Search results for "support"

showing 10 items of 2310 documents

A genetic algorithm approach to purify the classifier training labels for the analysis of remote sensing imagery

2017

This paper proposes a Genetic Algorithm (GA) approach to clean a given classifier training set for remote sensing image analysis. Starting from an initial set of training data, the new method called GA-Training Label Purifying (GA-TLP) consists of the significant training sample selection using GAs in order to maximize the classifier accuracy. This means to retain the most informative samples and to remove the uncertain, redundant, and misclassified ones. As a result of the selection process, we can obtain a purified training set. The proposed model is implemented and evaluated using a LANDSAT 7 ETM+ image. The experimental results confirm the effectiveness of the proposed approach.

Sample selectionSupport vector machineTraining set020204 information systemsGenetic algorithm0211 other engineering and technologies0202 electrical engineering electronic engineering information engineering02 engineering and technologyClassifier (UML)021101 geological & geomatics engineeringRemote sensing2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
researchProduct

Italian 'strappare': Unwilling vs struggling agents

2014

Saussure support verb opérateur causatif noun predicate metaphorSettore L-LIN/01 - Glottologia E Linguistica
researchProduct

On Obtaining Classification Confidence, Ranked Predictions and AUC with Tsetlin Machines

2020

Tsetlin machines (TMs) are a promising approach to machine learning that uses Tsetlin Automata to produce patterns in propositional logic, leading to binary (hard) classifications. In many applications, however, one needs to know the confidence of classifications, e.g. to facilitate risk management. In this paper, we propose a novel scheme for measuring TM confidence based on the logistic function, calculated from the propositional logic patterns that match the input. We then use this scheme to trade off precision against recall, producing area under receiver operating characteristic curves (AUC) for TMs. Empirically, using four real-world datasets, we show that AUC is a more sensitive meas…

Scheme (programming language)Decision support systemReceiver operating characteristicComputer sciencebusiness.industry0206 medical engineeringBinary number02 engineering and technologyPropositional calculusMachine learningcomputer.software_genreAutomatonSupport vector machine0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligenceLogistic functionbusinesscomputer020602 bioinformaticscomputer.programming_language2020 IEEE Symposium Series on Computational Intelligence (SSCI)
researchProduct

A General Frame for Building Optimal Multiple SVM Kernels

2012

The aim of this paper is to define a general frame for building optimal multiple SVM kernels. Our scheme follows 5 steps: formal representation of the multiple kernels, structural representation, choice of genetic algorithm, SVM algorithm, and model evaluation. The computation of the optimal parameter values of SVM kernels is performed using an evolutionary method based on the SVM algorithm for evaluation of the quality of chromosomes. After the multiple kernel is found by the genetic algorithm we apply cross validation method for estimating the performance of our predictive model. We implemented and compared many hybrid methods derived from this scheme. Improved co-mutation operators are u…

Scheme (programming language)Multiple kernel learningbusiness.industryComputationPattern recognitionCross-validationSupport vector machineGenetic algorithmArtificial intelligenceGeneral framebusinesscomputerKernel (category theory)Mathematicscomputer.programming_language
researchProduct

Toward Self-Supervised Feature Learning for Online Diagnosis of Multiple Faults in Electric Powertrains

2021

This article proposes a novel online fault diagnosis scheme for industrial powertrains without using historical faulty or labeled training data. The proposed method combines a one-class support vector machine (SVM) based anomaly detection and supervised convolutional neural network (CNN) algorithms to online detect multiple faults and fault severities under variable speeds and loads. The one-class SVM algorithm is to derive a score for defining faults or health classes in the first stage, and the resulting health classes are used as the training data for the CNN-based classifier in the second stage. Within this framework, the self-supervised learning of the proposed CNN algorithm allows the…

Scheme (programming language)business.industryComputer science020208 electrical & electronic engineering02 engineering and technologyMachine learningcomputer.software_genreFault (power engineering)Convolutional neural networkComputer Science ApplicationsSupport vector machineStatistical classificationControl and Systems EngineeringClassifier (linguistics)0202 electrical engineering electronic engineering information engineeringAnomaly detectionArtificial intelligenceElectrical and Electronic EngineeringbusinesscomputerFeature learningInformation Systemscomputer.programming_languageIEEE Transactions on Industrial Informatics
researchProduct

Health-Related Behaviors Among School-Aged Children and Adolescents During the Spanish Covid-19 Confinement

2020

In response to the coronavirus disease 2019 (Covid-19) world pandemic, affected countries such as Spain enacted measures comprising compulsory confinement as well as restrictions regarding free movement. Such measures likely influence children's and adolescents' lifestyles. Our study aimed to investigate the impact that the Covid-19 confinement has on health-related behaviors (HRBs) among Spanish children and adolescents. An online survey was administered to 516 parents to collect data about 860 children and adolescents (49.2% girls) aged between 3 and 16 years in relation to physical activity, screen exposure, sleep time, and fruit and vegetable consumption during the Covid-19 confinement.…

