Search

Your search keyword '"AN Cui-hong"' showing total 194 results
Start Over Author "AN Cui-hong" Publication Type Conference Materials
194 results on '"AN Cui-hong"'

3. MARTT: Using Induced Knowledge Base to Automatically Mark up Plant Taxonomic Descriptions with XML

Author

Cui, Hong and Grove, Andrew

Subjects
IB. Content analysis (A and I, class.), IE. Data and metadata structures., LP. Intelligent agents., IA. Cataloging, bibliographic control.
Abstract

Despite the sub-language nature of taxonomic descriptions of plants, researchers warned about the large variations among different collections of descriptions in terms of information contents and presentations. These variations impose a serious challenge to the development of automatic tools for the semantic markup of large volumes of freetext descriptions. This paper presents a new approach to automatic markup of multiple collections of taxonomic descriptions with XML. The effectiveness of the approach was demonstrated with markup experiments using three contemporary floras. The markup system, MARTT, was based on supervised machine learning algorithms and enhanced by machine learned association rules representing certain types of domain knowledge and conventions. Experiments showed that our simple and efficient markup algorithm outperformed popular general-purpose algorithms (including SVMs) across different floras. More importantly, the results demonstrated that the domain knowledge learned from one flora was useful for improving the markup performance on a second flora, especially on elements with sparse training examples. The system design and the evaluation of markup algorithms are reported in this paper. The study on the effectiveness of the induced knowledge base will be reported in a later paper. In this paper, common practices of flora authors and the potentials of MARTT system for improving the efficiency and effectiveness of the creation, organization, and utilization of plant descriptions are also discussed.

Published
2005

10. Automated Metadata Enhancement for Physical Sample Record Aggregation in the iSamples Project.

Author

Song, Hyunju, Cui, Hong, Vieglais, Dave, Mandel, Danny, and Thomer, Andrea K.

Subjects
INFORMATION science, TECHNOLOGICAL innovations, INFORMATION technology, ARTIFICIAL intelligence, DIGITAL technology
Abstract

Large amounts of samples have been collected and stored by different institutions and collections across the world. However, even the most carefully curated collections can appear incomplete when aggregated. To solve this problem and support the increasing multidisciplinary science conducted on these samples, we propose a method to support the FAIRness of the aggregation by augmenting the metadata of source records. Using a pipeline that is a combination of rule‐based and machine learning‐based procedures, we predict the missing values of the metadata fields of 4,388,514 samples. We use these inferred fields in our user interface to improve the reusability. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

18. Abstract A26: Characterization and development of a GPC2 ADC for neuroblastoma and other cancers

Author

Bosse, Kristopher R., primary, Raman, Swetha, additional, Buongervino, Samantha, additional, Lane, Maria, additional, Upton, Kristen, additional, Cui, Hong, additional, Martinez, Benjamin, additional, Martinez, Daniel, additional, Zhelev, Doncho V., additional, Pawel, Bruce, additional, Dimitrov, Dimiter S., additional, Julien, Jean-Philippe, additional, and Maris, John M., additional

Published
2020
Full Text
View/download PDF

23. Internet of Samples.

Author

Richard, Stephen M., Vieglais, Dave, Cui, Hong, Davies, Neil, Deck, John, Gan, Quan, Kansa, Eric C, Kansa, Sarah Whitcher, Kunze, John, Mandel, Danny, Meyer, Christopher, Orrell, Thomas, Ramdeen, Sarah, Snyder, Rebecca, Walls, Ramona L, Zhou, Yuxuan, and Lehnert, Kerstin

Subjects
INTERNET, NATURAL history, PROTOTYPES, SEMI-structured interviews, MATERIALS
Abstract

Material samples are indispensable data sources in many natural science, social science, and humanity disciplines. More and more researchers recognize that samples collected in one discipline can be of great value for another. This has motivated organizations that manage a large number of samples to make their holdings accessible to the world. Currently, multiple projects are working to connect natural history and other samples managed by individual institutions or individuals into a universe of samples that follow FAIR principles. This poster reports the progress of the US NSF‐funded iSamples project, in the context of other efforts initiated by US DOE, DiSCCo, BCoN, and GBIF. By October 2021, we will also be able to present an iSamples prototype. We encourage individual organizations that hold material samples to get to know these projects and help shape these projects to realize the goal of a global linked sample cloud that connects all material samples and is accessible to all. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

24. A Peek into the US Informal STEM Landscape through Theconnectory.org.

Author

Deimen, Sebastian, Cui, Hong, and Higgins, Michelle

Subjects
STEM education, LEARNING, DATA analysis, DATA analytics, EDUCATORS
Abstract

It's well‐known that informal STEM learning is a critical component of STEM education. However, there is not a comprehensive directory, at the state or national level, listing informal STEM programs offered in the US. This makes it difficult to assess the national landscape of informal STEM programs. Theconnectory.org is by far the most comprehensive listing that aims to connect learners and volunteers to informal STEM learning opportunities. In this poster, we present the results from a data analytics project using the informal STEM program information collected through theconnectory.org API to sketch a preliminary picture of what kind of programs are offered and what audiences are targeted. Theconnectory.org has the potential to become a primary resource for STEM learners, educators, and policymakers. There are ways the ASIST community (faculty and students) can help enrich this resource. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results