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.
Artificial neural networks(ANN) have been used successfully in applications such as pattern recognition, image processing, automation and control. Majority of today's applications use backpropagate feedforward ANN. In this paper, two methods of P pattern L layer ANN learning on n x n RMESH have been presented. One required memory space of O(nL) but conceptually is simpler to develop and the other...
Deep Neural Networks (DNNs) have progressed significantly in recent years. Novel DNN methods allow tasks such as image and speech recognition to be conducted easily and efficiently, compared with previous methods that needed to search for valid feature values or algorithms. However, DNN computations typically consume a significant amount of time and high-performance computing resources. To facilitate...
Under the opportunistic network environments, normal network protocols can hardly transfer data successfully and efficiently. In order to overcome this problem, many new routing algorithms have been raised pertinently. Thereinto, the Epidemic routing algorithm is a typical approach, which maintains least delay with a highest delivery ratio. However, it is a defective method for routing data as it...
Currently, cultivated land areas throughout China are differentially susceptible to a variety of natural hazards, social risks, and economic challenges. A risk evaluation model is developed in order to capture the degree of risk to the quality of cultivated land and cultivated land areas in China. Based on the Probabilistic Neural Network (PNN), the model seeks to provide insights/recommendations...
With the development of power industry, the proportion of Large-scale Generating Unit in power grid is getting bigger and bigger. The control object of the generating unit is a complicated manufacturing process which is strong-coupling, time-variable, nonlinear and big-lag. It is difficult to establish accurate model when the parameters of control object is uncertainty because of all disturbances,...
The theories of phase space reconstruction and Support Vector Machines (SVM) are introduced firstly. A novel time series forecasting model based on wavelet and SVM is proposed. It first performances multi-scaled decomposition on complex time series using discrete wavelet transformation. Then the reconstructed approximate series and detail series are forecasted respectively using SVM. Finally, the...
In popular outlier processing methods, some emphasize on spotted outliers processing and some emphasize on isolated outliers processing. They have seldom processed outliers from the perspective of outlier producing mechanism. This paper aims at the problem of outliers in dam safety monitoring and an outlier identify method which based on BP neural network is presented. This method based on the mechanism...
Six semiconductor gas sensors which are sensitive to carbon monoxide (CO), methane (CH4) and hydrogen (H2) were chosen to compose the gas sensor array, and an on-line data acquisition system was constructed. Combining with the pattern recognition techniques of back propagation (BP) neuron network, the system was used to carry out the quantitative analysis of the partial gas concentration in a mixture...
The dynamics of a discrete-time predator-prey system is investigated in the closed first quadrant R+2. First, the existence and local stability of the fixed points in the closed first quadrant R+2 are discussed in detail. Then, by using center manifold theorem and bifurcation theory, it is proved rigorously that when the bifurcation parameters vary in the small neighborhood of the corresponding...
The elevator system is important in mine safety manufacture. Aiming the character of frequent startup and stop with nonlinearity, the sync tracing method based on improved genetic algorithm neural network is presented. Because the condition of the normal adaptation function is too free, the adaptation function is improved, which is the new function altering with input space, then, improved genetic...
Scientific workflow is becoming an important paradigm for scientific computations and collaborations. Provenance information plays an important role to reproduce data and prove the soundness of result for scientific workflow. The provenance information can be collected by keeping a complete trace of the workflow execution. In this paper, we give a high level Workflow Net model based on many-sorted...
The neural network risk analysis model for the project with fragmentary information is proposed by this paper. With plenty of adjustable parameters, the neural network risk analysis model is more flexible and shows more advantage in evaluating fragmentary information. Simulated by neurons, risk items are transferred within neural network and finally the evaluation result is obtained.
A novel method for the detection of multiple moving objects is proposed in this paper. In order to get the detailed information of the objects, fast level set method which is only based on the evolution of single link list is mainly used to detect the boundaries of moving objects. The whole process consists of two main procedures: the coarse detection and the fine localization. During the coarse detection...
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.