Personalized Action Rules for Side Effects Object Grouping - International Journal of Intelligence Science

IJIS > Vol.3 No.1, March 2013

Personalized Action Rules for Side Effects Object Grouping ()

HTML XML

Download as PDF (Size: 303KB) PP. 24-33

DOI: 10.4236/ijis.2013.31A004 5,028 Downloads 7,659 Views Citations

Author(s)

Hakim Touati, Jieyan Kuang, Ayman Hajja, Zbigniew W. Ras

Affiliation(s)

College of Computing and Informatics, University of North Carolina, Charlotte, USA.
Institute of Computer Science, Warsaw University of Technology, Warsaw, Poland.

ABSTRACT

There have been multiple techniques to discover action-rules, but the problem of triggering those rules was left exclusively to domain knowledge and domain experts. When meta-actions are applied on objects to trigger a specific rule, they might as well trigger transitions outside of the target action rule scope. Those additional transitions are called side effects, which could be positive or negative. Negative side effects could be devastating in some domains such as healthcare. In this paper, we strive to reduce those negative side effects by extracting personalized action rules. We proposed three object-grouping schemes with regards to same negative side effects to extract personalized action rules for each object group. We also studied the tinnitus handicap inventory data to apply and compare the three grouping schemes.

KEYWORDS

Meta-Actions; Action-Rules; Personalization; Optimization; Grouping

Share and Cite:

H. Touati, J. Kuang, A. Hajja and Z. Ras, "Personalized Action Rules for Side Effects Object Grouping," International Journal of Intelligence Science, Vol. 3 No. 1A, 2013, pp. 24-33. doi: 10.4236/ijis.2013.31A004.

Journals Menu

Follow SCIRP

	+1 323-425-8868
	customer@scirp.org
	+86 18163351462(WhatsApp)
	1655362766

	Paper Publishing WeChat

Journals Menu

Home

About SCIRP

Service

Policies