Simulation is indispensable during the design of many biomedical prostheses that are based on fundamental electrical and electronic actions. However, simulation necessitates the use of adequate models. The main difficulties related to the modeling of such devices are their nonlinearity and dynamic behavior. Here we report the application of recurrent artificial neural networks for modeling of a nonlinear, two-terminal circuit equivalent to a specific implantable hearing device. The method is general in the sense that any nonlinear dynamic two-terminal device or circuit may be modeled in the same way. The model generated was successfully used for simulation and optimization of a driver (operational amplifier)-transducer ensemble. This confirms our claim that in addition to the proper design and optimization of the hearing actuator, optimization in the electronic domain, at the electronic driver circuit-to-actuator interface, should take place in order to achieve best performance of the complete hearing aid.
HákanssonB.E., CarlssonP.U., TjellstrómA., LidénG.. The bone-anchored hearing aid: principal design and audiometric results.Ear Nose Throat J.1994; 73(9): 670–675.
2.
DietzT.G., BallG.R., KatzB.H.. Partially implantable vibrating ossicular prosthesis.: Proceedings of the Ninth International Conference on Solid-State Sensors and Actuators (Transducers ‘97), Chicago, Illinois, June 1997, Vol. 1: 433–436.
3.
BallG., MaxfieldB.. Floating mass transducer for middle ear applications.Sec Intl Symp Electr Impl.1996; 8.
4.
DazertS., Shehata-DielerW.E., DielerR., HelmsJ.. [“Vibrant Soundbridge” middle ear implant for auditory rehabilitation in sensory hearing loss. I. Clinical aspects, indications and initial results] (in German).Laryngorhinootologie.2000; 79(8): 459–464.
5.
ParkI.Y., ShimizuY., O'ConnorK.N., PuriaS., ChoJ.H.. Comparisons of electromagnetic and piezoelectric floating-mass transducers in human cadaveric temporal bones.Hear Res.2011; 272(1-2): 187–192.
6.
HeinrichB.M.. Evaluation of a VR (Virtual Reality) system for CT-based surgical planning at the lateral skull base, Ph.D Dissertation, Faculty of Medicine, Eberhard-Karls-University of Tübingen, Germany, 2005.
7.
ChuaL.O., LinP.M.. Computer-Aided Analysis of Electronic circuits.New Jersey, Prentice-Hall; 1975.
8.
MirriD., IuculanoG., FilicoriF., PasiniG., VanniniG., GabriellaG.P.. A Modified Volterra Series Approach for Nonlinear Dynamic Systems Modeling.IEEE Trans Circuits Syst., I: Fundamental Theory and Applications.2002; 49(8): 1118–1128.
KiliçR., Yildirim DalkiranF.. Utilizing SIMULINK in Modeling and Simulation of Generalized Chaotic Systems with Multiple Nonlinear Functions.Computer Applications in Engineering Education.2010; 18(4): 684–693.
12.
LitovskiV.B., RadjenovićJ.I., MrčaricaŽM, MilenkovićSLj. MOS transistor modeling using neural network.Electron Lett.1992; 28(18): 1766–1768.
13.
LitovskiV.B., MrčcaricaŽ, IlićT.. Simulation of non-linear magnetic circuits modeled using artificial neural network.Simulation Practice and Theory.1997; 5(6): 553–570.
14.
LitovskiV.B., AndrejevicM., PetkovićP., DamperR.. ANN Application to Modelling of the D/A and A/D Interface for Mixed-Mode Behavioural Simulation.Journal of Circuits, Systems and Computers.2004; 13(1): 181–192.
15.
LitovskiV., AndrejevićM., ZwolinskiM.. Behavioural Modelling, Simulation, Test and Diagnosis of MEMS using ANNs.IEEE Int. Symposium on Circuits and Systems, Kobe, Japan, May 23-25, 2005: 5182–5185.
16.
AndrejevićM., LitovskiV.. 6th Seminar on Neural Networks applications in Electrical Engineering - Neurel 2002. Belgrade, Serbia, September 2002: 119–122.
17.
BartissolP., ChuaL.O.. The double hook.IEEE Trans Circuits Syst.1988; 35(12): 1512–1522.
ScarselliF., TsoiA.C.. Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results.Neural Netw.1998; 11(1): 15–37.
21.
BernieriA., D'ApuzzoM., SansoneL., SavastanoM.. A Neural Network Approach for Identification and Fault Diagnosis on Dynamic Systems.IEEE Transactions on Instrumentation and Measurement.1994; 43(6): 867–873.
22.
LitovskiV., ZwolinskiM.. VLSI Circuit Simulation and Optimization.London: Chapman and Hall; 1997.
23.
IlićT., ZarkovićK., LitovskiV., DamperR.. ANN Application in Modelling of Dynamic Linear Circuits.Small Systems Simulation Symposium, SSSS2000, Niš, Serbia, 2000; 43–47. http://eprints.soton.ac.uk/id/eprint/253947.
24.
AndrejevićM., LitovskiV.. Non-Linear Dynamic Network Modeling Using Neural Networks. Proceedings of the 10th International Congress on Computational and Applied Mathematics (ICCAM-2002), University of Leuven, Belgium, July 22-26, 2002. J Comput Appl Math.2002; 16.
25.
AndrejevićM., LitovskiV.. Electronic Modeling Using ANNs for Analogue and Mixed-Mode Behavioral Simulation.Journal of Automatic Control.2003; 131: 31–37.
26.
AndrejevićM., MilovanovićD., PetkovicćP., LitovskiV.. Extraction of Frequency Characteristics of Switched-Capacitor Circuits Using Time-Domain Analysis. 23rd International Conference on Microelectronics, MIEL 2002, Niš, Serbia, 2002.Microelectronics.2002; 2: 635–638.
27.
ZografskiZ.. A Novel Machine Learning Algorithm and Its Use in Modeling and Simulation of Dynamical Systems. Proceedings of the 5th Annual European Computer Conference, COMPEURO'91, Bologna, Italy, 1991; 860–864.
28.
BaumE.B., HausslerD.. What size net gives valid generalization.Neural Computation.1989; 1(1): 151–160.
29.
BernieriA., D'ApuzzoM., SansoneL., SavastanoM.. A neural network approach for identification and fault diagnosis on dynamic systems.IEEE Transactions on Instrumentation and Measurement.1994; 436: 867–873.
30.
LitovskiV., MaksimovicD., MrcaricaŽMixed-signal modelling with AleC++: Specific features of the HDL.Simulation Practice and Theory.2001; 8(6-7): 433–449.
