Search results for "NEURAL NETWORK"

2021

Abstract Reliable patient-specific ventricular repolarization times (RTs) can identify regions of functional block or afterdepolarizations, indicating arrhythmogenic cardiac tissue and the risk of sudden cardiac death. Unipolar electrograms (UEs) record electric potentials, and the Wyatt method has been shown to be accurate for estimating RT from a UE. High-pass filtering is an important step in processing UEs, however, it is known to distort the T-wave phase of the UE, which may compromise the accuracy of the Wyatt method. The aim of this study was to examine the effects of high-pass filtering, and improve RT estimates derived from filtered UEs. We first generated a comprehensive set of UE…

QSPR with descriptors based on averages of vertex invariants. An artificial neural network study

2014

New type of indices, the mean molecular connectivity indices (MMCI), based on nine different concepts of mean are proposed to model, together with molecular connectivity indices (MCI), experimental parameters and random variables, eleven properties of organic solvents. Two model methodologies are used to test the different descriptors: the multilinear least-squares (MLS) methodology and the Artificial Neural Network (ANN) methodology. The top three quantitative structure–property relationships (QSPR) for each property are chosen with the MLS method. The indices of these three QSPRs were used to train the ANNs that selected the best training sets of indices to estimate the evaluation sets of…

Visual spike-based convolution processing with a Cellular Automata architecture

2010

this paper presents a first approach for implementations which fuse the Address-Event-Representation (AER) processing with the Cellular Automata using FPGA and AER-tools. This new strategy applies spike-based convolution filters inspired by Cellular Automata for AER vision processing. Spike-based systems are neuro-inspired circuits implementations traditionally used for sensory systems or sensor signal processing. AER is a neuromorphic communication protocol for transferring asynchronous events between VLSI spike-based chips. These neuro-inspired implementations allow developing complex, multilayer, multichip neuromorphic systems and have been used to design sensor chips, such as retinas an…

Integrated System for Monitoring the Tool State Using Temperature Measuring by Natural Thermocouple Method

2014

The intensive developments of intelligent manufacturing systems in the last decades open the large possibilities of more accurate monitoring of the metal cutting process. One of the most important factors of the process is the tool state given by the rate of the tool wear, which is the result of a lot of influences of almost all cutting parameters. The modern tool monitoring systems relieved that the accuracy of the results increases when using a combination of surveyed signals such as: vibrations, power consumption, acoustic emission, forces or tool temperature. Combining the output signals in a monitoring function using the neural network method gives the best results when using on-line m…

Neural network-based models for a vibration suppression system equipped with MR brake

2012

This paper is devoted to the modeling and simulation of a full-scale commercially available magnetorheological (MR) brake installed in a semi-active suspension (SAS) system. The analysis of the Bouc-Wen and Dahl mathematical models of MR damper is presented. Influence of their parameters on the response is explored. Subsequently, by using the neural networks, the parameters characterizing each model are estimated. This makes it possible to perform the comparative analysis of the suggested damper models responses with the measured experimental results. The novelty of the presented methodology is the application of artificial intelligence methods to estimate model parameters of a MR brake uti…

A Comparative Study of Nonlinear Machine Learning for the "In Silico" Depiction of Tyrosinase Inhibitory Activity from Molecular Structure.

2011

In the preset report, for the first time, support vector machine (SVM), artificial neural network (ANN), Baye- sian networks (BNs), k-nearest neighbor (k-NN) are applied and compared on two "in-house" datasets to describe the tyrosinase inhibitory activity from the molecular structure. The data set Data I is used for the identification of tyrosi- nase inhibitors (TIs) including 701 active and 728 inactive compounds. Data II consists of active chemicals for potency estimation of TIs. The 2D TOMOCOMD-CARDD atom-based quadratic indices are used as molecular descriptors. The de- rived models show rather encouraging results with the areas under the Receiver Operating Characteristic (AURC) curve …

Modeling anti-allergic natural compounds by molecular topology.

2013

Molecular topology has been applied to the search of QSAR models able to identify the anti-allergic activity of a wide group of heterogeneous compounds. Through the linear discriminant analysis and artificial neural networks, correct classification percentages above 85% for both the training set and the test set have been obtained. After carrying out a virtual screening with a natural product library, about thirty compounds with theoretical anti-allergic activity have been selected. Among them, hesperidin, naringin, salinomycin, sorbitol, curcumol, myricitrin, diosmin and kinetin stand out. Some of these compounds have already been referenced as having anti-allergic activity.

Channel Capacity in Psychovisual Deep-Nets: Gaussianization Versus Kozachenko-Leonenko

2020

In this work, we quantify how neural networks designed from biology using no statistical training have a remarkable performance in information theoretic terms. Specifically, we address the question of the amount of information that can be extracted about the images from the different layers of psychophysically tuned deep networks. We show that analytical approaches are not possible, and we propose the use of two empirical estimators of capacity: the classical Kozachenko-Lonenko estimator and a recent estimator based on Gaussianization. Results show that networks purely based on visual psychophysics are extremely efficient in two aspects: (1) the internal representation of these networks dup…

Heart Failure Occurrence: Mining Significant Patterns and 10 Days Early Prediction

2021

Electronic health records containing patient’s medical history, drug prescription, vital signs measurements, and many more parameters, are being frequently extracted and stored as unused raw data. On the other hand, machine learning and data mining techniques are becoming popular in the medical field, providing the ability to extract knowledge and valuable information from electronic health records along with accurately predicting future disease occurrence. This chapter presents a study on medical data containing vital signs recorded over the course of some years, for real patients suffering from heart failure. The first significant patterns that come along with heart failure occurrence are…

Experimental studies on continuous speech recognition using neural architectures with “adaptive” hidden activation functions

2010

The choice of hidden non-linearity in a feed-forward multi-layer perceptron (MLP) architecture is crucial to obtain good generalization capability and better performance. Nonetheless, little attention has been paid to this aspect in the ASR field. In this work, we present some initial, yet promising, studies toward improving ASR performance by adopting hidden activation functions that can be automatically learned from the data and change shape during training. This adaptive capability is achieved through the use of orthonormal Hermite polynomials. The “adaptive” MLP is used in two neural architectures that generate phone posterior estimates, namely, a standalone configuration and a hierarch…