A Novel Unsupervised Spectral Clustering for Pure-Tone Audiograms towards Hearing Aid Filter Bank Design and Initial Configurations
Source abstract
Abstract
The current practice of adjusting hearing aids (HA) is tiring and time-consuming for both patients and audiologists. Of hearing-impaired people, 40–50% are not satisfied with their HAs. In addition, good designs of HAs are often avoided since the process of fitting them is exhausting. To improve the fitting process, a machine learning (ML) unsupervised approach is proposed to cluster the pure-tone audiograms (PTA). This work applies the spectral clustering (SP) approach to group audiograms according to their similarity in shape. Different SP approaches are tested for best results and these approaches were evaluated by Silhouette, Calinski-Harabasz, and Davies-Bouldin criteria values. Kutools for Excel add-in is used to generate audiograms’ population, annotated using the results from SP, and different criteria values are used to evaluate population clusters. Finally, these clusters are mapped to a standard set of audiograms used in HA characterization. The results indicated that grouping the data in 8 groups or 10 results in ones with high evaluation criteria. The evaluation for population audiograms clusters shows good performance, as it resulted in a Silhouette coefficient >0.5. This work introduces a new concept to classify audiograms using an ML algorithm according to the audiograms’ similarity in shape.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Speech and Audio Processing · Music and Audio Processing · Hearing Loss and Rehabilitation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Advanced Communication Engineering, Centre of Excellence (ACE), Universiti Malaysia Perlis (UniMAP), Kangar 01000, Perlis, Malaysia
Faculty of Electronic Engineering Technology, Universiti Malaysia Perlis (UniMAP), Arau 02600, Perlis, Malaysia
Faculty of Engineering and Information Sciences, University of Wollongong in Dubai, Dubai 20183, United Arab Emirates
Faculty of Electrical Engineering Technology, Universiti Malaysia Perlis (UniMAP), Arau 02600, Perlis, Malaysia
Biotechnology Research Institute, Universiti Malaysia Sabah (UMS), Jln UMS, Kota Kinabalu 88400, Sabah, Malaysia
References (48)
Show source-provided references
1. WHO (2020, April 01). Deafness and Hearing Loss, Available online: https://www.who.int/news-room/fact-sheets/detail/deafness-and-hearing-loss.
2. Bagozzi, D. (2021, June 15). WHO Calls on Private Sector to Provide Affordable Hearing Aids in Developing World. Available online: https://www.who.int/news/item/11-07-2001-who-calls-on-private-sector-to-provide-affordable-hearing-aids-in-developing-world.
3. Whelan, C. (2020, February 25). What to Know about Hearing Aid Costs. Available online: https://www.healthline.com/health/cost-of-hearing-aids#a-quick-look-at-costs.
4. Design and implementation of reconfigurable filter bank structure for low complexity hearing aids using 2-level sound wave decomposition10.1016/j.bspc.2018.02.020 ↗
5. Design of Low Complexity Adjustable Filter Bank for Personalized Hearing Aid Solutions10.1109/TASLP.2015.2409774 ↗
6. A Reconfigurable Sound Wave Decomposition Filterbank for Hearing Aids Based on Nonlinear Transformation10.1109/TBCAS.2015.2436916 ↗
7. Design of reconfigurable low-complexity digital hearing aid using Farrow structure based variable bandwidth filters10.1016/j.jart.2016.03.005 ↗
8. High performance continuous variable bandwidth digital filter design for hearing aid application10.1016/j.aeue.2018.05.006 ↗
9. Low-complexity implementation of efficient reconfigurable structure for cost-effective hearing aids using fractional interpolation10.1016/j.compeleceng.2019.02.008 ↗
10. A 16-Channel Low-Power Nonuniform Spaced Filter Bank Core for Digital Hearing Aids10.1109/TCSII.2006.881821 ↗
11. Girish, G.K., and Pinjare, S.L. (2016, January 3–5). Audiogram equalizer using fast fourier transform. Proceedings of the 2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), Paralakhemundi, India.10.1109/SCOPES.2016.7955772 ↗
12. Data-Driven Audiogram Classification for Mobile Audiometry10.1038/s41598-020-60898-3 ↗
13. AutoAudio: Deep Learning for Automatic Audiogram Interpretation10.1007/s10916-020-01627-1 ↗
14. Liang, R., Guo, R., Xi, J., Xie, Y., and Zhao, L. (2017). Self-Fitting Algorithm for Digital Hearing Aid Based on Interactive Evolutionary Computation and Expert System. Appl. Sci., 7.10.3390/app7030272 ↗
15. Standard audiograms for the IEC 60118-15 measurement procedure10.1177/1084713810379609 ↗
16. Clason, D. (2020, April 04). Understanding the Degrees of Hearing Loss. Available online: https://www.healthyhearing.com/report/41775-Degrees-of-hearing-loss.
17. BSA FAQs (2020, March 20). British Society of Audiology. Available online: https://www.thebsa.org.uk/public-engagement/faqs/.
