Abstract
In many real word applications of neural networks and other machine learning approaches, large experimental datasets are available, containing a huge number of variables, whose effect on the considered system or phenomenon is not completely known or not deeply understood. Variable selection procedures identify a small subset from original feature space in order to point out the input variables, which mainly affect the considered target. The identification of such variables leads to very important advantages, such as lower complexity of the model and of the learning algorithm, savings of computational time and improved performance. Moreover, variable selection procedures can help to acquire a deeper knowledge of the considered problem, system or phenomenon by identifying the factors which mostly affect it. This concept is strictly linked to the crucial aspect of the stability of the variable selection, defined as the sensitivity of a machine learning model with respect to variations in the dataset that is exploited in its training phase. In the present review, different categories of variable section procedures are presented and discussed, in order to highlight strengths and weaknesses of each method in relation to the different tasks and to the variables of the considered dataset.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ali, S., Smith, K.: On learning algorithm selection for classification. Appl. Soft Comput. 6(2), 119–138 (2006)
Brazdil, P., Carrier, C., Soares, C., Vilalta, R.: Metalearning: Applications to Data Mining. Springer, Heidelberg (2008)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Wadsworth and Brooks, Belmont (1984)
Brodley, C.E.: Addressing the selective superiority problem: automatic algorithm/model class selection. In: Proceedings of 10th International Conference on Machine Learning, pp. 17–24 (1993)
Cam, L.L.: Maximum likelihood an introduction. ISI Rev. 58(2), 153–171 (1990)
Cateni, S., Colla, V.: The importance of variable selection for neuralnetworks-based classification in an industrial context. In: Advances in Neural Networks (Computational Intelligence for ICT). Smart Innovation, Systems and Technologies (2016)
Cateni, S., Colla, V.: Improving the stability of wrapper variable selection applied to binary classification. Int. J. Comput. Inf. Syst. Ind. Manage. Appl. (2016) (in press)
Cateni, S., Colla, V.: A hybrid variable selection approach for nn-based classification in industrial context. In: Smart Innovation, Systems and Technologies (in press)
Cateni, S., Colla, V., Vannucci, M.: General purpose input vvariable extraction: a genetic algorithm based procedure give a gap. In: Proceedings of the 9th International Conference on Intelligence Systems design and Applications ISDA09 (2009)
Cateni, S., Colla, V., Vannucci, M.: Variable selection through genetic algorithms for classification purpose. In: IASTED International Conference on Artificial Intelligence and Applications (2010)
Cateni, S., Colla, V., Vannucci, M.: A genetic algorithm-based approach for selecting input variables and setting relevant network parameters of a som-based classifier. Int. J. Simul. Syst. Sci. Technol. 12(2), 30–37 (2011)
Cateni, S., Colla, V., Vannucci, M.: A hybrid feature selection method for classification purposes. In: 8th European Modeling Symposium on Mathematical Modeling and Computer simulation EMS2014, Pisa, Italy, vol. 1, pp. 1–8 (2014)
Cateni, S., Colla, V., Vannucci, M.: A fuzzy system for combining filter features selection methods. Int. J. Fuzzy Syst. (In press)
Cateni, S., Colla, V., Vannucci, M.: A genetic algorithms-based approach for selecting the most relevant input variables in classification tasks. In: Proceedings of the 4th European Modelling Symposium on Mathematical Modelling and Computer simulation EMS2010, Pisa, pp. 63–67, 17–19 November 2010
Cateni, S., Colla, V., Vannucci, M., Vannocci, M.: A procedure for building reduced reliable training datasets from real-world data. In: 13th IASTED International Conference on Artificial Intelligence and Applications AIA 2014, Innsbruck, Austria, 17–19 Febbraio 2014
Coetzee, F.: Correcting the kullback-leibler distance for feature selection. Pattern Recogn. Lett. 26(11), 1675–1683 (2005)
