@conference {1621, title = {Accelerating Digitization of Biodiversity Research Specimens through Online Public Participation}, booktitle = {Botany 2014}, year = {2014}, keywords = {EF-1115210}, url = {http://www.2014.botanyconference.org/engine/search/index.php?func=detail\&aid=692}, author = {Elizabeth R. Ellwood and Betty Dunckel and Paul Flemons and Robert Guralnick and Nelson, Gil and Greg Newman and Paul, Deborah L. and Greg Riccardi and Nelson E. Rios and Katja Seltmann and Austin R. Mast} } @conference {2417, title = {Accelerating Digitization of Biodiversity Research Specimens Through Online Public Participation}, booktitle = {SPNHC 2015}, year = {2015}, keywords = {EF-1115210, Presentation, SPNHC2015}, author = {Ellwood, Elizabeth R. and Dunckel, Betty A. and Flemons, Paul and Guralnick, Robert P. and Nelson, Gil and Paul, Deborah L. and Riccardi, Greg and Rios, Nelson and Seltmann, Katja C. and Mast, Austin R.} } @article {2418, title = {Accelerating Digitization of Biodiversity Specimens through Online Public Participation}, year = {2015}, abstract = {Biodiversity research specimens provide a historical baseline of diversity and distributions against which to compare new samples and project changes to diversity and distribution into the future. However, just ca. 10 percent of the estimated 1 billion specimens in U.S. collections have been digitized (e.g., databased, imaged, and/or georeferenced) with the data made available online. A goal of the biodiversity research community is to digitize most of the remaining specimens within a decade. However, meeting this ambitious goal requires increased collaboration, technological innovation, and broader engagement in digitization beyond the walls of biodiversity research collections. Engaging the public in digitization, rather than simply hiring more digitizers, promises to both serve the digitizing institutions and further public understanding of biodiversity science. We identify 24 digitization tasks that the public could participate in online and examples from three broad areas that will accelerate research progress: label and ledger transcribing/cataloging from digital images, georeferencing from collection locality descriptions, and specimen tagging/categorizing from images. We illustrate each activity, identify and compare useful tools, present relevant best practices and standards, and identify gaps in our knowledge and areas for improvement. We will also highlight the citizen science projects of iDigBio, NSF{\textquoteright}s National Resource for Advancing the Digitization of Biodiversity Collections. This includes Biospex (www.biospex.org), a system that provides project management functionality for public participation tools like Notes from Nature (www.notesfromnature.org).The field of public participation in digitization of biodiversity research specimens is clearly in a growth phase with many emerging opportunities for scientists, educators, and the public. The field will benefit from broader communication with complementary or overlapping projects in other fields, such as the digital humanities.}, keywords = {AAAS2015, EF-1115210, poster}, url = {https://aaas.confex.com/aaas/2015/webprogram/Paper15507.html}, author = {Ellwood, Elizabeth R. and Guralnick, Robert and Riccardi, Greg and Rios, Nelson and Seltmann, Katja and Mast, Austin} } @article {1622, title = {Aiming Up: Natural History Collections as Emerging Resources for Innovative Undergraduate Education in Biology}, journal = {BioScience}, volume = {64}, year = {2014}, month = {08/2014}, chapter = {725}, abstract = {There is an emerging consensus that undergraduate biology education in the United States is at a crucial juncture, especially as we acknowledge the need to train a new generation of scientists to meet looming environmental and health crises. Digital resources for biology now available online provide an opportunity to transform biology curricula to include more authentic and inquiry-driven educational experiences. Digitized natural history collections have become tremendous assets for research in environmental and health sciences, but, to date, these data remain largely untapped by educators. Natural history collections have the potential to help transform undergraduate science education from passive learning into an active exploration of the natural world, including the exploration of the complex relationships among environmental conditions, biodiversity, and human well-being. By incorporating natural history specimens and their associated data into undergraduate curricula, educators can promote participatory learning and foster an understanding of essential interactions between organisms and their environments.}, keywords = {EF-1115210}, url = {http://www.academia.edu/7991735/Natural_History_Collections_as_Emerging_Resources_for_Innovative_Education}, author = {Joseph A. Cook and Scott Edwards and Eileen A. Lacey and Robert P. Guralnick and Soltis, Pamela S. and Douglas E. Soltis and Corey K. Welch and Kayce C. Bell and Kurt E. Galbreath and Christopher Himes and Julie M. Allen and Tracy A. Heath and Ann C. Carnaval and Kimberly L. Cooper and Mark Liu and James Hanken and Stefanie Ickert-Bond} } @article {2196, title = {AIM-UP!: Bringing big data to educators at small institutions}, year = {2015}, keywords = {Small Collections Symposium SPNHC 2015, SPNHC 2015}, url = {https://www.idigbio.org/wiki/images/a/a3/Galbreath_spnhc.pdf}, author = {Joe Cook and Kurt Galbreath} } @article {2129, title = {Arctos as a database management system for vertebrate specimens and images }, year = {2015}, keywords = {Strategies for Vertebrate Digitization}, url = {https://www.idigbio.org/wiki/images/a/ac/Gunderson-arctos_iDigBio_2015_AMG.pdf}, author = {Aren M. Gunderson and Link Olson} } @article {1041, title = {Avocational paleontologists and volunteers:critical partners}, year = {2014}, keywords = {NAPC Symposium}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/napc-2014/Mon-9-45.Molineux.pdf}, author = {Ann Molineux and Linda McCall and Faye Geigerman} } @inbook {701, title = {Biodiversity in a Rapidly Changing World: How to Manage and Use Information?}, year = {2011}, keywords = {Mobilization}, url = {http://www.intechopen.com/source/pdfs/24422/InTech-Biodiversity_in_a_rapidly_changing_world_how_to_manage_and_use_information_.pdf}, author = {Tereza C. Giannini and Tiago M. Francoy and Antonio M. Saraiva and Vera L. Imperatriz-Fonseca} } @conference {2503, title = {Bringing Biodiversity into the Classroom: Digital Educational Resources from Natural History Collections}, booktitle = {2016 Annual League of Environmental Educators in Florida Confeence}, year = {2016}, month = {03/2016}, keywords = {Education and Outreach}, author = {Goodwin, Jillian and Phillips, Molly} } @article {2218, title = {Building a Networked National Community for Collections}, year = {2015}, abstract = {In recent years, the scientific community has developed a national strategy for a Network Integrated Biocollections Alliance (NIBA) to establish a framework for leveraging the wealth of resources represented by the nation{\textquoteright}s biocollections through digitization of specimens and associated metadata, creating a massive, distributed tool for addressing grand challenges across a wide range of scientific endeavor. Significant progress has been made toward the implementation of NIBA, but much more work remains. In 2014, the National Science Foundation funded a Research Coordination Network (RCN) grant to support efforts to foster the continued engagement with and development of a sustainable, networked community of practice. The NIBA RCN is working with the community to evaluate current and future needs. This talk will summarize work and findings thus far, as well as solicit input on future activities.}, keywords = {Plenary Session SPNHC 2015, SPNHC 2015}, url = {https://vimeo.com/album/3424966/video/129829472}, author = {Robert Gropp} } @article {989, title = {Career Tracks in Biology}, year = {2013}, keywords = {Broadening Diversity: Careers and Graduate Study in the Biological Sciences}, url = {http://vimeo.com/album/2712973/video/85762300}, author = {Charlotte Germaine-Aubrey} } @article {979, title = {Careers in Biology}, year = {2013}, keywords = {Broadening Diversity: Careers and Graduate Study in the Biological Sciences}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/broadening-diversity/OrlandoPres-germain.pdf}, author = {Charlotte Germaine-Aubrey} } @booklet {1184, title = {Code and Data for the Social Sciences: A Practitioner{\textquoteright}s Guide}, year = {2014}, abstract = {What does it mean to do empirical social science? Asking good questions. Digging up novel data. Designing statistical analysis. Writing up results. For many of us, most of the time, what it means is writing and debugging code. We write code to clean data, to transform data, to scrape data, and to merge data. We write code to execute statistical analyses, to simulate models, to format results, to produce plots. We stare at, puzzle over, fight with, and curse at code that isn{\textquoteright}t working the way we expect it to. We dig through old code trying to figure out what we were thinking when we wrote it, or why we{\textquoteright}re getting a different result from the one we got the week before. Even researchers lucky enough to have graduate students or research assistants who write code for them still spend a significant amount of time reviewing code, instructing on coding style, or fixing broken code. Though we all write code for a living, few of the economists, political scientists, psychologists, sociologists, or other empirical researchers we know have any formal training in computer science. Most of them picked up the basics of programming without much effort, and have never given it much thought since. Saying they should spend more time thinking about the way they write code would be like telling a novelist that she should spend more time thinking about how best to use Microsoft Word. Sure, there are people who take whole courses in how to change fonts or do mail merge, but anyone moderately clever just opens the thing up and figures out how it works along the way. This manual began with a growing sense that our own version of this self-taught seat-of-the-pants approach to computing was hitting its limits. Copyright (c) 2014, Matthew Gentzkow and Jesse M. Shapiro. E-mail: matthew.gentzkow@chicagobooth.edu, jesse.shapiro@chicagobooth.edu. Please cite this document as: Gentzkow, Matthew and Jesse M. Shapiro. 2014. Code and Data for the Social Sciences: A Practitioner{\textquoteright}s Guide. University of Chicago mimeo, http://faculty.chicagobooth.edu/matthew.gentzkow/research/CodeAndData.pdf, last updated January 2014.}, keywords = {code, Data analysis, Data Mining, Data reuse, Data Standards, research methods}, url = {http://faculty.chicagobooth.edu/matthew.gentzkow/research/CodeAndData.pdf}, author = {Matthew Gentzkow and Jesse M. Shapiro} } @conference {1414, title = {A Computational- and Storage-Cloud for Integration of Biodiversity Collections}, booktitle = {Proceedings of the 2013 IEEE 9th International Conference on e-Science}, year = {2013}, publisher = {IEEE}, organization = {IEEE}, address = {Beijing, China}, abstract = {A core mission of the Integrated Digitized Biocollections (iDigBio) project is the building and deployment of a cloud computing environment customized to support the digitization workflow and integration of data from all U.S. nonfederal biocollections. iDigBio chose to use cloud computing technologies to deliver a cyberinfrastructure that is flexible, agile, resilient, and scalable to meet the needs of the biodiversity community. In this context, this paper describes the integration of open source cloud middleware, applications, and third party services using standard formats, protocols, and services. In addition, this paper demonstrates the value of the digitized information from collections in a broader scenario involving multiple disciplines.