Search results for "MAG"

showing 10 items of 30133 documents

Social Collaborative Viewpoint Regression with Explainable Recommendations

2017

A recommendation is called explainable if it not only predicts a numerical rating for an item, but also generates explanations for users' preferences. Most existing methods for explainable recommendation apply topic models to analyze user reviews to provide descriptions along with the recommendations they produce. So far, such methods have neglected user opinions and influences from social relations as a source of information for recommendations, even though these are known to improve the rating prediction. In this paper, we propose a latent variable model, called social collaborative viewpoint regression (sCVR), for predicting item ratings based on user opinions and social relations. To th…

ta113Topic modelInformation retrievalComputer sciencetopic modeling02 engineering and technologyRecommender systemtrusted social relationsViewpointsSocial relationRegression020204 information systemsBenchmark (surveying)0202 electrical engineering electronic engineering information engineeringuser comment analysis020201 artificial intelligence & image processingrecommender systemsTupleLatent variable modelProceedings of the Tenth ACM International Conference on Web Search and Data Mining
researchProduct

Convolutional neural networks in skin cancer detection using spatial and spectral domain

2019

Skin cancers are world wide deathly health problem, where significant life and cost savings could be achieved if detection of cancer can be done in early phase. Hypespectral imaging is prominent tool for non-invasive screening. In this study we compare how use of both spectral and spatial domain increase classification performance of convolutional neural networks. We compare five different neural network architectures for real patient data. Our models gain same or slightly better positive predictive value as clinicians. Towards more general and reliable model more data is needed and collection of training data should be systematic. peerReviewed

ta113Training setskin cancerArtificial neural networkComputer sciencebusiness.industryspektrikuvausHyperspectral imagingspectral imagingSpectral domainPattern recognitionneuroverkotmedicine.diseaseneural networksWorld wideConvolutional neural networkihosyöpämedicineArtificial intelligenceSkin cancerEarly phasebusinessta217
researchProduct

Automatic dynamic texture segmentation using local descriptors and optical flow

2012

A dynamic texture (DT) is an extension of the texture to the temporal domain. How to segment a DT is a challenging problem. In this paper, we address the problem of segmenting a DT into disjoint regions. A DT might be different from its spatial mode (i.e., appearance) and/or temporal mode (i.e., motion field). To this end, we develop a framework based on the appearance and motion modes. For the appearance mode, we use a new local spatial texture descriptor to describe the spatial mode of the DT; for the motion mode, we use the optical flow and the local temporal texture descriptor to represent the temporal variations of the DT. In addition, for the optical flow, we use the histogram of orie…

ta113business.industrySegmentation-based object categorizationComputer scienceTexture DescriptorComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONOptical flowScale-space segmentationPattern recognitionImage segmentationComputer Graphics and Computer-Aided DesignImage textureMotion fieldRegion growingComputer Science::Computer Vision and Pattern RecognitionHistogramComputer visionSegmentationArtificial intelligencebusinessSoftwareIEEE Transactions on Image Processing
researchProduct

Turing's error-revised

2016

Many important lines of argumentation have been presented during the last decades claiming that machines cannot think like people. Yet, it has been possible to construct devices and information systems, which replace people in tasks which have previously been occupied by people as the tasks require intelligence. The long and versatile discourse over, what machine intelligence is, suggests that there is something unclear in the foundations of the discourse itself. Therefore, we critically studied the foundations of used theory languages. By looking critically some of the main arguments of machine thinking, one can find unifying factors. Most of them are based on the fact that computers canno…

ta113computationClass (set theory)modelformal language02 engineering and technologyconsciousnessArgumentation theoryEpistemologyTuring machineTuring machinesymbols.namesake020204 information systemsFormal language0202 electrical engineering electronic engineering information engineeringsymbolsSelection (linguistics)020201 artificial intelligence & image processingSociologyConstruct (philosophy)TuringcomputermindNatural languagecomputer.programming_languageInternational Journal of Philosophy Study
researchProduct

Efficient Time Integration of Maxwell's Equations with Generalized Finite Differences

2015

We consider the computationally efficient time integration of Maxwell’s equations using discrete exterior calculus (DEC) as the computational framework. With the theory of DEC, we associate the degrees of freedom of the electric and magnetic fields with primal and dual mesh structures, respectively. We concentrate on mesh constructions that imitate the geometry of the close packing in crystal lattices that is typical of elemental metals and intermetallic compounds. This class of computational grids has not been used previously in electromagnetics. For the simulation of wave propagation driven by time-harmonic source terms, we provide an optimized Hodge operator and a novel time discretizati…

ta113crystal structureElectromagneticsDiscretizationApplied Mathematicsta111Mathematical analysisFinite differenceFinite-difference time-domain methodDegrees of freedom (statistics)harmonic Hodge operatordiscrete exterior calculusmesh generationComputational Mathematicssymbols.namesakeDiscrete exterior calculusMaxwell's equationsMaxwell's equationsMesh generationnonuniform time discretizationsymbolsMathematicsSIAM Journal on Scientific Computing
researchProduct