18. A software tool for puretone audiometry. Classification of audiograms for inclusion of patients in clinical trials. English version10.1007/s00106-015-0089-3 ↗
19. Data-Driven Approach for Auditory Profiling and Characterization of Individual Hearing Loss
20. A Machine Learning Based Clustering Protocol for Determining Hearing Aid Initial Configurations from Pure-Tone Audiograms
21. Charih, F., Bromwich, M., Lefrancois, R., Mark, A.E., and Green, J.R. (2018, January 11–13). Mining Audiograms to Improve the Interpretability of Automated Audiometry Measurements. Proceedings of the 2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Rome, Italy.10.1109/MeMeA.2018.8438746 ↗
22. Classification of audiograms in the prevention of noise-induced hearing loss: A clinical perspective
23. A Novel Method for Classifying Hearing Impairment in Epidemiological Studies of Aging: The Wisconsin Age-Related Hearing Impairment Classification Scale10.1044/2019_AJA-19-00021 ↗
24. Spectral methods for graph clustering—A survey10.1016/j.ejor.2010.08.012 ↗
25. (2021, April 01). Matlab Spectralcluster. Available online: https://se.mathworks.com/help/stats/spectralcluster.html#mw_d30c2539-9b01-4ee2-a5f6-9018ca8021e0.
26. Exploratory Item Classification Via Spectral Graph Clustering10.1177/0146621617692977 ↗
27. Research on Spectral Clustering10.4028/www.scientific.net/AMM.687-691.1350 ↗
28. Aggarwal, C.C., and Reddy, C.K. (2013). Data Clustering: Algorithms and Applications, CRC Press LLC.10.1201/b15410 ↗
29. Sammut, C., and Webb, G.I. (2010). K-Medoids Clustering. Encyclopedia of Machine Learning, Springer.10.1007/978-0-387-30164-8 ↗
30. Shiledarbaxi, N. (2021, April 25). Comprehensive Guide to K-Medoids Clustering Algorithm. Analytics India Magazine. Available online: https://analyticsindiamag.com/comprehensive-guide-to-k-medoids-clustering-algorithm/.
31. A tutorial on spectral clustering10.1007/s11222-007-9033-z ↗
32. A Hierarchical Clustering algorithm based on Silhouette Index for cancer subtype discovery from genomic data10.1007/s00521-019-04636-5 ↗
33. Shutaywi, M., and Kachouie, N.N. (2021). Silhouette Analysis for Performance Evaluation in Machine Learning with Applications to Clustering. Entropy, 23.10.3390/e23060759 ↗
34. Liu, E. (2021, July 15). Calinski-Harabasz Index and Boostrap Evaluation with Clustering Methods. Available online: https://ethen8181.github.io/machine-learning/clustering_old/clustering/clustering.html.
35. Rhys, H. (2020). Machine Learning with R, the Tidyverse, and mlr. Manning.
36. Wei, H. (2021, June 01). How to Measure Clustering Performances When There Are No Ground Truth?. Available online: https://medium.com/@haataa/how-to-measure-clustering-performances-when-there-are-no-ground-truth-db027e9a871c.
37. Floudas, C.A., and Pardalos, P.M. (2009). Determining the optimal number of clustersDetermining the Optimal Number of Clusters. Encyclopedia of Optimization, Springer.10.1007/978-0-387-74759-0 ↗
38. Dudek, A. (2021). Evaluation of Two-Step Spectral Clustering Algorithm for Large Untypical Data Sets. Data Analysis and Classification, Springer.10.1007/978-3-030-75190-6_1 ↗
39. Li, T., Zhang, Y., Liu, H., Xue, G., and Liu, L. (2019). Fast Compressive Spectral Clustering for Large-Scale Sparse Graph. IEEE Trans. Big Data, 1.
40. Shinnou, H., and Sasaki, M. (2008). Spectral Clustering for a Large Data Set by Reducing the Similarity Matrix Size. The International Conference on Language Resources and Evaluation, European Language Resources Association (ELRA).
41. Vector quantization based approximate spectral clustering of large datasets10.1016/j.patcog.2012.02.012 ↗
42. Fast kernel spectral clustering10.1016/j.neucom.2016.12.085 ↗
43. Fast Large-Scale Spectral Clustering via Explicit Feature Mapping10.1109/TCYB.2018.2794998 ↗
44. A general framework for scalable spectral clustering based on document models10.1016/j.patrec.2019.06.010 ↗
45. Comparing partitions10.1007/BF01908075 ↗
46. A novel design and implementation technique for low complexity variable digital filters using multi-objective artificial bee colony optimization and a minimal spanning tree approach10.1016/j.engappai.2016.12.011 ↗
47. Elkhouly, A., Rahim, H.A., Abdulaziz, N., and Abd Malek, M.F. (2020, January 3–5). Modelling Audiograms for People with Dementia Who Experience Hearing Loss Using Multiple Linear Regression Method. Proceedings of the 2020 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI), Sharjah, United Arab Emirates.10.1109/CCCI49893.2020.9256679 ↗
48. Ahmad, M.I., Husin, Z., Ahmad, R.B., Rahim, H.A., Hassan, M.S.A., and Md Isa, M.N. (2008, January 13–15). FPGA based control IC for multilevel inverter. Proceedings of the 2008 International Conference on Computer and Communication Engineering, Kuala Lumpur, Malaysia.10.1109/ICCCE.2008.4580620 ↗