{ "types" : { "Bookmark" : { "pluralLabel" : "Bookmarks" }, "Publication" : { "pluralLabel" : "Publications" }, "GoldStandardPublication" : { "pluralLabel" : "GoldStandardPublications" }, "GoldStandardBookmark" : { "pluralLabel" : "GoldStandardBookmarks" }, "Tag" : { "pluralLabel" : "Tags" }, "User" : { "pluralLabel" : "Users" }, "Group" : { "pluralLabel" : "Groups" }, "Sphere" : { "pluralLabel" : "Spheres" } }, "properties" : { "count" : { "valueType" : "number" }, "date" : { "valueType" : "date" }, "changeDate" : { "valueType" : "date" }, "url" : { "valueType" : "url" }, "id" : { "valueType" : "url" }, "tags" : { "valueType" : "item" }, "user" : { "valueType" : "item" } }, "items" : [ { "type" : "Bookmark", "id" : "https://puma.ub.uni-stuttgart.de/url/42f8f08e86748ab00c12037a9b83d1a2/diglezakis", "tags" : [ "bigdata","forschungsdaten","multidimensional","array","dataverses","data","infrastructure" ], "intraHash" : "42f8f08e86748ab00c12037a9b83d1a2", "label" : "Big Earth Datacube Standards: Coverages, WCS, WCPS on rasdaman", "user" : "diglezakis", "description" : "Big Earth Datacube Standards: Coverages, WCS, WCPS on rasdaman", "date" : "2021-09-27 14:30:49", "changeDate" : "2021-09-27 12:30:49", "count" : 1, "url" : "https://standards.rasdaman.com/" } , { "type" : "Bookmark", "id" : "https://puma.ub.uni-stuttgart.de/url/02b8ee917bacbba881c9fd691278643a/diglezakis", "tags" : [ "bigdata","forschungsdaten","visualization","wiki","tools" ], "intraHash" : "02b8ee917bacbba881c9fd691278643a", "label" : "Community Wiki Home - Pentaho Community - Pentaho Wiki", "user" : "diglezakis", "description" : "", "date" : "2018-07-30 08:44:11", "changeDate" : "2018-07-30 06:44:11", "count" : 1, "url" : "https://wiki.pentaho.com/" } , { "type" : "Bookmark", "id" : "https://puma.ub.uni-stuttgart.de/url/750641cf82027b8a3d0e59721f70a75e/diglezakis", "tags" : [ "bigdata","forschungsdaten","visualization","tools" ], "intraHash" : "750641cf82027b8a3d0e59721f70a75e", "label" : "Hitachi Vantara | Pentaho download | SourceForge.net", "user" : "diglezakis", "description" : "Download Hitachi Vantara | Pentaho for free. Easy-to-Use business intelligence (BI) for all. Pentaho tightly couples data integration with business analytics in a modern platform that brings together IT and business users to easily access, visualize and explore all data that impacts business results. Use it as a full suite or as individual components that are accessible on-premise in the cloud or on-the-go (mobile).", "date" : "2018-07-30 08:42:51", "changeDate" : "2018-07-30 06:42:51", "count" : 1, "url" : "https://sourceforge.net/projects/pentaho/" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/23bfc5faff91370571e13df24f7ac713a/diglezakis", "tags" : [ "bigdata","forschungsdaten","metadata" ], "intraHash" : "3bfc5faff91370571e13df24f7ac713a", "interHash" : "3e3f23e73b92925210028a38badf2643", "label" : "Device-Driven Metadata Management Solutions for Scientific Big Data Use Cases", "user" : "diglezakis", "description" : "Device-Driven Metadata Management Solutions for Scientific Big Data Use Cases - IEEE Xplore Document", "date" : "2017-08-21 13:26:42", "changeDate" : "2017-08-21 11:26:42", "count" : 2, "pub-type": "inproceedings", "booktitle": "22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing", "year": "2014", "url": "", "author": [ "Richard Grunzke","Jürgen Hesser","Jürgen Starek","Nick Kepper","Sandra Gesing","Marcus Hardt","Volker Hartmann","Stephan Kindermann","Jan Potthoff","Michael Hausmann","Ralph Müller-Pfefferkorn","René Jäkel" ], "authors": [ {"first" : "Richard", "last" : "Grunzke"}, {"first" : "Jürgen", "last" : "Hesser"}, {"first" : "Jürgen", "last" : "Starek"}, {"first" : "Nick", "last" : "Kepper"}, {"first" : "Sandra", "last" : "Gesing"}, {"first" : "Marcus", "last" : "Hardt"}, {"first" : "Volker", "last" : "Hartmann"}, {"first" : "Stephan", "last" : "Kindermann"}, {"first" : "Jan", "last" : "Potthoff"}, {"first" : "Michael", "last" : "Hausmann"}, {"first" : "Ralph", "last" : "Müller-Pfefferkorn"}, {"first" : "René", "last" : "Jäkel"} ], "pages": "317-321","abstract": "Big