TY - JOUR
T1 - Estudio empírico del enfoque asociativo en el contexto de los problemas de clasificación
AU - Sánchez, Laura Cleofas
AU - Briseño, Anabel Pineda
AU - Rosas, Rosa María Valdovinos
AU - Garreta, José Salvador Sánchez
AU - Jiménez, Vicente García
AU - Nieto, Oscar Camacho
AU - Meana, Héctor Pérez
AU - Miyatake, Mariko Nakano
N1 - Publisher Copyright:
© 2019 Instituto Politecnico Nacional. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Research carried out by the scientific community has shown that the performance of the classifiers depends not only on the learning rule, if not also on the complexities inherent in the data sets. Some traditional classifiers have been commonly used in the context of classification problems (three Neural Networks, C4.5, SVM, among others). However, the associative approach has been further explored in the recovery context, than in the classification task, and its performance almost has not been analyzed when several complexities in the data are presented. The present investigation analyzes the performance of the associative approach (CHA, CHAT and original Alpha Beta) when three classification problems occur (class imbalance, overlapping and atypical patterns). The results show that the CHAT algorithm recognizes the minority class better than the rest of the classifiers in the context of class imbalance. However, the CHA model ignores the minority class in most cases. In addition, the CHAT algorithm requires well-defined decision boundaries when Wilson's method is applied, because of its performance increases. Also, it was noted that when a balance between the rates is emphasized, the performance of the three classifiers increase (RB, RFBR and CHAT). The original Alfa Beta model shows poor performance when pre-processing the data is done. The performance of the classifiers increases significantly when the SMOTE method is applied, which does not occur without a pre-processing or with a subsampling, in the context of the imbalance of the classes.
AB - Research carried out by the scientific community has shown that the performance of the classifiers depends not only on the learning rule, if not also on the complexities inherent in the data sets. Some traditional classifiers have been commonly used in the context of classification problems (three Neural Networks, C4.5, SVM, among others). However, the associative approach has been further explored in the recovery context, than in the classification task, and its performance almost has not been analyzed when several complexities in the data are presented. The present investigation analyzes the performance of the associative approach (CHA, CHAT and original Alpha Beta) when three classification problems occur (class imbalance, overlapping and atypical patterns). The results show that the CHAT algorithm recognizes the minority class better than the rest of the classifiers in the context of class imbalance. However, the CHA model ignores the minority class in most cases. In addition, the CHAT algorithm requires well-defined decision boundaries when Wilson's method is applied, because of its performance increases. Also, it was noted that when a balance between the rates is emphasized, the performance of the three classifiers increase (RB, RFBR and CHAT). The original Alfa Beta model shows poor performance when pre-processing the data is done. The performance of the classifiers increases significantly when the SMOTE method is applied, which does not occur without a pre-processing or with a subsampling, in the context of the imbalance of the classes.
KW - C4.5
KW - Recovery
KW - SMOTE.
KW - SVM
KW - Wilson
KW - associative approach
KW - atypical patterns
KW - classification
KW - imbalance
KW - neural networks
KW - overlap
KW - selective
UR - http://www.scopus.com/inward/record.url?scp=85069726707&partnerID=8YFLogxK
U2 - 10.13053/CyS-23-2-3026
DO - 10.13053/CyS-23-2-3026
M3 - Artículo
AN - SCOPUS:85069726707
SN - 1405-5546
VL - 23
SP - 601
EP - 617
JO - Computacion y Sistemas
JF - Computacion y Sistemas
IS - 2
ER -