Online Support Vector Regression with Varying Parameters for Time-Dependent Data

Journal Article · Sat Jan 01 04:00:00 EST 2011 · IEEE Transactions on Systems, Man and Cybernetics Part A: Systems and Humans

DOI:https://doi.org/10.1109/TSMCA.2010.2055156· OSTI ID:993446

Omitaomu, Olufemi A ^[1]; Jeong, Myong K ^[1]; Badiru, Adedeji B ^[1]

---

1. ORNL

Support vector regression (SVR) is a machine learning technique that continues to receive interest in several domains including manufacturing, engineering, and medicine. In order to extend its application to problems in which datasets arrive constantly and in which batch processing of the datasets is infeasible or expensive, an accurate online support vector regression (AOSVR) technique was proposed. The AOSVR technique efficiently updates a trained SVR function whenever a sample is added to or removed from the training set without retraining the entire training data. However, the AOSVR technique assumes that the new samples and the training samples are of the same characteristics; hence, the same value of SVR parameters is used for training and prediction. This assumption is not applicable to data samples that are inherently noisy and non-stationary such as sensor data. As a result, we propose Accurate On-line Support Vector Regression with Varying Parameters (AOSVR-VP) that uses varying SVR parameters rather than fixed SVR parameters, and hence accounts for the variability that may exist in the samples. To accomplish this objective, we also propose a generalized weight function to automatically update the weights of SVR parameters in on-line monitoring applications. The proposed function allows for lower and upper bounds for SVR parameters. We tested our proposed approach and compared results with the conventional AOSVR approach using two benchmark time series data and sensor data from nuclear power plant. The results show that using varying SVR parameters is more applicable to time dependent data.

• Research Organization: Oak Ridge National Laboratory (ORNL)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 993446
• Journal Information: IEEE Transactions on Systems, Man and Cybernetics Part A: Systems and Humans, Journal Name: IEEE Transactions on Systems, Man and Cybernetics Part A: Systems and Humans Journal Issue: 1 Vol. 41; ISSN 1083-4427; ISSN 1558-2426
• Country of Publication: United States
• Language: English

Related Subjects

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS
BENCHMARKS
FORECASTING
LEARNING
MANUFACTURING
MEDICINE
MONITORING
NUCLEAR POWER PLANTS
PROCESSING
Support vector regression
TRAINING
VECTORS
data mining
non-stationary data
on-line learning
time-dependent data