{"@type": "dcat:Dataset", "accessLevel": "public", "accrualPeriodicity": "irregular", "bureauCode": ["026:00"], "contactPoint": {"@type": "vcard:Contact", "fn": "Elizabeth Foughty", "hasEmail": "mailto:elizabeth.a.foughty@nasa.gov"}, "description": "SPATIALLY ADAPTIVE SEMI-SUPERVISED LEARNING WITH GAUSSIAN\r\nPROCESSES FOR HYPERSPECTRAL DATA ANALYSIS\r\nGOO JUN * AND JOYDEEP GHOSH*\r\n\r\n\r\nAbstract. A semi-supervised learning algorithm for the classification of hyperspectral data,\r\nGaussian process expectation maximization (GP-EM), is proposed. Model parameters for each\r\nland cover class is first estimated by a supervised algorithm using Gaussian process regressions\r\nto find spatially adaptive parameters, and the estimated parameters are then used to initialize a\r\nspatially adaptive mixture-of-Gaussians model. The mixture model is updated by expectationmaximization\r\niterations using the unlabeled data, and the spatially adaptive parameters for unlabeled\r\ninstances are obtained by Gaussian process regressions with soft assignments. Two sets\r\nof hyperspectral data taken from the Botswana area by the NASA EO-1 satellite are used for experiments.\r\nEmpirical evaluations show that the proposed framework performs significantly better\r\nthan baseline algorithms that do not use spatial information, and the results are also better than\r\nany previously reported results by other algorithms on the same data.", "distribution": [{"@type": "dcat:Distribution", "description": "SPATIALLY ADAPTIVE SEMI-SUPERVISED LEARNING WITH GAUSSIAN PROCESSES FOR HYPERSPECTRAL DATA ANALYSIS", "downloadURL": "https://c3.nasa.gov/dashlink/static/media/publication/Paper_3_.pdf", "format": "PDF", "mediaType": "application/pdf", "title": "Paper 3 .pdf"}, {"@type": "dcat:Distribution", "description": "Presentation", "downloadURL": "https://c3.nasa.gov/dashlink/static/media/publication/Paper3_presentation.pdf", "format": "PDF", "mediaType": "application/pdf", "title": "Paper3_presentation.pdf"}], "identifier": "DASHLINK_225", "issued": "2010-10-13", "keyword": ["ames", "dashlink", "nasa"], "landingPage": "https://c3.nasa.gov/dashlink/resources/225/", "modified": "2025-03-31", "programCode": ["026:029"], "publisher": {"@type": "org:Organization", "name": "Dashlink"}, "title": "SPATIALLY ADAPTIVE SEMI-SUPERVISED LEARNING WITH GAUSSIAN PROCESSES FOR HYPERSPECTRAL DATA ANALYSIS"}