Colla, V., Nastasi, G., Cateni, S., Vannucci, M., Vannocci, M.: Genetic algorithms applied to discrete distribution fitting. In: Proceedings - UKSim-AMSS 7th European Modelling Symposium on Computer Modelling and Simulation, EMS 2013, pp. 30–35 (2013)
Colla, V., Nastasi, G., Materese, N.: Gadf - genetic algorithms for distribution fitting. In: Proceedings of the 2010 10th International Conference on Intelligent Systems Design and Applications, ISDA 2010, pp. 6–11 (2010)
Colla, V., Valentini, R., Bioli, G.: Mechanical properties prediction for aluminium-killed and interstitial-free steels, Revue de Métalurgie Special Issue JSI, pp. 100–101, Dicembre 2004
Colla, V., Vannucci, M., Fera, S., Valentini, R.: Ca-treatment of al-killed steels: inclusion modification and application of artificial neural networks for the prediction of clogging. In: Proceedings of 5th European Oxygen Steelmaking Conference EOSC 2006, vol. 1, pp. 387–394, 26–28 June 2006
Colla, V., Vannucci, M., Reyneri, L.: Artificial neural networks applied for estimating a probability density function. Intell. Data Anal. 19(1), 29–41 (2014)
Cover, T., Thomas, A.: Elements of Information Theory. Telecommunications and Signal Processing. Wiley Series, Hoboken (1991)
Duda, R., Hart, P., Stork, D.: Pattern Classification. Wiley, New York (2001)
Eid, H., Hassanien, A., Kim, T.H., Banerjee, S.: Linear correlation-based feature selection for network intrusion detection model. Commun. Comput. Inf. Sci. 381, 240–248 (2013)
Epanechnikov, V.: Non-parametric estimation of a multivariate probability density. Theory Probab. Appl. 14, 239–250 (1969)
Fakhraei, S., Zadeh, H.S., Fotouhi, F.: Bias and stability of single variable classifiers for feature ranking and selection. Expert Syst. Appl. 14(15), 6945–6958 (2014)
Fiasché, M., Taisch, M.: On the use of quantum-inspired optimization techniques for training spiking neural networks: a new method proposed. Smart Innov. Syst. Technol. 37, 359–368 (2015)
Froelich, W., Wrobel, K., Porwik, P.: Diagnosing parkinson’s disease using the classification of speech signals. J. Med. Inform. Technol. 23, 187–194 (2014)
Ghumbre, S., Patil, C., Ghatol, A.: Heart disease diagnosis using support vector machine. In: International Conference on Computer Science and Information Technology, ICCSIT 2011, Pattaya (2011)
Golub, T., Slonim, D., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J., Coller, H., Loh, M., Downing, J., Caligiuri, M., Lander, C.B.E.: Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 286, 531–537 (1999)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Mach. Learn. 3, 1157–1182 (2003)
Hall, M.A.: Correlation-based feature selection for machine learning. Ph.D. thesis, The University of Waikato (1999)
Kalousis, A., Gama, J., Hilario, M.: On data and algorithms: understanding inductive performance. Mach. Learn. 54(3), 275–312 (2004)
Kalousis, A., Prados, J., Hilario, M.: Stability of feature selection algorithms. In: Proceedings of 5th IEEE International Conference on Data Mining, ICDM 2005, pp. 218–225 (2005)
Kalousis, A., Prados, J., Hilario, M.: Stability of feature selection algorithms: a study on high-dimensional spaces. Knowl. Inf. Syst. 12, 95–116 (2007)
Khashei, M., Eftekhari, S., Parvizian, J.: Diagnosing diabetes type ii using a soft intelligent binary classification model. Rev. Bioinform. Biometrics (RBB) 1, 9–23 (2012)
Koc, L., Carswell, A.D.: Network intrusion detection using a hnb binary classifier. In: 17th UKSIM-AMSS International Conference on Modelling and Simulation (2015)
Kohavi, R., John, G.: Wrappers for feature selection. Artif. Intell. 97, 273–324 (1997)
Kullback, S., Leibler, R.: On information and sufficiency. Ann. Math. Stat. 22, 79–86 (1951)
Loscalzo, S., Yu, L., Ding, C.: Consensus group stable feature selection. In: Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 1, pp. 567–575 (2009)
Mammone, N., Fiasché, M., Inuso, G., La Foresta, F., Morabito, C.F.C., Versaci, M.: Information theoretic learning for inverse problem resolution in bio-electromagnetism. In: Apolloni, B., Howlett, R.J., Jain, L. (eds.) KES 2007, Part III. LNCS (LNAI), vol. 4694, pp. 414–421. Springer, Heidelberg (2007)
