Abstract
In this chapter, we explain and illustrate the“feature space processing” paradigm, in relation to artificial neural network filtering and prediction. We use hybrid neural processors that explicitly include feature space representations of the data sets to illustrate this paradigm. A general feature space processing system is presented and several implementations are proposed. In order to outline the feature space processing concepts, both filtering and the prediction tasks are undertaken. In these cases, the input and the output lie in the same space. This facilitates the comparison of data vs. data plus feature space models. We focus on improvements to the neural model with respect to a reference feature space characterization. The resulting models perform similarly in the sample space and display a better feature space behavior. The modeling accuracy of the proposed neural hybrid systems is illustrated in two signal processing applications: spectrogram filtering, and tremor signal prediction.
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
Alesch, F., Pinter, M.M., Helscher, R.J., Fertl, L., Benabid, A.L., Koos, W.T. (1995). “Stimulation of the ventral intermediate thalamic nucleus in tremor dominated Parkinson’ s disease and essential tremor.” Acta Neurochir. (Wien), 136 (1–2), 75–81.
Anouti, A., Koller WC. (1995).“Tremor Disorders. Diagnosis and Management.” West J. Med., 162(6), 510–3.
Bain, P.G., Findley, L.J., Britton, T.C., Rothwell, J.C., Gresty, M.A., Thompson, P.D., Marsden, CD. (1995).“Primary writing tremor.” Brain, 118(Pt 6), 1461–1472.
Bonciu, C, Teodorescu, H.N. (1997).“Feature space Filtering With RBF Networks.” Proc. of the EUFIT97 Conf, Aachen, Germany, 241–249.
Bonciu, C, Teodorescu, H.N. (1998).“Feature space Neural Systems for Identification and Control”, World Multiconf. on Systemics, Cybernetics and Informatics SCI’ 98, Orlando, Florida, 507–514.
Britton, T.C. (1995).“Essential tremor and its variants.” Curr. Opin. Neurol., 8(4), 314–319.
Elble, R.J., Brilliant, M., Leffler, K., Higgins, C. (1996).“Quantification of essential tremor in writing and drawing.” Mov. Disord., 11(1), 70–8.
Ferraz, H.B., De Andrade, L.A., Silva, S.M., Borges, V., Rocha, M.S. (1994)“Postural tremor and dystonia. Clinical aspects and physiopathological considerations.” Arq. Neuropsiquiatr., 52(4),466–470.
Girossi, F., Poggio, T. (1990).“Networks and the Best Approximation Property.” Biological Cybernetics, 63, 169–176.
Hanna, M., Mills, K., Pazdera, L., Newsom-Davis, J. (1997).“Primary orthostatic tremor with prominent muscle hypertrophy.” Neurology, 49(3), 872–874.
Haykin, S. (1994). Neural Networks: A Comprehensive Foundation, IEEE Press.
Hebb, D.O. (1949), The Organization of Behaviour, Jon Wiley, New York.
Miccelli, C.A. (1986).“Interpolation of Scattered Data: Distance Matrices and Conditionally Positive Definite Functions.” Constructive Approximations, 2(1), 11–22.
Minsky, M. (1992).“Future Models for Mind-Machines.” Proc. Int. Symposium on Natural Language Understanding and Al (ISKIT’ 92), Iizuka, Japan, 1–6.
Mlynek, D., Teodorescu, H.N., Ropota, I., Teodorescu, C, Ciorap, R. (1997).“Fuzzy Control of Electrical Stimulation in Rehabilitation: A Dynamics Control.” Proc. Int. Conf EUFIT97, Aachen, Germany. 246–249.
Nerrand, O., Roussel-Ragot, P., Urbani, D., Personnaz, L., Dreyfus, G. (1994).“Training Recurrent Neural Networks: Why and How? An Illustration in Dynamical Process Modelling.” IEEE Transactions on Neural Networks, 5(2). 178–184.
Park, J., Sandberg, I.W. (1993).“Approximation and Radial Basis Functions.” Neural Computation, 5(2), 305–316.
Pineda, F.J. (1988).“Dynamics and Architecture for Neural Computation.” Journal of Complexity 4, 216–275.
Poggio, T. Girossi, F. (1990).“Networks for Approximation and Learning.” Proceedings of the IEEE, 78(9), 1481–1497.
Powell, M.J.D. (1987).“Radial Basis Functions for Multivariable Interpolation: A Review”, in Mason, J.C., Cox, M.G. (eds.), Algorithms for Approximations, Clarendon Press, Oxford.
Rosenblatt, F. (1958).“The Perceptron: A Probabilistic Model For Information Storage and Organization In The Brain.” Psychological Review, 65(6), 386–408.
Sanger, T.D. (1989).“Optimal Unsupervised Learning in a Single-Layer Linear Feedforward Neural Network.” Neural Networks, 2,459–473.
