Online Support Vector Regression With Varying Parameters for Time-Dependent Data. Omitaomu, O. A., Jeong, M. K., & Badiru, A. B. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 41(1):191–197, January, 2011. Conference Name: IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humansdoi abstract bibtex 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 data sets arrive constantly and in which batch processing of the data sets is infeasible or expensive, an accurate online SVR (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 nonstationary, such as sensor data. As a result, we propose AOSVR with varying parameters 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 online 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 a nuclear power plant. The results show that using varying SVR parameters is more applicable to time-dependent data.
@article{omitaomu_online_2011,
title = {Online {Support} {Vector} {Regression} {With} {Varying} {Parameters} for {Time}-{Dependent} {Data}},
volume = {41},
issn = {1558-2426},
doi = {10.1109/TSMCA.2010.2055156},
abstract = {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 data sets arrive constantly and in which batch processing of the data sets is infeasible or expensive, an accurate online SVR (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 nonstationary, such as sensor data. As a result, we propose AOSVR with varying parameters 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 online 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 a nuclear power plant. The results show that using varying SVR parameters is more applicable to time-dependent data.},
number = {1},
journal = {IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans},
author = {Omitaomu, Olufemi A. and Jeong, Myong K. and Badiru, Adedeji B.},
month = jan,
year = {2011},
note = {Conference Name: IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans},
keywords = {Automobile manufacture, Condition monitoring, Data engineering, Machine learning, Manufacturing, Medical diagnostic imaging, Power generation, Sensor systems, Systems engineering and theory, Training data, inferential sensing, online prediction, support vector machine, system diagnosis},
pages = {191--197},
}
Downloads: 0
{"_id":"4shR4YbxLWF6QMGdJ","bibbaseid":"omitaomu-jeong-badiru-onlinesupportvectorregressionwithvaryingparametersfortimedependentdata-2011","author_short":["Omitaomu, O. A.","Jeong, M. K.","Badiru, A. B."],"bibdata":{"bibtype":"article","type":"article","title":"Online Support Vector Regression With Varying Parameters for Time-Dependent Data","volume":"41","issn":"1558-2426","doi":"10.1109/TSMCA.2010.2055156","abstract":"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 data sets arrive constantly and in which batch processing of the data sets is infeasible or expensive, an accurate online SVR (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 nonstationary, such as sensor data. As a result, we propose AOSVR with varying parameters 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 online 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 a nuclear power plant. The results show that using varying SVR parameters is more applicable to time-dependent data.","number":"1","journal":"IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans","author":[{"propositions":[],"lastnames":["Omitaomu"],"firstnames":["Olufemi","A."],"suffixes":[]},{"propositions":[],"lastnames":["Jeong"],"firstnames":["Myong","K."],"suffixes":[]},{"propositions":[],"lastnames":["Badiru"],"firstnames":["Adedeji","B."],"suffixes":[]}],"month":"January","year":"2011","note":"Conference Name: IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans","keywords":"Automobile manufacture, Condition monitoring, Data engineering, Machine learning, Manufacturing, Medical diagnostic imaging, Power generation, Sensor systems, Systems engineering and theory, Training data, inferential sensing, online prediction, support vector machine, system diagnosis","pages":"191–197","bibtex":"@article{omitaomu_online_2011,\n\ttitle = {Online {Support} {Vector} {Regression} {With} {Varying} {Parameters} for {Time}-{Dependent} {Data}},\n\tvolume = {41},\n\tissn = {1558-2426},\n\tdoi = {10.1109/TSMCA.2010.2055156},\n\tabstract = {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 data sets arrive constantly and in which batch processing of the data sets is infeasible or expensive, an accurate online SVR (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 nonstationary, such as sensor data. As a result, we propose AOSVR with varying parameters 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 online 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 a nuclear power plant. The results show that using varying SVR parameters is more applicable to time-dependent data.},\n\tnumber = {1},\n\tjournal = {IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans},\n\tauthor = {Omitaomu, Olufemi A. and Jeong, Myong K. and Badiru, Adedeji B.},\n\tmonth = jan,\n\tyear = {2011},\n\tnote = {Conference Name: IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans},\n\tkeywords = {Automobile manufacture, Condition monitoring, Data engineering, Machine learning, Manufacturing, Medical diagnostic imaging, Power generation, Sensor systems, Systems engineering and theory, Training data, inferential sensing, online prediction, support vector machine, system diagnosis},\n\tpages = {191--197},\n}\n\n","author_short":["Omitaomu, O. A.","Jeong, M. K.","Badiru, A. B."],"key":"omitaomu_online_2011","id":"omitaomu_online_2011","bibbaseid":"omitaomu-jeong-badiru-onlinesupportvectorregressionwithvaryingparametersfortimedependentdata-2011","role":"author","urls":{},"keyword":["Automobile manufacture","Condition monitoring","Data engineering","Machine learning","Manufacturing","Medical diagnostic imaging","Power generation","Sensor systems","Systems engineering and theory","Training data","inferential sensing","online prediction","support vector machine","system diagnosis"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["automobile manufacture","condition monitoring","data engineering","machine learning","manufacturing","medical diagnostic imaging","power generation","sensor systems","systems engineering and theory","training data","inferential sensing","online prediction","support vector machine","system diagnosis"],"search_terms":["online","support","vector","regression","varying","parameters","time","dependent","data","omitaomu","jeong","badiru"],"title":"Online Support Vector Regression With Varying Parameters for Time-Dependent Data","year":2011}