May, R., Dandy, G., Maier, H.: Review of input variable selection methods for artificial neural networks. In: Suzuki, K. (ed.) Artificial Neural Networks Methodological Advances and Biomedical Applications. INTECH, Rijeka (2011)
Mitchell, T., Toby, J., Beauchamp, J.: Bayesian variable selection in linear regression. J. Am. Stat. Assoc. 83, 1023–1032 (1988)
Novovicova, J., Somol, P., Pudil, P.: A new measure of feature selection algorithms stability. In: IEEE International Conference on Data Mining Workshops, vol. 1, pp. 382–387 (2009)
Reyneri, L., Colla, V., Vannucci, M.: Estimate of a probability density function through neural networks. In: Cabestany, J., Rojas, I., Joya, G. (eds.) IWANN 2011, Part I. LNCS, vol. 6691, pp. 57–64. Springer, Heidelberg (2011)
Rice, J.A.: Mathematical Statistics and Data Analysis, 3rd edn. Duxbury Advanced, Duxbury (2006)
Rosenblatt, M.: Remarks on some nonparametric estimates of a density function. Ann. Math. Stat. 27(3), 443–471 (1956)
Schliebs, S., Defoin-Platel, M., Worner, S., Kasabov, N.: Integrated feature and parameter optimization for an evolving spiking neural network: exploring heterogeneous probabilistic models. Neural Netw. 22(5–6), 623–632 (2009)
Shetty, M., Shekokar, N.M.: Data mining techniques for real time intrusion detection systems. Int. J. Sci. Eng. Res. 3(4), 1–7 (2012)
Sokolova, M., Lapalme, G.: A systsystem analysis of performance measures for classification tasks. Inf. Process. Manage. 45, 427–437 (2009)
Song, Q.B., Wang, G., Wang, C.: Automatic recommendation of classification algorithms based on data set characteristics. Pattern Recogn. 45(7), 2672–2689 (2012)
Souza, F., Araujo, R., Soares, S., Mendes, J.: Variable selection based on mutual information for soft sensors application. In: Proceedings of the 9th Portuguese Conference on Automatic Control, Controlo 2010, At Coimbra, Portugal (2010)
Spearman, C.: The proof and measurement of association between two things. Am. J. Psychol. 15, 72–101 (1904)
Stigler, S.: Francis galtons account of the invention of correlation. Stat. Sci. 4(2), 73–79 (1989)
Sun, Y., Robinson, M., Adams, R., Boekhorst, R., Rust, A.G., Davey, N.: Using feature selection filtering methods for binding site predictions. In: Proceedings of 5th IEEE International Conference on Cognitive Informatics, ICCI 2006 (2006)
Turney, P.: Techncal note: bias and the quantification of stability. Mach. Learn. 20, 23–33 (1995)
Vitalta, R., Drissi, Y.: A perspective view and survey of meta-learning. Artif. Intell. Rev. 18(2), 77–95 (2002)
Wang, G., Song, Q., Sun, H., Zhou, X.: A feature subset selection algorithm automatic reccomendation method. J. Artif. Intell. Res. 47, 1–34 (2013)
Wang, S., Zhu, J.: Variable selection for model-based high dimensional clustering and its application on microarray data. Biometrics 64, 440–448 (2008)
Yu, L., Ding, C., Loscalzo, S.: Stable feature selection via dense feature groups. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 803–811 (2008)
Yu, L., Liu, H.: Feature selection for high-dimensional data: a fast correlation basedfilter solution. In: Proceedings of the 20th International Conference on Machine Learning ICML, vol. 1, pp. 856–863 (2003)
Zhang, K., Li, Y., Scarf, P., Ball, A.: Feature selection for high-dimensional machinery fault diagnosis data using multiple models and radial basis function networks. Neurocomputing 74, 2941–2952 (2011)
Zhao, Z., Liu, H.: Searching for interacting features. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence Morgan Kaufmann Publishers Inc., pp. 1156–1161 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Cateni, S., Colla, V. (2016). Variable Selection for Efficient Design of Machine Learning-Based Models: Efficient Approaches for Industrial Applications. In: Jayne, C., Iliadis, L. (eds) Engineering Applications of Neural Networks. EANN 2016. Communications in Computer and Information Science, vol 629. Springer, Cham. https://doi.org/10.1007/978-3-319-44188-7_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-44188-7_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44187-0
Online ISBN: 978-3-319-44188-7
eBook Packages: Computer ScienceComputer Science (R0)