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 constrained combinatorial optimization approach to the design of cellular neural networks with sparse connectivity. The method applies to cases where maintaining links between neurons incurs a cost, which could possibly vary between these links. The interconnection topology of the cellular neural network is diluted without significantly degrading its performance, the latter quantified...
This paper presents a novel architecture for the FPGA-based implementation of multilayer neural network (NN), which integrates the layer-multiplexing and pipeline architecture together. The proposed method is aimed at enhancing the efficiency of resource usage and improving the forward speed at the module level, so that a larger NN can be implemented on commercial FPGAs. We developed a mapping method...
New technological advances in large-scale protein-protein interaction (PPI) detection provide researchers a valuable source for elucidating the bimolecular mechanism in the cell. In this paper, we investigate the problem of protein complex detection from noisy protein interaction data, i.e., finding the subsets of proteins that are closely coupled via protein interactions. Many people try to solve...
A novel representation of Recurrent Artificial neural network is proposed for non-linear markovian and non-markovian control problems. The network architecture is inspired by Cartesian Genetic Programming. The neural network attributes namely weights, topology and functions are encoded using Cartesian Genetic Programming. The proposed algorithm is applied on the standard benchmark control problem:...
In the paper, by using topological degree theory and Lyapunov function method, the issue of global robust stability is investigated for a class of interval bidirectional associative memory neural networks with inverse Lipschitz neuron activations, a novel sufficient conditions are established towards the existence, uniqueness and global robust stability of the equilibrium point, finally, a examples...
Though several approaches have already been proposed in the literature to evolve neural network topologies for solving a wide range of machine learning tasks, this paper presents an alternative one, capable of evolving arbitrarily connected feed forward neural networks (ACFNNs), including linear and nonlinear neurons. A genetic algorithm is conceived to adjust the topology and also to perform variable...
A novel method utilizing state space neural network (SSNN) with adaptive filters is proposed to estimate the traffic flow parameters. The SSNN's network topology is derived from delays and stops estimation problem, so the design of SSNN reflects the relationships that exist in physical traffic systems. To improve SSNN effectiveness, the adaptive filters is proposed to train the SSNN instead of conventional...
Track-to-track association is a fundamental problem in multi-sensor data fusion, which is complicated by random errors, false alarms, missed detections, and most profoundly, individual sensor bias. The state-of-the-art approach is to deal with bias estimates and track-to-track association jointly. However, the complexity of this approach is infeasible in the presence of a large number of targets....
In this paper, a modified Neural Gas algorithm is proposed and used to approximate hand topology. As original Neural Gas algorithm is intractable for real-time applications, some optimization such as unnecessary adaption removal and simple learning rate function are introduced to make it applicable for real-time applications. With segmented hand area, the topology representation can be obtained based...
Due to the limited energy of wireless sensor networks (WSN), lots of research works have been done with topology algorithm in WSN. To solve the problem of the unbalanced energy consumption and improve the life circle, this paper proposes an Improved Energy Efficient Unequal Clustering (IEEUC) algorithm based on node degree, the clusters closer to the base station have less members than the farther...
At present, several artificial intelligence (AI) techniques are used to identify complex systems. The data collected is extremely important, as it enables the evaluation, prediction and correction variables' behavior in any given process. The most recent methods tend to associate such techniques in order to obtain models that are continuously closer to those desired. This paper presents a method based...
This paper designs multiclassifiers according to the structural feature of the character. Meanwhile, use Bayes method to integrate the result of the classifier to general the exact character. If the character is in the similar set, we need to distinguish similar characters. According to the topological structure of the similar character, we could make the similar character apart. In this way, we could...
In recent years, communication signal identification become a new issue in the field of communication reconnaissance, which is very important in the security of communication system and network, radio monitoring, cognitive radio, communication countermeasure and so on. So, in this paper, it provides a new approach for the recognition of communication signal. This approach combines evidence theory...
We present a methodology that integrates an artificial intelligent technology called Artificial Neural Networks (ANN's) to develop and build a forecasting system that determines the behavior of the pressure of an oil reservoir, from its behavior, considered as reference in relation to four neighboring wells, which are producing at the same stratum. 356 data records were taken (a period of one year)...
Focusing on using Oracle to implement the differentiation of spatial topological relations between lines and regions, an algorithm based on Oracle Spatial Topology Data Model and the 9-intersection model is designed to determine the nine elements of the 9-intersection matrix, which can be used to differentiate the 19 kinds of spatial topological relations between a line and a region. Three elements...
In this paper, a constraint shifting combined homotopy method for solving brouwer fixed-point problems with both equality and inequality constraints is presented. It needs not the starting point to be an interior point and even a feasible point and hence is convenient to use. Under some assumptions, existence and convergence of a smooth path to an efficient solution is proven. Simple numerical results...
Automated software testing has become a fundamental requirement for several software engineering methodologies. Software development companies very often outsource the test of their products. In such cases, the hired companies sometimes have to test softwares without any access to the source code. This type of service is called black box testing, which includes presentation of some ad-hoc input to...
Historically, learning algorithms have been applied to games as a test of their performance, and with the exponential increases in available computational power, machine learning has been attempted in increasingly complex environments. This paper details the application of neuroevolution of augmenting topologies (NEAT) and accuracy-based learning classifier system (XCS) to the Robocode game environment,...
The purpose of this paper is to investigate the overfitting behavior of particle swarm optimization (PSO) trained neural networks. Neural networks trained with PSOs using the global best, local best and Von Neumann information sharing topologies are investigated. Experiments are conducted on five classification and five time series regression problems. It is shown that differences exist in the degree...
Usually, many high-skilled human resources are required to create sophisticated control systems. Automatic generation of control systems can overcome these requirements. Because of their versatility and flexibility neural networks gained an important role for this task. While evolutionary methods have been relatively successful in generating neural networks, they have some limitations, in addition...
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.