}, keywords = {appliances, biocollections infrastructure, biodiversity, cloud computing, data access, data store, digitization, EF-1115210}, doi = {10.1109/eScience.2013.48}, url = {http://dx.doi.org/10.1109/eScience.2013.48}, author = {Matsunaga, Andr{\'e}a and Thompson, Alex and Figueiredo, Renato J. and Germain-Aubrey, Charlotte C. and Collins, Matthew and Beaman, Reed S. and MacFadden, Bruce J. and Riccardi, Greg and Soltis, Pamela S. and Page, Lawrence M. and Fortes, Jos{\'e} A.B.} } @article {290, title = {Cyberinfrastructure and the NSF Dimensions of Biodiversity Program Solicitation - Planning for Success}, year = {2010}, month = {10/2010}, abstract = {The NSF {\textquoteleft}Dimensions of Biodiversity{\textquoteright} program recognizes that emerging technologies in compu- ting and cyberinfrastructure are revolutionizing our ability to investigate the broad scale patterns and processes underlying biodiversity. This report documents the outcomes of an NSF sponsored workshop (DBI-1047800) held at Madison, WI during October 13-15, 2010 that was charged with identifying aspects of cyberinfrastructure necessary for supporting successful research in the Di- mensions of Biodiversity program. Workshop participants represented a broad spectrum of discip- lines, ranging from cyberinfrastructure, informatics, and computer science to biodiversity, biology, and environmental science, and provided excellent insights into the major cyberinfrastructure needs of biodiversity science.}, keywords = {CI, Workshop Report}, url = {https://www.idigbio.org/sites/default/files/sites/default/files/CIDimensionsReportAndNSF_v1.pdf}, author = {Corinna Gries and Allen Rodrigo and Matthew B. Jones and David Vieglais} } @article {235, title = {Darwin Core: An Evolving Community-Developed Biodiversity Data Standard}, journal = {PLoS One}, volume = {7}, year = {2012}, month = {01/2012}, chapter = {e29715}, abstract = {Biodiversity data derive from myriad sources stored in various formats on many distinct hardware and software platforms. An essential step towards understanding global patterns of biodiversity is to provide a standardized view of these heterogeneous data sources to improve interoperability. Fundamental to this advance are definitions of common terms. This paper describes the evolution and development of Darwin Core, a data standard for publishing and integrating biodiversity information. We focus on the categories of terms that define the standard, differences between simple and relational Darwin Core, how the standard has been implemented, and the community processes that are essential for maintenance and growth of the standard. We present case-study extensions of the Darwin Core into new research communities, including metagenomics and genetic resources. We close by showing how Darwin Core records are integrated to create new knowledge products documenting species distributions and changes due to environmental perturbations.}, keywords = {Darwin Core, Data Standards, metagenomics}, doi = {10.1371/journal.pone.0029715}, url = {http://www.plosone.org/article/info\%3Adoi\%2F10.1371\%2Fjournal.pone.0029715}, author = {John Wieczorek}, editor = {David Bloom and Robert Guralnick and Stan Blum and Markus D{\"o}ring and Renato Giovanni and Tim Robertson and David Vieglais} } @article {1100, title = {Darwin Core Terms: A quick reference guide}, year = {2009}, month = {2013-10-22}, abstract = {This document is a quick reference for all recommended Darwin Core terms. For complete historical term information, including version changes and pre-standard terms, see [HISTORY]. For a comparative table of elements from pre-standard versions of Darwin Core to the current terms in the standard, see [VERSIONS]. }, keywords = {iDigBio Georeferencing Workshop Group (GWG), iDigBio GWG TTT 2}, url = {http://rs.tdwg.org/dwc/terms/}, author = {Darwin Core Task Group and John Wieczorek and Markus D{\"o}ring and Renato Giovanni and Tim Robertson and Dave Vieglais} } @article {1574, title = {Data management tools and database options}, year = {2014}, keywords = {Small Herbarium Workshop Botany 2014}, url = {https://www.idigbio.org/wiki/images/7/7d/EGilbert_NANSH_Management.pdf}, author = {Edward Gilbert} } @proceedings {1579, title = {Digitization: Just do it! The importance of and challenges to getting started}, year = {2014}, keywords = {Small Herbarium Workshop Botany 2014}, url = {https://www.idigbio.org/wiki/images/4/44/Morris_Gillespie_iDigBio_Botany2014.pdf}, author = {Ashley Morris and Emily Gillespie} } @article {1876, title = {Digitization @ USNM: Where we are}, year = {2014}, keywords = {ECN 2014}, url = {https://www.idigbio.org/wiki/images/4/4f/Poole-ECN_talk_FINAL.pdf}, author = {Patricia Gentili-Poole and Jessica Bird} } @article {1016, title = {Digitizing North American Lichen and Bryophyte Specimens}, year = {2014}, keywords = {iDigBio Education and Outreach Workshop}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/eoworkshop/Nash-E\%26O\%20workshop\%20No\%20Amer\%20lichen\%20and\%20bryophyte\%20-\%202014.pdf}, author = {Corinna Gries} } @article {1763, title = {Digitizing North American lichen and bryophyte specimens}, year = {2014}, keywords = {Summit 2014}, url = {https://www.idigbio.org/wiki/images/3/3f/LBCC_lichen_and_bryophyte_-_2014.pdf}, author = {Corinna Gries and Edward Gilbert and Thomas H Nash III} } @article {1795, title = {Digitizing North American lichen and bryophyte specimens}, year = {2014}, keywords = {Summit 2014}, url = {http://vimeo.com/album/3113100/video/110900200}, author = {Corinna Gries and Edward Gilbert and Thomas H Nash III} } @article {926, title = {Digitizing Peabody Paleo: history, EMu, portals \& campus-wide digital infrastructures at Yale}, year = {2013}, keywords = {Paleo Digitization Workshop}, url = {https://www.idigbio.org/wiki/images/b/b3/Gall_Wednesday.pdf}, author = {Larry Gall} } @article {709, title = {Digitizing the Yale Collections {\textendash} it takes a Village}, year = {2010}, keywords = {Databasing, Imaging, LabelCapture, UseCase, WorkFlows}, url = {http://ecnweb.org/sites/default/files/gall-ecn-posted.pdf}, author = {L. Munstermann and L. Gall} } @article {1861, title = {Do all dung beetles prefer dung? Tips an tricks for successful collecting.}, year = {2014}, keywords = {ECN 2014}, url = {https://www.idigbio.org/wiki/images/5/51/Gunter_ECN_talk_2014.pdf}, author = {Nicole Gunter} } @article {1039, title = {Engagement with the Public and Avocational Paleontologist at the Calvert Marine Museum}, year = {2014}, keywords = {NAPC Symposium}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/napc-2014/Mon-9.15-Godfrey.pdf}, author = {Stephen J. Godfrey} } @conference {2437, title = {ePandda Project: increasing accessibility to digitized data from the paleontological and neontological communities}, booktitle = {2015 GSA Annual Meeting}, year = {2015}, month = {2015}, address = {Baltimore, Maryland}, abstract = {The ePANDDA project, Enhancing PAleontological and Neontological Data Discovery API, is focused on the development of software tools that will connect three established, well-supported, and critically important data sources: the Paleobiology Database (PBDB, paleontological, literature-based), iDigPaleo (paleontological, specimen-based) and iDigBio (neontological and paleontological, specimen-based). At present, the ability to access and integrate data from across the geological and biological sciences is a cumbersome and time-consuming process, as the connectivity between modern and fossil, and specimen and literature-based resources does not currently exist. ePANDDA will use application programming interfaces (APIs) to streamline and normalize data acquisition, including retrieval from disparate data sources. This is a major shift in the way the geoscience community has traditionally approached data acquisition and publishing (e.g., building a new portal). It will allow for more growth and flexibility in which existing data portals can be utilized and facilitate coordination with future data initiatives in other geoscience disciplines. Ultimately, for the researcher, the ePANDDA project will eliminate a significant barrier to data collection and processing, as users will be able to access and query multiple data sources at the same time from their preferred portal, resulting in a much richer, combined dataset. The development of APIs will provide researchers the opportunity to collaborate across disciplinary boundaries, to ask and answer new research questions affecting a diversity of fields (e.g., biogeographic/niche modeling, systematics, functional morphology, evolutionary biology, ecology, climatology, conservation biology, oceanography, and petroleum geology) and has the potential to change the nature and scope of the research questions that can be addressed by the scientific community. Geological Society of America Abstracts with Programs. Vol. 47, No. 7, p.613}, keywords = {239-11, EF-1115210, GSA2015, Presentation}, url = {https://gsa.confex.com/gsa/2015AM/webprogram/Paper270315.html}, author = {Smith, Dena M. and Butts, Susan H. and Gall, Lawrence and Karim, Talia S and Landman, Neil H. and Nelson, Gil and Norris, Christopher A and Sessa, Jocelyn A. and Uhen, Mark D.} } @article {1495, title = {Fish Bones }, year = {2014}, keywords = {Biological Collections Digitization in the Pacific}, url = {https://www.idigbio.org/wiki/images/c/c3/Garetano-FishBonesPresentation.pdf}, author = {Lydia M. Garetano} } @article {1057, title = {FOSSIL- A national network of amateur and professional paleontologists in the U.S.}, year = {2014}, keywords = {NAPC Symposium}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/napc-2014/Mon-4.00-MacFadden.pdf}, author = {Bruce MacFadden and Kent Crippen and Betty Dunckel and Shari Ellis and Austin Hendy and Katherine Hendy and Claudia Grant} } @article {1064, title = {FOSSIL- A national network of amateur and professional paleontologists in the U.S.}, year = {2014}, keywords = {NAPC Symposium}, url = {http://vimeo.com/album/2740344/video/87100158}, author = {Bruce MacFadden and Kent Crippen and Betty Dunckel and Shari Ellis and Austin Hendy and Katherine Hendy and Claudia Grant} } @article {1530, title = {From Biocollections to Global Change Biology: New Conceptual and Cyberinfrastructure Frameworks For Closing The Gap}, year = {2014}, keywords = {Collections for the 21st Century Symposium}, url = {https://www.idigbio.org/wiki/images/b/b1/Guralnick-FromCollectionsToGlobalChangeV1.pdf}, author = {Robert Guralnick} } @article {241, title = {The future of citizen science: emerging technologies and shifting paradigms}, journal = {Frontiers in Ecology and the Environment}, volume = {10}, year = {2012}, month = {08/2012}, pages = {298-304}, type = {Citizen-Science Reviews}, chapter = {298}, abstract = {Citizen science creates a nexus between science and education that, when coupled with emerging technologies, expands the frontiers of ecological research and public engagement. Using representative technologies and other examples, we examine the future of citizen science in terms of its research processes, program and participant cultures, and scientific communities. Future citizen-science projects will likely be influenced by sociocultural issues related to new technologies and will continue to face practical programmatic challenges. We foresee networked, open science and the use of online computer/video gaming as important tools to engage non-traditional audiences, and offer recommendations to help prepare project managers for impending challenges. A more formalized citizen-science enterprise, complete with networked organizations, associations, journals, and cyberinfrastructure, will advance scientific research, including ecology, and further public education.}, keywords = {Citizen Science, public engagement}, issn = {1540-9295}, doi = {doi:10.1890/110294}, url = {http://www.esajournals.org/doi/full/10.1890/110294}, author = {Greg Newman}, editor = {Andrea Wiggins and Alycia Crall and Eric Graham and Sarah Newman and Kevin Crowston} } @article {1450, title = {Georeferencing at the Field Museum}, year = {2013}, keywords = {iDigBio Georeferencing Workshop Group (GWG), iDigBio GWG TTT 2}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/ttt2/GrantSharonTTT2FMNH_iDigBio2013.ppt}, author = {Sharon Grant} } @conference {2537, title = {A global survey of natural history collections}, booktitle = {Society for the Preservation of Natural History Collections 31st Annual Meeting}, year = {2016}, month = {06/2016}, address = {Berlin, Germany}, author = {Paul, Deborah L. and Masinde, Siro and Shari Ellis and Leonard Krishtalka and Barbara M. Thiers and Ganglo, Jean and Dalcin, Eduardo and Nakae, Masanori} } @article {1900, title = {How Do You Solve A Problem Like Multimedia?