Search results for " Neural Networks"
showing 10 items of 390 documents
Deep Neural Networks for Prediction of Exacerbations of Patients with Chronic Obstructive Pulmonary Disease
2018
Chronic Obstructive Pulmonary Disease (COPD) patients need help in daily life situations as they are burdened with frequent risks of acute exacerbation and loss of control. An automated monitoring system could lead to timely treatments and avoid unnecessary hospital (re-)admissions and home visits by doctors or nurses. Therefore we present a Deep Artificial Neural Networks for approach prediction of exacerbations, particularly Feed-Forward Neural Networks (FFNN) for classification of COPD patients category and Long Short-Term Memory (LSTM), for early prediction of COPD exacerbations and subsequent triage. The FFNN and LSTM models are trained on data collected from remote monitoring of 94 pa…
Diffusion processes with ultrametric jumps
2007
Abstract In the theory of spin glasses the relaxation processes are modelled by random jumps in ultrametric spaces. One may argue that at the border of glassy and nonglassy phases the processes combining diffusion and jumps may be relevant. Using the Dirichlet form technique we construct a model of diffusion on the real line with jumps on the Cantor set. The jumps preserve the ultrametric feature of a random process on unit ball of 2-adic numbers.
Review on Higher-Order Neural Units to Monitor Cardiac Arrhythmia Patterns
2017
An electrocardiogram (ECG) is a non-invasive technique that checks for problems with the electrical activity of a patient’s heart. ECG is economical and extremely versatile. Some of its characteristics make it a very useful tool to detect cardiac pathologies. The ECG records a series of characteristic waves called PQRST; however, the QRS complex analysis enables the detection of a type of arrhythmia in an ECG. Technological developments enable the storage of a large amount of data, from which knowledge extraction is impossible without a powerful data processing tool; in particular, an adequate signal processing tool, whose output provides reliable parameters as a basis to make a precise cli…
New fitting scheme to obtain effective potential from Car-Parrinello molecular dynamics simulations: Application to silica
2008
A fitting scheme is proposed to obtain effective potentials from Car-Parrinello molecular dynamics (CPMD) simulations. It is used to parameterize a new pair potential for silica. MD simulations with this new potential are done to determine structural and dynamic properties and to compare these properties to those obtained from CPMD and a MD simulation using the so-called BKS potential. The new potential reproduces accurately the liquid structure generated by the CPMD trajectories, the experimental activation energies for the self-diffusion constants and the experimental density of amorphous silica. Also lattice parameters and elastic constants of alpha-quartz are well-reproduced, showing th…
Improving the accuracy of rainfall prediction using a regionalization approach and neural networks
2018
Spatial and temporal analysis of precipitation patterns has become an intense research topic in contemporary climatology. Increasing the accuracy of precipitation prediction can have valuable results for decision-makers in a specific region. Hence, studies about precipitation prediction on a regional scale are of great importance. Artificial Neural Networks (ANN) have been widely used in climatological applications to predict different meteorological parameters. In this study, a method is presented to increase the accuracy of neural networks in precipitation prediction in Chaharmahal and Bakhtiari Province in Iran. For this purpose, monthly precipitation data recorded at 42 rain gauges duri…
Ideal Chaotic Pattern Recognition is achievable: The Ideal-M-AdNN - its design and properties
2013
Published version of a chapter in the book: Transactions on Computational Collective Intelligence XI. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-41776-4_2 This paper deals with the relatively new field of designing a Chaotic Pattern Recognition (PR) system. The benchmark of such a system is the following: First of all, one must be able to train the system with a set of “training” patterns. Subsequently, as long as there is no testing pattern, the system must be chaotic. However, if the system is, thereafter, presented with an unknown testing pattern, the behavior must ideally be as follows. If the testing pattern is not one of the trained patterns, the system …
Inverse simulated annealing for the determination of amorphous structures
2013
We present a new and efficient optimization method to determine the structure of disordered systems in agreement with available experimental data. Our approach permits the application of accurate electronic structure calculations within the structure optimization. The new technique is demonstrated within density functional theory by the calculation of a model of amorphous carbon.
Non-exponential relaxation in disordered materials: Phenomenological correlations and spectrally selective experiments
1998
Abstract In most glass-forming materials external perturbations are relaxed in a non-exponential fashion. It is shown that the degree of non-exponentiality is phenomenologically correlated with the departure from simple thermally activated behavior as measured by the fragility index m. In model glass formers such as the Ge-As-Se ternary alloy, and to some degree for amorphous materials in general, the correlations with these properties are observed also for other characteristic features. These include the specific heat step and the aging kinetics in the glass transformation range. While phenomenological correlations have proven very useful for rationalizing the properties of many glass form…
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.