Search results for "Neural"
showing 10 items of 2783 documents
Parameters identification of induction motor dynamic model for offshore applications
2014
The paper presents a technique to identify parameters of the LuGre dynamic friction model applied to represent mechanical losses of an induction motor. This method is based on Artificial Neural Networks (ANNs) system identification which is able to estimate parameters of nonlinear mathematical models. Within the presented approach, the network is first trained to associate model parameters with predicted friction torque, being given the reference motor speed. When this process completes, the inverse operation is performed and the network delivers estimated parameters of the model based on the reference friction torque. These parameters are then integrated with the dynamic model of the induc…
A taxonomy for wavelet neural networks applied to nonlinear modelling
2008
This article presents a novel classification of wavelet neural networks based on the orthogonality/non-orthogonality of neurons and the type of nonlinearity employed. On the basis of this classification different network types are studied and their characteristics illustrated by means of simple one-dimensional nonlinear examples. For multidimensional problems, which are affected by the curse of dimensionality, the idea of spherical wavelet functions is considered. The behaviour of these networks is also studied for modelling of a low-dimension map.
A Comparative Analysis of Residual Block Alternatives for End-to-End Audio Classification
2020
Residual learning is known for being a learning framework that facilitates the training of very deep neural networks. Residual blocks or units are made up of a set of stacked layers, where the inputs are added back to their outputs with the aim of creating identity mappings. In practice, such identity mappings are accomplished by means of the so-called skip or shortcut connections. However, multiple implementation alternatives arise with respect to where such skip connections are applied within the set of stacked layers making up a residual block. While residual networks for image classification using convolutional neural networks (CNNs) have been widely discussed in the literature, their a…
Visual information flow in Wilson-Cowan networks.
2020
In this paper, we study the communication efficiency of a psychophysically tuned cascade of Wilson-Cowan and divisive normalization layers that simulate the retina-V1 pathway. This is the first analysis of Wilson-Cowan networks in terms of multivariate total correlation. The parameters of the cortical model have been derived through the relation between the steady state of the Wilson-Cowan model and the divisive normalization model. The communication efficiency has been analyzed in two ways: First, we provide an analytical expression for the reduction of the total correlation among the responses of a V1-like population after the application of the Wilson-Cowan interaction. Second, we empiri…
Neuropathic pain. Redefinition and a grading system for clinical and research purposes.
2008
Pain usually results from activation of nociceptive afferents by actually or potentially tissue-damaging stimuli. Pain may also arise by activity generated within the nervous system without adequate stimulation of its peripheral sensory endings. For this type of pain, the International Association for the Study of Pain introduced the term neuropathic pain, defined as "pain initiated or caused by a primary lesion or dysfunction in the nervous system." While this definition has been useful in distinguishing some characteristics of neuropathic and nociceptive types of pain, it lacks defined boundaries. Since the sensitivity of the nociceptive system is modulated by its adequate activation (e.g…
Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
2021
[EN] Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in Xe-136. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6 MeV gamma rays from a Th-228 calibration source. We train a network on Monte Carlo-simulat…
Artificial neural networks for neutron/ γ discrimination in the neutron detectors of NEDA
2020
Three different Artificial Neural Network architectures have been applied to perform neutron/? discrimination in NEDA based on waveform and time-of-flight information. Using the coincident ?-rays from AGATA, we have been able to measure and compare on real data the performances of the Artificial Neural Networks as classifiers. While the general performances are quite similar for the data set we used, differences, in particular related to the computing times, have been highlighted. One of the Artificial Neural Network architecture has also been found more robust to time misalignment of the waveforms. Such a feature is of great interest for online processing of waveforms. Narodowe Centrum Nau…
Classification and retrieval on macroinvertebrate image databases
2011
Aquatic ecosystems are continuously threatened by a growing number of human induced changes. Macroinvertebrate biomonitoring is particularly efficient in pinpointing the cause-effect structure between slow and subtle changes and their detrimental consequences in aquatic ecosystems. The greatest obstacle to implementing efficient biomonitoring is currently the cost-intensive human expert taxonomic identification of samples. While there is evidence that automated recognition techniques can match human taxa identification accuracy at greatly reduced costs, so far the development of automated identification techniques for aquatic organisms has been minimal. In this paper, we focus on advancing …
Differentiating Malignant from Benign Pigmented or Non-Pigmented Skin Tumours—A Pilot Study on 3D Hyperspectral Imaging of Complex Skin Surfaces and …
2022
Several optical imaging techniques have been developed to ease the burden of skin cancer disease on our health care system. Hyperspectral images can be used to identify biological tissues by their diffuse reflected spectra. In this second part of a three-phase pilot study, we used a novel hand-held SICSURFIS Spectral Imager with an adaptable field of view and target-wise selectable wavelength channels to provide detailed spectral and spatial data for lesions on complex surfaces. The hyperspectral images (33 wavelengths, 477–891 nm) provided photometric data through individually controlled illumination modules, enabling convolutional networks to utilise spectral, spatial, and skin-surface mo…
Predictive assessment of ochratoxin A accumulation in grape juice based-medium by Aspergillus carbonarius using neural networks
2009
Aims: To study the ability of multi-layer perceptron artificial neural networks (MLP-ANN) and radial-basis function networks (RBFNs) to predict ochratoxin A (OTA) concentration over time in grape-based cultures of Aspergillus carbonarius under different conditions of temperature, water activity (a(w)) and sub-inhibitory doses of the fungicide carbendazim. Methods and Results: A strain of A. carbonarius was cultured in a red grape juice-based medium. The input variables to the network were temperature (20-28 degrees C), a(w) (0 center dot 94-0 center dot 98), carbendazim level (0-450 ng ml(-1)) and time (3-15 days after the lag phase). The output of the ANNs was OTA level determined by liqui…