}, year = {2014}, keywords = {SiBBr 2014}, url = {https://www.idigbio.org/wiki/images/8/8a/SGrant_editedEMu2014_FINAL.pdf}, author = {Sharon Grant and Kate Webbink and Marc Lambruschi} } @article {2267, title = {I downloaded 3D fossils for the classroom, and then what? An intro to open source 3D modeling software.}, year = {2015}, keywords = {3D Digitization of Fossils for Educators \& Citizen Scientists, Carr 221}, url = {http://idigbio.adobeconnect.com/p6x8wd1woty/}, author = {Claudia Grant} } @conference {546, title = {iConference2013: Improving the Character of Optical Character Recognition (OCR): iDigBio Augmenting OCR Working Group Seeks Collaborators and Strategies to Improve OCR Output and Parsing of OCR Output}, booktitle = {iConference 2013}, year = {2013}, month = {02/2013}, publisher = {iSchools}, organization = {iSchools}, address = {Ft. Worth, Texas}, abstract = {There are an estimated 2 {\textendash} 3 billion museum specimens world {\textendash} wide (OECD 1999, Ari{\~n}o 2010). In an effort to increase the research value of their collections, institutions across the U. S. have been seeking new ways to cost effectively transcribe the label information associated with these specimen collections. Current digitization methods are still relatively slow, labor-intensive, and therefore expensive. New methods, such as optical character recognition (OCR), natural language processing, and human-in-the-loop assisted parsing are being explored to reduce these costs. The National Science Foundation (NSF), through the Advancing Digitization of Biodiversity Collections (ADBC) program, funded Integrated Digitized Biocollections (iDigBio) in 2011 to create a Home Uniting Biodiversity Collections (HUB) cyberinfrastructure to aggregate and collectively integrate specimen data and find ways to digitize specimen data faithfully and faster and disseminate the knowledge of how to achieve this. The iDigBio Augmenting OCR Working Group is part of this national effort. - speed up the overall digitization process, - lower the cost, - improve overall efficiency, - assure digitized data is fit-for-use (NIBA 2010, Chapman 2005), and - provide the resulting digitized data records to researchers more quickly. The iDigBio Augmenting OCR (A-OCR) working group is actively engaged in identifying opportunities for collaboration to leverage OCR tools and technologies that are successful (both within and outside of the biology digitization domain) and disseminate these tools to the public or seek funding for development.}, keywords = {EF-1115210, iConference2013, iDigBio, information analysis, information organization, information retrieval, information services, machine language, Natural Language, OCR, qualitative data analysis, research methods}, doi = {10.9776/13493}, url = {https://www.ideals.illinois.edu/bitstream/handle/2142/42089/493.pdf?sequence=2}, author = {Robert Anglin and Jason Best and Figueiredo, Renato and Gilbert, Edward and Gnanasambandam, Nathan and Gottschalk, Stephen and Haston, Elspeth and Heidorn, P. Bryan and Lafferty, Daryl and Lang, Peter and Nelson, Gil and Deborah L Paul and Ulate, William and Kimberly Watson and Zhang, Qianjin} } @article {558, title = {iConference2013: Symbiota -- Creating an OCR and NLP enabled user interface and workflow to efficiently digitize 2.3 million lichen and bryophyte specimens}, year = {2013}, abstract = {This talk focuses on how the Lichen and Bryophyte Climate Change TCN (LBCC) project plans to make use of Optical Character Recognition (OCR) and Natural Language Processing (NLP) to help process over 2.3 million North American lichen and bryophyte specimens held within over 60 U.S. herbaria. A strong component of the LBCC image processing workflow includes separate automated OCR and NLP processing steps that hope to capture a significant component of the metadata found on the specimen labels. After converting specimen images to text fragments using the open source Tesseract OCR engine, previously developed and custom designed NLP algorithms will be used to parse the results into the appropriate Darwin Core fields. The resulting data will be then be imported into a central database and made public through a unified user interface. The final steps will include transferring the results back to the management database systems used by each collection. The presentation will begin with a brief overview of the LBCC project along with a simple workflow diagram. The OCR/NLP components of the workflow will be emphasized in greater detail. The Symbiota user interface will be displayed with a short explanation of how it will be used to digitize the label metadata. Current limitations and challenges with OCR and NLP processing will be explained as they pertain to this project. Several solutions to these issues that are being explored by the project will be explained in detail along with their preliminary results. }, keywords = {Augmenting Optical Character Recognition, Darwin Core, Natural Language Processing, User Interface, WorkFlows}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/aocr-hackathon/iSchool.pptx}, author = {Edward Gilbert} } @proceedings {548, title = {iConference2013: Workshop -- Help iDigBio Reveal Hidden Data: iDigBio Augmenting OCR Working Group Needs You ($\#$CNFWSP11)}, year = {2013}, abstract = {Integrated Digitized Biodiversity Collections, iDigBio, is an initiative funded under the National Science Foundation{\textquoteright}s (NSF) Advancing Digitization of Biological Collections (ADBC) program set up to help natural history museums get specimen data for hundreds of millions of specimens out of drawers, off of labels, out of field notebooks, out of old publications and into integrated databases for everyone{\textquoteright}s use. The iDigBio Augmenting OCR Working Group needs your wisdom, knowledge and collaboration as part of our multi-faceted approach to improve OCR strategies and natural language processing (NLP) algorithms used in digitization. Our workshop panelists, members of our working group, are eager to introduce the iSchools community to our challenges and get your input in our break-out sessions. Our research areas of interest include: image segmentation, autocorrection of typographical errors, semantic autocorrection, autonormalization, automated text segmentation, generating consensus records and user interfaces for these tasks. We seek your insights, collective experiences and partnership in order to find ways to improve the digitization process to create a national searchable online specimen-based data set that is fit-for-use by scientists and the public. Some ideas generated in this session may be implemented at the iDigBio hackathon being held at the Botanical Research Institute of Texas (BRIT) during the iConference. }, keywords = {aocr, EF-1115210, iConference2013, iDigBio hackathon, information analysis, information organization, information retrieval, information services, iSchools, machine language, Natural Language, OCR, qualitative data analysis, research methods}, doi = {10.9776/13471}, url = {http://idigbio.adobeconnect.com/p6463wkhtx1/}, author = {Paul, Deborah L. and Heidorn, P. Bryan and Best, Jason and Gilbert, Edward and Neill, Amanda and Nelson, Gil and Ulate, William} } @conference {1630, title = {iConference2013:Help iDigBio reveal hidden data: iDigBio Augmenting OCR working group needs you - Part II}, year = {2013}, publisher = {iSchools}, organization = {iSchools}, address = {Ft. Worth, Texas}, abstract = {Integrated Digitized Biocollections (iDigBio) is a nation-wide effort funded by the National Science Foundation (NSF) to digitize data from hundreds of millions of natural history museum specimens. In a concerted five-part outreach effort, the iDigBio Augmenting Optical Character Recognition Working Group (A-OCR WG) coordinated a 2013 iConference Workshop, Poster, Notes submission, Alternative Event and a concurrent Hackathon hosted by the Botanical Research Institute of Texas (BRIT). The Workshop titled, " Help iDigBio Reveal Hidden Data: iDigBio Augmenting OCR Working Group Needs You" introduces the iSchools community to iDigBio and the A-OCR WG mission and challenges to improve digitization efficiency. This related Alternative Event provides the A-OCR WG an opportunity to report back to iConference Workshop attendees about our first experience using a Hackathon model to work on parsing and user interface design issues specific to our needs. We anticipate to a lively, open discussion with event attendees and future collaborators.}, keywords = {EF-1115210, iConference2013, iDigBio}, url = {http://hdl.handle.net/2142/42515}, author = {Paul, Deborah L. and Heidorn, P. Bryan and Jason Best and Edward Gilbert and Amanda Neill and Ulate, William} } @article {374, title = {iDigBio Augmenting OCR Workshop: }, year = {2012}, abstract = {Oboyski, Peter with Phuc Nguyen, Serge Belongie, Rosemary Gillespie. Essig Museum. Digitization California Arthropod Collection - CalBug.}, keywords = {iDigBio Augmenting OCR Workshop}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/aocr-wgw/Oboyski-CalBug_OCR.pptx}, author = {Peter Oboyski and Phuc Nguyen and Serge Belongie and Rosemary Gillespie} } @article {368, title = {iDigBio Augmenting OCR Workshop: Lichens, Bryophytes and Climate Change}, year = {2012}, abstract = {Gilbert, Edward et al. Symbiota Software Lead Developer. Lichens, Bryophytes and Climate Change}, keywords = {iDigBio Augmenting OCR Workshop}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/aocr-wgw/Gilbert_OcrWorkshop.pptx}, author = {Edward Gilbert and Corinna Gries and Thomas H Nash III and Robert Anglin} } @article {371, title = {iDigBio Augmenting OCR Workshop: OCR implementation in The Caribbean Plants Digitization Project}, year = {2012}, abstract = {Gottschalk, Stephen. Curatorial Assistant, New York Botanical Garden (NYBG). OCR implementation in The Caribbean Plants Digitization Project, a project to image and catalog over 150,000 Caribbean specimens at the New York Botanical Garden. Bronx, New York.}, doi = {iDigBio Augmenting OCR Workshop}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/aocr-wgw/gottschalk_gainesville.pptx}, author = {Stephen Gottschalk} } @article {281, title = {iDigBio Botany 2012 Symposium: "Digitizing {\textquoteright}all{\textquoteright} North American lichen and bryophyte specimens: 2.3 million specimens, 65 institutions, 1 year later. "}, year = {2012}, abstract = {This presentation was given by Corinna Gries, Edward Gilbert, and Thomas H Nash III at the iDigBio Botany 2012 Symposium.}, keywords = {iDigBio Botany 2012 Symposium}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/botany2012/symposium/DigitizingallNorthAmericanlichenandbryophyte.pptx}, author = {Corinna Gries and Edward Gilbert and Thomas H Nash III} } @article {262, title = {iDigBio Botany 2012 Workshop: Best Practices for Managing and Motivating the Digitizers}, year = {2012}, abstract = {This presentation was given by Larry Gall at the iDigBio Botany 2012 Workshop.}, keywords = {iDigBio Botany 2012 Workshop}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/botany2012/workshop/gall-idigbio-posted.ppt}, author = {Larry Gall} } @article {269, title = {iDigBio Botany 2012 Workshop: Implementing Optical Character Recognition in Herbarium Digitization Workflows: Current practices and challenges}, year = {2012}, abstract = {This presentation was given by Stephen Gottschalk at the iDigBio Botany 2012 Workshop.}, keywords = {iDigBio Botany 2012 Workshop}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/botany2012/workshop/ocr_presentation.pptx}, author = {Stephen Gottschalk} } @article {276, title = {iDigBio Botany 2012 Workshop: SilverBiology}, year = {2012}, abstract = {This presentation was given by Michael Giddens at the iDigBio Botany 2012 Workshop.