Search results for "Learning"

showing 10 items of 6669 documents

Machine learning in remote sensing data processing

2009

Remote sensing data processing deals with real-life applications with great societal values. For instance urban monitoring, fire detection or flood prediction from remotely sensed multispectral or radar images have a great impact on economical and environmental issues. To treat efficiently the acquired data and provide accurate products, remote sensing has evolved into a multidisciplinary field, where machine learning and signal processing algorithms play an important role nowadays. This paper serves as a survey of methods and applications, and reviews the latest methodological advances in machine learning for remote sensing data analysis.

Data processingContextual image classificationFire detectionbusiness.industryComputer scienceMultispectral imageMachine learningcomputer.software_genreField (computer science)Support vector machineRemote sensing (archaeology)Radar imagingArtificial intelligencebusinesscomputerRemote sensing2009 IEEE International Workshop on Machine Learning for Signal Processing
researchProduct

Dimensionality Reduction Techniques: An Operational Comparison On Multispectral Satellite Images Using Unsupervised Clustering

2006

Multispectral satellite imagery provides us with useful but redundant datasets. Using Dimensionality Reduction (DR) algorithms, these datasets can be made easier to explore and to use. We present in this study an objective comparison of five DR methods, by evaluating their capacity to provide a usable input to the K-means clustering algorithm. We also suggest a method to automatically find a suitable number of classes K, using objective "cluster validity indexes" over a range of values for K. Ten Landsat images have been processed, yielding a classification rate in the 70-80% range. Our results also show that classical linear methods, though slightly outperformed by more recent nonlinear al…

Data processingContextual image classificationPixelbusiness.industryComputer scienceDimensionality reductionMultispectral imagek-means clusteringUnsupervised learningPattern recognitionArtificial intelligencebusinessCluster analysisProceedings of the 7th Nordic Signal Processing Symposium - NORSIG 2006
researchProduct

Active learning in a real-world bioengineering problem: A pilot-study on ophthalmologic data processing

2019

Active learning is a format alternative to the conventional lecture/recitation/laboratory; research results have reported that it is suitable to encourage student inquiry and foster peer mentoring. Although the availability of computer-based learning materials in biomedical sciences is increasing, there are relatively few studies aimed to integrate traditional methods of teaching with inquiry-based approaches utilizing these Information and Communication Technologies (ICT) tools. This paper describes a pilot-study on a comprehensive active laboratory course about digital ophthalmologic signal classification, experienced by a group of undergraduates in Bio-Electronic Engineering. During the …

Data processingGeneral Computer ScienceMultimediaComputer scienceSettore FIS/08 - Didattica E Storia Della Fisica05 social sciencesGeneral Engineering050301 educationcomputer.software_genreSettore FIS/07 - Fisica Applicata(Beni Culturali Ambientali Biol.e Medicin)Settore FIS/03 - Fisica Della MateriaEducation03 medical and health sciences0302 clinical medicineActive learning0503 educationcomputer030217 neurology & neurosurgeryactive learning technologies collaborative learning tools educational software applicationselectroretinogram learning via discoveryComputer Applications in Engineering Education
researchProduct

A Special Issue on Advances in Machine Learning for Remote Sensing and Geosciences [From the Guest Editors]

2016

Machine learning has become a standard paradigm for the analysis of remote sensing and geoscience data at both local and global scales. In the upcoming years, with the advent of new satellite constellations, machine learning will have a fundamental role in processing large and heterogeneous data sources. Machine learning will move from mere statistical data processing to actual learning, understanding, and knowledge extraction. The ambitious goal is to provide responses to the challenging scientific questions about the earth system. This special issue aims at providing an updated, refreshing view of current developments in the field. For this special issue, we have collected five articles t…

Data processingGeneral Computer Sciencebusiness.industryComputer science020206 networking & telecommunications02 engineering and technologyMachine learningcomputer.software_genreData scienceField (computer science)Earth system scienceKnowledge extractionRemote sensing (archaeology)0202 electrical engineering electronic engineering information engineeringGeneral Earth and Planetary Sciences020201 artificial intelligence & image processingArtificial intelligenceElectrical and Electronic EngineeringbusinessInstrumentationcomputerRemote sensingConstellationIEEE Geoscience and Remote Sensing Magazine
researchProduct

EHRtemporalVariability

2020

Functions to delineate temporal dataset shifts in Electronic Health Records through the projection and visualization of dissimilarities among data temporal batches. This is done through the estimation of data statistical distributions over time and their projection in non-parametric statistical manifolds, uncovering the patterns of the data latent temporal variability. EHRtemporalVariability is particularly suitable for multi-modal data and categorical variables with a high number of values, common features of biomedical data where traditional statistical process control or time-series methods may not be appropriate. EHRtemporalVariability allows you to explore and identify dataset shifts t…

Data quality managementMedical informaticsBioinformaticsMachine learningData visualisation
researchProduct

