Abstract
Recognizing the human arm movements has several applications, and it can be performed in a number of ways through the use of one or more sensor devices that the technology offers. This paper aims to exploit the exercises performed by jugglers in order to recognize the arm movements on the basis of the only information on the arm orientation provided by the Euler Angles. The proposed recognizer has two modules, i.e., a feature extractor and a classifier. The former reconstructs the dynamics of the system and estimates three correlation dimensions, each associated with a given Euler Angle. The latter is formed by a Linear Support Vector Machine. Extensive experimentations show the effectiveness of the proposed approach.
Similar content being viewed by others
Notes
Dynamics has to be intended in terms of a dynamical system, namely a system where a mathematical function describes the dependence of a point in a geometrical space.
A manifold (http://en.wikipedia.org/wiki/Manifold) is a mathematical space in which every point has a neighborhood which resembles Euclidean space, but in which the global structure may be more complicated. In a one-dimensional manifold every point has a neighborhood that looks like a line segment; in a two-dimensional manifold the neighborhood looks like a disk. \(\mathbb {R}^n\) is a n-dimensional manifold.
In dynamical systems, an attractor is a set of numerical values toward a system tends to evolve asymptotically, as time increases, for a wide variety of initial conditions of the system [38].
Takens–Mañé embedding theorem is a consequence of a Whitney Embedding Theorem [47] stating that a generic map from an S-dimensional manifold to a \((2S+1)\)-dimensional Euclidean space is an embedding, i.e., the image of the S-dimensional manifold is completely unfolded in the larger space. Therefore, two data points in the S-dimensional manifold do not map to the same point in the \((2S+1)\)-dimensional space.
Colibri is a registered trademark of Trivisio Prototyping GmbH.
The maximum number of balls, for few seconds, that a professional juggler is able to handle in his movements is seven.
The database is available, on request, for further investigations.
A KNN experiment can be performed by LVQ-pak command: eveninit -noc 2 -din fileinput -cout fileoutput -knn 3 where noc stands for the number of codevectors (i.e., 2), din corresponds to the name of input data file, cout provides the name of the codevector file, and knn denotes the number of k nearest neighbors (i.e., 3).
References
Austin H (1974) A computational view of the skill of juggling. Tech. Rep. 317, MIT, Laboratory of Artificial Intelligence
Banos O, Damas M, Pomares H, Prieto A, Rojas I (2012) Daily living activity recognition based on statistical feature quality group selection. Expert Syst Appl 39(9):8013–8021
Beek P (1989) Juggling dynamics. Free University Press, Amsterdam
Beek PJ, Lewbel A (1995) The science of juggling. Sci Am 273(11):92–97
Biswas D, Cranny A, Gupta N, Maharatna K, Achner J, Klemke J, Jöbges M, Ortmann S (2015) Recognizing upper limb movements with wrist worn inertial sensors using k-means clustering classification. Hum Mov Sci 40:59–76
Botia J, Villa A, Palma J (2012) Ambient assisted living system for in-home monitoring of healthy independent elders. Expert Syst Appl 39(9):8136–8148
Bühler M, Koditschek D, Kindlmann P (1990) Planning and control of robotic juggling tasks. In: The fifth international symposium on robotic research, The MIT Press, pp 321–332
Burdea G, Coiffet P (2003) Virtual reality technology. Wiley, New York
Camastra F, Filippone M (2009) A comparative evaluation of nonlinear dynamics methods for time series prediction. Neural Comput Appl 18(8):1021–1029
Camastra F, Staiano A (2016) Intrinsic dimension estimation: advances and open problems. Inf Sci 328:26–41
Carter KM, Hero AO, Raich R (2007) De-biasing for intrinsic dimension estimation. In: Proceedings of IEEE statistics signal processing workshop, pp 601–605
Chaaraoui A, Climent-Pérez P, Flórez-Revuelta F (2012) A review on vision techniques applied to human behaviour analysis for ambient-assisted living. Expert Syst Appl 39(12):10,873–10,888
Chang CC, Lin CJ (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1–27
Chernbumroong S, Cang S, Atkins A, Yu H (2013) Elderly activities recognition and classification for applications in assisted living. Expert Syst Appl 40(5):1662–1674
Chernbumroong S, Cang S, Yu H (2014) A practical multi-sensor activity recognition system for home-based care. Decis Support Syst 66:61–70
Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:1–25
Dubovikov MM, Starchenko NV, Dubovikov MS (2004) Dimension of the minimal cover and fractal analysis of time series. Phys A Stat Mech Appl 339(3–4):591–608