Data applications in science are producing\r\nhuge amounts of data, which require advanced processing, handling,\r\nand analysis capabilities. For the organization of large\r\nscale data sets it is essential to annotate these with metadata,\r\nindex them, and make them easily findable. In this paper we\r\ninvestigate two scientific use cases from biology and photon\r\nscience, which entail complex situations in regard to data\r\nvolume, data rates and analysis requirements. The LSDMA\r\nproject provides an ideal context for this research, combining\r\nboth innovative R&D on the processing, handling, and analysis\r\nlevel and a wide range of research communities in need of\r\nscalable solutions. To facilitate the advancement of data life\r\ncycles we present preferred metadata management strategies.\r\nIn biology the Open Microscopy Environment (OME) and in\r\nphoton science NeXus/ICAT are presented. We show that these\r\nare well suited for the respective data life cycles. To facilitate\r\nsearching across communities we discuss solutions involving\r\nthe Open Archive Initiative - Protocol for Metadata Harvesting\r\n(OAI-PMH) and Apache Lucene/Solr.", "eventtitle" : "22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing", "bibtexKey": "noauthororeditor" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/23f6c27b8af75462b9f1026355ced1233/diglezakis", "tags" : [ "bigdata","forschungsdaten" ], "intraHash" : "3f6c27b8af75462b9f1026355ced1233", "interHash" : "dfd1f6c045d444e9475b2d3e27008fcb", "label" : "Optimization of data life cycles", "user" : "diglezakis", "description" : "Optimization of data life cycles - IOPscience", "date" : "2017-08-21 13:03:30", "changeDate" : "2017-08-21 11:03:30", "count" : 1, "pub-type": "article", "journal": "Journal of Physics: Conference Series", "year": "2014", "url": "http://stacks.iop.org/1742-6596/513/i=3/a=032047", "author": [ "C Jung","M Gasthuber","A Giesler","M Hardt","J Meyer","F Rigoll","K Schwarz","R Stotzka","A Streit" ], "authors": [ {"first" : "C", "last" : "Jung"}, {"first" : "M", "last" : "Gasthuber"}, {"first" : "A", "last" : "Giesler"}, {"first" : "M", "last" : "Hardt"}, {"first" : "J", "last" : "Meyer"}, {"first" : "F", "last" : "Rigoll"}, {"first" : "K", "last" : "Schwarz"}, {"first" : "R", "last" : "Stotzka"}, {"first" : "A", "last" : "Streit"} ], "volume": "513","number": "3","pages": "032047","abstract": "Data play a central role in most fields of science. In recent years, the amount of data from experiment, observation, and simulation has increased rapidly and data complexity has grown. Also, communities and shared storage have become geographically more distributed. Therefore, methods and techniques applied to scientific data need to be revised and partially be replaced, while keeping the community-specific needs in focus. The German Helmholtz Association project \"Large Scale Data Management and Analysis\" (LSDMA) aims to maximize the efficiency of data life cycles in different research areas, ranging from high energy physics to systems biology. In its five Data Life Cycle Labs (DLCLs), data experts closely collaborate with the communities in joint research and development to optimize the respective data life cycle. In addition, the Data Services Integration Team (DSIT) provides data analysis tools and services which are common to several DLCLs. This paper describes the various activities within LSDMA and focuses on the work performed in the DLCLs.", "bibtexKey": "1742-6596-513-3-032047" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/28e03b4aeb58ea1b36ed9a9a6c72d54d1/diglezakis", "tags" : [ "bigdata","forschungsdaten","obib","engineering","iag" ], "intraHash" : "8e03b4aeb58ea1b36ed9a9a6c72d54d1", "interHash" : "bfc959092e0f6966f300d2ac25215c25", "label" : "Turbulence in the Era of Big Data: Recent Experiences