TY - JOUR
T1 - Subclass problem-dependent design for error-correcting output codes
AU - Escalera, Sergio
AU - Tax, David M.J.
AU - Pujol, Oriol
AU - Radeva, Petia
AU - Duin, Robert P.W.
N1 - Funding Information:
This research is/was supported in part by the projects TIN2006-15308-C02, FIS PI061290, Dutch Technology Foundation STW, Applied Science Division of NWO, and the technology program of the Dutch Ministry of Economic Affairs.
PY - 2008/6
Y1 - 2008/6
N2 - A common way to model multi-class classification problems is by means of Error-Correcting Output Codes (ECOC). Given a multi-class problem, the ECOC technique designs a codeword for each class, where each position of the code identifies the membership of the class for a given binary problem. A classification decision is obtained by assigning the label of the class with the closest code. One of the main requirements of the ECOC design is that the base classifier is capable of splitting each sub-group of classes from each binary problem. However, we can not guarantee that a linear classifier model convex regions. Furthermore, non-linear classifiers also fail to manage some type of surfaces. In this paper, we present a novel strategy to model multi-class classification problems using sub-class information in the ECOC framework. Complex problems are solved by splitting the original set of classes into sub-classes, and embedding the binary problems in a problem-dependent ECOC design. Experimental results show that the proposed splitting procedure yields a better performance when the class overlap or the distribution of the training objects conceil the decision boundaries for the base classifier. The results are even more significant when one has a sufficiently large training size.
AB - A common way to model multi-class classification problems is by means of Error-Correcting Output Codes (ECOC). Given a multi-class problem, the ECOC technique designs a codeword for each class, where each position of the code identifies the membership of the class for a given binary problem. A classification decision is obtained by assigning the label of the class with the closest code. One of the main requirements of the ECOC design is that the base classifier is capable of splitting each sub-group of classes from each binary problem. However, we can not guarantee that a linear classifier model convex regions. Furthermore, non-linear classifiers also fail to manage some type of surfaces. In this paper, we present a novel strategy to model multi-class classification problems using sub-class information in the ECOC framework. Complex problems are solved by splitting the original set of classes into sub-classes, and embedding the binary problems in a problem-dependent ECOC design. Experimental results show that the proposed splitting procedure yields a better performance when the class overlap or the distribution of the training objects conceil the decision boundaries for the base classifier. The results are even more significant when one has a sufficiently large training size.
KW - Embedding of dichotomizers
KW - Error-correcting output codes
KW - Multiclass classification
KW - Subclasses
UR - http://www.scopus.com/inward/record.url?scp=43249104670&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2008.38
DO - 10.1109/TPAMI.2008.38
M3 - Journal article
C2 - 18421109
AN - SCOPUS:43249104670
SN - 0162-8828
VL - 30
SP - 1041
EP - 1054
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 6
ER -