Naslov
Multi-Label Classifier Performance Evaluation with Confusion Matrix

Autori
Krstinić, Damir ; Braović, Maja ; Šerić, Ljiljana ; Božić-Štulić, Dunja

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

Izvornik
International Conference on Soft Computing, Artificial Intelligence and Machine Learning (SAIM 2020), June 27~28, 2020, Copenhagen, Denmark Volume Editors : David C. Wyld, Dhinaharan Nagamalai (Eds) ISBN : 978-1-925953-22-0 / David C. Wyld, Dhinaharan Nagamalai - Kopenhagen, 2020

ISBN
978-1-925953-22-0

Skup
International Conference on Soft Computing, Artificial Intelligence and Machine Learning (SAIM 2020)

Mjesto i datum
Kopenhagen, Danska, 27.06.2020. - 28.06.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Classification, Multi label classifier, Performance evaluation, Confusion matrix

Sažetak
Confusion matrix is a useful and comprehensive presentation of the classifier performance. It is commonly used in the evaluation of multi-class, single-label classification models, where each data instance can belong to just one class at any given point in time. However, the real world is rarely unambiguous and hard classification of data instance to a single class, i.e. defining its properties with single distinctive feature, is not always possible. For example, an image can contain multiple objects and regions which makes multi-class classification inappropriate to describe its content. Proposed solutions to this set of problems are based on multi-label classification model where each data instance is assigned one or more labels describing its features. While most of the evaluation measures used to evaluate singlelabel classifier can be adapted to a multi-label classification model, presentation and evaluation of the obtained results using standard confusion matrices cannot be expanded to this case. In this paper we propose a novel method for the computation of a confusion matrix for multi-label classification. The proposed algorithm overcomes the limitations of the existing approaches in modeling relations between the classifier output and the Ground Truth (i.e. hand-labeled) classification, and due to its versatility can be used in many different research fields.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA