Affordable Access

Qualitative System Identification from Imperfect Data

Association for the Advancement of Artificial Intelligence
Publication Date
  • Biology
  • Mathematics


csk180808.dvi Journal of Artificial Intelligence Research 32 (2008) 825–877 Submitted 06/07; published 08/08 Qualitative System Identification from Imperfect Data George M. Coghill [email protected] School of Natural and Computing Sciences University of Aberdeen, Aberdeen, AB24 3UE. UK. Ashwin Srinivasan [email protected] IBM India Research Laboratory 4, Block C, Institutional Area Vasant Kunj Phase II, New Delhi 110070, India. and Department of CSE and Centre for Health Informatics University of New South Wales, Kensington Sydney, Australia. Ross D. King [email protected] Deptartment of Computer Science University of Wales, Aberystwyth, SY23 3DB. UK. Abstract Experience in the physical sciences suggests that the only realistic means of under- standing complex systems is through the use of mathematical models. Typically, this has come to mean the identification of quantitative models expressed as differential equations. Quantitative modelling works best when the structure of the model (i.e., the form of the equations) is known; and the primary concern is one of estimating the values of the param- eters in the model. For complex biological systems, the model-structure is rarely known and the modeler has to deal with both model-identification and parameter-estimation. In this paper we are concerned with providing automated assistance to the first of these prob- lems. Specifically, we examine the identification by machine of the structural relationships between experimentally observed variables. These relationship will be expressed in the form of qualitative abstractions of a quantitative model. Such qualitative models may not only provide clues to the precise quantitative model, but also assist in understand- ing the essence of that model. Our position in this paper is that background knowledge incorporating system modelling principles can be used to constrain effectively the set of good qualitative models. Utilising the model-identification framework provided by Induc- tive Logi

There are no comments yet on this publication. Be the first to share your thoughts.


Seen <100 times

More articles like this

Learning from imperfect data

on Applied Soft Computing Jan 01, 2007

Qualitative system identification: deriving struct...

on Artificial Intelligence Jan 01, 1996

Qualitative models and fuzzy systems: an integrate...

on Artificial Intelligence in Med... 1998
More articles like this..