Sökning: "artificial neural networks"

Visar resultat 16 - 20 av 106 avhandlingar innehållade orden artificial neural networks.

  1. 16. Utilizing Diversity and Performance Measures for Ensemble Creation

    Detta är en avhandling från Örebro universitet

    Författare :Tuve Löfström; Högskolan i Skövde.; Högskolan i Skövde.; Högskolan i Borås.; [2009]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; TECHNOLOGY Information technology Computer science; TEKNIKVETENSKAP Informationsteknik Datavetenskap; Teknik; Technology; Ensemble Learning; Machine Learning; Diversity; Artificial Neural Networks; Data Mining; Information Fusion; ensemble learning; machine learning; diversity; artificial neural networks; information fusion; Computer Science; data mining;

    Sammanfattning : An ensemble is a composite model, aggregating multiple base models into one predictive model. An ensemble prediction, consequently, is a function of all included base models. Both theory and a wealth of empirical studies have established that ensembles are generally more accurate than single predictive models. LÄS MER

  2. 17. Neural Networks Applications and Electronics Development for Nuclear Fusion Neutron Diagnostics

    Detta är en avhandling från Uppsala : Acta Universitatis Upsaliensis

    Författare :Emanuele Ronchi; Uppsala universitet.; [2009]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Neural networks; tomography; unfolding; real time; pulse shape discrimination; PSD; neutron spectroscopy; MPRu; TOFOR; KN3; neutron camera; LED; summing amplifiers; electronics; JET; NATURAL SCIENCES Physics Geocosmophysics and plasma physics Plasma physics; NATURVETENSKAP Fysik Geokosmofysik och plasmafysik Plasmafysik; NATURAL SCIENCES Physics Other physics Computational physics; NATURVETENSKAP Fysik Övrig fysik Beräkningsfysik; Applied Nuclear Physics; Tillämpad kärnfysik; Elektronik; Electronics;

    Sammanfattning : This thesis describes the development of electronic modules for fusion neutron spectroscopy as well as several implementations of artificial neural networks (NN) for neutron diagnostics for the Joint European Torus (JET) experimental reactor in England.The electronics projects include the development of two fast light pulser modules based on Light Emitting Diodes (LEDs) for the calibration and stability monitoring of two neutron spectrometers (MPRu and TOFOR) at JET. LÄS MER

  3. 18. Space Weather Physics, Prediction and classification of solar wind structures and geomagnetic activity using artificial neural networks

    Detta är en avhandling från Lund Observatory, Lund University

    Författare :Peter Wintoft; Lunds universitet.; Lund University.; [1997]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Astronomi; cosmic chemistry; space research; Astronomy; solar magnetic fields; space weather; solar wind; magnesphere; artificial neural networks; geomagnetic activity; rymdvetenskap; kosmisk kemi; Fysicumarkivet A:1997:Wintoft;

    Sammanfattning : This thesis concerns the application of artificial neural network techniques to space weather physics. The networks applied include multi-layer error-backpropagation, radial basis function, and self-organized maps. LÄS MER

  4. 19. Neural Network Approaches To Survival Analysis

    Detta är en avhandling från Department of Astronomy and Theoretical Physics, Lund University

    Författare :Jonas Kalderstam; Lunds universitet.; Lund University.; [2015]
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Survival Analysis; Artificial Neural Networks; Machine Learning; Genetic Algorithms; Evolutionary Algorithms; Fysicumarkivet:2015:Kalderstam;

    Sammanfattning : Popular Abstract in Swedish Denna avhandling behandlar artificiella neuron nätverk och deras applikation inom medicin. Den utgår ifrån att det är viktigt att kunna uppskatta en patients överlevnadschanser för att kunna erbjuda rätt behandling för olika former av cancer. LÄS MER

  5. 20. Morphometric and Landscape Feature Analysis with Artificial Neural Networks and SRTM data Applications in Humid and Arid Environments

    Detta är en avhandling från Stockholm : KTH

    Författare :Amir Houshang Ehsani; KTH.; [2008]
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Self Organizing Map; Neural Network; Morphometric Feature; Landscape; Yardang; Lut Desert; Potential natural vegetation; geoecosystem; Landform; Landsat ETM ; Morphometric Parameters; SRTM; Resolution; Curvatures; DEM.; TECHNOLOGY; TEKNIKVETENSKAP;

    Sammanfattning : This thesis presents a semi-automatic method to analyze morphometric features and landscape elements based on Self Organizing Map (SOM) as an unsupervised Artificial Neural Network algorithm in two completely different environments: 1) the Man and Biosphere Reserve “Eastern Carpathians” (Central Europe) as a complex mountainous humid area and 2) Lut Desert, Iran, a hyper arid region characterized by repetition of wind-eroded features.In 2003, the National Aeronautics and Space Administration (NASA) released the SRTM/ SIR-C band data with 3 arc seconds (approx. LÄS MER