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.
Search engines usually return relevant sorted results based on the keywords. Because of the lack of considering the user's current search interest and intention, this kind of strategy may not meet users' personalized search requirements. In order to retrieve results associated with the user's current search interest, existing researches integrate the user's interest information into the search process...
Aiming at the problem of service performance modelling, this paper uses ANN to establish the mapping relationships between virtual machine resource status and cloud service performance, and proposes an I-ABC-ELM method to train ANN. For the stability problems of the ELM training, this paper proposes the use of I-ABC algorithm to optimize the input layer weight matrix and hidden layer bias in ELM....
Aiming at the problem that it is difficult to confirm the parameters of the PID controller and the parameters can not be changed once identified, an intelligent PID control method is proposed. According to the size of the system error, this algorithm controls the system with different subsections of different parameters, by using the particle swarm optimization (PSO) to optimize the parameters of...
Automatic modulation recognition of modulation signals is the key problem in non-cooperative communication systems. The method which combines the rough set theory and the neural network is designed for identifying the six modulation types based on the research on the feature set of digital modulation recognition. Simulation results show that the new method simplifies the structure of neural networks...
In this article, based on the FIST model, it proposes four parameters to describe the crowd massing risk in public venues that are the density (D), mutual interaction between each others(I), the personnel characteristics (C) and the impact derived form environmental (E) disturbance on the massing crowd. Then, it carries out the corresponding technical analysis for the four predefined parameters. First,...
Support vector regression optimized by genetic algorithm (G-SVR) is proposed to forecast tourism demand. Genetic algorithm (GA) is used to search for SVR's optimal parameters, and adopt the optimal parameters to construct the SVR models. This study examines the feasibility of SVR in tourism demand forecasting by comparing it with back-propagation neural networks (BPNN).The experimental results indicate...
Forecasting the tax gross exactly is significant to carry on the macroscopic regulation efficiently under the market economy. Conventional linear macroscopic economic model is very difficult to hold non-linear phenomena in economic system, thus the tax forecasting error will increase. Support vector machine (SVM) has been successfully employed to solve regression problem of nonlinearity and small...
Forecasting agriculture water consumption is significant to optimize confiration of water resources. In the paper, we have combined particle swarm optimization (PSO) and support vector machines (SVM) for agriculture water consumption forecasting. Compared to GA, the advantages of PSO are that PSO is easy to implement and there are few parameters to adjust. Thus, PSO is very suitable to determine training...
In this paper a novel text classification method based on biomimetic pattern recognition (BPR) is proposed. And we implement a BPR text classifier with multi-weight neural network; the model of three-weight neural network and its construction method are described in detail. Some text classification experiments have been done to test the performance of our BPR text classifier; experimental results...
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.