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 improved algorithm of WNN based on BP was proposed in this paper. Theoretical analysis and simulation result show it avoids both the blindness of framework designs for BP neural networks and the problem of nonlinear optimizations, such as local optimization. So it can simplify the training of neural networks. It has better abilities in function learning and generalization. This algorithm was successfully...
Robotics is a compelling topic for students of all ages, and it is an excellent tool for teaching science and engineering. The paper has considered what makes robotics motivating to students, and it has shown how context, need, and the desire to 'make it work' draw them to that learning so naturally that they hardly notice the intellectual strides they are making. The potential of robotics to educate...
Rice leaf diseases have occurred all over the world, including china. They have had a significant impact on rice quality and yield. Now, the control method rely mainly on artificial means.In this study, BP neural network classifiers were designed for classifying the healthy and diseased parts of rice leaves. This paper select rice brown spot as study object, the training and testing samples of the...
The instability disaster prediction model of tailings dam had been established, based on system analysis of the factors that caused the instability disaster of tailings dam, by selecting 6 prediction index, medium unit weight, cohesion, internal friction angle, slope angle, slope height and pore pressure ratio and combining with using theory of the rough set and neural network. First the rough set...
It is important to detect defects in wood, when it reduce the performance. The data and signal processing technology providing researchers with more damage identification problem solution ideas and methods. This article explore the wavelet analysis and artificial neural network for the wood defects based on non-destructive testing, and build an artificial neural network model for wood non-destructive...
Fuzzy systems have been used as a mechanism to build classifiers which are called fuzzy rule based classification systems (FRBCSs). In this paper, a new method for improving this kind of classifiers, based on ensemble strategy, is proposed. Here instead of building a classifier or a fusion of a group of them, we build some base classifiers and select one for every test pattern. A number of UCI datasets...
Supply chain is a complicated, open system, for the constant development, and fierce degree of market competition of the society increase day by day, the discrimination and management of risk of Supply chain are more essential. Kinds of risk factors of Supply chain are analyzed in the text, according to the influence degree of each risk factor, a method combined BP neural network and fuzzy evaluation...
Teachers in secondary vocational schools play an important role in training qualified first-line skilled workers for enterprises, while teachers have been limited to a fixed mode of teaching and teaching context in schools for a long time. With advancement of technology, the knowledge of teachers in secondary vocational school should be updated which puts forward higher requirements on the professional...
On the basis of analyzing the significance of assessing operation capability in SMB, the Appraisal-index system of operation capability for SMB is built, and appraisal model is established using BP neural network. The conjunction weights of the neural network are continuously modified layer by layer from output layer to input layer in the process of neural network training to reduce the errors between...
Against the low efficiency of training on large-scale SVM, a reduction approach based on kernel distance clustering is proposed. The kernel distance's formulation is brought in to cluster the highly-dimensioned dataset, and the clustering step will reduce a large amount of unsupport vectors during training, thereby, the training time will decrease. The experiments show that this new training algorithm...
Test question duplicate checking by the computer program is the requirement of construction of test question library. To enhance the availability of test question duplicate checking, course knowledge tree and domain term table are introduced in the paper. Based on the domain term table, the domain terms of test question can be easily identified, therefore, the calculating of similarity deals with...
In order to predict gas content of coal seam accurately in binchang mining, we use core data to build the BP neural network. We select the important controlling factors which impacted gas content of coal seam, coal bed thickness, ash and max vitrinite reflectance as the basic features of the BP neural network model, and establish the BP neural network prediction model between coal bed methane content...
This paper presents a novel approach to recognize traffic signs using support vector machines and radial Tchebichef moments. More than 3000 real road images were captured by a digital camera under various weather conditions and at different times and locations. After traffic sign is detected from real road images, it is then normalized, and radial Tchebichef moments are computed as the features of...
Large and complex problem can be solved easily and quickly by decomposing it to be small sub-problems. We propose a heuristic method to isolate the larger state space into some smaller state spaces for decomposing learning task. During the learning process, after remove the state loops in these learned episodes, we find some states are critical for agent can reach goal state. These critical states...
The course in probability theory and the stochastic processes is one of the fundamental courses in the college mathematics curriculum. It is also a course which attracts considerable attention in the educational reform. Integrating the characteristics of the course of the stochastic process with longterm teaching practice, the author addresses issues on: (1) how to apply the idea of mathematical modeling...
Transductive inference based on support vector machine is a new research region in statistical learning theory. An improved algorithm is proposed in this paper, which overcome the disadvantages of studying process complexity and slow in the progressive transductive support vector machine learning algorithm. The algorithm optimized the samples which near the support vector only, and large number of...
In order to realize safety prediction of workface stray current, it's important to confirm the characteristic indexes of workface stray current so as to insure the time margin and reliability of prediction. By analyzing the resistance distribution network of the system, the paper confirms the four parameters as follows to be the characteristic indexes of coalface stray current safety prediction: the...
In distributed virtual environment many methods of data distribution management (DDM) are presented to efficiently improve network traffic situation and save system resources, these technologies are based on virtual environment partition. The grid size of the partition affects the data distribution results. This paper aims to present a neural-network based study mechanism, which adjusts the grid size...
Choosing the kernel and error penalty parameters for support vector machine (SVM) is very important for the performance of classifiers. An improved grid-search algorithm is proposed to choose the optimal parameters of SVM. The battlefield multi-target SVM classifier is designed using this algorithm. Also three classifiers including k-nearest neighborhood classifier, improved BP neural network classifier...
This paper proposes an Assembling Learning Approach (ALA) for multi classification concerned with weighted-voting label assignment strategy. This weighted-voting idea is reflected in two components of ALA: a Weighted SVMs method (WSVM) that identifies regular data label and a Locally Adaptive ANN (LAANN) that addresses the rejected case. Basic SVM of WSVM is equipped with confidence coefficient to...
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.