Search results for "artificial intelligence"

showing 10 items of 6122 documents

<title>Restoration of a short-exposure image sequence degraded by atmospheric turbulence</title>

2000

This paper deals with the restoration of the shape of an object observed with a high-resolution infrared imaging device, through atmospheric turbulence. The propagation path is quite long (a few tenth kilometer) and the image is thus disturbed. A sequence of short-exposure images of the interesting object is recorded. We can see that the object shape fluctuates randomly during the sequence, but that its edges remain sharp, thanks to the very short exposure time. A bayesian analysis of the Fourier descriptors associated to the edges shows that the optimal shape is the one corresponding to the mean Fourier descriptors. We thus propose two ways to estimate this shape. The first one consists in…

SequenceActive contour modelGeographyMatching (graph theory)Position (vector)business.industryActive shape modelPath (graph theory)Computer visionPoint (geometry)Artificial intelligencebusinessImage restorationSPIE Proceedings
researchProduct

A Mushroom Bodies inspired spiking network for classification and sequence learning

2015

Sequence learning is a complex capability shown by living beings, able to extract information from the environment. Looking into the insect world, there are several examples where the presentation time of specific stimuli is considered to select the proper behavioural response. On the basis of previously developed neural models for sequence learning, inspired by the Drosophila melanogaster, a new formalization of key brain structures involved in the process is here provided. The input classification is performed through resonant neurons, stimulated by the complex dynamics generated in a lattice of recurrent spiking neurons modelling the Mushroom Bodies neuropile in the insect brain. The net…

SequenceBasis (linear algebra)Computer scienceProcess (engineering)business.industryContext (language use)Crystal latticesComplex dynamicsMushroom bodiesArtificial intelligenceSequence learningCrystal lattices; Filtration; Neural networksbusinessFiltrationNeural networksTRACE (psycholinguistics)Filtering; Insects; Lattices; Neurons
researchProduct

Classification of Sequences with Deep Artificial Neural Networks: Representation and Architectural Issues

2021

DNA sequences are the basic data type that is processed to perform a generic study of biological data analysis. One key component of the biological analysis is represented by sequence classification, a methodology that is widely used to analyze sequential data of different nature. However, its application to DNA sequences requires a proper representation of such sequences, which is still an open research problem. Machine Learning (ML) methodologies have given a fundamental contribution to the solution of the problem. Among them, recently, also Deep Neural Network (DNN) models have shown strongly encouraging results. In this chapter, we deal with specific classification problems related to t…

SequenceBiological dataSequence classificationSettore INF/01 - InformaticaArtificial neural networkProcess (engineering)Computer sciencebusiness.industryDeep learningBacteria classificationSequence classificationBacteria classificationNucleosome identificationDeep neural networkMachine learningcomputer.software_genreData typeNucleosome identificationComponent (UML)Artificial intelligenceMetagenomicsRepresentation (mathematics)businesscomputer
researchProduct

Cloud motion detection from infrared satellite images

2002

The estimation of cloud motion from a sequence of satellite images can be considered a challenging task due to the complexity of phenomena implied. Being a non-rigid motion and implying non-linear events, most motion models are not suitable and new algorithms have to be developed. We propose a novel technique, combining a Block Matching Algorithm (BMA) and a best candidate block search along with a vector median regularisation.

SequenceComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONMotion detectionCloud computingMotion (physics)Jump searchMotion estimationSatelliteComputer visionArtificial intelligencebusinessBlock-matching algorithmSPIE Proceedings
researchProduct

An Overview of the Application of Deep Learning in Short Read Sequence Classification

2020

AbstractAdvances in sequencing technology have led to an ever increasing amount of available short read sequencing data. This has, consequently, exacerbated the need for efficient and precise classification tools that can be used in the analysis of this data. As it stands, recent years have shown that massive leaps in performance can be achieved when it comes to approaches that are based in heuristics, and alongside these improvements there has been an ever increasing interest in applying deep learning techniques to revolutionize this classification task. We attempt to gather up these approaches and to evaluate their performance in a reproducible fashion to get a better perspective on the c…

SequenceComputer sciencebusiness.industryDeep learningState (computer science)Artificial intelligenceShort readHeuristicsbusinessData scienceTask (project management)
researchProduct

Sequence Q-learning: A memory-based method towards solving POMDP

2015

Partially observable Markov decision process (POMDP) models a control problem, where states are only partially observable by an agent. The two main approaches to solve such tasks are these of value function and direct search in policy space. This paper introduces the Sequence Q-learning method which extends the well known Q-learning algorithm towards the ability to solve POMDPs through adding a special sequence management framework by advancing from action values to “sequence” values and including the “sequence continuity principle”.

