Search results for "Artificial intelligence"

showing 10 items of 6122 documents

Symmetry operators in computer vision

1996

Abstract Symmetry plays a remarkable role in perception problems. For example, peaks of brain activity are measured in correspondence with visual patterns showing symmetry . Relevance of symmetry in vision was already noted by Koler in 1929. Here, properties of a symmetry operator are reported and a new algorithm to measure local symmetries is proposed. Its performance is tested on segmentation of complex visual patterns and the classification of sparse images.

business.industryComputer sciencemedia_common.quotation_subjectAstronomy and AstrophysicsMeasure (mathematics)Operator (computer programming)PerceptionHomogeneous spaceVisual patternsSegmentationComputer visionRelevance (information retrieval)Artificial intelligenceSymmetry (geometry)businessmedia_commonVistas in Astronomy
researchProduct

Invalid Syntax: NooJ Assisted Automatic Detection of Errors in Auxiliaries and Past Participles in Italian

2017

The work targets two areas of Italian morphosyntax: auxiliary selection (AS) and past participle agreement (PPA). In selecting such inflectional morphemes, learners of Italian commit frequent errors, even after a long period of constant study. We aim to enclose AS and PPA within the boundaries of NLP in order that a tool can be developed with a twofold purpose: first, it helps experts to build specific computer drills regarding AS and PPA; second, it assists self-taught learners in verifying whether their periphrastic sentences in Italian are well-turned. This area of Computer-Assisted Language Learning is currently poorly investigated. Further research might substantiate the importance of …

business.industryComputer sciencemedia_common.quotation_subjectComputer Science (all)Foreign languageCommitInflectional morpheme generationLanguage acquisitioncomputer.software_genreSyntaxAgreementSettore L-LIN/01 - Glottologia E LinguisticaMorphemeCALLSelection (linguistics)Mathematics (all)Artificial intelligencebusinessParticiplecomputerAutomatic identification of grammatical relationNatural language processingmedia_common
researchProduct

Aquatic Surface Robots: the State of the Art, Challenges and Possibilities

2020

In this paper, a survey of the state of the art, challenges, and possibilities for aquatic surface robots is presented. To this end, a survey and classification of aquatic surface robots is first outlined. Then, different levels of autonomy are identified for this typology of robots and categorised into environmental complexity, mission complexity, and external system independence. From this perspective, a step-wise approach is adopted on how to increment aquatic surface robots abilities within guidance, navigation, and control in order to target the different levels of autonomy. Possibilities and challenges for designing aquatic surface robots as carriers for conducting research activities…

business.industryComputer sciencemedia_common.quotation_subjectControl (management)Perspective (graphical)RoboticsField (computer science)Benchmark (surveying)Systems engineeringRobotState (computer science)Artificial intelligencebusinessAutonomymedia_common2020 IEEE International Conference on Human-Machine Systems (ICHMS)
researchProduct

Automated quality control of next generation sequencing data using machine learning

2019

AbstractControlling quality of next generation sequencing (NGS) data files is a necessary but complex task. To address this problem, we statistically characterized common NGS quality features and developed a novel quality control procedure involving tree-based and deep learning classification algorithms. Predictive models, validated on internal data and external disease diagnostic datasets, are to some extent generalizable to data from unseen species. The derived statistical guidelines and predictive models represent a valuable resource for users of NGS data to better understand quality issues and perform automatic quality control. Our guidelines and software are available at the following …

business.industryComputer sciencemedia_common.quotation_subjectDeep learningMachine learningcomputer.software_genreDNA sequencingStatistical classificationTree (data structure)Task (computing)SoftwareResource (project management)Data fileQuality (business)Artificial intelligencebusinesscomputermedia_common
researchProduct

On the Use of Preferential Weights in Interactive Reference Point Based Methods

2009

We introduce a new way of utilizing preference information specified by the decision maker in interactive reference point based methods. A reference point consists of aspiration levels for each objective function. We take the desires of the decision maker into account more closely when projecting the reference point to become nondominated. In this way we can support the decision maker in finding the most satisfactory solutions faster. In practice, we adjust the weights in the achievement scalarizing function that projects the reference point. We demonstrate our idea with an example and we summarize results of computational tests that support the efficiency of the idea proposed.

business.industryComputer sciencemedia_common.quotation_subjectMultiobjective programmingInformation and Computer ScienceArtificial intelligencebusinessFunction (engineering)Decision makerMulti-objective optimizationPreferencemedia_common
researchProduct

