent transportation system, higher identification accuracy, robustness and real-time are needed in vehicle recognition. Therefore, in view of the features of vehicle types, this paper proposes a BP neural network car types classifier method based on fuzzy C-means clustering. First, on the basis of the pretreatment of the images of the vehicle, we abstract the features...
The north of Jiaozhou Bay has become the important region for the development strategy of Qingdao in China, because the development space of the old city district gets saturated. The Moshui River will become the main contaminated river of this area. Neural network was used to build the water quality prediction model of the discharge outlet of the river to predict the concentration of COD, ammonia...
The study proposed the barrel algorithm based on barrel principle. The concept and operative steps were introduced and tested in auto-grading of tobacco leaves. The experiment demonstrated that the barrel algorithm could get a satisfied classification results in solving pattern recognition problems tallying with barrel theory. The method may provide the tobacco industry with a rapid and accurate method...
Applying Emotion Behavior Selection Mechanism to Dom World fight mode, a fight behavior mechanism based on emotions is built to discover how the result of a former fight influences, in emotion pattern, the decision and achievement of a letter fight. On Swarm soft platform of Artificial Life, consulting to the design and data of Dom Word simulation, a simulation of the proposed mechanism has been conducted...
The number of death and injury in the traffic accident is continue increasing year by year in China, which brings a great lost for social economy. In this paper we mainly studied on the data of traffic accident and follow volume in a certain section of road. And based on the theory of fuzzy mathematics and linear regulation to construct the fuzzy linear regression prediction model, and make an evaluation...
This paper presents a method of using nonlinear decision function to improve the performance of AdaBoost with SVM based weak learners. Compared with the existing AdaBoostSVM methods, this method, named ERBF-AdaBoostSVM, has advantages of higher hate rate and better generalization performance. This method also provides non-linear separator in the weak learner space and classifies accurately more examples...
This paper presents a GPS positioning method based on neural network adaptive Kalman filter. Using the innovation vector which reflects the degree how the model fits the data, and real-timely accessing to the innovation vector's ratio of the theoretical variance to the actual of variance, we can get the working conditions of Kalman filter. Then track the change of system parameters through neural...
Based on particle filter, a new training algorithm combining the extended Kalman filter (EKF) for neural network is presented. The new algorithm is firstly applied to train diagonal recurrent neural network (DRNN). A method to evaluate the dynamical performance of DRNN is introduced. Network weights of particles are optimized by the resampling algorithm. Simulation results of the nonlinear dynamical...
For the explosion of information in the World Wide Web, this paper proposed a new method of summarization for Internet news based on clustering algorithm. It used Google search engine to extract relevant documents, and mixed query sentence into sentences set which segmented from relevant document set, then this paper adopted effective cluster algorithm to cluster all the sentences. In the period of...
The job shop scheduling problem (JSSP) is one of the most difficult problems, as it is classified as an NP-complete one. In this paper, by integrating chaos mechanism and niche technique, a novel artificial immune algorithm based on the clonal selection principle and idiotypic immune network theory exhibited in biological immune system is proposed to solve classical job shop scheduling problem. Taking...
A great deal of region-related concept detection algorithms have been proposed so far, but there are few of them concerning about the problem of mismatched regions at training and testing stages. In order to investigate the mismatch problem in region-related concept detection, we introduce three kinds of methods to annotate the datasets, and then conduct experiments on differently annotated training...
Ontology is widely used in the computer domain to structure concepts that represent a view of world. In this paper, we present the coordination between two Agent Crawlers based on ontology and try to measure the understanding between them relying on Formal Concept Analysis instead of comparing terms only. Here we propose a novel method on concept similarity for computing the Concept-Concept similarity,...
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.