}, keywords = {iDigBio Botany 2012 Workshop}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/botany2012/workshop/GIDDENS.SilverBiology-Botany2012.pptx}, author = {Michael Giddens} } @article {339, title = {iDigBio Public Participation in Digitization of Biodiversity Specimens Workshop: Symbiota: using specimen data to support community inventories}, year = {2012}, abstract = {Gilbert, Edward. Symbiota Software Project. Symbiota: using specimen data to promote citizen science and the exploration of backyard biodiversity.}, keywords = {Public Participation in Digitization of Biodiversity Specimens Workshop}, author = {Edward Gilbert} } @article {340, title = {iDigBio Public Participation in Digitization of Biodiversity Specimens Workshop: Label Processing Method HelpingScience.org}, year = {2012}, abstract = {Giddens, Michael. SilverBiology Software Project. HelpingScience.org, an online citizen science solution for converting image labels into occurrence Records.}, keywords = {Public Participation in Digitization of Biodiversity Specimens Workshop}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/ppws-2012/Giddens_SilverBiology-2012.ppt}, author = {Michael Giddens} } @article {470, title = {IDigBio Summit II: Augmenting OCR (aOCR)}, year = {2012}, keywords = {IDigBio Summit II}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/summit2/Paul_AocrSummit2012.pptx}, author = {Edward Gilbert and Deborah L Paul} } @article {468, title = {IDigBio Summit II: North American Lichens and Bryophytes {\textendash} Sensitive Indicators of Environmental Quality and Change}, year = {2012}, keywords = {IDigBio Summit II}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/summit2/Gries_LBCCupdate2012.pptx}, author = {Corinna Gries} } @article {394, title = {iDigBio Summit: TCN Overview, {\textquotedblleft}North American Lichens and Bryophytes{\textquotedblright}}, year = {2011}, keywords = {iDigBio 2011 Summit}, url = {https://www.idigbio.org/videos/idigbio-summit-TCN-Gries-30NOV2011.mp4}, author = {Corinna Gries} } @article {395, title = {iDigBio Summit: TCN Overview, {\textquotedblleft}North American Lichens and Bryophytes{\textquotedblright}}, year = {2011}, keywords = {iDigBio 2011 Summit}, url = {https://www.idigbio.org/videos/slides/09griesEtAlHUBsummit2011.pptx}, author = {Corinna Gries} } @conference {2502, title = {iDigBio: Using Biodiversity Specimen Data for Designing Effective Interpretive Programs}, booktitle = {39th Annual Southeastern State Parks Programs Seminar}, year = {2015}, month = {12/2015}, address = {Gainesville, FL}, abstract = {This session will highlight iDigBio and the National Science Foundation{\textquoteright}s {\textquotedblleft}Advancing the Digitization of Biodiversity Collections{\textquotedblright} initiative. With currently over 45 million records, the digitization of biodiversity specimens provides a huge data store which can be an excellent resource. Join us as we show you what information is available, how it can be used in interpretive programs and how iDigBio{\textquoteright}s education and outreach program can benefit state park interpretation.}, keywords = {portal}, url = {http://sspps.net/wp-content/uploads/2015/09/2015-SSPPS-Program.pdf}, author = {Nelson, Gil and Goodwin, Jillian and Phillips, Molly} } @conference {2528, title = {iDigBio: using museum collections specimen data to improve biodiversity measures}, booktitle = {Research Data Alliiance Sixth Plenary Meeting, Paris, France}, year = {2016}, month = {09/2015}, address = {Paris, France}, url = {https://rd-alliance.org/sites/default/files/attachment/RDA-P6-Programme.pdf$\#$overlay-context=plenary-meetings/sixth-plenary/programme.html}, author = {Germain-Aubrey, Charlotte C. and Allen, Julie M. and Guralnick, Robert and Neubig, Kurt M. and Ponciano, Jose Miguel and Lamy, Thomas and Soltis, Douglas E. and Mischler, Brent and Laffan, S. and Majure, Lucas and Soltis, Pamela S.} } @article {931, title = {Imaging in amber}, year = {2013}, keywords = {Paleo Digitization Workshop}, url = {https://www.idigbio.org/wiki/images/c/cd/Imaging_in_Amber_Grimaldi.pdf}, author = {Dave Grimaldi} } @article {716, title = {Initiating a Collection Digitization Project}, year = {2008}, keywords = {Mobilization}, url = {http://www.gbif.org/orc/?doc_id=2176}, author = {C. K. Frazier and J. Wall and S. Grant} } @conference {253, title = {Label Recognition in Herbarium Specimens by using Database-Queries}, booktitle = {ICDM 2011 IEEE International Conference on Data Mining}, year = {2011}, month = {09/2011}, publisher = {IEEE}, organization = {IEEE}, address = {Vancouver, Canada}, abstract = {For hundreds of years plant specimens are collected in herbariums for scientific purposes. These plants are mounted on specimen sheets and labeled with the essential data such as the name of the collector, the date and the place it was found. To make them available for a wider public the specimen sheets get digitized for online use. The purpose of our project in cooperation with the Botanical Garden in Berlin (Germany) is the development of a software-system for the analysis of these high resolution images. There are different approaches like template matching or SURF for detecting stable objects like color-charts, rulers, barcodes or even labels (fig. 1) on specimens. This paper describes a new method for the automatic scale- and rotation-invariant recognition of prior defined label-types by using OCR-engine generated texts contained in a database.}, keywords = {database, label recognition, OCR-texts, rotation-invariant, scale-invariant, SURF, template matching}, author = {M Gehrke and KH Steinke and R Dzido} } @article {779, title = {LBCC - Lichens Bryophytes and Climate Change}, year = {2013}, keywords = {Summit 3}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/summit3/LBCC-LichenBryophytesandClimateChange.pdf}, author = {Corinna Gries} } @article {997, title = {LBCC-Lichens Bryophytes and Climate Change}, year = {2013}, keywords = {Summit 3}, url = {http://vimeo.com/album/2684234/video/84223535}, author = {Corinna Gries} } @conference {2439, title = {Lifemapper{\textquoteright}s species distribution modeling based on iDigBio Biocollections}, booktitle = {SPNHC 2015}, year = {2015}, keywords = {EF-1115210, Presentation, SPNHC2015}, author = {Stewart, Aimee and Matsunaga, Andr{\'e}a and Beach, James H. and Grady, C.J. and Cavner, Jeffrey and Fortes, Jos{\'e} A.B.} } @article {1374, title = {Lightning Talk:The East Texas Natural History Collections }, year = {2014}, keywords = {TORCH VIII and iDigBio Workshop}, url = {https://www.idigbio.org/wiki/images/9/9a/GodwinTorch.pdf}, author = {Will Godwin} } @article {914, title = {Managing Digitization Personnel and Workflows}, year = {2013}, keywords = {Paleo Digitization Workshop}, url = {https://www.idigbio.org/wiki/images/f/f4/Gall_Tuesday.pdf}, author = {Larry Gall} } @article {1970, title = {Maximizing and sources of student labor }, year = {2015}, keywords = {Workflows Herbarium Digitization}, url = {https://www.idigbio.org/wiki/images/c/c6/Gilespie-iDigBio.pdf}, author = {Emily Gillespie} } @conference {2434, title = {Measuring Megalodon: classroom driven research made possible with 3D technology}, booktitle = {2015 GSA Annual Meeting}, year = {2015}, month = {2015}, address = {Baltimore, Maryland}, abstract = {The Florida Museum of Natural History has been collaborating with iDigBio and Duke University to incorporate 3D printing technology and compelling scientific research into K-12 classrooms. Recently, an associated dentition of Megalodon (Carcharocles megalodon), donated by amateur paleontologist Gordon Hubbell, was scanned and 3D printed for research and education purposes. Associated sets of Megalodon teeth are extremely rare and offer insurmountable information regarding the life history of this captivating creature. A lesson has since been developed, available on www.paleoteach.org, that integrates scientific research concerning body length estimates of Megalodon with 3D printing technology in order to develop an understanding of fundamental concepts in paleontology, geology, and biology. Body length estimates for Megalodon are commonly based off of the anatomy of the living Great White shark (Carcharodon carcharias), most prominent are a set of equations developed by Kenshu Shimada (2003) that estimates body length based off a linear relationship observed between crown height and body length for each tooth position. In this lesson, students are given teeth from the associated set at random and first asked to identify the tooth position of their isolated teeth, allowing them to compose a personal understanding of the tooth morphology. Subsequently, students estimate body length using the equations established by Shimada and their corresponding tooth positions, which requires solving a linear equation and, consequently, incorporates mathematics (i.e., STEM integration). A geometry extension was also developed that exploits the natural triangular shape of the teeth and the inherent dignathic heterodonty exhibited by Megalodon. Tooth dimensions vary, in terms of size and symmetry, between positions; which allows students to explore the geometric properties of triangles. Interestingly, upon testing these equations with the associated dentition, the students found that different tooth positions resulted in vastly different body length estimates. This had never been tested before and is in fact a new discovery to science made possible by a harmonious collaboration between technologic innovation, scientific institutions, researchers, amateur paleontologists, teachers, and students. Geological Society of America Abstracts with Programs. Vol. 47, No. 7, p.99}, keywords = {education, EF-1115210, GSA2015, poster}, url = {https://gsa.confex.com/gsa/2015AM/webprogram/Paper266196.html}, author = {Perez, Victor J. and Grant, Claudia and Hendrickson, Megan and Tovani, Jason} } @article {2138, title = {Meeting report: Identifying practical applications of ontologies for biodiversity informatics}, journal = {Standards in Genomic Sciences C7 - 25}, volume = {10}, year = {2015}, pages = {1-6}, abstract = {This report describes the outcomes of a recent workshop, building on a series of workshops from the last three years with the goal if integrating genomics and biodiversity research, with a more specific goal here to express terms in Darwin Core and Audubon Core, where class constructs have been historically underspecified, into a Biological Collections Ontology (BCO) framework. For the purposes of this workshop, the BCO provided the context for fully defining classes as well as object and data properties, including domain and range information, for both the Darwin Core and Audubon Core. In addition, the workshop participants reviewed technical specifications and approaches for annotating instance data with BCO terms. Finally, we laid out proposed activities for the next 3 to 18 months to continue this work.}, keywords = {Ontology Biodiversity Population Community Darwin core OWL RDF Microbial ecology Sequencing}, doi = {10.1186/s40793-015-0014-0}, url = {http://dx.doi.org/10.1186/s40793-015-0014-0}, author = {Deck, John and Guralnick, Robert and Walls, Ramona and Blum, Stanley and Haendel, Melissa and Matsunaga, Andr{\'e}a and Wieczorek, John} } @article {1999, title = {Motivating Digitization Personnel}, year = {2015}, keywords = {Digitizing Dried Insects Digitization Workshop}, url = {https://www.idigbio.org/wiki/images/c/c9/LFG-idigbio-thursday.pdf}, author = {Larry Gall} } @article {1598, title = {Natural History Collections as Emerging Resources for Innovative Education}, journal = {BioScience}, volume = {64}, year = {2014}, month = {08/2014}, chapter = {725}, abstract = {There is an emerging consensus that undergraduate biology education in the United States is at a crucial juncture, especially as we acknowledge the need to train a new generation of scientists to meet looming environmental and health crises. Digital resources for biology now available online provide an opportunity to transform biology curricula to include more authentic and inquiry-driven educational experiences. Digitized natural history collections have become tremendous assets for research in environmental and health sciences, but, to date, these data remain largely untapped by educators. Natural history collections have the potential to help transform undergraduate science education from passive learning into an active exploration of the natural world, including the exploration of the complex relationships among environmental conditions, biodiversity, and human well-being. By incorporating natural history specimens and their associated data into undergraduate curricula, educators can promote participatory learning and foster an understanding of essential interactions between organisms and their environments.