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.
Indoor Location information service (ILS) has been the hot topics of research in recent years. However, localization cost and positioning accuracy is still a challenge for indoor positioning system (IPS). RFID positioning technology is low cost but high positioning accuracy which is usually used for an IPS. In this study, a RFID indoor positioning algorithm is proposed, which is based on the Particle...
In the context-awareness problems, classification models are used to recognize the user scenes based on the sensor signal data. To improve the classification accuracy, a Dynamic Key Context Information Based scenes recognition method is proposed in this paper. Since the location information can be easily obtained by the sensors, the data set is divided into groups by their location information. An...
In this paper, we study the impact of imperfect channel state information at the transmitter and receiver (CSITR) on the diversity-multiplexing tradeoff in single-input multi-output (SIMO)/multi- input single-output (MISO) fading channels with two- way training. We consider two two-way training strategies: 1) the destination initiates the training, and 2) the source initiates the training. We show...
In view of the defect that the gray method can only predict the tendency approximately and artificial neural network can not predict the future tendency really, a new organic gray neural network model was proposed by the advantages of ARMA and rbf neural network. The neural network was trained to get the optimal structure of neural network. According to the dynamic law of one river water quality in...
Customer is one of the most important resources of an enterprise. Customer value analysis is the basis of customer relationship management and customer classification is an important item of customer value analysis. Aiming at the characteristics of customer in the mobile telecommunication industry, the thesis designed the BP neural network model, and presented the doable evaluating programs using...
Web document classification is an important technique of Web mining. Web pages classification has been studied extensively since the Internet has become a huge database of information. The k-NN is a simple classification algorithm that is used to assign patterns of unknown classification to the class of the majority of its k nearest neighbors of known classification according to the distance measure,...
At present, with the popularization of higher education and acceleration of college students every year, colleges and universities are increasing scale. Expansion of the scale for colleges and universities on the one hand, broadens the scope for development, on the other hand it also brings many problems, including the issue of the quality of teaching which is particularly prominent. Owing to the...
At present, classic methods are used to predict reservoir runoff, but the result is not ideal. Due to the shortages of neural network and grey system, in this paper, a grey neural network model is set up based on grey and neural network theory. The data got from the GM(1, 4) on the factors affecting the reservoir runoff is used as the input of the neural network and the origin data of reservoir runoff...
This paper proposed a fast search algorithm that are based on multi-scale. The source image is decomposed using lifting wavelet. Firstly we find the rough position of the target on larger frequency scale. According to the result, the accurate position will be obtained on less frequency scale. Comparing to the traditional matching algorithm, the result shows that the method can increase the searching...
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.