Eckmann JP, Ruelle D (1985) Ergodic theory of chaos and strange attractors. Rev Mod Phys 57:617–659
Eckmann JP, Ruelle D (1992) Fundamental limitations for estimating dimensions and lyapounov exponents in dynamical systems . Phys D 56:185–187
Einbeck J, Kalantana Z (2013) Intrinsic dimensionality estimation for high-dimensional data sets: new approaches for the computation of correlation dimension. J EmergTechnol Web Intell 5(2):91–97
Fan M, Qiao H, Zhang B (2009) Intrinsic dimension estimation of manifolds by incising balls. Pattern Recognit 42:780–787
Field M, Stirling D, Pan Z, Ros M, Naghdy F (2015) Recognizing human motions through mixture modeling of inertial data. Pattern Recognit 48(8):2394–2406
Fuentes D, Gonzalez-Abril L, Angulo C, Ortega J (2012) Online motion recognition using an accelerometer in a mobile device. Expert Syst Appl 39:2461–2465
Goldstein H (1980) Classical mechanics. Addison-Wesley, Boston
Grassberger P, Procaccia I (1983) Measuring the strangeness of strange attractors. Phys D 9:189–208
Hastie T, Tibshirani R, Friedman R (2001) The elements of statistical learning. Springer, New York
Haykin S, Bo Li X (1995) Detection of signals in chaos. Proc IEEE 83(1):95–122
Joachim T (1999) Making large-scale SVM learning practical. In: Schölkopf B, Burges CJC (eds) Advances in Kernel methods—support vector learning. MIT Press, Cambridge, pp 169–184
Kober J, Graham R, Mistry M (2012) Playing catch and juggling with a humanoid robot. In: Proceedings of \(12^{th}\) IEEE-RAS international conference on humanoid robots, IEEE, pp 875–881
Kohonen T (1995) Learning vector quantization. In: Arbib MA (ed) The handbook of brain theory and neural networks. MIT Press, Cambridge, pp 537–540
Kohonen T (1997) Self-organizing maps. Springer, Berlin
Kohonen T, Hynninen J, Kangas J, Laaksonen J, Torkkola K (1996) Lvq-pak: The learning vector quantization program package. Tech. Rep. A30, Helsinki University of Technology, Laboratory of Computer and Information Science
Landau L, Lifshitz EM (1996) Mechanics. Butterworth-Heinemann, Oxford
Mañé R (1981) On the dimension of compact invariant sets of certain nonlinear maps. In: Rand D, Young L-S (eds) Dynamical systems and turbolence, Warwick 1980. Springer, Berlin, pp 230–242
Nikolic D, Moca V, Singer W, Muresan R (2008) Properties of multivariate data investigated by fractal dimensionality. J Neurosci Methods 172:27–33
North B, Blake A, Isard M, Rittscher J (2000) Learning and classification of complex dynamics. IEEE Trans Pattern Anal Mach Intell 22(9):1016–1034
Ordóõez F, Iglesias J, de Toledo P, Ledezma A, Sanchis A (2013) Online activity recognition using evolving classifiers. Expert Syst Appl 40(4):1248–1255
Ott E (1988) Chaos in dynamical systems. Cambridge University Press, Cambridge
Packard N, Crutchfield J, Farmer J, Shaw R (1980) Geometry from a time series. Phys Rev Lett 45(1):712–716
Polster B (2003) The Mathematics of Juggling. Springer, Berlin
Richards GR (2004) A fractal forecasting model for financial time series. J Forecast 23(8):586–601
Shannon C (1993) Scientific aspects of juggling. In: C.E. Shannon Collected Papers, Wiley, pp 230–242
Stone M (1974) Cross-validatory choice and assessment of statistical prediction. J RStat Soc 36(1):111–147
Takens F (1981) Detecting strange attractor in turbolence. In: Rand D, Young L-S (eds) Dynamical Systems and Turbolence, Warwick 1980. Springer, Berlin, Heidelberg, pp 366–381
Takens F (1985) On the numerical determination of the dimension of anattractor. In: Braaksma BLJ, Broer HW, Takens F (eds) Dynamical systems and bifurcations, Proceedings Groningen 1984. Addison Wesley, New York, pp 99–106
Vapnik V (1998) Statistical learning theory. Wiley, New York
Whitney H (1936) Differentiable manifolds. Ann Math 37:645–680
Ziethen KH, Allen A (1985) Juggling, the art and its artists. Werner Rausch and Werner Luft Inc, Berlin
Acknowledgments
Firstly, the authors are indebted to the anonymous reviewers for their valuable comments. The research was developed when Francesco Esposito was at the Department of Science and Technology, University of Naples Parthenope, as B. Sc. student in Computer Science. Francesco Camastra and Antonino Staiano were funded by Sostegno alla ricerca individuale per il triennio 2015–17 project of University of Naples Parthenope. Finally, the authors wish to thank Lara De Vinco for her help in preparing the paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Camastra, F., Esposito, F. & Staiano, A. Linear SVM-based recognition of elementary juggling movements using correlation dimension of Euler Angles of a single arm. Neural Comput & Applic 29, 1005–1013 (2018). https://doi.org/10.1007/s00521-016-2616-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2616-x