with Sharing Large Datasets", "user" : "diglezakis", "description" : "", "date" : "2017-07-18 09:41:03", "changeDate" : "2018-02-16 08:37:20", "count" : 1, "pub-type": "inbook", "booktitle": "Whither turbulence and big data in the 21st century?","publisher":"Springer","address":"Switzerland", "year": "2017", "url": "", "author": [ "Charles Meneveau","Ivan Marusic" ], "authors": [ {"first" : "Charles", "last" : "Meneveau"}, {"first" : "Ivan", "last" : "Marusic"} ], "editor": [ "Andrew Pollard","Luciano Castillo","Luminita Danaila","Mark Glauser" ], "editors": [ {"first" : "Andrew", "last" : "Pollard"}, {"first" : "Luciano", "last" : "Castillo"}, {"first" : "Luminita", "last" : "Danaila"}, {"first" : "Mark", "last" : "Glauser"} ], "pages": "497-507","abstract": "In the context of the contemporary push for \u201Cbig data\u201D in many fields, we review recent experiences building large databases for turbulence research. We consider data from direct numerical simulations (DNS) of various canonical flows and from experimental studies and related numerical simulations of wall-bounded turbulence, where the data storage needs are particularly challenging due to the very large range of length and time scales that exists in these flows at high Reynolds numbers. The focus is on a move from the traditional approach of data-handling and analysis where datasets are moved to individual computers, to one where much of the analysis is moved to the hosting system that stores these data. In this context we give a summary of a unique open numerical laboratory that archives over 200\u2009Terabytes of DNS data, including full spatio-temporal flow fields of various canonical flows. Particular attention is given to the unique access requirements for large datasets to become open to the research community and the success the system has had in democratizing access to large datasets.", "isbn" : "978-3-319-41217-7", "doi" : "http://dx.doi.org/10.1007/978-3-319-41217-7", "bibtexKey": "meneveau2017turbulence" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/299e8a3d8e32d794bbb8872e3e32bf103/diglezakis", "tags" : [ "bigdata","forschungsdaten","reuse","dissemination","simulation","obib","engineering","iag" ], "intraHash" : "99e8a3d8e32d794bbb8872e3e32bf103", "interHash" : "dc6a0df4ec49e56c562c7b9c86c63cc7", "label" : "Public Dissemination of Raw Turbulence Data", "user" : "diglezakis", "description" : "PUMA", "date" : "2017-07-18 09:33:00", "changeDate" : "2018-02-16 08:39:42", "count" : 1, "pub-type": "inbook", "booktitle": "Whither turbulence and big data in the 21st century?","publisher":"Springer","address":"Switzerland", "year": "2017", "url": "", "author": [ "Juan A. Sillero","Javier Jiminéz" ], "authors": [ {"first" : "Juan A.", "last" : "Sillero"}, {"first" : "Javier", "last" : "Jiminéz"} ], "editor": [ "Andrew Pollard","Luciano Castillo","Luminita Danaila","Mark Glauser" ], "editors": [ {"first" : "Andrew", "last" : "Pollard"}, {"first" : "Luciano", "last" : "Castillo"}, {"first" : "Luminita", "last" : "Danaila"}, {"first" : "Mark", "last" : "Glauser"} ], "pages": "509-515","abstract": "It is argued that there is a certain urgency to the discussion of whether raw data should be made publicly available within the turbulence community, and about the best ways, technology and rules for possible dissemination. Besides expressing the personal opinion that such sharing would be advantageous for the field, the urgency mostly arises from the danger that funding agencies or other institutions would otherwise set standards without proper community input. This paper is in part a plea for community action in that direction. As an example, the experience of the Madrid school of Aeronautics with the dissemination of numerical simulation results is briefly reviewed, including the present technological solutions and usage statistics.", "isbn" : "978-3-319-41215-3", "doi" : "10.1007/978-3-3 19-41217-7_28", "bibtexKey": "noauthororeditor" } ] }