A learning model for the dual evolution of human social behaviors

2003

In this work we modelize, with an abstract mathematical model by computer simulation, the processes that have made to appear in the world a strong duality between orient and occident, by combining changes in conditions of initialization, natural system and the opposition gregarious/individualism of the social behaviors. Finally we present a statistical study of the influence of the repression adaptability, resignation and recycling on the ecological destruction and social evolution. This model can help us to analyze if the current capitalist globalization can be stopped, changed or regulated, and if it is possible to overcome it towards a Free Scientific Society.

business.industryComputer sciencemedia_common.quotation_subjectOpposition (politics)DUAL (cognitive architecture)AdaptabilityTheoretical Computer ScienceGlobalizationIndividualismControl and Systems EngineeringComputer Science (miscellaneous)CyberneticsArtificial intelligencePositive economicsSocial evolutionbusinessEngineering (miscellaneous)Social Sciences (miscellaneous)Social behaviormedia_commonKybernetes
researchProduct

Métricas epistemológicas para modelos basados en fractales lingüísticos de PLN

2016

This work is part of a wider research named BIOTECH that intends to assure the quality of linguistic modeling activity for automatic systems, making it possible to automate the management of words and natural language. Words are considered part of the complex articulation of language expressions. BIOTECH aims to take it as a tool to evaluate and track linguistic and verbal communication distorsion in patients with Autistic Spectrum Disorder. The main contribution of this paper is to discuss the validity of fractals when used to model linguistic reasoning, and the relevance of considering not only statistics but also epistemology-related metrics. Furthermore, a set of metrics is introduced a…

business.industryComputer sciencemedia_common.quotation_subjectPragmaticscomputer.software_genreRepresentativeness heuristicNonverbal communicationRelevance (information retrieval)Quality (business)In patientArtificial intelligencebusinessSet (psychology)computerNatural language processingNatural languagemedia_common2016 IEEE Biennial Congress of Argentina (ARGENCON)
researchProduct

Anchoring by Imitation Learning in Conceptual Spaces

2005

In order to have a robotic system able to effectively learn by imitation, and not merely reproduce the movements of a human teacher, the system should have the capabilities of deeply understanding the perceived actions to be imitated. This paper deals with the development of a cognitive architecture for learning by imitation in which a rich conceptual representation of the observed actions is built. The purpose of the following discussion is to show how the same conceptual representation can be used both in a bottom-up approach, in order to learn sequences of actions by imitation learning paradigm, and in a top-down approach, in order to anchor the symbolical representations to the perceptu…

business.industryComputer sciencemedia_common.quotation_subjectRepresentation (systemics)RoboticsCognitive architectureRobotics Imitation learningHuman–computer interactionPerceptionCognitive developmentArtificial intelligenceCognitive imitationImitationbusinessSet (psychology)media_common
researchProduct

Using System Dynamics to Model Student Performance in an Intelligent Tutoring System

2017

One basic adaptation function of an Intelligent Tutoring System (ITS) consists of selecting the most appropriate next task to be offered to the learner. This decision can be based on estimates, such as the expected performance of the student, or the probability that the student successfully solves each particular task. However, the computation of these values is intrinsically difficult, as they may depend on other complex latent variables that also need to be estimated from observable quantities, e.g. the current student's ability. In this work, we have used system dynamics to model learning and predict the student's performance in a given exercise, in an existing ITS that was developed to …

business.industryComputer sciencemedia_common.quotation_subjectUser modelingComputation05 social sciences050301 education02 engineering and technologyLatent variableMachine learningcomputer.software_genreIntelligent tutoring systemSystem dynamicsTask (project management)ComputingMilieux_COMPUTERSANDEDUCATION0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligenceFunction (engineering)businessAdaptation (computer science)0503 educationcomputermedia_commonProceedings of the 25th Conference on User Modeling, Adaptation and Personalization
researchProduct

<title>Expanding context against weighted voting of classifiers</title>

2000

In the paper we propose a new method to integrate the predictions of multiple classifiers for Data Mining and Machine Learning tasks. The method assumes that each classifier stands in it's own context, and the contexts are partially ordered. The order is defined by monotonous quality function that maps each context to the value from the interval [0,1]. The classifier that has the context with better quality is supposed to predict better than the classifier from worse quality. The objective is to generate the opinion of `virtual' classifier that stands in the context with quality equal to 1. This virtual classifier must have the best accuracy of predictions due to the best context. To do thi…

business.industryComputer sciencemedia_common.quotation_subjectWeighted votingFeature selectionQuadratic classifiercomputer.software_genreMachine learningInformation extractionComputingMethodologies_PATTERNRECOGNITIONKnowledge extractionVotingMargin classifierArtificial intelligencebusinesscomputerClassifier (UML)media_commonSPIE Proceedings
researchProduct