}, keywords = {database, inquiry driven, museum, place based, undergraduate education}, issn = {1525-3244}, doi = {10.1093/biosci/biu096}, url = {http://bioscience.oxfordjournals.org/content/64/8/725.full.pdf+htm}, author = {Joseph A. Cook and Scott V. Edwards and Eileen A. Lacey and Robert P. Guralnick and Pamela S. Soltis and Douglas E. Soltis and Corey K. Welch and Kayce C. Bell and Kurt E. Galbreath and Christopher Himes and Julie M. Allen and Tracy A. Heath and Ana C. Carnaval and Kimberly L. Cooper and Mark Liu and James Hanken and Stefanie Ickert-Bond} } @article {2105, title = {Natural History Collections as Emerging Resources for Innovative Education}, journal = {BioScience}, volume = {64}, year = {2014}, month = {08/2014}, chapter = {725}, abstract = {Nearly four decades ago, Roose \& Gottlieb (Roose \& Gottlieb 1976 Evolution 30, 818{\textendash}830. (doi:10.2307/2407821)) showed that the recently derived allotetraploids Tragopogon mirus and T. miscellus combined the allozyme profiles of their diploid parents (T. dubius and T. porrifolius, and T. dubius and T. pratensis, respectively). This classic paper addressed the link between genotype and biochemical phenotype and documented enzyme additivity in allopolyploids. Perhaps more important than their model of additivity, however, was their demonstration of novelty at the biochemical level. Enzyme multiplicity{\textemdash}the production of novel enzyme forms in the allopolyploids{\textemdash}can provide an extensive array of polymorphism for a polyploid individual and may explain, for example, the expanded ranges of polyploids relative to their diploid progenitors. In this paper, we extend the concept of evolutionary novelty in allopolyploids to a range of genetic and ecological features. We observe that the dynamic nature of polyploid genomes{\textemdash}with alterations in gene content, gene number, gene arrangement, gene expression and transposon activity{\textemdash}may generate sufficient novelty that every individual in a polyploid population or species may be unique. Whereas certain combinations of these features will undoubtedly be maladaptive, some unique combinations of newly generated variation may provide tremendous evolutionary potential and adaptive capabilities.}, keywords = {EF-1115210}, url = {https://www.idigbio.org/sites/default/files/sites/default/files/Cook\%20et\%20al\%20BioScience-2014-Cook-725-34.pdf}, author = {Joseph A. Cook and Scott V. Edwards and Eileen A. Lacey and Robert P. Guralnick and Soltis, Pamela S. and Douglas E. Soltis and Corey K. Welch and Kayce C. Bell and Kurt E. Galbreath and Christopher Himes and Julie M. Allen and Tracy A. Heath and Ana C. Carnaval and Kimberly L. Cooper and Mark Liu and James Hanken and Stefanie Ickert-Bond} } @article {2103, title = {A New iDigBio Web Feature Links DNA Banks and Genetic Resources Repositories in the United States}, journal = {DNA Banking for the 21st Century}, year = {2014}, month = {04/2014}, abstract = {Collections of genetic resources have served the needs of molecular biologists for many decades, providing valu able sources of materials for molecular studies of biodiversity and facilitating long-term archival of samples from pub lished studies. However, the needs of the research community are rapidly changing and contributing to an increasing demand for high-quality genetic resources. Curators and researchers in the United States (U.S.) have recently engaged in an active dialogue about the future of these collections, as well as about best practices and standards for collecting and preserving new materials. The discussion has reemphasized a previously identified need for networked data on genetic resources to better link samples housed in U.S. collections with research consumers. However, there are no comprehensive lists of DNA banks, genetic resources repositories, or tissue collections available, and significant gaps remain in our knowledge about the types of genetic resources that are available as well as their physical localities. In this paper, we describe a newly available web feature developed and maintained by Integrated Digitized Biocollections (iDigBio) that is helping to compile the first comprehensive list of genetic resources collections in the U.S. Our new tool provides information on a diverse set of collections and enables rapid searching of multiple collections.}, keywords = {DNA bank, EF-1115210, genetic resources, iDigBio, natural history, tissue collections}, issn = {10: 0-9808415-9-8}, url = {https://www.idigbio.org/sites/default/files/sites/default/files/GoddenSoltis\%20DNA\%20Banking2014.pdf}, author = {Soltis, Pamela S and Godden, Grant T} } @article {1113, title = {The Nexus Dissemination or Trying to become/ impersonate an Archivist/Librarian}, year = {2014}, keywords = {Digitizing from Source Materials}, url = {https://www.idigbio.org/wiki/images/5/5c/Gall-archives.pdf}, author = {Larry Gall} } @article {1703, title = {NIBA RCN: Organizing and Sustaining a National Community }, year = {2014}, keywords = {Leveraging Digitization}, url = {https://www.idigbio.org/wiki/images/5/57/Gropp-NIBA_101.pdf}, author = {Robert Gropp} } @article {1766, title = {NIBA RCN: Organizing and Sustaining a National Community}, year = {2014}, keywords = {Summit 2014}, url = {https://www.idigbio.org/wiki/images/4/49/NIBA_101.pdf}, author = {Robert Gropp} } @article {1796, title = {NIBA RCN: Organizing and Sustaining a National Community}, year = {2014}, keywords = {Summit 2014}, url = {http://vimeo.com/album/3113100/video/111036679}, author = {Robert Gropp} } @article {1614, title = {Nomenclatural benchmarking: the roles of digital typification and telemicroscopy}, journal = {Zookeys}, volume = {209}, year = {2012}, month = {2012}, chapter = {193}, abstract = {Nomenclatural benchmarking is the periodic realignment of species names with species theories and is necessary for the accurate and uniform use of Linnaean binominals in the face of changing species limits. Gaining access to types, often for little more than a cursory examination by an expert, is a major bottleneck in the advance and availability of biodiversity informatics. For the nearly two million described species it has been estimated that five to six million name-bearing type specimens exist, including those for synonymized binominals. Recognizing that examination of types in person will remain necessary in special cases, we propose a four-part strategy for opening access to types that relies heavily on digitization and that would eliminate much of the bottleneck: (1) modify codes of nomenclature to create registries of nomenclatural acts, such as the proposed ZooBank, that include a requirement for digital representations (e-types) for all newly described species to avoid adding to backlog; (2) an {\textquotedblleft}r{\textquotedblright} strategy that would engineer and deploy a network of automated instruments capable of rapidly creating 3-D images of type specimens not requiring participation of taxon experts; (3) a {\textquotedblleft}K{\textquotedblright} strategy using remotely operable microscopes to engage taxon experts in targeting and annotating informative characters of types to supplement and extend information content of rapidly acquired e-types, a process that can be done on an as-needed basis as in the normal course of revisionary taxonomy; and (4) creation of a global e-type archive associated with the commissions on nomenclature and species registries providing one-stop-shopping for e-types. We describe a first generation implementation of the {\textquotedblleft}K{\textquotedblright} strategy that adapts current technology to create a network of Remotely Operable Benchmarkers Of Types (ROBOT) specifically engineered to handle the largest backlog of types, pinned insect specimens. The three initial instruments will be in the Smithsonian Institution(Washington, DC), Natural History Museum (London), and Museum National d{\textquoteright}Histoire Naturelle (Paris), networking the three largest insect collections in the world with entomologists worldwide. These three instruments make possible remote examination, manipulation, and photography of types for more than 600, 000 species. This is a cybertaxonomy demonstration project that we anticipate will lead to similar instruments for a wide range of museum specimens and objects as well as revolutionary changes in collaborative taxonomy and formal and public taxonomic education.}, keywords = {SES-09083935}, url = {http://www.pensoft.net/journals/zookeys/article/3486/nomenclatural-benchmarking-the-roles-of-digital-typification-and-telemicroscopy}, author = {Q. Wheeler and T. Bourgoin and J. Coddington and T. Gostony and A. Hamilton and R. Larimer and A. Polaszek and M. Schauff and M.A. Solis} } @article {1080, title = {North American Lichens and Bryophytes {\textendash} Sensitive Indicators of Environmental Quality and Change}, year = {2012}, keywords = {IDigBio Summit II}, url = {http://vimeo.com/album/2163675/video/54320795}, author = {Corinna Gries} } @article {1118, title = {Notes from Nature: a tool for citizen science engagement and transcription of natural history records Or NFN:Where Now?}, year = {2014}, keywords = {Digitizing from Source Materials}, url = {https://www.idigbio.org/wiki/images/8/87/NFNlighteningish.pdf}, author = {Robert Guralnick} } @conference {2421, title = {Notes From Nature: Advancing a next generation citizen science platform for biodiversity transcription}, booktitle = {TDWG 2015}, year = {2015}, keywords = {EF-1115210, Presentation, TDWG2015}, author = {Guralnick, Robert Penn and Denslow, Michael W. and Mast, Austin} } @conference {254, title = {Object Recognition in Herbarium Specimens}, booktitle = {ICDM 2011 IEEE International Conference on Data Mining}, year = {2011}, month = {09/2011}, publisher = {IEEE}, organization = {IEEE}, address = {Vancouver, Canada}, abstract = {About 3.5 million dried plants on paper sheets are deposited in the Botanical Museum Berlin in Germany. The aim of our project is the image analysis of scanned high resolution images. There are many different objects contained in a herbarium sheet like ruler, barcode, stamps, color-chart, labels with printed title, red type designator, envelopes, hand-written and printed annotations and the plant. Some objects are very stable like the ruler, others are extremely variable like handwriting or plant. So each class of objects requires a special detection method. Algorithms like template matching or SURF can be applied to some of the stable objects. For variable objects like handwriting detection methods are already developed by the authors and are described in other papers.