Search results for " NEURAL NETWORKS"

showing 10 items of 390 documents

From orientational glasses to structural glasses: What computer simulations have contributed to understand experiments

2002

Abstract Orientational glasses, produced by random dilution of molecular crystals, exhibit a freezing transition of the quadrupole moments. Monte Carlo simulations of lattice models (generalization of the Edwards–Anderson spin glass model) have been used to elucidate this behavior. While short range models exhibit a static glass transition at zero temperature only, the infinite range Potts glass exhibits a transition where a glass order parameter appears discontinuously. At higher temperature, a dynamical transition occurs, described by mode-coupling theory (MCT). MCT has also been tested by Monte Carlo and molecular dynamics simulations of coarse-grained models of glass-forming polymers. W…

chemistry.chemical_classificationSpin glassCondensed matter physicsMonte Carlo methodPolymerCondensed Matter PhysicsCondensed Matter::Disordered Systems and Neural NetworksElectronic Optical and Magnetic MaterialsCondensed Matter::Soft Condensed MatterMolecular dynamicschemistryLattice (order)Materials ChemistryCeramics and CompositesGlass transitionAnderson impurity modelPotts modelJournal of Non-Crystalline Solids
researchProduct

One and Two Dimensional Convolutional Neural Networks for Seizure Detection Using EEG Signals

2021

Deep learning for the automated detection of epileptic seizures has received much attention during recent years. In this work, one dimensional convolutional neural network (1D-CNN) and two dimensional convolutional neural network (2D-CNN) are simultaneously used on electroencephalogram (EEG) data for seizure detection. Firstly, using sliding windows without overlap on raw EEG to obtain the definite one-dimension time EEG segments (1D-T), and continuous wavelet transform (CWT) for 1D-T signals to obtain the two-dimension time-frequency representations (2D-TF). Then, 1D-CNN and 2D-CNN model architectures are used on 1D-T and 2D-TF signals for automatic classification, respectively. Finally, t…

convolutional neural networks (CNN)Computer scienceseizure detection02 engineering and technologyneuroverkotElectroencephalographyConvolutional neural network0202 electrical engineering electronic engineering information engineeringmedicineEEGContinuous wavelet transformSignal processingArtificial neural networkmedicine.diagnostic_testbusiness.industryelectroencephalogram (EEG)signaalinkäsittelyDeep learningtime-frequency representationtideep learningsignaalianalyysi020206 networking & telecommunicationsPattern recognitionkoneoppiminenBenchmark (computing)020201 artificial intelligence & image processingArtificial intelligencebusinessepilepsia
researchProduct

Computational Modeling of Human Visual Function using Psychophysics, Deep Neural Networks, and Information Theory

2023

Visual perception is a key to unlocking the secrets of brain functions because most of the information is processed through the early visual system and then transmitted to the high-level cognitive perception brain regions. The brain functions as a self-organizing, bio-dynamic, and chaotic system that receives outside information and then decomposes it into pieces of information that can be processed efficiently and independently. The work connects natural image statistics, psychophysics, deep neural networks, and information theory to perceptual vision systems to explore how vision processes information from the outside world and how the information coupled drives functional connectivity be…

deep neural networkshuman vision systemUNESCO::FÍSICAperceptioninformation theory
researchProduct

Nonlinear Relaxation in Population Dynamics

2001

We analyze the nonlinear relaxation of a complex ecosystem composed of many interacting species. The ecological system is described by generalized Lotka-Volterra equations with a multiplicative noise. The transient dynamics is studied in the framework of the mean field theory and with random interaction between the species. We focus on the statistical properties of the asymptotic behaviour of the time integral of the i-th population and on the distribution of the population and of the local field.

education.field_of_studyDistribution (number theory)Statistical Mechanics (cond-mat.stat-mech)Applied MathematicsPopulationFOS: Physical sciencesDisordered Systems and Neural Networks (cond-mat.dis-nn)Condensed Matter - Disordered Systems and Neural NetworksMultiplicative noiseQuantitative BiologyNonlinear systemMean field theoryModeling and SimulationFOS: Biological sciencesQuantitative Biology::Populations and EvolutionGeometry and TopologyRelaxation (approximation)Statistical physicseducationFocus (optics)Local fieldCondensed Matter - Statistical MechanicsQuantitative Biology (q-bio)Mathematics
researchProduct

Characterization of E'delta and triplet point defects in oxygen-deficient amorphous silicon dioxide

2005

We report an experimental study by electron paramagnetic resonance (EPR) of gamma ray irradiation induced point defects in oxygen deficient amorphous SiO2 materials. We have found that three intrinsic (E'gamma, E'delta and triplet) and one extrinsic ([AlO4]0) paramagnetic centers are induced. All the paramagnetic defects but E'gamma center are found to reach a concentration limit value for doses above 10^3 kGy, suggesting a generation process from precursors. Isochronal thermal treatments of a sample irradiated at 10^3 kGy have shown that for T>500 K the concentrations of E'gamma and E'delta centers increase concomitantly to the decrease of [AlO4]0. This occurrence speaks for an hole tra…

electron paramagnetic resonanceFOS: Physical sciencesDisordered Systems and Neural Networks (cond-mat.dis-nn)Condensed Matter - Disordered Systems and Neural NetworksDangling bondsParamagnetic resonance
researchProduct