Biased graph walks for RDF graph embeddings

2017

Knowledge Graphs have been recognized as a valuable source for background information in many data mining, information retrieval, natural language processing, and knowledge extraction tasks. However, obtaining a suitable feature vector representation from RDF graphs is a challenging task. In this paper, we extend the RDF2Vec approach, which leverages language modeling techniques for unsupervised feature extraction from sequences of entities. We generate sequences by exploiting local information from graph substructures, harvested by graph walks, and learn latent numerical representations of entities in RDF graphs. We extend the way we compute feature vector representations by comparing twel…

ta113graph embeddingsGraph kernelComputer scienceVoltage graphComparability graphdata mining02 engineering and technologycomputer.software_genre020204 information systemsyhdistetty avoin tietolinked open data0202 electrical engineering electronic engineering information engineeringTopological graph theoryGraph (abstract data type)020201 artificial intelligence & image processingData miningtiedonlouhintaGraph propertyNull graphLattice graphavoin tietocomputerProceedings of the 7th International Conference on Web Intelligence, Mining and Semantics
researchProduct

UAV-based hyperspectral monitoring of small freshwater area

2014

Recent development in compact, lightweight hyperspectral imagers have enabled UAV-based remote sensing with reasonable costs. We used small hyperspectral imager based on Fabry-Perot interferometer for monitoring small freshwater area in southern Finland. In this study we shortly describe the utilized technology and the field studies performed. We explain processing pipeline for gathered spectral data and introduce target detection-based algorithm for estimating levels of algae, aquatic chlorophyll and turbidity in freshwater. Certain challenges we faced are pointed out.

ta113hyperspectral imaginguavtarget detectionta1171Hyperspectral imagingPipeline (software)InterferometryGeographyRemote sensing (archaeology)Fabry-Perot interferometerSpectral datafreshwaterta218Remote sensing
researchProduct

An intelligent learning support system

2017

Fast-growing technologies are shaping many aspects of societies. Educational systems, in general, are still rather traditional: learner applies for school or university, chooses the subject, takes the courses, and finally graduates. The problem is that labor markets are constantly changing and the needed professional skills might not match with the curriculum of the educational program. It might be that it is not even possible to learn a combination of desired skills within one educational organization. For example, there are only a few universities that can provide high-quality teaching in several different areas. Therefore, learners may have to study specific modules and units somewhere e…

ta113intelligent learning systemsoppimisympäristöError-driven learningoppiminenComputer scienceIntelligent decision support system02 engineering and technologyopetuscareer developmenturakehityspersonalized educationHuman–computer interactionadaptive education020204 information systems0202 electrical engineering electronic engineering information engineeringComputingMilieux_COMPUTERSANDEDUCATIONälytekniikka020201 artificial intelligence & image processingLearning supportta516personointi
researchProduct

Supporting Institutional Awareness and Academic Advising using Clustered Study Profiles

2017

The purpose of academic advising is to help students with developing educational plans that support their academic career and personal goals, and to provide information and guidance on studies. Planning and management of the students’ study path is the main joint activity in advising. Based on a study log of passed courses, we propose to use robust, prototype-based clustering to identify a set of actual study path profiles. Such profiles identify groups of students with similar progress of studies, whose analysis and interpretation can be used for better institutional awareness and to support evidence-based academic advising. A model of automated academic advising system utilizing the possi…

ta113learning analyticsMedical educationKnowledge managementopiskelijatoppiminenComputer sciencebusiness.industry05 social sciencestutorointi050301 education02 engineering and technologyAcademic advisingopintopolutmentorointikorkea-asteen koulutusComputingMilieux_COMPUTERSANDEDUCATION0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingta516academic advisingbusinessrobust clustering0503 educationarviointi
researchProduct

Using VIS/NIR and IR spectral cameras for detecting and separating crime scene details

2012

Detecting invisible details and separating mixed evidence is critical for forensic inspection. If this can be done reliably and fast at the crime scene, irrelevant objects do not require further examination at the laboratory. This will speed up the inspection process and release resources for other critical tasks. This article reports on tests which have been carried out at the University of Jyväskylä in Finland together with the Central Finland Police Department and the National Bureau of Investigation for detecting and separating forensic details with hyperspectral technology. In the tests evidence was sought after at an assumed violent burglary scene with the use of VTT's 500-900 nm wave…

ta113medicine.medical_specialtySDG 16 - PeaceComputer scienceGunshot residueSDG 16 - Peace Justice and Strong InstitutionsdetectionHyperspectral imagingPolice departmentspectral imagingFingerprint recognition/dk/atira/pure/sustainabledevelopmentgoals/peace_justice_and_strong_institutionslatent fingerprintsJustice and Strong InstitutionsVNIRSpectral imagingmedicineCrime sceneDried bloodforensic investigationseparation of bloodRemote sensingCrime scene
researchProduct