Abstract
The challenges involved in integrating, maintaining and administrating real-world systems have motivated the proposal of the Autonomic Computing area which aims at making systems capable of self-managing their tasks, avoiding or minimizing the human interference. Autonomic Computing self-managing aspects are provided by the Autonomic Manager which relies on a structure called control loop. This loop is responsible for monitoring components, analyzing information and taking decisions to optimize, configure, heal and protect systems. Among such steps, the analysis is probably the most complex of the loop, due to it needs to model data, infer situations, estimate behavior or states, and make prediction. In order to proceed with the analysis, we need to study how systems produce information over time (here called time series) and, by modeling such information, we can understand system components behavior, transitions, relations to other systems, make estimations and predictions. In that sense, many techniques were designed to model such temporal information or time series, most of them involve statistics and artificial neural networks which require specific configurations based on series properties, what may not be bearable for online systems. All this scenario motivated this paper which proposes an approach to simplify and improve the accuracy of modeling, estimating and predicting time series. This approach considers chaos theory tools to unfold time series and organize them into multidimensional vectors which better represent interdependencies among observations. Techniques (such as artificial neural networks, e.g. RBF, RRBF, TDNN and ATNN, and statistical tools, e.g. Markov Models) can take advantage of such reorganization and, therefore, improve the accuracy of modeling, estimating and predicting. Experimental results confirm that the proposed approach provides good accuracy at very low computational costs.
Similar content being viewed by others
Notes
The considered dataset is available at the book Chaos and Order in the Capital Markets, second edition, Edgar Peters.
This Lyapunov exponent was computed by using 10 iterations of the command lyap_k available at the TISEAN package (Hegger et al. 2009). The number of iterations is informed by using the parameters.
This table shows more observations than Table 2. This is only an unfolding example to obtain the rule, or function, which generates this dynamical system.
References
Albertini MK, Mello RF (2007) A self-organizing neural network for detecting novelties. In: SAC ’07: Proceedings of the 2007 ACM symposium on Applied computing, ACM, Nova Iorque, EUA, pp 462–466. doi:10.1145/1244002.1244110
Abarbanel HDI, Brown R, Sidorowich JJ, Tsimring LS (1993) The analysis of observed chaotic data in physical systems. Rev Mod Phys 65:1331–1392
Alligood KT, Sauer TD, Yorke JA (1997) Chaos: an introduction to dynamical systems, Springer, New York
Bishop C (1991) Improving the generalization properties of radial basis function neural networks. Neural Comput 3(4):579–588. doi:10.1162/neco.1991.3.4.579
Bretscher O (2004) Linear Algebra with applications. Prentice Hall, Englewood Cliffs
Buhmann MD (2003) Radial basis functions: theory and implementations. In: Cambridge monographs on applied and computational mathematics. Cambridge University Press, Cambridge, pp x+259
Bianchi G, Tinnirello I (2003) Kalman filter estimation of the number of competing terminals in an ieee 802.11 network. In: INFOCOM 2003. Twenty-Second Annual Joint Conference of the IEEE Computer and Communications Societies, vol 2, pp 844–852
Box G, Jenkins GM, Reinsel G (1994) Time series analysis: forecasting and control. 3rd edn. Prentice Hall, Holden-Day, Inc.
