P
Paul Jen-Hwa Hu
Researcher at University of Utah
Publications - 142
Citations - 10658
Paul Jen-Hwa Hu is an academic researcher from University of Utah. The author has contributed to research in topics: Information system & Information technology. The author has an hindex of 37, co-authored 135 publications receiving 9589 citations. Previous affiliations of Paul Jen-Hwa Hu include University of South Florida.
Papers
More filters
Proceedings ArticleDOI
Introduction to the minitrack: databases, data warehousing, and data mining in health care
TL;DR: The first Databases, Data Warehousing and Data Mining in Health Care Minitrack was organized, which intended to serve as a presentation and discussion vehicle for sharing interesting recent research work among researchers and practitioners from both information systems and health care communities.
Journal ArticleDOI
Predicting hepatocellular carcinoma recurrences: A data-driven multiclass classification method incorporating latent variables.
Da Xu,Jessica Qiuhua Sheng,Paul Jen-Hwa Hu,Ting Shuo Huang,Ting Shuo Huang,Wei-Chen Lee,Wei-Chen Lee +6 more
TL;DR: A novel Bayesian network-based method to predict different HCC recurrence outcomes by considering the respective recurrence evolution paths is proposed, which consistently and significantly outperforms all the benchmark techniques in terms of accuracy, precision, recall, and F-measures.
Journal Article
A knowledge-based patient image prefetching system: design, evaluation and management.
Paul Jen-Hwa Hu,Wei Cp,Sheng Or +2 more
TL;DR: To address the problem of inadequate image prefetching methods used by many health care organizations, the design of IRES is described, its preliminary evaluation results are highlighted, and issues important for managing this and similar technologies in a health care organization are discussed.
Journal ArticleDOI
Use of a domain-specific ontology to support automated document categorization at the concept level: Method development and evaluation
TL;DR: This study takes a concept-based approach and proposes a text categorization method that incorporates a domain-specific ontology to support automated document categorization more effectively and achieves better performances when using a complete concept hierarchy without considering the hierarchical relationships among concepts.
Journal ArticleDOI
An ontology-based technique for preserving user preferences in document-category evolutions
TL;DR: An ontology-based category evolution (ONCE), a technique that first enriches a concept hierarchy by incorporating important concept descriptors and then employs the resulting enriched ontology to support category evolutions at a concept level rather than analyzing and comparing feature vectors at the lexicon level, is developed.