Streamlining distributed Deep Learning I/O with ad hoc file systems

2021

With evolving techniques to parallelize Deep Learning (DL) and the growing amount of training data and model complexity, High-Performance Computing (HPC) has become increasingly important for machine learning engineers. Although many compute clusters already use learning accelerators or GPUs, HPC storage systems are not suitable for the I/O requirements of DL workflows. Therefore, users typically copy the whole training data to the worker nodes or distribute partitions. Because DL depends on randomized input data, prior work stated that partitioning impacts DL accuracy. Their solutions focused mainly on training I/O performance on a high-speed network but did not cover the data stage-in pro…

Data setWorkflowDistributed databaseProcess (engineering)Computer sciencebusiness.industryDeep learningDistributed computingComputer data storageData deduplicationArtificial intelligenceGlobal Namespacebusiness2021 IEEE International Conference on Cluster Computing (CLUSTER)
researchProduct

Diagnóstico de Enfermedades Card´ıacas con los algoritmos supervisados Naives Bayesian

2020

Las enfermedades cardíacas son la principal causa de muerte en la actualidad. Este paper contrasta la performance de los diferentes algoritmos supervisados de Machine Learning, que tienen aplicaciones en el a´rea de la medicina, con los algoritmos supervisados Naives Bayes para ayudar a clasificar pacientes propensos a sufrir enfermedades cardíacas. Como fuente de datos se usan 303 instancias de pacientes con diferentes características que fueron analizados al procesar los datos con los respectivos algoritmos. Los resultados con el algoritmo de Naives Bayes son pro- metedores, obteniendo una precisio´n del 86,81 %, usando la fuente de datos mencionada. Esta familia de algoritmos tiene un me…

Data sourceNaive Bayes classifierBayes' theoremArtificial neural networkComputer sciencebusiness.industryGeneral MedicineMedicine fieldArtificial intelligenceMachine learningcomputer.software_genrebusinesscomputerCiencia y Tecnología
researchProduct

Integrating LSTMs with Online Density Estimation for the Probabilistic Forecast of Energy Consumption

2019

In machine learning applications in the energy sector, it is often necessary to have both highly accurate predictions and information about the probabilities of certain scenarios to occur. We address this challenge by integrating and combining long short-term memory networks (LSTMs) and online density estimation into a real-time data streaming architecture of an energy trader. The online density estimation is done in the MiDEO framework, which estimates joint densities of data streams based on ensembles of chains of Hoeffding trees. One attractive feature of the solution is that queries can be sent to the here-called forecast-based point density estimators (FPDE) to derive information from …

Data streamComputer scienceData stream mining020209 energyProbabilistic logicEstimator02 engineering and technologyEnergy consumptionDensity estimationcomputer.software_genre0202 electrical engineering electronic engineering information engineeringFeature (machine learning)020201 artificial intelligence & image processingData miningRepresentation (mathematics)computer
researchProduct

Prototype-based learning on concept-drifting data streams

2014

Data stream mining has gained growing attentions due to its wide emerging applications such as target marketing, email filtering and network intrusion detection. In this paper, we propose a prototype-based classification model for evolving data streams, called SyncStream, which dynamically models time-changing concepts and makes predictions in a local fashion. Instead of learning a single model on a sliding window or ensemble learning, SyncStream captures evolving concepts by dynamically maintaining a set of prototypes in a new data structure called the P-tree. The prototypes are obtained by error-driven representativeness learning and synchronization-inspired constrained clustering. To ide…

Data streamConcept driftbusiness.industryComputer scienceData stream miningConstrained clusteringcomputer.software_genreData structureMachine learningEnsemble learningSynchronization (computer science)Data miningArtificial intelligencebusinesscomputerProceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining
researchProduct

Optical remote sensing and the retrieval of terrestrial vegetation bio-geophysical properties – A review

2015

Abstract: Forthcoming superspectral satellite missions dedicated to land monitoring, as well as planned imaging spectrometers, will unleash an unprecedented data stream. The processing requirements for such large data streams involve processing techniques enabling the spatio-temporally explicit quantification of vegetation properties. Typically retrieval must be accurate, robust and fast. Hence, there is a strict requirement to identify next-generation bio-geophysical variable retrieval algorithms which can be molded into an operational processing chain. This paper offers a review of state-of-the-art retrieval methods for quantitative terrestrial bio-geophysical variable extraction using op…

Data streamEconomicsComputer scienceOperational variable retrievalcomputer.software_genreLaboratory of Geo-information Science and Remote SensingMachine learningPhysicalLaboratorium voor Geo-informatiekunde en Remote SensingBio-geophysical variablesComputers in Earth SciencesParametricEngineering (miscellaneous)Parametric statisticsRemote sensingData stream miningPhysicsTransparency (human–computer interaction)VegetationPE&RCNon-parametricHybridAtomic and Molecular Physics and OpticsComputer Science ApplicationsVariable (computer science)SatelliteData miningEngineering sciences. TechnologyRetrievabilitycomputerISPRS Journal of Photogrammetry and Remote Sensing
researchProduct