Fernando Farfán
Postdoctoral Research Fellow | CSE | University of Michigan
Research Interests
My current research interests include:
- Genetic Data Integration: Integration of known genetic information, as found in databases, to perform a more effective analysis of gene expression data from micro-array experiments.
- Domain-specific Data Management: How to use domain knowledge and domain information to improve the management of data, as well of the information discovery experience.
- Information Retrieval on Semistructured Documents: Efficient algorithms to search XML documents, and to evaluate the results.
- Storage and Processing of Semistructured Data: How to efficiently store and parse XML documents.
Projects
-
THINK Back: KNowledge-based Interpretation of High Throughput data.
http://www.eecs.umich.edu/db/think/
This project uses computational techniques to glean biological knowledge from the literature and from public databases to address this challenge.
-
PatentsSearcher
http://www.patentssearcher.com/
This search engine for patent documents exploits domain semantics to improve the quality of discovery and ranking. PatentsSearcher also offers other novel functionalities to help users locate and navigate relevant and important patents or applications.
Recent Publications
List of recent publications:
Journal Papers
-
THINK Back: KNowledge-based Interpretation of High Throughput data
F. Farfán, J. Ma, M.A. Sartor, G. Michailidis, H.V. Jagadish.
BMC Bioinformatics 2012, 13(Suppl 2):S4 - Proceedings of the Great Lakes Bioinformatics Conference GLBIO 2011 -
Storing Semi-structured Data on Disk Drives.
M. Bhadkamkar, F. Farfán, V. Hristidis, and R. Rangaswami.
ACM Transactions on Storage, Vol. 5, Issue # 2, May, 2009. -
2LP: A double-lazy XML parser.
Fernando Farfán, Vagelis Hristidis and Raju Rangaswami.
Elsevier Information Systems 34 (2009), pp. 145-163.
Book Chapters
INFORMATION DISCOVERY ON ELECTRONIC MEDICAL RECORDS
Chapman & Hall/CRC Data Mining and Knowledge Discovery Series, 2009
Editor: Vagelis Hristidis
Chapters co-authored:
- Overview of XML. - Fernando Farfán, Vagelis Hristidis.
- Electronic Health Records. - Fernando Farfán, Ramakrishna Varadarajan, Vagelis Hristidis.
- Searching Electronic Health Records. - Vagelis Hristidis, Ramakrishna Varadarajan, Fernando Farfán.
NEXT GENERATION OF DATA MINING
Chapman & Hall/CRC Data Mining and Knowledge Discovery Series, 2008.
Editors: Hillol Kargupta, Jiawei Han, Philip Yu, Rajeev Motwani, Vipin Kumar
Chapter co-authored:
- Challenges for Information Discovery on Electronic Medical Records. - Vagelis Hristidis, Fernando Farfán, Redmond P. Burke, Anthony F. Rossi, Jeffrey A. White.
Conference Papers
- PatentsSearcher: A Novel Portal to Search and Explore Patents.
Vagelis Hristidis, Eduardo Ruiz, Alejandro Hernández, Fernando Farfán, Ramakrishna Varadarajan
3rd International Workshop on Patent Information Retrieval PaIR 2010, at ACM CIKM 2010. - XOntoRank: Ontology-Aware Search of Electronic Medical Records
Fernando Farfán, Vagelis Hristidis, Anand Ranganathan, and Michael Weiner MD
Proceedings of the IEEE International Conference on Data Engineering, ICDE 2009.
Shanghai, China. March-April 2009 (Acceptance Rate: 17%). - Information Discovery on Electronic
Medical Records.
Vagelis Hristidis, Fernando Farfán, Redmond P. Burke, Anthony F. Rossi and Jeffrey A. White.
National Science Foundation Symposium on Next Generation of Data Mining and Cyber-Enabled Discovery for Innovation, NGDM 2007.
Baltimore, Maryland. October 2007 (Acceptance Rate: 28%). - Beyond Lazy XML Parsing.
Fernando Farfán, Vagelis Hristidis and Raju Rangaswami.
18th International Conference on Database and Expert System Applications, DEXA 2007.
Regensburg, Germany. September 2007 (Acceptance Rate: 32%).
Posters/Short Papers
- Ontology-Aware Search on XML-based Electronic Medical Records.
Fernando Farfán, Vagelis Hristidis, Anand Ranganathan, and Redmond P. Burke.
Proceedings of the IEEE International Conference on Data Engineering 2008 (acceptance rate 31%)
- Storing Trees on Disk Drives.
Medha Bhadkamkar, Fernando Farfán, Vagelis Hristidis, and Raju Rangaswami.
Proceedings of the File and Storage Technologies WiP, 2005.
Technical Reports
- Efficient Native Storage Systems for Semistructured Data.
Medha Bhadkamkar, Fernando Farfán, Vagelis Hristidis and Raju Rangaswami.
Florida International University Technical Report TR-2006-09-01. September 2006.