Casdagli M (1989) Nonlinear prediction of chaotic time series. Physica D Nonlinear Phenomena 35:335–356. doi:10.1016/0167-2789(89)90074-2
Cai M, Cai F, Shi A, Zhou B, Zhang Y (2004) Chaotic time series prediction based on local-region multi-steps forecasting model. In: ISNN (2), pp 418–423
Doblinger G (1998) An adaptive Kalman filter for the enhancement of noisy AR signals. In: IEEE international symposium on circuits and systems, Monterey, CA, USA, pp 1–4
Day S, Davenport M (1993) Continuous-time temporal back-propagation with adaptable time delays. IEEE Trans Neural Netw 4(2):348–354. doi:10.1109/72.207622
de Castro LN, Von Zuben FJ (2001) An immunological approach to initialize centers of radial basis function neural networks. In: Proc. of 5th Brazilian conference on Neural Networks, pp 79–84
Edmonds AN (1996) Time series prediction using supervised learning and tools from chaos theory, Ph.D. thesis, University of Luton
Elmer F-J (1998) The Lyapunov exponent. http://monet.unibas.ch/elmer/pendulum/lyapexp.ht. Accessed 10 Sep 2007
Elert G (2005) The Chaos hypertextbook: measuring Chaos. http://hypertextbook.com/chaos. Accessed 10 Sep 2007
Eckmann J-P, Ruelle D (1985) Ergodic theory of chaos and strange attractors. Rev Mod Phys 57:617–656. doi:10.1103/RevModPhys.57.617
Feller W (1968) An introduction to probability theory and its applications, 3rd edn, vol 1. Wiley, New York
Fogel D (1991) An information criterion for optimal neural network selection. IEEE Trans Neural Netw 2(5):490–497. doi:10.1109/72.134286
Fraser AM, Swinney HL (1986) Independent coordinates for strange attractors from mutual information. Phys Rev A 33(2):1134–1140. doi:10.1103/PhysRevA.33.1134
Gibbs WW (2002) Autonomic Computing. Scientific American. http://www.sciam.com/article.cfm?id=autonomic-computin. Accessed 10 Oct 2008
Gholipour A, Araabi BN, Lucas C (2006) Predicting chaotic time series using neural and neurofuzzy models: a comparative study. Neural Process Lett 24(3):217–239. doi:10.1007/s11063-006-9021-x
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. http://citeseer.ist.psu.edu/hochreiter96long.html
Hegger R, Kantz H, Schreiber T (2009) Tisean 3.0.1: nonlinear time series analysis. http://www.mpipks-dresden.mpg.de/∼tisean/Tisean_3.0.1/index.html. Accessed 26 Jan 2009
Kaplan I (2003) Estimating the hurst exponent. http://www.bearcave.com/misl/misl_tech/wavelets/hurst/index.html Accessed 10 Sep 2007
Kennel M (2002) The multiple-dimensions mutual information program. http://www-ncsl.postech.ac.kr/en/softwares/archives/mmi.tar. Accessed 10 Sep 2007
Klenke A (2008) Probability theory: a comprehensive course, Springer, London
Kohler M (1997) Using the Kalman filter to track human interactive motion: modelling and initialization of the Kalman filter for translational motion. Tech. Rep. 629/1997, Fachbereich Informatik, Universität Dortmund, Fachbereich Informatik, Universität Dortmund, 44221 Dortmund, Alemanha
Kennel MB, Brown R, Abarbanel HDI (1992a) Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys Rev A 45(6):3403–3411. doi:10.1103/PhysRevA.45.3403
Kennel M, Brown R, Abarbanel H (1992b) Determining embedding dimension for phase space reconstruction using the method of false nearest neighbors, Tech rep, Institute for Nonlinear Science and Department of Physics, University of California, San Diego, Mail Code R-002, La Jolla, CA, EUA
Kumar U, Prakash A, Jain VK (2009) A multivariate time series approach to study the interdependence among O3, NOx, and VOCs in ambient urban atmosphere. Environ Model Assess 14(5):631–643
Lorenz E (1963) Deterministic nonperiodic flow. J Atmos Sci 20:130–141
Leung H, Lo T, Wang S (2001) Prediction of noisy chaotic time series using an optimal radial basis function neural network. IEEE Trans Neural Netw 12(5):1163–1172. doi:10.1109/72.950144
Liebert W, Pawelzik K, Schuster HG (1991) Optimal embeddings of chaotic attractors from topological considerations. Europhys Lett 14(6):521–526
Lin D-T, Dayhoff JE, Ligomenides PA (1995a) Trajectory production with the adaptive time-delay neural network. Neural Netw 8(3):447–461. doi:10.1016/0893-6080(94)00104-T
