Naslov
Experiments with noise filtering in a medical domain

Autori
Gamberger, Dragan ; Lavrač, Nada ; Grošelj, Ciril

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proc. of International Conference of Machine Learning / - , 1999

Skup
Proc. of International Conference of Machine Learning, ICML'99

Mjesto i datum
Bled, Slovenija, 27.06.1999. - 30.06.1999

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
inductive learning; noise detection; outliers; target theory

Sažetak
The paper presents a series of noise detection experiments in a medical problem of coronary artery disease diagnosis. The following algorithms for noise detection and elimination are tested: a saturation filter, a classification filter, a combined classification-saturation filter, and a consensus saturation filter. The distinguishing feature of the novel consensus saturation filter is its high reliability which is due to the multiple detection of potentially noisy examples. Reliable detection of noisy examples is important for the analysis of patient records in medical databases, as well as for the induction of rules from filtered data, representing genuine characteristics of the diagnostic domain. Medical evaluation in the problem of coronary artery disease diagnosis shows that the detected noisy examples are indeed noisy or non-typical class representatives.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika

POVEZANOST RADA