Search results for "NEURAL NETWORK"

Stochastic models for wind speed forecasting

2011

Abstract This paper is concerned with the problem of developing a general class of stochastic models for hourly average wind speed time series. The proposed approach has been applied to the time series recorded during 4 years in two sites of Sicily, a region of Italy, and it has attained valuable results in terms both of modelling and forecasting. Moreover, the 24 h predictions obtained employing only 1-month time series are quite similar to those provided by a feed-forward artificial neural network trained on 2 years data.

Disorder and interactions in systems out of equilibrium : the exact independent-particle picture from density functional theory

2017

Density functional theory (DFT) exploits an independent-particle-system construction to replicate the densities and current of an interacting system. This construction is used here to access the exact effective potential and bias of non-equilibrium systems with disorder and interactions. Our results show that interactions smoothen the effective disorder landscape, but do not necessarily increase the current, due to the competition of disorder screening and effective bias. This puts forward DFT as a diagnostic tool to understand disorder screening in a wide class of interacting disordered systems.

Integrated fuzzy classification

2003

Improvement of Temperature Based ANN Models for ETo Prediction in Coastal Locations by Means of Preliminary Models and Exogenous Data

2008

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 of the United Nations (FAO) as the standard method for ETo forecast, has been used to provide the ANN targets. The number of stations where reliable climatic data are available for the application of the Penman-Monteith equation is limited. Thus, the development of more precise predicting tools…

The on-line curvilinear component analysis (onCCA) for real-time data reduction

2015

Real time pattern recognition applications often deal with high dimensional data, which require a data reduction step which is only performed offline. However, this loses the possibility of adaption to a changing environment. This is also true for other applications different from pattern recognition, like data visualization for input inspection. Only linear projections, like the principal component analysis, can work in real time by using iterative algorithms while all known nonlinear techniques cannot be implemented in such a way and actually always work on the whole database at each epoch. Among these nonlinear tools, the Curvilinear Component Analysis (CCA), which is a non-convex techni…

Using Aerial Platforms in Predicting Water Quality Parameters from Hyperspectral Imaging Data with Deep Neural Networks

2020

In near future it is assumable that automated unmanned aerial platforms are coming more common. There are visions that transportation of different goods would be done with large planes, which can handle over 1000 kg payloads. While these planes are used for transportation they could similarly be used for remote sensing applications by adding sensors to the planes. Hyperspectral imagers are one this kind of sensor types. There is need for the efficient methods to interpret hyperspectral data to the wanted water quality parameters. In this work we survey the performance of neural networks in the prediction of water quality parameters from remotely sensed hyperspectral data in freshwater basin…

Neural networks with non-uniform embedding and explicit validation phase to assess Granger causality

2015

A challenging problem when studying a dynamical system is to find the interdependencies among its individual components. Several algorithms have been proposed to detect directed dynamical influences between time series. Two of the most used approaches are a model-free one (transfer entropy) and a model-based one (Granger causality). Several pitfalls are related to the presence or absence of assumptions in modeling the relevant features of the data. We tried to overcome those pitfalls using a neural network approach in which a model is built without any a priori assumptions. In this sense this method can be seen as a bridge between model-free and model-based approaches. The experiments perfo…

Blocking NMDA-receptors in the pigeon's "prefrontal" caudal nidopallium impairs appetitive extinction learning in a sign-tracking paradigm

2015

Extinction learning provides the ability to flexibly adapt to new contingencies by learning to inhibit previously acquired associations in a context-dependent manner. The neural networks underlying extinction learning were mostly studied in rodents using fear extinction paradigms. To uncover invariant properties of the neural basis of extinction learning, we employ pigeons as a model system. Since the prefrontal cortex of mammals is a key structure for extinction learning, we assessed the role of N-methyl-D-aspartate receptors (NMDARs) in the nidopallium caudolaterale, the avian functional equivalent of mammalian prefrontal cortex. Since NMDARs in prefrontal cortex have been shown to be rel…

Contextual neural-network based spectrum prediction for cognitive radio

2015

Cognitive radio is the technique of effective electromagnetic spectrum usage important for future wireless communication including 5G networks. Neural networks are nature-inspired computational models used to solve cognitive radio prediction problems. This paper presents the use of contextual Sigma-if neural network in prediction of channel states for cognitive radio. Our results indicate that Sigma-if neural network confirms better predictions than Multilayer Perceptron (MLP) network and decreases sensing time for the benefit of the increase of the effectiveness of e-m spectrum usage.

Panel Summary: Knowledge Model Representations

1997

Following the usual classifications of cognitive psychologists, we can say that the problem of representation spans three domains: the environment, the brain, and cognitive processes, which are usually studied by different scientists: the physicists, the neurobiologists and the psychologists. With the development of computer science and artificial intelligence new approaches have been introduced, which make possible simulation and implementation of cognitive processes through neural networks and symbolic systems. But the contribution of new methods is not limited to simulation, because they try to provide new models which consider cognitive process as information processing, not as reaction…