شماره ركورد كنفرانس :
5263
عنوان مقاله :
A Relational Geometric Approach to Identify Insulin-glucose Dynamics
پديدآورندگان :
Jamshidi Arta Amir arta.jamshidi@ut.ac.ir School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran, Tehran, Iran. , Rokni Lamouki Gholam Reza rokni@ut.ac.ir College of Science, University of Tehran, Tehran, Iran.
كليدواژه :
Data Driven Modeling , Dynamical Systems , Diabetes
عنوان كنفرانس :
54 امين كنفرانس رياضي ايران
چكيده فارسي :
In this paper, we develop a data driven tool to identify the healthy/ unhealthy insulin-glucose dynamics. We do this by extracting the geometric properties of the limit cycles for each case. In this work we use the blood insulin-glucose measurements of $768$ diabetic patients. Our algorithm successfully finds two separate limit cycles which their sizes, locations and orientations separate healthy and unhealthy cases.
