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 paper presents a deep analysis of the literature on the problems of optimization of parameters and the structure of the neural networks and the basic disadvantages that are present in the observed algorithms and methods. As a result, there are suggested a new algorithm for neural network structure optimization, which is devoided of the major shortcomings of other algorithms. The paper includes...
In this paper we explore the hybrid application of evolutionary computation and artificial neural networks in the development of intelligent systems able to solve the problem of approximating the optimal strategy in a tile-matching puzzle game. Three intelligent systems are proposed: an evolutionary heuristic technique, artificial neural networks, and a hybrid approach that combines both. Results...
This paper propose a new multi-objective model optimization allow training the multi-layer perceptron neural network (MLPNN) and optimizing its architecture. More precisely, this model aims to satisfy two objectives: the first one is minimizing the perceptron error (training objective) and the second one is minimizing the sum of the absolute weights (optimizing architecture objective). As known, a...
This paper surveys research on applying neuroevolution (NE) to games. In neuroevolution, artificial neural networks are trained through evolutionary algorithms, taking inspiration from the way biological brains evolved. We analyze the application of NE in games along five different axes, which are the role NE is chosen to play in a game, the different types of neural networks used, the way these networks...
The information of electricity demand forecasting is a base for energy generation enterprise to develop electricity supply system. The purpose of this study is to develop a monthly electricity forecasting model in order to predict electricity demand for energy management. The proposed approach to monthly electricity demand time series forecasting model, describes the trend of the electricity demand...
In this paper we present a method for creating two-dimensional virtual creatures. Their shape and controlling systems are generated automatically by the use of a genetic algorithms. Unlike previous work, our system has an emphasis in approachability and simplicity, but sacrifices simulation realism. This trade off is done with the intention of using the framework for highly interactive applications...
A review of digital watermarking schemes based on neural networks has been shown. A digital watermarking scheme based on autoassociative neural networks with geometric transformations model has been considered. The structure of neural network and methods of forming, embedding and extraction of a digital watermark have been presented.
A common artificial neural network (ANN) uses the same activation function for all hidden and output neurons. Therefore, it has an optimization limitation for complex big data analysis due to its single mathematical functionality. In addition, an ANN with a complicated activation function uses a very long training time and consumes a lot of energy. To address these issues, this paper presents a new...
Advanced Driving Assitance Systems (ADAS) cover a wide range of systems that aim to provide increasingly a safe and efficient driving. Many of these systems are endowed with some intelligent skills which are, in many cases, addressed by means of Soft Computing (SC) paradigms like Neural Networks (NN) or fuzzy systems among others. However, SC algorithms require normally large computational resources...
PCNN Model is widely used because it simulates the working of visual cortex in cats, but parameter setting in PCNN is hefty affair because of manual adjusting of many initial parameters. Through this paper, we present an efficient optimization approach to reducing the parameter setting in original PCNN model by changing the threshold function to modified Heaviside function. Experimental result reveals...
The parallel genetic algorithms implementation for neural networks models construction is discussed. The modification of this global optimization algorithm is proposed. The artificial neural networks are effective instrument to solve most problems of technological objectives and processes modelling. The article describes the aspects of genetic algorithms implementation for neural networks structure-parametric...
A Deep Neural Network (DNN) using the same activation function for all hidden neurons has an optimization limitation due to its single mathematical functionality. To solve it, a new DNN with different activation functions is designed to globally optimize both parameters (weights and biases) and function selections. In addition, a novel Genetic Deep Neural Network (GDNN) with different activation functions...
This paper presents a novel technique in which fuzzy and evolutionary techniques are fused for the design of a class of optimum neural controllers. In the proposed technique the attributes of the performance of the closed system, i.e. overshoot, rise time and settling time in response to a step demand are related to the suitability of the controller through fuzzy linguistic rules. De-fuzzification...
The paper presents a novel dynamic neural architecture that allows a flexible and compact representation of nonlinear processes. The suggested neural topology is obtained by providing local internal recurrence for the static neural network with complex weights. An evolutionary multiobjective design procedure assists the automatic selection of appropriate neural topologies and parameters. It searches...
Analysis of structural changes in the brain through magnetic resonance imaging can provide useful data for diagnosis and clinical supervision of patients through dementia. While the degree of sophistication reached by the MRI equipment is high, the quantification of tissue structures and has not yet been completely solved. Segmentations that these teams now allow those structures fail where the edges...
The intermittent nature of wind poses significant problems to generation companies that wish to keep a close watch on the performance of their wind mills. A regular data mining process on historical measures becomes mandatory to analyze the behavior of each turbine, especially during periods of normal operation – that is when working regularly but with a possible loss of generation...
Network activity has become an essential part of daily life of almost any modern person or company. At the same time the number of network threats and attacks of various types in private and corporate networks is constantly increasing. Therefore, the development of effective methods of intrusion detection is an urgent problem at the present day. In this paper we propose a new approach to intrusion...
Stewart Platform Mechanism (SPM) is a type of parallel mechanism (PM) which has 6 degrees of freedom. Due to features like precise positioning and high load carrying capacity, PMs have been used in many areas in recent years. But relatively small workspace of the mechanism is the major disadvantage. This paper aims to improve the method for PM workspace analysis. The structure of Artificial Neural...
A new method of neural networks based on genetic algorithm is put forward for factors weight determination of safety assessment in the paper. The procedure on optimizing neural networks by genetic algorithm is expatiated. How to pick up the information of factors weight from the network link weight after training is analyzed in detail. The influence of primary network weight on final determination...
The accurate and reliable Trip-generation Forecasting Model is the most basic and important part of the traffic forecasting model. This paper focuses on combining the neural network which has a strong fitting capability and genetic algorithm which has an excellent Global search capability with trip-generation forecasting model in order to achieve the purpose of improving the accuracy of prediction...
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.