Summary
This work explores the capacity of Stacking to generate multivariate time series classifiers from classifiers of their univariate time series components. The Stacking scheme proposed uses k-nearest neighbors (K-NN) with dynamic time warping (DTW) as a dissimilarity measure for the level 0 learners. Support vector machines and Naïve Bayes are applied at level 1. The method has been tested on two data sets: Continuous plant diagnosis and Japanese vowels. Experimental results show that for these data sets the proposed Stacking configuration performs well when multivariate DTW fails to produces precise K-NN classifiers, increasing the accuracy achieved by K-NN as a stand alone method by the order of magnitude. This is an interesting issue because good univariate time series classifiers do not always perform satisfactory when adapted to the multivariate case. On the contrary, if the multivariate classifier is accurate, Stacking univariate classifiers may perform worse.
This work has been partially funded by Spanish Ministry of Education and Culture through grant DPI2005-08498, and Junta Castilla y León VA088A05.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kadous MW (2002) Temporal classification: extending the classification paradigm to multivariate time series. PhD Thesis, University of New South Wales, Sydney, http://www.cse.unsw.edu.au/~waleed/phd/
Rodríguez JJ, Alonso CJ (2004) Técnicas de aprendizaje automático para la clasificación de series. In: Giráldez R, Riquelme JC, Aguilar-Ruiz JS (eds), Tendencias de la Minería de Datos en España: Red Española de Minería de Datos, Universidad de Valladolid, España, pp 217–228
Bengio Y (1999) Markovian models for sequential data. Neural Computing Surveys 2:129–162, http://www.iro.umontreal.ca/~lisa/bib/pub_subject/markov/pointeurs/hmms.ps
Rabiner L, Juang B-H (1993) Fundamentals of speech recognition. Prentice Hall, Upper Saddle River
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Haykin S (1998) Neural networks: a comprehensive foundation. Prentice Hall, Upper Saddle River
Keogh E, Ratanamahatana CA (2005) Exact indexing of dynamic time warping. Knowl Inf Syst 7:358–386
Colomer J, Meléndez J, Gamero FI (2002) Qualitative representation of process trends for situation assessment based on cases. In: Proc the 15th IFAC World Congress, Barcelona, Spain. Elsevier, Amsterdam
Myers CS, Rabiner LR (1981) A comparative study of several dynamic time-warping algorithms for connected word recognition. The Bell Syst Tech J 60:1389–1409
Wolpert DH (1992) Stacked generalization. Neural Networks 5:241–259, http://citeseer.csail.mit.edu/wolpert92stacked.html
Feng C (1992) Inducting temporal fault diagnostic rules from a qualitative model. In: Muggleton S (ed) Inductive Logic Programming. Academic Press, London
Venkatasubramanian V, Chan K (1989) A neural network methodology for process fault diagnosis. The Amer Inst of Chemical Engineers J 35:1993–2002
Sleeman D, Mitchell F, Milne R (1996) Applying KDD techniques to produce diagnostic rules for dynamic systems. Tech Report AUCS/TR9604, University of Aberdeen, Scotland
Suárez AJ, Abad PJ, Ortega JA, Gasca RM (2002) Diagnosis progresiva en el tiempo de sistemas dinámicos. In: Ortega JA, Parra X, Pulido B (eds) Proc IV Jornadas de ARCA, Sistemas Cualitativos y Diagnosis, pp 111–120
Roverso D (2003) Fault diagnosis with the Aladdin transient classifier. In: Willett PK, Kirubarajan T (eds) Proc of the SPIE Conf Syst Diagnosis and Prognosis: Security and Condition Monitoring Issues III, Orlando, FL, USA. SPIE Press, Bellingham, pp 162–172
Alonso C, Rodríguez JJ, Pulido B (2004) Enhancing consistency based diagnosis with machine learning techniques. In: Conejo R, Urretavizcaya M, Pérez-de-la-Cruz J-L (eds) Proc the 10th Conf Spanish Assoc Artif Intell, San Sebastian, Spain. Springer, Berlin/Heidelberg, pp 312–321
Witten IH, Frank E (2000) Data mining: practical machine learning tools with Java implementations. Morgan Kaufmann, San Francisco
Nadeau C, Bengio Y (2003) Inference for the generalization error. Mach Learn 52:239–281
Kudo M, Toyama J, Shimbo M (1999) Multidimensional curve classification using passing-through regions. Pattern Recogn Lett 20:1103–1111
Hettich S, Bay SD (1999) The UCI KDD Archive, University of California, Irvine, http://kdd.ics.uci.edu
Gunn SR (1998) Support vector machines for classification and regression. Tech Report, University of Southampton, UK
Lin H-T, Li L (2005) Novel distance-based SVM kernels for infinite ensemble learning. In: Proc the 12th Int Conf Neural Inf Proc, Taipei, Taiwan, pp 761–766
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Alonso, C., Prieto, Ó., Rodríguez, J.J., Bregón, A. (2008). Multivariate Time Series Classification via Stacking of Univariate Classifiers. In: Okun, O., Valentini, G. (eds) Supervised and Unsupervised Ensemble Methods and their Applications. Studies in Computational Intelligence, vol 126. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78981-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-78981-9_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78980-2
Online ISBN: 978-3-540-78981-9
eBook Packages: EngineeringEngineering (R0)