Abstract
In the data stream (DS) context, data is received at high speed, and it must be processed as soon as possible. Furthermore, it is not possible to guarantee that all data is labelled. Consequently, semi-supervised learning (SSL) becomes an efficient attempt to build an effective model in this context. Dynamic Data Stream Learning (DyDaSL) is a framework that uses a SSL algorithm to build a model able to classify instances in a data stream context. In this paper, an extension of the DyDaSL drift detection module is proposed. Its main aim is to make drift detection more flexible and, in turn, to improve the whole data stream process. An empirical analysis is conducted using real and synthetic datasets. The proposed approach achieved better results than the original one and some state-of-art drift detection methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chapelle, O., SchÖlkopf, B., Zien, A.: Semi-Supervised Learning. The MIT Press, Cambridge (2006)
Gollapudi, S.: Pratical Machine Learning. Packt Publishing Ltd., Livery Place (2016)
Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on concept drift adaptation. ACM Comput. Surv. 46(4), 44:1–44:37 (2014)
Gorgônio, A.C., de P. Canuto, A.M., Vale, K.M.O., Gorgônio, F.L.: A semi-supervised based framework for data stream classification in non-stationary environments. In: International Joint Conference on Neural Networks (2020)
Vale, K.M.O., et al.: Automatic adjustment of confidence values in self-training semi-supervised method. In: International Joint Conference on Neural Networks (2018)
Zhou, Z.-H.: Ensemble Methods, 1st edn. Chapman & Hall/CRC, New York (2012)
Gharroudi, O.: Ensemble Multi-label Learning in Supervised and Semi-supervised Settings. Université de Lyon, Theses (2017)
Kuncheva, L.I., Rodriguez, J.J.: Classifier ensembles with a random linear oracle. IEEE Trans. Knowl. Data Eng. 19(4), 500–508 (2007)
Khezri, S., Tanha, J., Ahmadi, A., Sharifi, A.: STDS: self-training data streams for mining limited labeled data in non-stationary environment. Appl. Intell. 50, 1448–1467 (2020)
Bi, X., Zhang, C., Zhao, X., Li, D., Sun, Y., Ma, Y.: Codes: efficient incremental semi-supervised classification over drifting and evolving social streams. IEEE Access 8, 14024–14035 (2020)
Zhang, S., Jung Huang, D.T., Dobbie, G., Koh, Y.S.: Sled: semi-supervised locally-weighted ensemble detector. In 2020 IEEE 36th International Conference on Data Engineering (ICDE), pp. 1838–1841. IEEE, Dallas, Texas (2020)
Tanha, J., Samadi, N., Abdi, Y., Razzaghi-Asl, N.: Cpssds: conformal prediction for semi-supervised classification on data streams. Inf. Sci. 584, 212–234 (2022)
Sebastião, R., Fernandes, J.M.: Supporting the page-hinkley test with empirical mode decomposition for change detection. In: Kryszkiewicz, M., Appice, A., Ślȩzak, D., Rybinski, H., Skowron, A., Raś, Z.W. (eds.) Foundations of Intelligent Systems, LNAI, vol. 10352, pp. 492–498. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60438-1_48
Page, E.S.: Continuous inspection schemes. Biometrika 41(1/2), 100–115 (1954)
Bifet, A., Holmes, G., Kirkby, R., Pfahringer, B.: MOA: massive online analysis. J. Mach. Learn. Res. 11, 1601–1604 (2010)
Dimitoglou, G., Adams, J.A., Jim, C.M.: Comparison of the c4.5 and a naive bayes classifier for the prediction of lung cancer survivability. J. Comput. 4(8) (2012)
Breiman, L., Friedman, J., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. CHAPMAN & HALL/CRC, New York (1984)
Cohen, W.W.: Fast effective rule induction. In: Machine Learning, ML95, pp. 115–123. Morgan Kaufmann Publishers, Tahoe City, California, USA, (1995)
Atkeson, C.G., Moore, A.W., Schaau, S.: Locally weighted learning. Artific. Intell. Rev. 11(1), 11–73 (1997)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. ACM SIGKDD Explor. Newsletter 11(1):10–18 (2009)
Olson, R.S., La Cava, W., Orzechowski, P., Urbanowicz, R.J., Moore, J.H.: Pmlb: a large benchmark suite for machine learning evaluation and comparison. BioData Mining 10(1), 36 (2017)
Acknowledgment
This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gorgônio, A.C., Barreto, C.A.d.S., da Costa, S.J.M.S., Canuto, A.M.d.P., Vale, K.M.O., Gorgônio, F.L. (2022). An Efficient Drift Detection Module for Semi-supervised Data Classification in Non-stationary Environments. In: Xavier-Junior, J.C., Rios, R.A. (eds) Intelligent Systems. BRACIS 2022. Lecture Notes in Computer Science(), vol 13653. Springer, Cham. https://doi.org/10.1007/978-3-031-21686-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-21686-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21685-5
Online ISBN: 978-3-031-21686-2
eBook Packages: Computer ScienceComputer Science (R0)