Lin D-T, Dayhoff JE, Ligomenides PA (1995b) Trajectory production with the adaptive time-delay neural network. Neural Netw 8(3):447–461. doi:10.1016/0893-6080(94)00104-T
Mañé R (1981) On the dimension of the compact invariant sets of certain nonlinear maps. In: Dynamical systems and turbulence, Warwick 1980, Lecture notes in mathematics 898. Springer, New York, pp 230–242
Meng A (2003) An introduction to markov and hidden markov models. http://www2.imm.dtu.dk/pubdb/p.php?3313
Milunovich G (2006) Modelling and valuing multivariate interdependencies in financial time series, Ph.D. thesis, School of Economics, University of New South Wales
Murch R (2004) Autonomic Computing. IBM Press, Upper Saddle River
Medio A, Gallo G (1992) Chaotic dynamics: theory and applications to economics. Cambridge University Press, Cambridge
Maas HLD, Verschure PF, Molenaar PC (1990) A note on chaotic behavior in simple neural networks. Neural Netw 3(1):119–122. doi:10.1016/0893-6080(90)90050-U
Palis J Jr, Melo W (1978) Introdutpo aos Sistemas DinGmicos. 1st edn. Edgard Blncher
Park J, Sandberg IW (1991) Universal approximation using radial-basis-function networks. Neural Comput 3(2):246–257. doi:10.1162/neco.1991.3.2.246
Parashar M, Hariri S (2006) Autonomic computing: concepts, infrastructure, and applications. CRC Press, Boca Raton
Penny W, Harrison L (2006) Multivariate autoregressive models. In: Friston K, Ashburner J, Kiebel S, Nichols T, Penny W (eds) Statistical parametric mapping: the analysis of functional brain images. Elsevier, Londres
Piovoso M, Laplante PA (2003) Kalman filter recipes for real-time image processing. Real Time Imaging 9(6):433–439. doi:10.1016/j.rti.2003.09.005
Pilgram B, Judd K, Mees A (2002) Modelling the dynamics of nonlinear time series using canonical variate analysis. Physica D 170(2):103–117. doi:10.1016/S0167-2789(02)00534-1
Rafajlowicz E, Pawlak M (2004) Optimization of centers’ positions for rbf nets with generalized kernels. In: ICAISC, pp 253–259
Rosenstein MT, Collins JJ, Luca CJD (1993) A practical method for calculating largest lyapunov exponents from small data sets. Physica D 65:117–134. http://citeseer.ist.psu.edu/rosenstein93practical.html
Ribert A, Stocker E, Lecourtier Y, Ennaji A (1997) Optimizing a neural network architecture with an adaptive parameter genetic algorithm. In: IWANN ’97: Proceedings of the international work-conference on artificial and natural neural networks, Springer, London, UK, pp 527–535
Shenshi G, Zhiqian W, Jitai C (1999) The fractal research and predicating on the times series of sunspot relative number. Appl Math Mech 20(1):84–89. doi:10.1007/BF02459277
Takens F (1980) Detecting strange attractors in turbulence. In: Dynamical systems and turbulence, Springer, Berlin, pp 366–381. doi:10.1007/BFb0091924
Wan E (1997) Time series prediction by using a connectionist network with internal delay lines. In: Time series prediction, Addison-Wesley, Reading, pp 195–217
Wan EA, Van Der Merwe R (2000) The unscented Kalman filter for nonlinear estimation. In: The IEEE 2000 Adaptive systems for signal processing, communications, and control symposium 2000 (AS-SPCC), pp 153–158
Whitney H (1936) Differentiable manifolds. Ann Math 37(3):645–680
Waibel A, Hanazawa T, Hinton G, Shikano K, Lang K (1989) Phoneme recognition using time delay neural networks. IEEE Trans Acoust 37:328–339
Zeng M, Cheng Z (2009) A method using genetic algorithm to optimize neural networks applied in sustainable development ability appraisal. In: ICECT '09: Proceedings of the 2009 international conference on electronic computer technology. IEEE Computer Society, Washington, DC, USA, pp 519–523. doi:http://dx.doi.org/10.1109/ICECT.2009.158
Zeevi AJ, Meir R, Adler RJ (1998) Non-linear models for time series using mixtures of autoregressive models. Tech rep
Zemouri R, Racoceanu D, Zerhouni N (2003) Recurrent radial basis function network for time-series prediction. Eng Appl Artif Intell 16(5–6):453–463
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
de Mello, R.F. Improving the performance and accuracy of time series modeling based on autonomic computing systems. J Ambient Intell Human Comput 2, 11–33 (2011). https://doi.org/10.1007/s12652-010-0028-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-010-0028-9