School age childCoronavirus disease 2019 (COVID-19)business.industrylcsh:RJ1-570Health relatedlcsh:Pediatricshealth-related behaviorsSleep timePediatricsFamily lifeOddschildrencoronavirus diseaseCommunity supportconfinementPediatrics Perinatology and Child HealthMedicineadolescentsHealth riskbusinessDemographyOriginal Researchlifestyle habits
researchProduct

Healthy lifestyles and academic success in a sample of Italian university students

2019

Scientific literature has shown that healthy lifestyles are implicated both in the risk reduction of several disorders and in the improvement of cognitive functions. The present study evaluated the association between lifestyle behaviors and academic performance in university students from twelve different degree courses at the University of Palermo, Italy. It was hypothesized that healthy lifestyles, measured as the practice of a good diet, satisfying quality of sleep, low-stress levels, perceived social support, abstention from the use of illegal drugs, non-problematic Internet use, and regular sports habits, were associated to academic success. A total of 466 students were surveyed (26.5…

School psychologybusiness.industryAddictionmedia_common.quotation_subject05 social sciencesSchool psychologyHealthy behavior050109 social psychologyCognitionAcademic succeScientific literature050105 experimental psychologyHealth psychologyHealth psychologySocial supportSettore M-PSI/08 - Psicologia Clinica0501 psychology and cognitive sciencesThe InternetPsychologybusinessAssociation (psychology)Settore MED/25 - PsichiatriaGeneral Psychologymedia_commonClinical psychology
researchProduct

Kindergarten teachers adjust their teaching practices in accordance with children's academic pre-skills

2011

This study examined the extent to which kindergarten children’s academic pre‐skills are associated with their teachers’ subsequent teaching practices. The pre‐skills in reading and math of 1268 children (655 boys, 613 girls) were measured in kindergarten in the fall. A pair of trained observers used the Classroom Assessment Scoring System instrument to observe 49 kindergarten teachers on their emotional support, classroom organisation and instructional support in kindergarten in the spring. The results of the multilevel modelling showed that low levels of academic pre‐skills in kindergarten classrooms in the fall predicted high classroom quality in the classrooms later on. The results sugge…

Scoring systemEmotional supportmedia_common.quotation_subjectTeaching methodMultilevel modellingeducationExperimental and Cognitive Psychologybehavioral disciplines and activitiesEducationReading (process)behavior and behavior mechanismsDevelopmental and Educational PsychologyMathematics educationta516Psychologyta515media_commonEducational Psychology
researchProduct

The relationship between classroom quality and students' engagement in secondary school

2013

Student engagement has been identified as an influential mediator between classroom interactional quality and adolescent learning outcomes. This study examined the relationship between classroom quality and student behavioural engagement in secondary school classrooms. Three dimensions of classroom quality (emotional, organisational and instructional support) and the dimension of student engagement were observed in nine classrooms using the Classroom Assessment Scoring System. Self-ratings of behavioural engagement were provided by 181 Finnish secondary school students along with their teachers’ ratings of classroom-level student engagement. The results showed, first, that there was variati…

Scoring systemEmotional supportmedia_common.quotation_subjectluokkahuoneen laatuclassroom qualityExperimental and Cognitive PsychologyStudent engagementsitoutuminenEducationOrganisational supportPedagogyobservointiDevelopmental and Educational PsychologyMathematics educationComputingMilieux_COMPUTERSANDEDUCATIONstudent engagementsecondary schoolta516Quality (business)yläkouluPsychologyclassroom observationsComputingMilieux_MISCELLANEOUSmedia_common
researchProduct

Hearing-impaired pupils in mainstream education in Finland: teachers’ experiences of inclusion and support

2017

Today, in Finland, the majority of hearing-impaired pupils attend regular schools. This is in line with inclusive policy. This study aims to investigate do these pupils receive support from teacher ...

Secondary educationgenetic structuresTeaching methodeducationPrimary educationHealth Professions (miscellaneous)Education030507 speech-language pathology & audiology03 medical and health scienceskuulovammaisethearing-impairedAssistive technologyPedagogyDevelopmental and Educational PsychologyosallisuusparticipationMainstreamta516osallistuminensupportMultimethodology05 social sciences050301 educationopetusopettajatteachingeye diseasesinclusiontukeminenHearing impairedsense organs0305 other medical sciencePsychology0503 educationInclusion (education)inkluusioEuropean Journal of Special Needs Education
researchProduct