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.
Clustered micro calcifications (MCs) are one of the early signs of breast cancer. In this paper, we propose a new computer aided diagnosis (CAD) system for automatic detection of MCs in two steps. First, pixels corresponding to potential micro calcifications are found using a multilayer feed-forward neural network. The input of this network consists of 4 wavelet and 2 gray-level features. The output...
Gas transmission and distribution system, the gas load is the main parameter to impact the project planning, which determines the capacity of equipments and operation program. Therefore, accurate prediction of gas load is of extremely important significance for gas companies to improve safety and reliability of gas supply. The forecasting method of tradition gas load would not meet the requirement...
In this paper a new license plates recognition method using a Neural Network, trained by Chaotic Imperialistic Algorithms (CICA), is introduced. In this paper the background of the plate image is omitted, the characters are separated, and then the features of the characters are extracted. The features vector is feed into a multi layered perception neural network trained by CICA. Our dataset include...
In recent years, computer - aided design approach based Artificial Neural Network has been introduced to microwave modeling, simulation & optimization. In this paper, a neural network model is proposed for the design of spiral strip monopole antenna fed by a coplanar waveguide (CPW) for radio frequency identification (RFID) applications is presented. The designed antenna, which, including the...
The sensitivity analysis can help to construct a tightly neural network. There are several methods to define the sensitivity of input and weight for perturbations to the trained neural network. This paper proposed a sensitivity definition based on elastic function. This definition considers the measure of the variable of the reference network. The sensitivity calculating formulae are deduced for perceptron...
It is easy for a multi-layered perception (MLP) to form open plane classification borders, and for a radial basis function network (RBFN) to form closed circular or elliptic classification borders. In contrast, it is difficult for a MLP to form closed circular or elliptic classification borders, and for RBFN to form open plane classification borders. Hence, MLP and RBFN have their own advantages and...
Sensor arrays also known as Electronic Noses (ENs) have been used to analyse the Volatile Organic Compounds (VOCs) of both healthy and infected tomato (Solanum lycopersicum) crops. Statistical and intelligent systems techniques were employed to process the data collected by an EN. Principal Component Analysis (PCA), K-Means clustering and Fuzzy C-Mean (FCM) clustering were applied to visualise any...
This paper proposes an intelligent trading system using support vector regression optimized by genetic algorithms (SVR-GA) and multilayer perceptron optimized with GA (MLP-GA). Experimental results show that both approaches outperform conventional trading systems without prediction and a recent fuzzy trading system in terms of final equity and maximum drawdown for Hong Kong Hang Seng stock index.
In this paper, the methods and experimental results of rotated irregular shaped edge objects from still images and recognition by supervised artificial neural network of irregular shapes (ANN) are discussed. The edge images are obtained during pre-processing stage from the input coloured images. The objects in the edge images are rotated by every 5° from 0° up to 355°. The rotated edge images are...
This paper presents a Learning Classifier System (LCS) where each traditional rule is represented by a spiking neural network, a type of network with dynamic internal state. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, providing the system with a flexible knowledge representation. It is shown how this approach allows for the evolution of networks...
In this paper, we propose an artificial neural network approach to determine the quantitative structure-activity relationship (QSAR) among known aldose reductase inhibitors (ARI). In order to accurately describe the structural properties of ARIs, besides the popularly used 2-dimensional (2D) descriptors, we have used 3-dimensional (3D) molecular descriptors which are obtained through the DRAGON software...
A proof-of-concept hardware neural network for the purpose of analog built-in self-test is presented. The network is reconfigurable into any one-hidden-layer topology within the constraints of the number of inputs and neurons. Analog operation domain of synapses and neurons in conjunction with the digital weight storage allow fast computational time, low power consumption and fast training cycle....
This paper presents a power control strategy based on multi-resonant operating points, which is realized by multilayer feedforward neural network applying back-propagation algorithm. The full-bridge contactless power transfer system and magnetizing current of the transmitter on primary side are respectively used as research object and control variable. After batch-learning and training, the converged...
In this paper, we present a new method for modeling the nonlinear transient behavior of I/O buffers in high-speed PCB design. The proposed method expands the existing StateSpace Dynamic Neural Network (SSDNN) into a more generalized and efficient technique for modeling nonlinear behavior of I/O buffers. A Multi-Layer Perceptron (MLP) neural network with multiple hidden layers is combined with the...
The presentation is focused on comparison of neural networks and fuzzy systems. Advantages and disadvantages of both technologies are discussed. Fuzzy systems are relatively easy to design but number of inputs in the system are significantly limited. It is very difficult to design neural networks so rather they have to be trained instead. Neural networks produce much smoother nonlinear mapping than...
This paper describes the development of an electronic tongue system for monitoring the freshness of meat. The analysis was made along 14 days on a whole piece of pork loin stored under refrigeration. The electronic tongue system is made by an array of potentiometric electrodes. Through the use of various multivariate analysis techniques, such as PCA and two types of artificial neural networks (i.e...
This paper presents the applicability of Artificial Neural Network (ANN) for weather forecasting using a Photovoltaic system. The main objective is to predict daily weather conditions based on various measured parameters gained from the PV system. In this work, Multiple Multilayer Perceptron (MMLP) network with majority voting technique was used and trained using Levenberg Marquardt (LM) algorithm...
The paper presents the neural network approach to the accurate forecasting of the daily average concentration of PM10. Few neural predictors are applied: the multilayer perceptron, radial basis function, Elman network and support vector machine. They are used for prediction either in direct application or in combination with wavelet decomposition, forming many individual prediction results that will...
Model compression is a required task when slow and large models are used, for example, for classification, but there are transmissions, space, time or computing capabilities constraints that have to be fulfilled. Multilayer Perceptron (MLP) models have been traditionally used as classifiers. Depending on the problem, they may need a large number of parameters (neuron functions, weights and bias) to...
In recent forecasting competitions, algorithms of Support Vector Regression (SVR) and Neural Networks (NN) have provided some of the most accurate time series predictions, but also some of the least accurate contenders failing to outperform even simple statistical benchmark methods. As both SVR and NN offer substantial degrees of freedom in model building (e.g. selecting input variables, kernel or...
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.