Abstract
The article discusses the possibilities of implementing a system for data mining (DM), which integrates Case-Based Reasoning (CBR) and artificial neural network (ANN). Currently, CBR-methods are widely used to solve various DM problems based on the accumulated experience and the ANN is used as an approximator for solving various applied problems. For ANN, an important condition for the success of solving the DM problem is the quality (correctness) of the training dataset. However, this condition is not always feasible, as well as the small size of the training set.
To improve the efficiency of the ANN functioning in a small training set, it is proposed to apply and adapt the existing experience using CBR-methods that can be used to generate a training dataset of sufficient size. Thus, the integration of CBR-methods and the ANN approach allows to increase the efficiency of the DM, because the generated set will include the most meaningful data for training the ANN.
The paper proposes the CBR-based algorithm for learning ANN (CBR-BackProp), which provides for automatic correction of the learning rate parameter, based on the learning iterations in the form of precedents. This algorithm is a part of ANN module that extends the capabilities of a CBR-system implemented in Python using the Flask web framework and the TensorFlow library. To evaluate the effectiveness of the solutions proposed in the work, computational experiments were performed on real data sets.
This work was supported by RFBR projects №. 18-29-03088,№. 20-07-00498, №. 20-57-00015.
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
Similar content being viewed by others
References
Varshavskiy, P.R., Alekhin, R.V., Kozhevnikov, A.V.: Development of the case-based reasoning module for identification of acoustic-emission monitoring signals of complex technical objects. Softw. Syst. 32(2), 207–213 (2019). (in Russian). https://doi.org/10.15827/0236-235X.126.207-213
Varshavskiy, P.R., Barat, V.A., Kozhevnikov, A.V.: The case-based reasoning module for identification of acoustic-emission monitoring signals of complex technical objects. Bull. MPEI (4), 122–128 (2020). (in Russian)
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Ciresan, D.C., Meier, U., Masci, J., Luca, M.J., Schmidhuber, J.: Flexible, high performance convolutional neural networks for image classification. In: Proceedings of IJCAI, pp. 1237–1242 (2011)
Mrazova, I., Kukacka, M.: Can deep neural networks discover meaningful pattern features? Proc. Comput. Sci. 12, 194–199 (2012). https://doi.org/10.1016/j.procs.2012.09.053
Bogachev, I.V., Levenets, A.V., Chy, E.U.: Artificial neural networks in classifying telemetry data for compression systems. Inf. Control Syst. 3, 2–7 (2016). (in Russian). https://doi.org/10.15217/issn1684-8853.2016.3.2
Du, K.-L.: Clustering: a neural network approach. Neural Netw. 23, 89–107 (2010). https://doi.org/10.1016/j.neunet.2009.08.007
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning, p. 800. MIT Press, Cambridge (2016)
Eremeev, A.P., Varshavkiy, P.R., Kurilenko, I.E.: Modelling the time-dependent in intellectual systems of decision making support on the basis of precedents. Int. J. Inf. Technol. Knowl. 6(3), 227–239 (2012). (in Russian)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach (2011). 937 p. https://doi.org/10.1016/j.artint.2011.01.005 (Russ. ed., Moscow (2006), 1408 p.) (2006)
Varshavskii, P., Alekhin, R., Polyakov, S., Blashonkov, T., Mukhacheva, I.: Development of a modular case-based reasoning system for data analysis. In: International Youth Conference on Radio Electronics, Electrical and Power Engineering, 12–14 March 2020. IEEE (2020)
Beazley, D., Jones, B.K.: Python Cookbook, 3rd edn. O’Reilly Media, Sebastopol (2013). 706 pp. ISBN 9781449340377
Grinberg, M.: Flask Web Development, 2nd edn. O’Reilly Media, Sebastopol (2018), 316 pp. ISBN 9781491991732
Aurélien, G.: Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd edn. O’Reilly Media (2019). 600 pp. ISBN 9781492032649
Bashlikov, A.A., Eremeev, A.P.: Methods and software tools for designing intelligent decision support systems for energy facilities. Bull. MPEI (1), 72–85 (2018). (in Russian)
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
Eremeev, A., Varshavskii, P., Kozhevnikov, A., Polyakov, S. (2022). Integrated Approach for Data Mining Based on Case-Based Reasoning and Neural Networks. In: Kovalev, S., Tarassov, V., Snasel, V., Sukhanov, A. (eds) Proceedings of the Fifth International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’21). IITI 2021. Lecture Notes in Networks and Systems, vol 330. Springer, Cham. https://doi.org/10.1007/978-3-030-87178-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-87178-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87177-2
Online ISBN: 978-3-030-87178-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)