One Dimensional Convolutional Neural Networks for Seizure Onset Detection Using Long-term Scalp and Intracranial EEG

2021

Epileptic seizure detection using scalp electroencephalogram (sEEG) and intracranial electroencephalogram (iEEG) has attracted widespread attention in recent two decades. The accurate and rapid detection of seizures not only reflects the efficiency of the algorithm, but also greatly reduces the burden of manual detection during long-term electroencephalogram (EEG) recording. In this work, a stacked one-dimensional convolutional neural network (1D-CNN) model combined with a random selection and data augmentation (RS-DA) strategy is proposed for seizure onset detection. Firstly, we segmented the long-term EEG signals using 2-sec sliding windows. Then, the 2-sec interictal and ictal segments w…

intracranial electroencephalogram (iEEG)convolutional neural networks (CNN).signaalinkäsittelyscalp electroencephalogram (sEEG)epilepsyseizure detectionsignaalianalyysineuroverkotEEGepilepsia
researchProduct

Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance

2022

Accurate sleep stage classification is vital to assess sleep quality and diagnose sleep disorders. Numerous deep learning based models have been designed for accomplishing this labor automatically. However, the class imbalance problem existing in polysomnography (PSG) datasets has been barely investigated in previous studies, which is one of the most challenging obstacles for the real-world sleep staging application. To address this issue, this paper proposes novel methods with signal-driven and image-driven ways of noise addition to balance the imbalanced relationship in the training dataset samples. We evaluate the effectiveness of the proposed methods which are integrated into a convolut…

mallintaminenluokitus (toiminta)trainingdatabasessleep stage classificationtime-frequency imagedeep learningsyväoppiminenneuroverkotneural networksuni (lepotila)convolutional neural networksclass imbalance problemtietokannatwhite noiseunihäiriötdata augmentation2022 International Joint Conference on Neural Networks (IJCNN)
researchProduct

A Navigation and Augmented Reality System for Visually Impaired People

2021

In recent years, we have assisted with an impressive advance in augmented reality systems and computer vision algorithms, based on image processing and artificial intelligence. Thanks to these technologies, mainstream smartphones are able to estimate their own motion in 3D space with high accuracy. In this paper, we exploit such technologies to support the autonomous mobility of people with visual disabilities, identifying pre-defined virtual paths and providing context information, reducing the distance between the digital and real worlds. In particular, we present ARIANNA+, an extension of ARIANNA, a system explicitly designed for visually impaired people for indoor and outdoor localizati…

navigation; visually impaired; computer vision; augmented reality; cultural context; convolutional neural network; machine learning; hapticExploitComputer scienceconvolutional neural networkImage processingContext (language use)02 engineering and technologyTP1-1185BiochemistryConvolutional neural networkArticleMotion (physics)computer visionAnalytical ChemistrySettore ING-INF/04 - AutomaticaArtificial IntelligenceHuman–computer interactioncultural context0202 electrical engineering electronic engineering information engineeringHumansElectrical and Electronic EngineeringnavigationInstrumentationHaptic technologySettore ING-INF/03 - TelecomunicazioniChemical technology020206 networking & telecommunicationsAtomic and Molecular Physics and Opticsaugmented realitymachine learning020201 artificial intelligence & image processingAugmented realityvisually impairedNeural Networks ComputerhapticAlgorithmsVisually Impaired PersonsPATH (variable)augmented reality computer vision convolutional neural network cultural context haptic machine learning navigation visually impaired Algorithms Artificial Intelligence Humans Neural Networks Computer Augmented Reality Visually Impaired PersonsSensors
researchProduct

Theoretical and experimental study of two discrete coupled Nagumo chains

2001

We analyze front wave (kink and antikink) propagation and pattern formation in a system composed of two coupled discrete Nagumo chains using analytical and numerical methods. In the case of homogeneous interaction among the chains, we show the possibility of the effective control on wave propagation. In addition, physical experiments on electrical chains confirm all theoretical behaviors.

nonlinear dynamicsNagumoneural network[NLIN.NLIN-PS] Nonlinear Sciences [physics]/Pattern Formation and Solitons [nlin.PS][SPI.TRON] Engineering Sciences [physics]/Electronics[PHYS.COND.CM-DS-NN] Physics [physics]/Condensed Matter [cond-mat]/Disordered Systems and Neural Networks [cond-mat.dis-nn]
researchProduct

Seizure Prediction Using EEG Channel Selection Method

2022

Seizure prediction using intracranial electroencephalogram (iEEG) is still challenging because of complicated signals in spatial and time domains. Feature selection in the spatial domain (i.e., channel selection) has been largely ignored in this field. Hence, in this paper, a novel approach of iEEG channel selection strategy combined with one-dimensional convolutional neural networks (1D-CNN) was presented for seizure prediction. First, 15-sec and 30-sec iEEG segments with an increasing number of channels (from one channel to all channels) were sequentially fed into 1D-CNN models for training and testing. Then, the channel case with the best classification rate was selected for each partici…

one-dimensional convolutional neural networks (1D-CNN)channel selectionintracranial electroencephalogram (iEEG)koneoppiminensignaalinkäsittelyseizure predictionsairauskohtauksetepilepsysignaalianalyysineuroverkotEEGepilepsia
researchProduct