}, keywords = {best template, connected component analysis, hue space, object recognition, SURF, template matching}, author = {KH Steinke and M Gehrke and R Dzido} } @article {1828, title = {The Open Drawer Project - Providing free access to high resolution images of entomological collection drawers}, year = {2014}, keywords = {TDWG 2014}, url = {http://www.tdwg.org/fileadmin/2014conference/slides/Kroupa__Open_Drawer_Project.pdf}, author = {Alexander Kroupa and Christoph H{\"a}user and Gregor Hagedorn and Felix Maier and Bernhard Schurian and Falko Gl{\"o}ckler and Stefan Schmidt} } @article {1841, title = {The Open Drawer Project - Providing free access to high resolution images of entomological collection drawers. }, year = {2014}, keywords = {TDWG 2014}, url = {http://idigbio.adobeconnect.com/p81as7fs075/}, author = {Alexander Kroupa and Gregor Hagedorn and Bernhard Schurian and Falko Gl{\"o}ckler and Christoph H{\"a}user and Felix Maier and Stefan Schmidt} } @conference {2420, title = {Paleoteach: use of paleontological data for K-12 education}, booktitle = {2015 GSA Annual Meeting}, year = {2015}, month = {11/2015}, address = {Baltimore, Maryland}, abstract = {PaleoTeach is a collaboration involving the Florida Museum of Natural History, and secondary science educators. The goal is to create curricula using high-quality 3D models for a K-12 audience. Fossils, present in required Earth Sciences curriculum, are oftentimes delicate or rare, and not universally suitable for classroom use. Therefore, 3D scanning and printing technology provides a unique opportunity to make these specimens available for K-12 education. In addition, paleontology is an interdisciplinary and engaging area of study that provides distinctive opportunities for STEM integration. STEM integration is an instructional method that aims to emphasize the connections between science, technology, engineering, and math. This method helps introduce concepts in these subjects in a way that is more meaningful to students and also replicates the way science is practiced. PaleoTeach advances our understanding of the potential efficacy of the recently developed 3D scanning technology in K-12 science learning. This approach to integrate 3D data can improve the relevance of educational practices in our schools and broaden the impact of ongoing digitization efforts of paleontological research collections. Lessons that we have developed are rooted in the idea of STEM integration. For example, research on Carcharocles megalodon provides multiple opportunities for K-12 educators. Lessons have been designed to teach concepts of extinction and evolution (science) through the use of 3D printed teeth (technology). Students replicate scientific processes by measuring the teeth and calculating the size of the animal (math). Ultimately, they reconstruct the entire jaw by applying concepts of engineering. Like the study of C. megalodon, there are other examples from the fossil record (e.g., Titanoboa cerrejonensis and equid evolution) that can increase educators{\textquoteright} content knowledge and guide students through this integrated process. Furthermore, making specific fossils available for 3D reproduction can help educators introduce examples of important topics, such as climate change, extinction and evolution, fostering new learning opportunities in issues of current societal relevance. Geological Society of America Abstracts with Programs. Vol. 47, No. 7, p.612}, keywords = {EF-1115210, GSA2015, Presentation}, url = {https://gsa.confex.com/gsa/2015AM/webprogram/Paper264381.html}, author = {Grant, Claudia} } @article {760, title = {Poster: Improving the Character of Optical Recognition (OCR)}, year = {2012}, abstract = {There are an estimated 2 {\textendash} 3 billion museum specimens world {\textendash} wide (OECD 1999, Ari{\~n}o 2010). In an effort to increase the research value of their collections, institutions across the U. S. have been seeking new ways to cost effectively transcribe the label information associated with these specimen collections. Current digitization methods are still relatively slow, labor-intensive, and therefore expensive. New methods, such as optical character recognition (OCR), natural language processing, and human-in-the-loop assisted parsing are being explored to reduce these costs. The National Science Foundation (NSF), through the Advancing Digitization of Biodiversity Collections (ADBC) program, funded Integrated Digitized Biocollections (iDigBio) in 2011 to create a Home Uniting Biodiversity Collections (HUB) cyberinfrastructure to aggregate and collectively integrate specimen data and find ways to digitize specimen data faithfully and faster and disseminate the knowledge of how to achieve this. The iDigBio Augmenting OCR Working Group is part of this national effort. - speed up the overall digitization process, - lower the cost, - improve overall efficiency, - assure digitized data is fit-for-use (NIBA 2010, Chapman 2005), and - provide the resulting digitized data records to researchers more quickly. The iDigBio Augmenting OCR (A-OCR) working group is actively engaged in identifying opportunities for collaboration to leverage OCR tools and technologies that are successful (both within and outside of the biology digitization domain) and disseminate these tools to the public or seek funding for development.}, keywords = {education, machine language, Natural Language Processing, NLP, optical character recognition, Outreach, poster}, url = {https://www.idigbio.org/sites/default/files/poster-files/ocr_dpaulposter.pdf}, author = {Robert Anglin and Jason Best and Renato Figueiredo and Edward Gilbert and Nathan Gnanasambandam and Stephen Gottschalk and Elspeth Haston and P. Bryan Heidorn and Daryl Lafferty and Peter Lang and Gil Nelson and Deborah L. Paul and William Ulate and Kimberly Watson and Qianjin Zhang} } @conference {244, title = {Recognition of Humboldt{\textquoteright}s Handwriting in Complex Surroundings}, booktitle = {12th International Conference on Frontiers in Handwriting Recognition (ICFHR)}, year = {2010}, month = {11/2010}, address = {Kolkata}, abstract = {In the Botanic Museum of Berlin in Germany exist about 3.5 million dried plants on paper sheets. They were collected in the last two hundred years by many collectors among those was the famous researcher {\textquotedblleft}Alexander von Humboldt{\textquotedblright}. because e every collector left his handwriting on the sheet the question came up if it is possible to find out automatically which sheet belongs to Humboldt{\textquoteright}s collection. To solve the problem many challenging sub problems have to be solved before. First text regions have to be localized and extracted. Then printing is to be distinguished from handwriting. For the latter an off-line writer recognition procedure had to be developed in order to determine the writer of the handwriting. Often two or more writers can be found on one sheet. To make sure that the suspect writer is correct an interactive method is applied which transforms the static character into a dynamic form. Different mathematical procedures are used such as the reproduction of the write line of individual characters by Legendre polynomials. All methods were proved on the international IAMdatabase [3]. 93 writers with at least 5 samples were chosen from the IAM-database. By combining multiple characters (up to thirteen), the recognition rate rises considerably and reaches 98.7\%. A global statistical approach using the whole handwritten text results in a similar recognition rate of more than 98\%. By combining the methods by a ranking method a recognition rate of 99.5\% is achieved.}, keywords = {Legendre polynomials, text localization, writer recognition}, doi = {10.1109/ICFHR.2010.91}, url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=5693621}, author = {KH Steinke}, editor = {M Gehrke} } @article {1349, title = {Reflectance Transformation Imaging }, year = {2014}, keywords = {Paleo Imaging Workshop}, url = {https://www.idigbio.org/wiki/images/7/70/Graham_0429.pdf}, author = {Chelsea Graham} } @article {1623, title = {Semantics in Support of Biodiversity Knowledge Discovery: An Introduction to the Biological Collections Ontology and Related Ontologies.}, journal = {PLoS ONE}, volume = {9}, year = {2014}, month = {03/2014}, chapter = {1}, abstract = {The study of biodiversity spans many disciplines and includes data pertaining to species distributions and abundances, genetic sequences, trait measurements, and ecological niches, complemented by information on collection and measurement protocols. A review of the current landscape of metadata standards and ontologies in biodiversity science suggests that existing standards such as the Darwin Core terminology are inadequate for describing biodiversity data in a semantically meaningful and computationally useful way. Existing ontologies, such as the Gene Ontology and others in the Open Biological and Biomedical Ontologies (OBO) Foundry library, provide a semantic structure but lack many of the necessary terms to describe biodiversity data in all its dimensions. In this paper, we describe the motivation for and ongoing development of a new Biological Collections Ontology, the Environment Ontology, and the Population and Community Ontology. These ontologies share the aim of improving data aggregation and integration across the biodiversity domain and can be used to describe physical samples and sampling processes (for example, collection, extraction, and preservation techniques), as well as biodiversity observations that involve no physical sampling. Together they encompass studies of: 1) individual organisms, including voucher specimens from ecological studies and museum specimens, 2) bulk or environmental samples (e.g., gut contents, soil, water) that include DNA, other molecules, and potentially many organisms, especially microbes, and 3) survey-based ecological observations. We discuss how these ontologies can be applied to biodiversity use cases that span genetic, organismal, and ecosystem levels of organization. We argue that if adopted as a standard and rigorously applied and enriched by the biodiversity community, these ontologies would significantly reduce barriers to data discovery, integration, and exchange among biodiversity resources and researchers.}, keywords = {EF-1115210}, url = {http://www.plosone.org/article/info\%3Adoi\%2F10.1371\%2Fjournal.pone.0089606}, author = {Ramona Wells and John Deck and Robert Guralnick and Steve Baskauf and Reed Beaman and Stanley Blum and Shawn Bowers and Pier Luigi Buttigieg and Neil Davies and Dag Endresen and Maria Alejandra Gandolfo and Robert Hanner and Alyssa Janning and Leonard Krishtalka and Matsunaga, Andr{\'e}a and Peter Midford and Norman Morrison and Eamonn O. Tuama and Mark Schidhauer and Barry Smith and Brian J. Stucky and Andrea Thomer and John Wieczorek and Jamie Whitacre and John Wooley} } @conference {2139, title = {A Specimen-based View of the World: Using the Biological Collections Ontology to Model Biodiversity Collections}, booktitle = {2014 ICBO Workshop: Starting an OBI-based Biobank Ontology}, year = {2014}, address = {Houston, TX, USA}, url = {http://ceur-ws.org/Vol-1309/paper8.pdf}, author = {Walls, Ramona and Guralnick, Robert and Deck, John and Matsunaga, Andr{\'e}a}, editor = {Brochhausen, Mathias and Haendel, Melissa and Stoeckert, Christian J. and Zheng, Jie} } @article {1411, title = {SPNHC 2014 DemoCamp: AnnoSys {\textendash} an online Tool to annotate Biodiversity Data}, year = {2014}, abstract = {Annotations are an important quality control mechanism in biodiversity research. The increasing accessibility of specimen data via the Internet calls for a general online annotation system that ensures the continuance of traditional data sharing and documentation of specimen data after their mobilisation through digitisation. The AnnoSys project (https://annosys.bgbm.fu-berlin.de) developed an annotation data repository for complex and cross-linked data including back-end server functionality, web services, a message system and an on-line user interface. AnnoSys is an open-source, web-based application. The intended audience includes scientists and curators as well as citizen scientists. Based on the W3C Open Annotation Data Model, annotations are accessible via web services supporting SPARQL and Linked Open Data. The AnnoSys interface allows researchers to create and search for annotations. If a record has been annotated, annotation and original record are stored together in the annotation data repository and are accessible through the AnnoSys user interface. A message system informs curators and scientists specifically interested in a subset of data about new annotations. Unlike simple annotation systems that allow only unstructured comments associated with records, AnnoSys allows structured annotations of specific elements of a record. AnnoSys has been implemented using ABCD-standardised data from botanical collections and is now integrated into the Virtual Herbarium Berolinense and