SequenceComputer sciencebusiness.industryQ-learningPartially observable Markov decision processMarkov processContext (language use)Markov modelsymbols.namesakeBellman equationsymbolsArtificial intelligenceMarkov decision processbusiness2015 20th International Conference on Methods and Models in Automation and Robotics (MMAR)
researchProduct

Positionless aspect based sentiment analysis using attention mechanism.

2021

Abstract Aspect-based sentiment analysis (ABSA) aims at identifying fine-grained polarity of opinion associated with a given aspect word. Several existing articles demonstrated promising ABSA accuracy using positional embedding to show the relationship between an aspect word and its context. In most cases, the positional embedding depends on the distance between the aspect word and the remaining words in the context, known as the position index sequence. However, these techniques usually employ both complex preprocessing approaches with additional trainable positional embedding and complex architectures to obtain the state-of-the-art performance. In this paper, we simplify preprocessing by …

SequenceInformation Systems and ManagementComputer sciencebusiness.industrySentiment analysisContext (language use)02 engineering and technologycomputer.software_genreLexiconManagement Information SystemsIndex (publishing)Artificial Intelligence020204 information systems0202 electrical engineering electronic engineering information engineeringPreprocessorEmbedding020201 artificial intelligence & image processingArtificial intelligencebusinesscomputerVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550SoftwareWord (computer architecture)Natural language processing
researchProduct

Display of travelling 3D scenes from single integral-imaging capture

2016

Integral imaging (InI) is a 3D auto-stereoscopic technique that captures and displays 3D images. We present a method for easily projecting the information recorded with this technique by transforming the integral image into a plenoptic image, as well as choosing, at will, the field of view (FOV) and the focused plane of the displayed plenoptic image. Furthermore, with this method we can generate a sequence of images that simulates a camera travelling through the scene from a single integral image. The application of this method permits to improve the quality of 3D display images and videos.

SequenceIntegral imagingbusiness.industryPlane (geometry)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONStereoscopyField of viewStereo displaylaw.inventionImage (mathematics)GeographylawComputer graphics (images)Computer visionArtificial intelligencebusinessSPIE Proceedings
researchProduct

Computation and Display of 3D Movie From a Single Integral Photography

2016

Integral photography is an auto-stereoscopic technique that allows, among other interesting applications, the display of 3D images with full parallax and avoids the painful effects of the accommodation-convergence conflict. Currently, one of the main drawbacks of this technology is the need of a huge amount of data, which have to be stored and transmitted. This is due to the fact that behind every visual resolution unit, i.e. behind any microlens of an integral-photography monitor, between 100 and 300 pixels should appear. In this paper, we make use of an updated version of our algorithm, SPOC 2.0, to alleviate this situation. We propose the application of SPOC 2.0 for the calculation of co…

SequencePixelComputer sciencebusiness.industryComputationPhotographyFrame (networking)Field of viewImage processing02 engineering and technology021001 nanoscience & nanotechnologyCondensed Matter Physics01 natural sciencesElectronic Optical and Magnetic Materials010309 opticsComputer graphics (images)0103 physical sciencesComputer visionArtificial intelligenceElectrical and Electronic Engineering0210 nano-technologyParallaxbusinessJournal of Display Technology
researchProduct

Extraction of ERP from EEG data

2007

In this article, a simple but novel technique for extracting a linear subspace related to event related potentials (ERPs) from ElectroEncephaloGraphy (EEG) data is introduced. The technique consists of a sequence of basic linear operations applied to multidimensional EEG data in a problem-specific manner. The derivation of the proposed technique is given and results with real data are described together with overall conclusions.

SequenceQuantitative Biology::Neurons and Cognitionmedicine.diagnostic_testComputer sciencebusiness.industrySpeech recognitionPattern recognitionElectroencephalographyIndependent component analysisLinear subspaceComputingMethodologies_PATTERNRECOGNITIONSignal-to-noise ratioEeg dataEvent-related potentialmedicineArtificial intelligenceNoise (video)business2007 9th International Symposium on Signal Processing and Its Applications
researchProduct