TY - JOUR
T1 - Fuzzy support vector machine for classification of time series data
T2 - A simulation study
AU - Sain, Hartayuni
AU - Kuswanto, Heri
AU - Purnami, Santi Wulan
AU - Rahayu, Santi Puteri
N1 - Publisher Copyright:
© 2023 by the authors; licensee Growing Science, Canada.
PY - 2023/6/1
Y1 - 2023/6/1
N2 - Support vector machine (SVM) has become one of most developed methods for classification, focusing on cross-sectional analysis. However, classification of time series data is an important issue in statistics and data mining. Classification of time series data using SVMs that focus on cross-sectional data leads to improper classification, and hence, the SVM needs to be extended for handling time series dataset. As with cross-section data, the problem of imbalanced data is also common in time series data. Fuzzy method has been proven to be capable of overcoming the case of imbalanced data. In this paper, we developed a Fuzzy Support Vector Machine (FSVM) model to classify time series data with imbalanced class. The proposed method puts the fuzzy membership function on the constraint function. Through simulation studies, this research aims to assess the performance of the developed FSVM in classifying time series data. Based on the classification accuracy criteria, we prove that the proposed FSVM method outperforms the standard SVM method for the classification of multiclass time series data.
AB - Support vector machine (SVM) has become one of most developed methods for classification, focusing on cross-sectional analysis. However, classification of time series data is an important issue in statistics and data mining. Classification of time series data using SVMs that focus on cross-sectional data leads to improper classification, and hence, the SVM needs to be extended for handling time series dataset. As with cross-section data, the problem of imbalanced data is also common in time series data. Fuzzy method has been proven to be capable of overcoming the case of imbalanced data. In this paper, we developed a Fuzzy Support Vector Machine (FSVM) model to classify time series data with imbalanced class. The proposed method puts the fuzzy membership function on the constraint function. Through simulation studies, this research aims to assess the performance of the developed FSVM in classifying time series data. Based on the classification accuracy criteria, we prove that the proposed FSVM method outperforms the standard SVM method for the classification of multiclass time series data.
KW - Classification of time series data
KW - FSVM
KW - Fuzzy
KW - Multiclass imbalanced
KW - Support Vector Machine
UR - http://www.scopus.com/inward/record.url?scp=85162054033&partnerID=8YFLogxK
U2 - 10.5267/j.dsl.2023.5.002
DO - 10.5267/j.dsl.2023.5.002
M3 - Article
AN - SCOPUS:85162054033
SN - 1929-5804
VL - 12
SP - 487
EP - 498
JO - Decision Science Letters
JF - Decision Science Letters
IS - 3
ER -