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 model to realize a supervised image segmentation task. It is based on the concept of receptive fields that intends to analyze pieces of an image considering not only the pixels or group of them, but also the relationship between them and their neighbors, called segmentation and classification with receptive fields (SCRF). Also, in order to work with the SCRF model, is proposed...
This paper presents the results of experiments in applying a spiking neural network to control the locomotion of a simulated biped robot. The neural model used in simulations was developed to allow for an analytic solution to a neuron's fire time, while maintaining a non-instant post-synaptic potential rise time. The synaptic weights and delays were tuned using an evolution-strategy. Simulation experiments...
In this paper, a bibliometric study on the interconnections between the fuzzy logic theory field and the other soft-computing techniques is presented. Bibliometric maps showing the associations between the main concepts between these research fields are provided for the periods 1990-1999, 2000-2003 and 2004-2007. The maps provide insight into the structure of these fields. They visualize the division...
The need to consider data that contain information that cannot be represented by classical models has led to the development of symbolic data analysis (SDA). As a particular case of symbolic data, symbolic interval time series are interval-valued data which are collected in a chronological sequence through time. This paper presents two approaches to symbolic interval time series analysis. The first...
We propose a supervised approach to word sense disambiguation based on neural networks combined with evolutionary algorithms. Large tagged datasets for every sense of a polysemous word are considered, and used to evolve an optimized neural network that correctly disambiguates the sense of the given word considering the context in which it occurs. The viability of the approach has been demonstrated...
This paper reports the application of artificial neural networks for estimating reference evapotranspiration (ETo) as a function of local maximum and minimum air temperatures and exogenous relative humidity and evapotranspiration in twelve coastal locations of the autonomous Valencia region, Spain. The Penman-Monteith model for ETo prediction, as been proposed by the Food and Agriculture Organization...
A new neural network-based approach is proposed to estimate motion hierarchy in image sequences taking into consideration motion discontinuities. The network consists in an input layer, an intermediate layer and an output layer. In order to estimate the most likely displacement at each pixel, we have transposed the block matching approach into the neural network approach and add mechanisms to detect...
CAC-RD (call admission control based on reservation and diagnosis) [1] is call admission control (CAC) for UMTS (universal mobile terrestrial system) 3G networks. It is based on two schemes: channel reservation and network diagnosis. When compared to other CAC mechanisms, CAC-RD can guarantee network availability, reducing priority classes blocking and guarantying some network QoS requirements. Due...
Rapid developments in computing-related technologies have enabled the collection of large amounts of data at unprecedented rates from diverse systems, both natural and engineered. The availability of such data has motivated the development of intelligent systems to gain new insights into how these systems work, leading thereby to superior decision making. In this paper we present recent advances in...
This paper presents the hybridization of global and mesoscale weather forecasting models with neural networks in order to tackle a problem of short-term wind speed prediction. The mean hourly wind speed forecast at aero-generators in a wind park is an important parameter used to predict the total energy production of the park. Our model for short-term wind speed forecast integrates two different meteorological...
The aim of this work is to present a segmentation method to detect moving objects in video scenes, based on the use of a multivalued discrete neural network to improve the results obtained by an underlying segmentation algorithm. Specifically, the multivalued neural model (MREM) is used to detect and correct some of the deficiencies and errors off the well-known mixture of Gaussians algorithm. Experimental...
The main problem with iris biometric identification systems is the presence of noises in the image of the eye (eyelid, eyelashes, etc...). To remove it many authors apply appropriate preprocessing to the image, but unfortunately this yields losses of information. Our work aims at correctly recognizing the subject also in presence of high rates of noise. The basic idea is that of partitioning the image...
Logistic regression (LR) has become a widely used and accepted method to analyse binary or multiclass outcome variables, since it is a flexible tool that can predict the probability for the state of a dichotomous variable. A recently proposed LR method is based on the hybridisation of a linear model and evolutionary product-unit neural network (EPUNN) models for binary classification. This produces...
The main objective of this work is to automatically design neural network models with sigmoidal basis units for classification tasks, so that classifiers are obtained in the most balanced way possible in terms of CCR and sensitivity (given by the lowest percentage of examples correctly predicted to belong to each class). We present a memetic Pareto evolutionary NSGA2 (MPENSGA2) approach based on the...
This paper addresses the problem of probability estimation in multiclass classification tasks combining two well known data mining techniques: support vector machines and neural networks. We present an algorithm which uses both techniques in a two-step procedure. The first step employs support vector machines within a one-vs-all reduction from multiclass to binary approach to obtain the distances...
In this work, we propose the use of a multivalued recurrent neural network with the aim of graph drawing. Particularly, the problem of drawing a graph in two parallel lines with the minimum number of crossings between edges is studied, and a formulation for this problem is presented. The neural model MREM is used to solve this problem. This model has been successfully applied to other optimization...
This paper presents a novel interval type-2 fuzzy inference system with automatic learning for handling uncertainty, called the hierarchical type-2 neuro-fuzzy BSP model (T2-HNFB). This new model combines the paradigms of the type-2 fuzzy inference systems and neural networks with recursive partitioning techniques (BSP - Binary Space Partitioning). The model is able to automatically create and expand...
One of the most important problems to be solved in direct sequence spread spectrum systems is to achieve a robust acquisition of the pseudo noise sequence. In multiuser time-varying environments this fact becomes even more important because acquisition and tracking performance can heavily degrade communication reliability. In this paper a new neural network estimator is presented, and it is compared...
In this paper, based on the fusion of the clonal selection algorithm (CSA) and differential evolution (DE) method, we propose a novel optimization scheme: CSA-DE. The DE is employed here to increase the affinities of the clones of the antibodies (Abs) in the CSA. Several nonlinear functions are used to verify and demonstrate the effectiveness of this hybrid optimization approach. It is further applied...
This paper describes a method to automatically tuning artificial neural networks parameters for a specific problem using an evolutionary algorithm. The method employs an evolutionary search to perform simultaneous tuning of initial weights, transfer functions, architectures and learning rules (learning algorithms parameters). Experiments were performed and the results demonstrate that the method in...
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.