the BioCASE portal. In contrast to the Filtered Push project, which pursues a distributed approach in facilitating and communicating online annotations, AnnoSys provides a central web interface and data repository that can be queried externally. }, keywords = {ABCD, AnnoSys, annotation, BioCASE, central web interface, open-source, SPNHC 2014 DemoCamp, web-based application}, author = {Okka Tsch{\"o}pe and Lutz Suhrbier and Anton G{\"u}ntsch and Walter G. Berendsohn} } @article {1410, title = {SPNHC 2014 DemoCamp: Crowdsourcing in LBCC using Symbiota}, year = {2014}, abstract = { The project {\textquoteleft}Lichens Bryophytes and Climate Change (LBCC){\textquoteright} is funded by the NSF-Advancing Digitization of Biological Collections (ADBC) Thematic Collections Network (TCN) program and aims to digitize ca. 2.3 million North American lichen and bryophyte specimens from over 60 collections representing well over 90\% of the remaining North American specimens from Canada, the United States and Mexico. In its third year of digitizing > 1.2 million lichen records are available at http://lichenportal.org and > 1.8 million bryophyte records at http://bryophyteportal.org. Digitization involved imaging the specimen labels and uploading them into the open source online collections management system {\textquoteleft}Symbiota{\textquoteright} (http://symbiota.org) where they become immediately available for transcription. The project was able to expand the already very sophisticated editing interface in Symbiota and developed functionality for citizen science to access the data. Employing the Drupal content management system, we developed simple querying tools in which volunteers can find specimens collected in a geographic area or taxonomic group of interest. The query utilizes information gathered from the label images via optical character recognition, presents the user with a set of records and forwards him/her to an abridged Symbiota screen for editing. In contrast to other citizen science interfaces that accomplish this task of transcribing information from an image, this approach allows the data to remain within the overall management framework, become available immediately, and do not have to be pulled out of the database and reintegrated later. This provides for seamless collaboration between volunteers, imagers, collections managers, and anyone interested in the data for research. In addition, this approach can take advantage of sophisticated quality control mechanism and search for duplicates already built into Symbiota, while not overwhelming the citizen scientist with the entire complexity of this system. The Drupal site allows for social networking among the volunteers and with the collections managers, plus posting of help specific for lichen and bryophyte labels. We will be demonstrating the functionality of the volunteer interface which can be access from http://lbcc.lichenportal.org and http://lbcc.bryophyteportal.org, as well as Symbiota{\textquoteright}s editing interface. }, keywords = {Citizen Science, crowdsourcing, Lichens Bryophyte and Climate Change (LBCC), OCR, optical character recognition, seamless integration, social networking, SPNHC 2014 DemoCamp, Symbiota, User Interface}, author = {Barbara Thiers and Edward Gilbert and Corinna Gries and Benjamin Brandt} } @article {1330, title = {SPNHC 2014: Progress in Digitization: The virtually browseable collection: connecting GIS to whole drawer imaging}, year = {2014}, abstract = {Accessibility is one of the most problematic aspects of offsite storage for collections. This project approaches that issue by creating virtual access to a large collection stored 8 miles from the main institution. To create virtual access, we used two elements that already exist for our collection. A GIS map of all cabinets in the repository and a Specify 6 database of records, which relates the specimens in those cabinets to their spatial locations. We combined database and spatial data using ArcGIS Online, because it has cross-platform compatibility. We related a third aspect, drawer and specimen images that are linked to the specimen records and can be viewed alongside the data and spatial records. Our final result is an online resource that allows the user to virtually examine the collection, query a database file and view the drawer content, individual specimens, and label images when they exist. This product is useful for researchers, teachers and the general public. The latter group is important from an educational stand point but also because many of the collections were amassed using public funds. It fulfills an additional role in that it is a time stamp marker for each drawer. What was located in that drawer, what was its condition? Over time additional images of drawers will be taken providing an archival record of their content and condition. }, keywords = {accessibility, digitization, education, GIS map, Specify, SPNHC 2014, SPNHC 2014: Progress in Digitization, whole drawer imaging}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/spnhc2014/13_Molineux-SPNHC2014-The\%20virtually\%20browseable\%20collection.pdf}, author = {Ann Molineux and Robert W. Burroughs and Faye Geigerman} } @article {1327, title = {SPNHC 2014: Progress in Digitization: ZooSphere - A tool for automated spheric image capturing and interactive 3D visualization}, year = {2014}, abstract = {Entomological collections, particularly the type specimens therein, are the fundament of the taxonomic research on insects. Since the beginning of collecting activities in the 18th century, some million type specimens (e.g. holotypes, lectotypes, paratypes.) are stored in museums worldwide. There are various threats to these collections: Valuable type specimens are damaged or even destroyed by museum beetles (e.g. Anthrenus verbasci) or moths (e.g. Teneola biselliella). Also changes and fluctuations in light exposure, temperature and high humidity may have negative effects on the objects. Especially the types are even more in danger by shipping them from the museums to specialists for their taxonomic work. To give full scientific access on the type specimens without shipping the valuable material across the globe, we developed a tool (ZooSphere) for automated image capture from about 400 positions around one specimen. A high resolution image with extremely high depth of focus is produced by using stacking technology in each position. The images will be freely available in the world wide web and will be displayed by a web-based tool developed for rotating and zooming the digital object in browsers. The same technology will be used for an interactive 3D presentation of the objects. The next steps are 1) joining the ZooSphere images with microCT images from internal specimen structures and 2) creating 3D models of the specimens by applying photogrammetric methods on the ZooSphere images. }, keywords = {3D, automation, digitization, Imaging, insects, Museum f{\"u}r Naturkunde Berlin, SPNHC 2014, SPNHC 2014: Progress in Digitization, ZooSphere}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/spnhc2014/10_kroupa\%20et\%20al\%20zoosphere.pdf}, author = {Alexander S. Kroupa and Martin Pluta and Bernhard Schurian and Falko Gl{\"o}ckler} } @article {1840, title = { StanDAP-Herb develops a standard process for extracting metadata from digitised herbarium specimens. }, year = {2014}, keywords = {TDWG 2014}, url = {http://idigbio.adobeconnect.com/p3iliimu2dd/}, author = {Agnes Kirchhoff and Walter G. Berendsohn and Ulrich B{\"u}gel and Fernando Chaves and Cailin Guan and Markus Lindhorst and Karl-Heinz Steinke and Hangyan Zheng and Dominik R{\"o}pert and Eduard Santamaria} } @article {1843, title = {StanDAP-Herb develops a standard process for extracting metadata from digitised herbarium specimens}, year = {2014}, keywords = {TDWG 2014}, url = {http://www.tdwg.org/fileadmin/2014conference/slides/Kirchhoff_StanDAPHerb.pdf}, author = {Agnes Kirchhoff and Walter G. Berendsohn and Ulrich B{\"u}gel and Fernando Chaves and Cailin Guan and Markus Lindhorst and Dominik R{\"o}pert and Eduard Santamaria and Karl-Heinz Steinke and Hangyan Zheng} } @article {2278, title = {STEM Integration through Paleontology and 3D Technology}, year = {2015}, keywords = {3D Digitization of Fossils for Educators \& Citizen Scientists, Carr 211}, url = {http://idigbio.adobeconnect.com/p1ruxhk7wqa/}, author = {~Claudia Grant} } @article {1858, title = {Stoneflies (Plecoptera), pre-European distributions and climate influenced future ranges in the Midwest}, year = {2014}, keywords = {ECN 2014}, url = {https://www.idigbio.org/wiki/images/7/79/DeWalt_ECN_2014.pdf}, author = {R.E. DeWalt and Y.Cao and J.L.Robinson and T. Tweddale and L.Hinz and S.A. Grubbs} } @article {941, title = {Symbiota: a specimen-based biodiversity portal platform}, year = {2013}, keywords = {Small Herbarium Workshop FSU}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/small-herbarium2013/Symbiota_2013-12-09_3.pdf}, author = {Edward Gilbert} } @article {961, title = {Symbiota: a specimen-based biodiversity portal platform}, year = {2013}, keywords = {Transcription Hackathon}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/citscribe/Symbiota_2013-12-16.pdf}, author = {Edward Gilbert} } @article {1558, title = {Symbiota: a specimen-based biodiversity portal platform}, year = {2014}, keywords = {Digitized Natural History Collections Symposium Botany 2014}, url = {https://www.idigbio.org/wiki/images/9/9e/Symbiota_2014-07-29.pdf}, author = {Gilbert, Edward} } @article {1566, title = {Symbiota: a specimen-based biodiversity portal platform}, year = {2014}, keywords = {Digitized Natural History Collections Symposium Botany 2014}, url = {http://idigbio.adobeconnect.com/p5jyze6pbzt/}, author = {Edward Gilbert} } @article {1968, title = {Symbiota workflows }, year = {2015}, keywords = {Workflows Herbarium Digitization}, url = {https://www.idigbio.org/wiki/images/4/41/Symbiota_2014-01-27.pdf}, author = {Ed Gilbert} } @article {1926, title = {Theory: publishing basic primary biodiversity data: IPT and other methods}, year = {2015}, keywords = {Data Sharing Data Standards and Demsifying the IPT}, url = {http://idigbio.org/sites/default/files/workshop-presentations/demystifyingIPT/IPTiDigBio-20150113-1D-demo-publishing-with-the-IPT.pptx}, author = {Alberto Gonzalez and James Macklin and Laura Russell} } @article {1575, title = {Understanding Data}, year = {2014}, keywords = {Small Herbarium Workshop Botany 2014}, url = {https://www.idigbio.org/wiki/images/3/3a/EGilbert_UnderstandingData.pdf}, author = {Edward Gilbert} } @article {729, title = {The use of specimen label images for efficient data acquisition in research collections cataloguing: Workflow}, year = {2006}, keywords = {WorkFlows}, url = {http://tdwg2006.tdwg.org/fileadmin/2006meeting/slides/GranzowCerda_ImagesM\%C3\%A9xMichCatalog_abs0098.pdf}, author = {Ingio Granzow-de la Cerda and Juan Carols Gomez-Martinez and Jose Luis Garcia-Castillo} } @conference {2529, title = {Using herbarium data for niche modeling to study phylogenetic diversity and endemism of Florida plants}, booktitle = {Botanical Society of America 2015}, year = {2015}, month = {07/2015}, address = {Edmonton, Alberta, Canada}, abstract = {The effort to digitize all biological collections in the USA is quickly leading to an online dataset of over one billion specimens, available for addressing questions at unprecedented scales. Florida hosts several biodiversity hotspots and is home to over 4,100 species of plants. Using herbarium collections, we took advantage of the historical data linked with the specimens and constructed a pipeline that extracts environmental variables at the time of the collection for each of over 1,500 species. Using this temporally fine-scale information, we built niche models for those species. In parallel, we sequenced two genes for those same species and constructed a dated ultrametric tree and a non-ultrametric tree. We combined the niche models with both phylogenies to examine patterns of phylogenetic diversity (PD) and endemism (PE) across Florida and applied a randomization test to find significant centers of paleo- and neo-endemism using Categorical Analysis of Neo- And Paleo-Endemism (CANAPE). We then examined the effect of phylogenetic uncertainty on these methods by randomly selecting 100 trees from the posterior distribution of both the ultrametric tree and the non-ultrametric tree and recalculating the phylogenetic diversity metrics. We visualize the spatial component of phylogenetic uncertainty and discuss how to take it into account. We also compared the results obtained using the ultrametric tree versus the non-ultrametric tree. PD measured on the dated ultrametric tree reflects the amount of evolutionary history in a location, while PD measured on the non-ultrametric tree reflects the amount of feature diversity in a location. We will discuss how each of these metrics shows a unique pattern and identifies different features of Florida{\textquoteright}s phylogenetic landscape. Lastly, we examined phylogenetic beta diversity among identified centers of significantly high PE and show how this measure can be used for applied conservation purposes.