ABSTRACT:The presented Softmax Regression classifier is a generalization of logistic regression. It is used for multi-class classification, where classes are mutually exclusive. Implemented in a classification framework, it provides a flexible approach to customize a classification process. Traditional classification is focused with classifiers that can only be applied on the same dataset. The Softmax Regression classifier can be created and trained on a reference dataset using spectral and spatial information and then applied to similar data multiple times. We present the general workflow of Softmax Regression classification as part of a case study that is based on attribute images derived from hyperspectral airborne and elevation imagery.
ABSTRACT:Suomi National Polar-orbiting Partnership (NPP) is the first of a new generation of NASA's Earth-observing research satellites. The Suomi NPP Visible Infrared Imaging Radiometer Suite (VIIRS) collects visible and infrared views of Earth's dynamic surface processes. This NPP mission produces a series of Environmental Data Records (EDRs). As accurate information on cloud occurrence is of utmost importance for a wide range of remote-sensing applications and analyses, we developed a cloud mask algorithm, adapted from the Landsat 7 Automatic Cloud Cover Assessment, for use with the VIIRS Imagery EDRs. The algorithm consists of a sequence of pixel-based tests that use thresholds on VIIRS top-of-atmosphere reflectances and brightness temperatures. Our cloud mask algorithm provides a simpler, though less informative and robust, alternative to the VIIRS Cloud Mask (VCM) Intermediate Product, with the advantage in that it can be applied to a higher spatial resolution VIIRS Imagery EDR. The algorithm is compared with the VCM in three case studies.
The German National Specialist Libraries cooperate closely in the field of digital preservation. One of the partners hosts the preservation system, while each library creates its own workflows and is free to ingest its digital material into this system. This paper delineates the factors for success of this collaboration. It describes the different aspects of collaboration in digital preservation and describes the benefits and costs of cooperation in this field as a case study.Digital preservation is resource intensive and the required technology is complex. Therefore the libraries benefit from synergy effects: Reduced cost by sharing the preservation system, usage of similar workflows and formats of digital objects, work sharing in networking activities and staff training.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.