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.
A neural network based asset evaluation method is proposed in this paper. The total amount value of remained asset can be evaluated by using the neural network prediction model, which obtained by training the disposed asset data. Examples show the effectiveness of algorithm. The method proposed has been successfully used for remaining assets evaluation in banking non-performing assets disposal.
Predicting the class label using neural networks through attribute relevance analysis is presented in this paper. This method has the advantage that the number of units required can be reduced so that we can increase the speed of neural network technique for predicting the class label of the new tuples. In this proposed paper attribute relevance analysis is used to eliminate irrelevant attributes...
Identification of a timber usually use the general characteristics, such as smell, impression felt, weight, color, and others. Key features include color, weight, felt the impression, and others. This method has low accuracy, and also requires a fairly long experience. Another way is to record the microscopic characteristics. It also requires quite a long time to recognize the type of wood. This type...
In this paper we present data mining and its utilization for childhood obesity prediction. Data mining was widely used in many childhood obesity prediction systems. Predicting obesity at an early age is both useful and important because the number of obese patients is increasing while its main cause cannot yet be defined. The ability to predict childhood obesity will help early prevention. The purpose...
One of the most popular machine learning algorithms, ANN (Artificial Neural Network) has been extensively used for Data Mining, which extracts hidden patterns and valuable information from large databases. Data mining has extensive and significant applications in a large variety of areas. This paper introduces a new adaptive Higher Order Neural Network (HONN) model and applies it in data mining tasks...
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...
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...
Through the measurement of molten steel and implanting equivalent blackbody, the characteristics of impurities in molten steel is extracted by analyzing the relationship between wavelength and spectral emissivity. The molten steel which contains impurities is separated by using self-organizing feature map neural network. Design consideration of the molten impurities filter system is then presented,...
Rough sets theory is a new tool for processing fuzzy and uncertain knowledge, and has already been applied to many areas successfully. In this paper, a freeway traffic flow model based on rough sets and Elman neural network is put forward. The main idea of this approach is that some redundant features of sample data are reduced by rough sets firstly, then Elman neural network is used to build traffic...
A method for modeling of the sandwich systems with hysteresis is proposed. Considering hysteresis involved in the system is a non-smooth function, the generalized gradients at non-smooth points are introduced. In order to realize the transformation of the multi-valued mapping of the sandwich system with hysteresis into a one-to-one mapping, an expanded input space is constructed. In this case, the...
A collaborative emergency call taking information system in the Czech Republic processes calls from the European 112 emergency number. Large amounts of various incident records are stored in its databases. The data can be used for mining spatial and temporal anomalies. When such an anomalous situation is detected so that the system could suffer from local or temporal performance decrease, either a...
For better predicting and optimizing the blasting parameters in underground deep-hole mining, 16 groups of deep-hole blasting parameters are collected and collated, combining rough set and artificial neuron network theory, an optimized model for basting parameters in underground mines' long-hole caving based on rough set and artificial neural network is set up. Adopting the rough set software for...
This paper presents a new method to recognize machine-printed traditional Mongolian characters by using back-propagation (BP) neural networks. First, the set of traditional Mongolian characters is divided into five subsets according to each character's position (initial, medial or final) within a word and some steady structural features. Then, each subset is trained and recognized by using a BP neural...
Aim at the actual complicacy and difficulty of controlling strength content in sinter, a 3-layer artificial neural network model with multi input factors has been set up in this work that provide a new method for strength content control in production field. The network has reasonable construction, high accuracy and strong generalization ability. The predicted results coincide with the experimental...
In this paper, a novel online self-constructing approach, named fast and parsimonious fuzzy neural network (FPFNN), which emerges the pruning strategy into the growing criteria, is proposed for a function approximator. The restrained growth not only speed up the online learning process but also build a more parsimonious fuzzy neural network while comparable performance and accuracy can be obtained...
This paper discusses a metamorphosis method for temporal data mining. We propose definition of temporal type and time granularity to divide into segments for time, then build an event temporal space which may describe something change of data over time. We give the conception of metamorphosis data in event temporal types space so that it is easier to discover valuable knowledge, but it is not clear...
This paper presents a customer segmentation model in coal enterprises based on SOM neural network. The index system in this model is designed into seven indexes according to the customer lifetime value and behavior character. Then it is divided into six sections to calculate much data in database of information system based on the SOM neural network. After completing the quantification and standardization...
Grid has evolved dramatically into the era of service-oriented grid, which facilitates building of large-scale systems in standard fashions, reusability of essential functions, and interoperability among components. However, grid resource allocation is still a challenging problem for which a grid scheduler has to be operating in a dynamic and uncertain environment. Conventional scheduling algorithms...
This paper proposes an approach based on ANN-QPSO (artificial neural network based on quantum-behaved particle swarm optimization) to evaluate integrated business efficiency of enterprise. It uses QPSO to train the neural network to overcome local-best solution in training process. We use a test example with 35 listed enterprises to show the feasibility and efficiency of the approach.
A new method based on the integration of rough set theory (RS) and Back Propagation (BP) neural network is put forward for selecting the infrastructure project financing mode. Firstly, the continuous attributes in the decision system are discretized with self-organizing map (SOM) neural network. Then, the remained indicators are found by using rough set theory to reduce attributes and eliminate superfluous...
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.