Search results for " artificial neural network"
showing 10 items of 22 documents
Neural Networks in ECG Classification
2011
In this chapter, we review the vast field of application of artificial neural networks in cardiac pathology discrimination based on electrocardiographic signals. We discuss advantages and drawbacks of neural and adaptive systems in cardiovascular medicine and catch a glimpse of forthcoming developments in machine learning models for the real clinical environment. Some problems are identified in the learning tasks of beat detection, feature selection/extraction, and classification, and some proposals and suggestions are given to alleviate the problems of interpretability, overfitting, and adaptation. These have become important problems in recent years and will surely constitute the basis of…
A Novel Expert System for Non-Invasive Liver Iron Overload Estimation in Thalassemic Patients
2014
Expert Systems can integrate logic based often on computational intelligence methods and they are used in complex problem solving. In this work an Expert System for classifying liver iron concentration in thalassemic patients is presented. In this work, an ANN is used to validate the output of the L.I.O.MO.T (Liver Iron Overload Monitoring in Thalassemia) method against the output of the state-of-the-art method based on MRI T2 assessment for liver iron concentration. The model has been validated with a dataset of 200 samples. The experimental Mean Squared Error results and Correlation show interesting performances. The proposed algorithm has been developed as a plug in for OsiriX Dicom View…
Estimation of Granger causality through Artificial Neural Networks: applications to physiological systems and chaotic electronic oscillators
2021
One of the most challenging problems in the study of complex dynamical systems is to find the statistical interdependencies among the system components. Granger causality (GC) represents one of the most employed approaches, based on modeling the system dynamics with a linear vector autoregressive (VAR) model and on evaluating the information flow between two processes in terms of prediction error variances. In its most advanced setting, GC analysis is performed through a state-space (SS) representation of the VAR model that allows to compute both conditional and unconditional forms of GC by solving only one regression problem. While this problem is typically solved through Ordinary Least Sq…
The computational power of continuous time neural networks
1997
We investigate the computational power of continuous-time neural networks with Hopfield-type units. We prove that polynomial-size networks with saturated-linear response functions are at least as powerful as polynomially space-bounded Turing machines.
Dorsal Column Nuclei Neural Signal Features Permit Robust Machine-Learning of Natural Tactile- and Proprioception-Dominated Stimuli
2020
Neural prostheses enable users to effect movement through a variety of actuators by translating brain signals into movement control signals. However, to achieve more natural limb movements from these devices, the restoration of somatosensory feedback is required. We used feature-learnability, a machine-learning approach, to assess signal features for their capacity to enhance decoding performance of neural signals evoked by natural tactile and proprioceptive somatosensory stimuli, recorded from the surface of the dorsal column nuclei (DCN) in urethane-anesthetized rats. The highest performing individual feature, spike amplitude, classified somatosensory DCN signals with 70% accuracy. The hi…
Empirical mode decomposition and neural network for the classification of electroretinographic data
2013
The processing of biosignals is increasingly being utilized in ambulatory situations in order to extract significant signals' features that can help in clinical diagnosis. However, this task is hampered by the fact that biomedical signals exhibit a complex behaviour characterized by strong non-linear and non-stationary properties that cannot always be perceived by simple visual examination. New processing methods need be considered. In this context, we propose to apply a signal processing method, based on empirical mode decomposition and artificial neural networks, to analyse electroretinograms, i.e. the retinal response to a light flash, with the aim to detect and classify retinal diseases…
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.
A NEURAL NETWORK PRIMER
1994
Neural networks are composed of basic units somewhat analogous to neurons. These units are linked to each other by connections whose strength is modifiable as a result of a learning process or algorithm. Each of these units integrates independently (in paral lel) the information provided by its synapses in order to evaluate its state of activation. The unit response is then a linear or nonlinear function of its activation. Linear algebra concepts are used, in general, to analyze linear units, with eigenvectors and eigenvalues being the core concepts involved. This analysis makes clear the strong similarity between linear neural networks and the general linear model developed by statisticia…
Assessment of indoor illuminance and study on best photosensors' position for design and commissioning of Daylight Linked Control Systems. A new meth…
2018
Abstract Artificial lighting systems have to ensure appropriate illuminance with high energy efficiency according to best design practice and technical standards. These aims can be tackled, by incorporating a Daylight linked control system. However, the system behaviour is strongly influenced by several factors and, in particular, by the sensors' position. Indeed, very often the illuminance on work-plane is not fully correlated with illuminance measured by the photo-sensor used to control the luminaires. This fact leads to wrong information for the Daylight linked control systems affecting its efficacy. The artificial intelligence of Neural Networks can be exploited to provide a method for …
ANN Model to predict the bake hardenability of Transformation-Induced Plasticity steels
2009
Neural networks are useful tools for optimizing material properties, considering the material’s microstructure and therefore the thermal treatments it has undergone. In this research an artificial neural network (ANN) with a Bayesian framework able to predict the bake hardening and the mechanical properties of the Transformation-Induced-Plasticity (TRIP) steels was designed. The forecast ability of the ANN model is achieved taking into account the operating parameters involved in the Intercritical Annealing (IA), in the Isothermal Bainite Treatment (IBT) and also considering the different prestrain values and the volume fraction of the retained austenite before the Bake Hardening (BH) treat…