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.
Spectrum sensing is a key function for the second users (SUs) to determine availability of a channel in the primary user's (PUs) spectrum in cognitive radio(CR). In order to achieve that, much research of energy detection has been studied, but they play poor performance in low signal-to-noise (SNR) environment. In this paper, we proposed Support Vector Machines (SVM) based on Genetic Algorithms (GA),...
Data pre-processing in modeling of neural network (NN) is relatively more complicated and usually manual. Trial and error method is commonly used to determine the number of hidden layer neurons, which is easily affected by human factors and is opportunistic. Relevant training parameters using default value commonly result in lower model accuracy. In this paper, a NN load forecasting model with higher...
Software cost estimation is a crucial element in project management. Failing to use a proper cost estimation method might lead to project failures. According to the Standish Chaos Report, 65% of software projects are delivered over budget or after the delivery deadline. Conducting software cost estimation in the early stages of the software life cycle is important and this would be helpful to project...
This paper presents a single multiplicative neuron model based on a polynomial architecture. The proposed neuron model consists of a non-linear aggregation function based on the concept of generalized mean of all multiplicative inputs. This neuron model has the same number of parameters as the single multiplicative neuron model (SMN). The SMN model is a special case of the proposed generalized mean...
In this paper, an Adaptive Neural Control (ANC) architecture is used for system replication and control within a Resilient Control framework. A dynamic model is chosen for our plant and a “maliciously attacked” plant. A Model Reference Adaptive Control (MRAC) architecture is used to replicate and control the plant to match an ideal reference system. At certain time, we replicate a malicious attack...
In this paper, a new method is proposed for neurons classifying based on its spatial structure. The part of neuron is geometrically similar to the whole. Neurons can be regarded as fractal. Different types of neurons fill with different levels in space. So, their fractal dimensions are also different. First, fractal dimensions are calculated for neurons. Then the other 16 spatial structure indicators...
This paper presents an algorithm based on a combination of Discrete Wavelet Transforms and back-propagation neural networks for location of interturn faults in a two-winding three-phase transformer. Fault conditions of the transformer are simulated using ATP/EMTP in order to obtain current signals. The training process for the neural network and fault diagnosis decision are implemented by MATLAB....
The geological information of logging data is very important for people to determine oil reserves and make the plan of exploitation. So it is essential to identify litho logy of the logging data. Neural network with self-organizing, self-learning and the ability of highly non-linear mapping has been widely used in the field of classification. It has achieved good results. Using self-organizing and...
In general, Online Handwriting Recognition refers to the dynamic movement of a Digitized pen on touchpad which simply involves collection of a sequence of x-yco-ordinates used to describe the online handwriting data. This paper presents a novel approach for online handwriting recognition of Kannada characters by combining Direction based Stroke Density principle(DSD) with Kohonen Neural Network(KNN)...
Accompanying the development of the information systems, there is more and more research focused on the evaluation of information systems. However, the evaluation of the enterprise information systems has always been a thorny problem because of the complexity of the information systems. Through analysis of the existing research achievements both domestic and foreign, we find that some important factors...
For the magnetization curve of switched reluctance motor (SRM) is high saturation and has the nonlinear characteristic. This paper presents a method of modeling based on BP neural network optimized by genetic algorithm (GA). The method adopts the simple BP neural network structure based on the characteristics of flux and torque, and the network learning algorithm combines the traditional BP neural...
According to the status quo of integrated support ability evaluation for meteorological equipment, index system of equipment integrated support ability evaluation for meteorological station is established. Using BP neural network method, equipment support ability evaluation model is established. Combined with concrete examples of meteorological station equipment support ability evaluation, a better...
Topology changes trigger routing protocol to undergo convergence process which prepares new shortest routes needed for packet delivery. Real-time applications (e.g. VoIP) nowadays require routing protocol to have a quick convergence time. This paper presents a new routing table calculation scheme for OSPF routing protocol to better serve real-time applications. The proposed scheme focus on speeding...
In this paper, a nonlinear modeling scheme of hysteresis in piezoelectric actuators is presented. In this modeling scheme, the extreme learning machine based model for hysteresis in piezoelectric actuators is proposed. In this method, a modified hysteresis operator extracting the main movement features of the hysteresis is introduced to construct an expanded space. Then, the multi-valued mapping of...
Due to the following characteristics of offshore program, such as one-time large-scale investment, comprehensive high-risk, long payback period, high uncertainty, high regional and political, the investors has been paid more and more attentions to the risk of offshore program. Combined with the characteristics of offshore program risk management, and with the use of BP neural network theory, this...
As an unlicensed wireless system, how to discover idle spectrum-bands efficiently and handover to minimize interferences to primary (licensed) users is the main focus for Cognitive Radio (CR). Therefore, the prerequisite for being “cognitive” lies in a deeper understanding of the characteristics of current spectrum behavior, such as a better model for spectrum behavior prediction, so as to design...
An artificial neural networks (ANN) approach was applied to develop a mathematic model which predicts the sales price of residential properties. The study is based on evaluation of sales of homes in Casablanca, Morocco Kingdom. North of Africa. A feed forward network with one hidden layer was trained using original set of residential property valuation database. The ANN was obtained by 148 sets of...
In this paper a three-layered, feedforward neural network based model of a starter motor was introduced. Teaching and validating datasets are collected from real system measurements where different character of load torque was applied on the motor's shaft. Different types of training datasets were used to investigate its influence on the trained network. Beside the well-known MSE, other information...
Self-organizing feature map (SOM) is well known artificial neural network using unsupervised learning for the data visualization and vector quantization. SOM has been used for cluster analysis. On the other hand, SOM cannot produce clarified clusters. And so SOM clustering capability is depends on visualization method. We proposed a variant of SOM that construct hierarchical neural network structure...
Find software defects is a complex and slow task which consumes most of the development budgets. In order to try reducing the cost of test activities, many researches have used machine learning to predict whether a module is defect-prone or not. Defect detection is a cost-sensitive task whereby a misclassification is more costly than a correct classification. Yet, most of the researches do not consider...
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.