C. Bourgeois-Republique
ABSTRACT
Cochlear implants are electronic devices that stimulate directly the auditory nerve to allow totally deaf patients to hear again. This paper presents an interactive evolutionary algorithm (IEA) designed to help finding the best parameters of a cochlear implant for a specific patient.If early cochlear implants only featured one electrode, modern devices now offer up to 22 electrodes, with the hope to be able to transmit more details and help the patient hear better. The work presented in this paper shows however that having more electrodes is not necessarily better.Tests on a patient show surprisingly that some combinations of electrodes yield better results than others, with the problem that there is no real way to determine which electrode is beneficial to speech understanding and which is not.The best result obtained by the patient on a speech understanding evaluation protocol was 48.5/100 after 10 years of fitting sessions by an expert practitioner. For many reasons explained in this paper, the evaluation of the best parameter setting found by the IEA in one day was 91.5/100.
- Banzhaf W, "Handbook of Evolutionary Computation" (chapter on Interactive Evolution) Oxford University Press 1997.]]Google Scholar
- Durant, E. A., Hearing Aid Fitting with Genetic Algorithms, PHD Thesis, University of Michigan, USA 2002]] Google ScholarDigital Library
- Pierre Collet, Evelyne Lutton, Marc Schoenauer, and Jean Louchet, "Take it EASEA," Lecture Notes in Computer Science, 1917:891--901, 2000.]] Google ScholarDigital Library
- Pierre Collet. Easea language, 2004. http://sourceforge.net/projects/easea.]]Google Scholar
- Loizou P., "Mimicking the Human Ear," IEEE Signal Processing Magazine, 15(5), 101--130, 1998.]]Google ScholarCross Ref
- Loizou P., Poroy O., Dorman M., "The Effect of Parametric Variations of Cochlear Implant Processors on Speech Understanding," Journal of Acoustical Society of America, 2000, pp790--802.]]Google ScholarCross Ref
- MXM Laboratories, http://mxmlab.com.]]Google Scholar
- Schwefel H.-P., Numerical Optimization of Computer Models. Second edition. John Wiley & Sons, 1995.]] Google ScholarDigital Library
- Takagi, H., "Interactive Evolutionary Computation: System Optimisation Based on Human Subjective Evaluation," Proceedings of the IEEE Intelligent Engineering Systems (INES'98) Vienna, Austria, 1998.]]Google Scholar
- Ohsaki M., Sakamoto S., Takagi H., "Development and Evaluation of an IEC Fitting System for Hearing Aids," International Conference on Acoustics (ICA2001), Rome, Italy, 5A.15.02 (Sept. 2--7, 2001).]]Google Scholar
- Takagi, H., "Interactive Evolution Computation: Fusion of the Capabilities of EC Optimization and Human Evaluation," Proceedings of the IEEE, Vol. 89, No 9, Sept 2002, pp 1275--1296.]]Google Scholar
Index Terms
- Using an interactive evolutionary algorithm to help fitting a cochlear implant
Recommendations
An interactive evolutionary algorithm for cochlear implant fitting: first results
SAC '05: Proceedings of the 2005 ACM symposium on Applied computingIn a previous SAC-COMPAHEC paper[1], a method was presented using an interactive evolutionary algorithm for cochlear implants fitting.The method has recently been put to test, with very unexpected and encouraging results: in a few words, it seems that ...
Automatic fitting of cochlear implants with evolutionary algorithms
SAC '04: Proceedings of the 2004 ACM symposium on Applied computingThis paper presents an optimisation algorithm designed to perform in-situ automatic fitting of cochlear implants.All patients are different, which means that cochlear parametrisation is a difficult and long task, with results ranging from perfect blind ...
Multi-channel Convolutional Neural Networks for Automatic Detection of Speech Deficits in Cochlear Implant Users
Progress in Pattern Recognition, Image Analysis, Computer Vision, and ApplicationsAbstractThis paper proposes a methodology for automatic detection of speech disorders in Cochlear Implant users by implementing a multi-channel Convolutional Neural Network. The model is fed with a 2-channel input which consists of two spectrograms ...
Comments