Nonlinear model structure identification of complex biomedical data using a genetic-programming-based technique

In this contribution, a genetic programming (GP)-based technique, which combines the ability of GP to explore both automatically and effectively, the whole set of candidate model structures and the robustness of evolutionary multimodel partitioning filters, is presented. The method is applied to the nonlinear system identification problem of complex biomedical data. Simulation results show that the algorithm identifies the true model and the true values of the unknown parameters for each different model structure, thus assisting the GP technique to converge more quickly to the (near) optimal model structure. The method has all the known advantages of the evolutionary multimodel partitioning filters, that is, it is not restricted to the Gaussian case; it is applicable to on-line/adaptive operation and is computationally efficient. Furthermore, it can be realized in a parallel processing fashion, a fact which makes it amenable to very large scale integration implementation.

[1]  Grigorios N. Beligiannis,et al.  Evolutionary Nonlinear Multimodel Partitioning Filters , 2001, J. Adv. Comput. Intell. Intell. Informatics.

[2]  Riccardo Poli,et al.  Foundations of Genetic Programming , 1999, Springer Berlin Heidelberg.

[3]  U. Shahani,et al.  Antenatal fetal magnetocardiography: a new method for fetal surveillance? , 1994, British journal of obstetrics and gynaecology.

[4]  P. A. Anninos,et al.  Derivation of a mathematical equation for the EEG and the general solution within the brain and in space , 1975 .

[5]  John R. Koza,et al.  Genetic Programming III: Automatic Pro-gramming and Automatic Circuit Synthesis , 2001 .

[6]  S. Sato,et al.  Magnetoencephalography and epilepsy research. , 1987, Science.

[7]  Brian B. Schwartz,et al.  Superconductor applications : SQUIDs and machines , 1977 .

[8]  P. Karp,et al.  The fetal magnetocardiogram. , 1974, Journal of perinatal medicine.

[9]  P H Crandall,et al.  The magnetic field of epileptic spikes agrees with intracranial localizations in complex partial epilepsy , 1988, Neurology.

[10]  F. H. Lopes da Silva,et al.  Biophysical aspects of EEG and magnetoencephalogram generation , 1998 .

[11]  Andreas Hans Kemna,et al.  Identification of combined physical and empirical models using nonlinear A priori knowledge , 1994 .

[12]  Fe Frans Veldpaus,et al.  An optimal estimation method for nonlinear models of mechanical systems , 1994 .

[13]  L. Gimeno,et al.  On the optimal and suboptimal nonlinear filtering problem for discrete time systems , 1977, 1977 IEEE Conference on Decision and Control including the 16th Symposium on Adaptive Processes and A Special Symposium on Fuzzy Set Theory and Applications.

[14]  Peter Nordin,et al.  Genetic programming - An Introduction: On the Automatic Evolution of Computer Programs and Its Applications , 1998 .

[15]  Grigorios N. Beligiannis,et al.  Genetically determined variable structure multiple model estimation , 2001, IEEE Trans. Signal Process..

[16]  D. Cohen,et al.  MEG versus EEG localization test using implanted sources in the human brain , 1990, Annals of neurology.

[17]  G Anogianakis,et al.  Biomagnetic measurements using squids. , 1987, The International journal of neuroscience.

[18]  E Ducla-Soares,et al.  Comparison of electroencephalography and magnetoencephalography. , 1990, Advances in neurology.

[19]  M. Netto,et al.  On the optimal and suboptimal nonlinear filtering problem for discrete-time systems , 1977 .

[20]  L. Schwartz,et al.  A computational comparison of several nonlinear filters , 1968 .

[21]  P Anninos,et al.  The hemodynamics of the umbilical artery in normal and pre-eclamptic pregnancies. A new application of SQUID biomagnetometry , 1997, Journal of Perinatal Medicine.

[22]  J R EVANS,et al.  RESPIRATORY QUOTIENT OF SCORBUTIC GUINEA PIGS. , 1964, Life sciences.

[23]  P A Anninos.  Electromagnetic fields generated from neuronal activity. , 1973, T.-I.-T. journal of life sciences.

[24]  V. Aidala,et al.  Observability Criteria for Bearings-Only Target Motion Analysis , 1981, IEEE Transactions on Aerospace and Electronic Systems.

[25]  Jerome Engel,et al.  The magnetic field of complex partial seizures agrees with intracranial localizations , 1987, Annals of neurology.

[26]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[27]  S. H. Hsieh,et al.  THRESHOLD MODELS FOR NONLINEAR TIME SERIES ANALYSIS. , 1987 .

[28]  B. Josephson.  Possible new effects in superconductive tunnelling , 1962 .

[29]  Hung Man Tong,et al.  Threshold models in non-linear time series analysis. Lecture notes in statistics, No.21 , 1983 .

[30]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[31]  Dominick Andrisani,et al.  A Nonlinear Tracker Using Attitude Measurements , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[32]  P A Anninos,et al.  Magnetic stimulation in the treatment of partial seizures. , 1991, The International journal of neuroscience.