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.
This paper presents a new approach for breast cancer detection based on Hierarchical Fuzzy Neural Network (HFNN). Generally in formal fuzzy neural networks (FNN), increasing the number of inputs, causes exponential growth in the number of parameters of the FNN system. This phenomenon named as "curse of dimensionality". An approach to deal with this problem is to use the hierarchical fuzzy...
In this study, an investigation over digestive diseases has been done in which the sound acts as a detector medium. Pursue to the processing, the extracted signal in wavelet domain is registered. Genetic Algorithm (G.A) with binary chromosomes is used for feature selection to reduce the dimensions of feature space. Classification of digestive diseases was carried out by fuzzy neural network and fuzzy...
The county level of basic public services analysis and classification play an important role in county economic growth and improve benefit of healthy development of urbanization in China. According to the county level of basic public services data which is large scale and imbalance, this paper presented a support vector machine model to classify the county level of basic public services. The method...
In this paper, a new kind of three-stage neural network was developed to identify the sorts of the biological surface. The visible spectrum (from 380nm to 780nm) of the micro areas with some specks on the surface of the apples was measured with the self-made fiber sensor spectrometer. To sort the apples, A kind of BP-ANN with single hidden layer was devised to identify the characteristics on the biological...
This paper deals with the advanced and developed methodology know for cancer multi classification using an Extreme Learning Machine (ELM) for microarray gene expression cancer diagnosis, this used for directing multicategory classification problems in the cancer diagnosis area. ELM avoids problems like local minima; improper learning rate and over fitting commonly faced by iterative learning methods...
The data related to our life experiences is called lifelog, which can easily be collected with mobile electronic devices in recent years. Although lifelog research has been conducted for a long time, practical applications such as a memory assistant system have not been fully developed yet. This is mainly due to the lack of methods to structurize the lifelog data efficiently. In our research, we developed...
Accurate short term load forecasting (STLF) is a prerequisite for proper generation scheduling and reliable operation of power utilities. Conventional methods of STLF, suffer from the disadvantages such as lack of ability to accurately model the weather parameters affecting the load, lack of robustness for representing weekends and public holidays and of being computation intensive. Application of...
Several adaptation approaches, such as policy-based and reinforcement learning, have been devised to ensure end-to-end quality-of-service (QoS) for enterprise distributed systems in dynamic operating environments. Not all approaches are applicable for distributed real-time and embedded (DRE) systems, however, which have stringent accuracy, timeliness, and development complexity requirements. Supervised...
Accurate land use/cover (LUC) classification data derived from remotely sensed data are very important for land use planning and environment sustainable development. Traditionally, statistical classifiers are often used to generate these data, but these classifiers rely on assumptions that may limit their utilities for many datasets. Conversely, artificial neural network (ANN) and decision tree (DT)...
Supplier performance evaluation is a key issue of supply chain and is complicated since a variety of attributes must be considered. In this article, an integrated DEA-NN model is proposed. By taking advantages from both data envelopment analysis (DEA) and neural networks (NN), an application of the integrated DEA-NN method is given. The results indicate that the method is effective and applicable.
Membrane proteins play an important role in many biological processes and are attractive drug targets. In this study, membrane proteins are classified using two feature extraction and several classification strategies. The first feature extraction strategy is pseudo amino acid (PseAA) composition; utilizing hydrophobicity and hydrophilicity for reflecting the sequence order effects, while the second...
The objective of this research paper is to analyze the momentum term for the performance of Back Propagation (BP) Algorithm of Artificial Neural Network (ANN) for the problem of hand written digit recognition. The two variations of BP algorithm are simple BP algorithm and BP algorithm with momentum. In this paper BP with momentum is used for the performance analysis of BP algorithm. Numbers of parameters...
In order to study the early warning of companies' financial risk, this paper used two models based on factor analysis, which are logistic regression and BP neural network. Finally, for the warming accuracy, BP neural network model is better than logistic regression model.
Image fusion is one of important image processing technologies. Multi-wavelets, Pulse Couple Neural Network (PCNN), and fractal dimension are very useful theoretical tools for image processing. We introduce the basic principles of image fusion at the level of pixel, feature, and decision. We describe the design rules and steps of Graphical User Interface (GUI). Image fusion system based on GUI is...
Accurate land use/cover (LUC) classifications from satellite imagery are very important for eco-environment monitoring, land use planning and climatic change detection. Traditional statistical classifiers such as minimum distance (MD) have been used to extract LUC classifications in urban areas, but these classifiers rely on assumptions that may limit their utilities for many datasets. On the contrary,...
To begin with, for indoor location system, the necessity of research on genetic neural network and its math model are introduced. Then, by analyzing principle of genetic optimized artificial neural network, an indoor location math model of genetic neural network is established. As for various coding types, regularity is taken as the measurement to determine the best coding type for parameter optimization...
Land cover and land use classification with Remote Sensing (RS) image is used broadly in dynamic monitoring of land use. For the RS image classification, the method of BP neutral network with one single hidden layer has been widely used. But the traditional BP neutral network based on gradient descendent of error has low classification rate. It is not easy to converge and often get into local minimum...
The automatic recognition of images has been always one of preceding issues in the filed of remote sensing. From traditional algorithm of K-Means, maximum likelihood to new decision tree, neural networks, wavelet transform and fuzzy recognition system, the classification accuracy has been improved. In this work, based on Decision Tree Classification (DTC) and Landsat ETM+ data, Ejina Oasis land cover...
Individual credit risk evaluation is an important and challenging data mining problem in financial analysis domain. This paper compares the effectiveness of four data mining algorithms - logistic regression (LR), decision tree (C4.5), support vector machine (SVM) and neural networks (NN) by applying them to two credit data sets. Experiment results show that the LR and SVM algorithms produced the best...
GPS height conversion is the key problem in survey engineering. To resolve it, researchers supposed some mathematical function to fit the surface of normal height such as plain surface, quadratic surface fitting and so on,however, which have model error. It should reduce the accuracy of the fitting result. In order to eliminate and reduce the model errors, this paper adopted BP neural network to convert...
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.