A meta-learning approach to the regularized learning-case study: blood glucose prediction

V Naumova; S V Pereverzyev; S Sivananthan

doi:10.1016/j.neunet.2012.05.004

A meta-learning approach to the regularized learning-case study: blood glucose prediction

Neural Netw. 2012 Sep:33:181-93. doi: 10.1016/j.neunet.2012.05.004. Epub 2012 Jun 1.

Authors

V Naumova¹, S V Pereverzyev, S Sivananthan

Affiliation

¹ Johann Radon Institute for Computational and Applied Mathematics-RICAM, Austrian Academy of Sciences, A-4040 Linz, Austria. [email protected]

PMID: 22706092
DOI: 10.1016/j.neunet.2012.05.004

Abstract

In this paper we present a new scheme of a kernel-based regularization learning algorithm, in which the kernel and the regularization parameter are adaptively chosen on the base of previous experience with similar learning tasks. The construction of such a scheme is motivated by the problem of prediction of the blood glucose levels of diabetic patients. We describe how the proposed scheme can be used for this problem and report the results of the tests with real clinical data as well as comparing them with existing literature.

Publication types

Clinical Trial
Research Support, Non-U.S. Gov't

MeSH terms

Adolescent
Adult
Aged
Algorithms
Blood Glucose / metabolism*
Case-Control Studies
Diabetes Mellitus / blood*
Diabetes Mellitus / diagnosis*
Female
Humans
Learning* / physiology
Male
Middle Aged
Predictive Value of Tests
Young Adult

Substances

Blood Glucose