Teodorescu, H.N. (1986).“Pattern-Oriented, Robust Filtering in Pattern Electrocardiography: A New Method.” 13th Int. Congress on Electrocardiology, George Washington University, Medical Center (summary in the Book of Abstracts).
Teodorescu, H.N. (1987).“Robustness In Terms of Fuzziness,” Proc. 2 nd. IFSA Congress, Tokyo, 2,733–736.
Teodorescu, H.N. (1988a).“Pattern-Oriented Robust Fuzzy Filtering,” Proc. of IIZUKA Conf. on Fuzzy Systems, Kyushu, Japan, 57–58.
Teodorescu, H.N. (1988b).“Pattern-Oriented Robust Fuzzy Filtering — Digital Methods,” Proc. of IIZUKA Conf. on Fuzzy Systems, Kyushu, Japan, 59–60.
Teodorescu, H.N. (1988c).“Robust Digital Signal Conditioning by Pattern-Oriented Filtering.” MESSCOMP’ 88, Network GmbH, Wiesbaden (Germany), 2B.71–2B.75.
Teodorescu, H.N. (1988d).“Pattern-Oriented Filtering of Images.” Archives of the 10 th ISPRS Congress, Kyoto, Japan.
Teodorescu, H.N., Yamakawa, T., Uchino, T., Miki, T., Inagawa, N., Sofron, E., Suceveanu, S. (1994).“Pattern Oriented Neuro-Fuzzy Filtering.” Proc. of the 3 rd Int. Conf. on Fuzzy Logic, Neural Nets and Soft Computing, Iizuka, Japan, 657–660.
Teodorescu, H.N., Bonciu, C. (1996).“Feedforward Neural Filter with Learning in Features Space. Preliminary Results.” Conference Report of the First Int. Symp. on Neuro-Fuzzy Systems AT96, Lausanne, Switzerland.
Teodorescu, H.N., Bonciu, C. (1997).“Learning Algorithm for RBF Networks as Features Extractors.” First Int. Conf. on Conventional & Knowledge-Based Intelligent Electronic Systems KES’ 97, Adelaide, Australia, 201–208.
Teodorescu, H.N., Kandel, A., Teodorescu, C, Mlynek, D., Rodriguez, W., Posa, C., Ropota, I. (1998a).“Fuzzy Methods Of Fusing Classic And Chaotic Numerical Parameters in A Hand Tremor Rehabilitation System.” Proc. Int. Conf IIZUKA’ 98, Iizuka, Japan.
Teodorescu, H.N. et al (1998b).“Analysis of Chaotic Movements and Fuzzy Assessment of Hands Tremor in Rehabilitation”, Proc. Int. Conf on Conventional & Knowledge-Based Intelligent Engineering Systems KES’ 98, Adelaide, Australia.
Teodorescu, H.N., Bonciu, C. (1999a).“Feature space Neural Filters and Controllers”, in Intelligent Adaptive Control. Industrial Applications, Jain, L.C., de Silva, C.W., (eds.), CRC Press, 105–147.
Teodorescu, H.N., Bonciu, C. (1999b).“Merging Signal and Pattern Processing: A Neural Hybrid Systems Approach”, Int. Journal of Knowledge-Based Intelligent Engineering Systems, 3(1), 12–19.
Teodorescu, H.N. and Kandel, A. (1999c).“Nonlinear Analysis of Tremor and Applications”.Japanese J. Bio-Medical Engineering. (Submitted as invited paper, to appear in 1999)
Tickle, A.B., Andrews, R., Golea, M., Diederich, J. (1998).“The Truth Will Come to Light: Directions and Challenges in Extracting the Knowledge Embedded Within Trained Artificial Neural Networks.” IEEE Transactions on Neural Networks 9(6), 1057–1067.
Tikhonov, A.V., Arsenin, V.Y. (1977). Solutions of Ill-Posed Problems, W.H. Winston, Washington D.C.
Weiss, S.M., Kulikowski, C.A. (1991). Computer systems that learn: Classification and prediction methods from statistics, neural nets, machine learning, and expert systems, Morgan Kaufmann, San Mateo, CA.
Wilkinson, J.H. (1985). The Algebraic Eigenvalue Problem, Oxford University Press.
Yan, W.-O., Helmke, U., Moore, J.B. (1994).“Global Analysis of Oja’ s Flow for Neural Networks.” IEEE Transactions on Neural Networks, 5,674–683.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Teodorescu, HN., Bonciu, C. (2000). Feature-Oriented Hybrid Neural Adaptive Systems and Applications. In: Teodorescu, HN., Mlynek, D., Kandel, A., Zimmermann, HJ. (eds) Intelligent Systems and Interfaces. International Series in Intelligent Technologies, vol 15. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-4401-2_6
Download citation
DOI: https://doi.org/10.1007/978-1-4615-4401-2_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6980-6
Online ISBN: 978-1-4615-4401-2
eBook Packages: Springer Book Archive