TY - JOUR
T1 - Evolvable fuzzy systems from data streams with missing values
T2 - With application to temporal pattern recognition and cryptocurrency prediction
AU - Garcia, Cristiano
AU - Esmin, Ahmed
AU - Leite, Daniel
AU - Škrjanc, Igor
N1 - Funding Information:
This work was supported by the Serrapilheira Institute (grant number Serra-1812-26777 ). Igor Škrjanc is grateful to the Slovenian Research Agency - Program P2-0219: Modeling, Simulation and Control.
Funding Information:
This work was supported by the Serrapilheira Institute (grant number Serra-1812-26777). Igor ?krjanc is grateful to the Slovenian Research Agency - Program P2-0219: Modeling, Simulation and Control.
Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2019/12/1
Y1 - 2019/12/1
N2 - Data streams with missing values are common in real-world applications. This paper presents an evolving granular fuzzy-rule-based model for temporal pattern recognition and time series prediction in online nonstationary context, where values may be missing. The model has a modified rule structure that includes reduced-term consequent polynomials, and is supplied by an incremental learning algorithm that simultaneously impute missing data and update model parameters and structure. The evolving Fuzzy Granular Predictor (eFGP) handles single and multiple Missing At Random (MAR) and Missing Completely At Random (MCAR) values in nonstationary data streams. Experiments on cryptocurrency prediction show the usefulness, accuracy, processing speed, and eFGP robustness to missing values. Results were compared to those provided by fuzzy and neuro-fuzzy evolving modeling methods.
AB - Data streams with missing values are common in real-world applications. This paper presents an evolving granular fuzzy-rule-based model for temporal pattern recognition and time series prediction in online nonstationary context, where values may be missing. The model has a modified rule structure that includes reduced-term consequent polynomials, and is supplied by an incremental learning algorithm that simultaneously impute missing data and update model parameters and structure. The evolving Fuzzy Granular Predictor (eFGP) handles single and multiple Missing At Random (MAR) and Missing Completely At Random (MCAR) values in nonstationary data streams. Experiments on cryptocurrency prediction show the usefulness, accuracy, processing speed, and eFGP robustness to missing values. Results were compared to those provided by fuzzy and neuro-fuzzy evolving modeling methods.
KW - Fuzzy system
KW - Machine learning
KW - On-line algorithm
KW - Real-time system
KW - Temporal pattern recognition
UR - http://www.scopus.com/inward/record.url?scp=85072565735&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2019.09.012
DO - 10.1016/j.patrec.2019.09.012
M3 - Article
AN - SCOPUS:85072565735
SN - 0167-8655
VL - 128
SP - 278
EP - 282
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
ER -