}, keywords = {BSA2015}, url = {http://2015.botanyconference.org/engine/search/index.php?func=detail\&aid=855}, author = {Germain-Aubrey, Charlotte C. and Allen, Julie M. and Neubig, Kurt M. and Laffan, S. and Guralnick, Robert P. and Lamy, Thomas and Majure, Lucas and Mischler, Brent D. and Soltis, Douglas E. and Ponciano, Jose Miguel and Richard J. Abbott and Soltis, Pamela S.} } @article {2527, title = {Using museum collections to improve biodiversity measures: the Florida Plants Diversity project}, year = {2016}, abstract = {Invited speaker, Middle Tennessee State University, March, 2016}, author = {Germain-Aubrey, Charlotte C. and Allen, Julie M. and Neubig, Kurt M. and Guralnick, Robert P. and Ponciano, Jose Miguel and Lamy, Thomas and Soltis, Douglas E. and Majure, Lucas and Soltis, Pamela S.} } @conference {2530, title = {Using museum data for large-scale questions: modeling Florida plant diversity}, booktitle = {Society for the Preservation of Natural History Collections 30th Annual Meeting}, year = {2015}, month = {05/2015}, address = {Gainesville, FL}, abstract = {The effort to digitize all biological collections in the USA is quickly leading to an online dataset of over one billion specimens, available for addressing questions at unprecedented scales. Florida hosts several biodiversity hotspots and is home to over 4,100 species of plants. Using herbarium collections, we took advantage of the historical data linked with the specimens and constructed a pipeline that extracts environmental variables at the time of the collection for each of 1,550 species. We used the collections to reconstruct niche models and project the effect of climate change on the Florida vegetation landscape. Moreover, we reconstructed the regional phylogeny for those species for which we built models, investigating similar questions through the lens of the evolutionary history of the region. This study emphasizes the importance of museum collections for research. We will discuss several steps and assumptions made in order to use as much of the data as possible. Through our experience, we will recommend concrete actions that collectors, collection managers, and researchers can take to facilitate the use of museum specimens by the maximum number of scientists and non-scientists.}, keywords = {SPNHC2015}, url = {https://www.flmnh.ufl.edu/files/7414/3171/6051/SPNHCProgramforWeb.pdf}, author = {Germain-Aubrey, Charlotte C. and Allen, Julie M. and Guralnick, Robert P. and Neubig, Kurt M. and Ponciano, Jose Miguel and Lamy, Thomas and Majure, Lucas and Soltis, Douglas E. and Soltis, Pamela S.} } @conference {2419, title = {Using museum data for niche modeling and phylogenetic diversity of Florida plants}, booktitle = {Ecological Society of America 2015}, year = {2015}, keywords = {EF-1115210, ESA2015, IGN 8-3, Presentation}, author = {Germain-Aubrey, Charlotte C. and Allen, Julie M. and Neubig, Kurt M. and Guralnick, Robert P. and Ponciano, Jose Miguel and Lamy, Thomas and Soltis, Douglas E. and Majure, Lucas and Soltis, Pamela S.} } @article {732, title = {VertNet: A New Model for Biodiversity Data Sharing (The VertNet Steering Committee)}, journal = {PLoS Biology}, volume = {8}, year = {2010}, keywords = {Mobilization}, url = {http://www.plosbiology.org/article/fetchObjectAttachment.action?uri=info\%3Adoi\%2F10.1371\%2Fjournal.pbio.1000309\&representation=PDF}, author = {Heather Constable and Robert Guralnick and John Wieczorek and Carol Spencer and A. Townsend Peterson} } @conference {2423, title = {WeDigBio: Worldwilde Engagement for the Digitization of Biocollections}, booktitle = {SPNHC 2015}, year = {2015}, keywords = {EF-1115210, Presentation, SPNHC2015}, author = {Kimberly, Paul G. and Flemons, Paul K.J. and Guralnick, Robert P. and Mast, Austin R. and Ellwood, Elizabeth R. and Paul, Deborah L. and Love, Kevin J.} } @article {1827, title = {What do you do when your Network Manager tells you there is no more space and they mean it?}, year = {2014}, keywords = {TDWG 2014}, url = {http://idigbio.adobeconnect.com/p6l6xceheha/}, author = {Sharon Grant and Kate Webbink and Marc Lambruschi and Mike Yoshida} } @article {1850, title = {What do you do when your Network Manager tells you there is no more space and they mean it?}, year = {2014}, keywords = {TDWG 2014}, url = {http://www.tdwg.org/fileadmin/2014conference/slides/Grant_DigTools_WhatDoYouDoWhen.pptx}, author = {Sharon Grant and Kate Webbink and Mike Yoshida and Marc Lambruschi} } @article {1540, title = {What does Antarctica really look like?}, year = {2013}, keywords = {iDigBio Georeferencing Workshop Group (GWG), iDigBio GWG TTT 2}, url = {https://www.idigbio.org/sites/default/files/workshop-presentations/ttt2/idigbio_polar_projections.ppt}, author = {Sharon Grant} } @article {1996, title = {Workflows: Perspectives from Peabody Entomology}, year = {2015}, keywords = {Digitizing Dried Insects Digitization Workshop}, url = {https://www.idigbio.org/wiki/images/0/09/LFG-idigbio-1-short.pdf}, author = {Larry Gall} } @conference {2425, title = {The Worldwide Engagement for Digitization of Biocollections (WeDigBio) Event}, booktitle = {Botanical Society of America 2015}, year = {2015}, keywords = {BSA2015, EF-1115210, Presentation}, author = {Mast, Austin R. and Kimberly, Paul and Flemons, Paul and Ellwood, Elizabeth and Love, Kevin and Paul, Deborah and Guralnick, Robert} } @conference {2515, title = {Worldwide Engagement for Digitizing Biocollections 2016: a call to the AsiaPacific region to participate in the WeDigBio Global Transcription Event!}, booktitle = {23rd Pacific Science Congress}, year = {2016}, month = {06/2016}, address = {Taipei, Taiwan}, abstract = {During its inaugural year, the Worldwide Engagement for Digitizing Biocollections Event, WeDigBio 2015, involved thousands of citizen scientists from >50 countries in transcribing biodiversity specimen labels from a variety of taxonomic groups over four days. Participants at onsite events at museums, universities, and science classrooms, as well as those distributed individually throughout the world, used online platforms at DigiVol, Les Herbonautes, Notes from Nature, Smithsonian Institution{\textquoteright}s Transcription Center, and Symbiota to transcribe almost 30,000 specimen labels. During the event, participants learned about collections and biodiversity, interacted with researchers, played games, shared experiences via social media, and contributed to the growing database of digital biocollections information. In 2016, WeDigBio is aiming to double the number of onsite events, online participants, and completed transcriptions, and we encourage biodiversity institutions and citizen scientists within the Asia-Pacific region to take part in activities. Resources are being developed to help make the event even more fun, educational, and productive, such as: improvements to the dynamic dashboard at wedigbio.org (http://wedigbio.org/) and enhanced interoperability with transcription platforms, lesson plans for teachers, activities for participants at transcription events, and opportunities to interact with transcribers across events. Certain platforms, such as DigiVol.org, can host images of specimens from collections in the Asia-Pacific region needing assistance with transcription. WeDigBio 2016 can be a way to increase the visibility of your biological collection, engage with local citizen scientists, and expedite digitization, all while being a part of a well publicized global event. Consider being one of the many online participants helping to mobilize biodiversity collections data, or hosting a WeDigBio event at your collection, university, or classroom from October 2023, 2016. Learn more at wedigbio.org (http://wedigbio.org/). }, keywords = {poster, WeDigBio}, url = {http://www.idigbio.org/sites/default/files/sites/default/files/WeDigBio_Poster_PSC__final.pdf}, author = {James, Shelley A. and Ellwood, Elizabeth R. and Kimberly, Paul G. and Guralnick, Robert P. and Flemons, Paul K.J. and Love, Kevin J. and Mast, Austin R.} } @conference {2521, title = {Worldwide Engagement for Digitizing Biocollections 2016: a call to the Flora Malesiana community to participate in the WeDigBio Global Transcription Event!}, booktitle = {Flora Malesiana 10}, year = {2016}, month = {07/2016}, address = {Edinburgh, UK}, abstract = {During its inaugural year, Worldwide Engagement for Digitizing Biocollections, WeDigBio 2015, involved citizen scientists from >50 countries in transcribing biodiversity specimen labels from a variety of taxonomic groups over four days. Participants at onsite events at museums, universities, and science classrooms, along with individuals across the globe, used online platforms at DigiVol, Les Herbonautes, Notes from Nature, Smithsonian Institution{\textquoteright}s Transcription Center, and Symbiota to transcribe almost 30,000 specimen labels. Participants learned about collections and biodiversity, interacted with researchers, played games, shared experiences via social media, and contributed to the growing database of digital biocollections information. WeDigBio 2016 is aiming to double the number of onsite events, online participants, and completed transcriptions, and we encourage herbaria and citizen scientists of the Flora Malesiana community to take part in activities. Resources are being developed to help make the event even more fun, educational, and productive, such as: improvements to the dynamic dashboard at wedigbio.org, enhanced interoperability with transcription platforms, lesson plans for teachers, activities for participants at transcription events, and interaction between transcribers across events. Certain platforms, such as DigiVol.org, can host images of specimens collections from the Malesian region needing transcription. WeDigBio 2016 can be a way to increase the visibility of your herbarium, engage with local citizen scientists, and expedite digitization of botanical specimens, while being a part of a well-publicized global event. Consider being one of the many online participants helping to mobilize biodiversity collections data, or hosting a WeDigBio event from October 20-23, 2016. Learn more at wedigbio.org. }, keywords = {poster}, url = {https://www.idigbio.org/sites/default/files/poster-files/WeDigBio_Poster_FlMal_small.pdf}, author = {Ellwood, Elizabeth R. and James, Shelley A. and Kimberly, Paul G. and Guralnick, Robert P. and Flemons, Paul K.J. and Love, Kevin J. and Mast, Austin R.} } @article {1839, title = { ZooSphere - Development of a software for automated spheric image capturing and interactive 3D visualization of biological collection objects. }, year = {2014}, keywords = {TDWG 2014}, url = {http://idigbio.adobeconnect.com/p6conw2y8su/}, author = {Martin Pluta and Falko Gl{\"o}ckler and Alexander Kroupa and Bernhard Schurian} } @article {1845, title = {ZooSphere - Development of a software for automated spheric image capturing and interactive 3D visualization of biological collection objects. }, year = {2014}, keywords = {TDWG 2014}, url = {http://www.tdwg.org/fileadmin/2014conference/slides/Pluta__ZooSphere.pdf}, author = {Martin Pluta and Alexander Kroupa and Bernhard Schurian and Falko Gl{\"o}ckler} }