Optimizing stimulus energy for cochlear implants with a machine learning model of the auditory nerve.

Autor: de Nobel J; Leiden Institute of Advanced Computer Science, Niels Bohrweg 1, Leiden, Netherlands. Electronic address: nobeljpde1@liacs.leidenuniv.nl., Kononova AV; Leiden Institute of Advanced Computer Science, Niels Bohrweg 1, Leiden, Netherlands., Briaire JJ; Department of Otorhinolaryngology, Leiden University Medical Center, Albinusdreef 2, Leiden, Netherlands., Frijns JHM; Department of Otorhinolaryngology, Leiden University Medical Center, Albinusdreef 2, Leiden, Netherlands; Leiden Institute for Brain and Cognition, Wassenaarseweg 52, Leiden, Netherlands., Bäck THW; Leiden Institute of Advanced Computer Science, Niels Bohrweg 1, Leiden, Netherlands.
Jazyk: angličtina
Zdroj: Hearing research [Hear Res] 2023 May; Vol. 432, pp. 108741. Date of Electronic Publication: 2023 Mar 14.
DOI: 10.1016/j.heares.2023.108741
Abstrakt: Performing simulations with a realistic biophysical auditory nerve fiber model can be very time-consuming, due to the complex nature of the calculations involved. Here, a surrogate (approximate) model of such an auditory nerve fiber model was developed using machine learning methods, to perform simulations more efficiently. Several machine learning models were compared, of which a Convolutional Neural Network showed the best performance. In fact, the Convolutional Neural Network was able to emulate the behavior of the auditory nerve fiber model with extremely high similarity (R 2 >0.99), tested under a wide range of experimental conditions, whilst reducing the simulation time by five orders of magnitude. In addition, a method for randomly generating charge-balanced waveforms using hyperplane projection is introduced. In the second part of this paper, the Convolutional Neural Network surrogate model was used by an Evolutionary Algorithm to optimize the shape of the stimulus waveform in terms of energy efficiency. The resulting waveforms resemble a positive Gaussian-like peak, preceded by an elongated negative phase. When comparing the energy of the waveforms generated by the Evolutionary Algorithm with the commonly used square wave, energy decreases of 8%-45% were observed for different pulse durations. These results were validated with the original auditory nerve fiber model, which demonstrates that the proposed surrogate model can be used as its accurate and efficient replacement.
(Copyright © 2023. Published by Elsevier B.V.)
Databáze: MEDLINE
Externí odkaz: