OpenLB
Open Library of Bioscience
Advanced Search
Frontiers in human neuroscience
2021;15 636191.

Decoding Multiple Sound-Categories in the Auditory Cortex by Neural Networks: An fNIRS Study.

So-Hyeon Yoo, Hendrik Santosa, Chang-Seok Kim, Keum-Shik Hong
Author Information
  1. So-Hyeon Yoo: School of Mechanical Engineering, Pusan National University, Busan, South Korea.
  2. Hendrik Santosa: Department of Radiology, University of Pittsburgh, Pittsburgh, PA, United States.
  3. Chang-Seok Kim: Department of Cogno-Mechatronics Engineering, Pusan National University, Busan, South Korea.
  4. Keum-Shik Hong: School of Mechanical Engineering, Pusan National University, Busan, South Korea.
PMID: 33994978 DOI: 10.3389/fnhum.2021.636191

Abstract

This study aims to decode the hemodynamic responses (HRs) evoked by multiple sound-categories using functional near-infrared spectroscopy (fNIRS). The six different sounds were given as stimuli (English, non-English, annoying, nature, music, and gunshot). The oxy-hemoglobin (HbO) concentration changes are measured in both hemispheres of the auditory cortex while 18 healthy subjects listen to 10-s blocks of six sound-categories. Long short-term memory (LSTM) networks were used as a classifier. The classification accuracy was 20.38 ± 4.63% with six class classification. Though LSTM networks' performance was a little higher than chance levels, it is noteworthy that we could classify the data subject-wise without feature selections.

Keywords

auditory cortex decoding deep learning functional near-infrared spectroscopy (fNIRS) long short-term memories (LSTMs)

References

  1. Front Neurorobot. 2020 Oct 15;14:54 [PMID: 33178005]
  2. Front Behav Neurosci. 2014 Dec 09;8:418 [PMID: 25538583]
  3. Interdiscip Sci. 2020 Dec;12(4):383-394 [PMID: 32833194]
  4. Front Hum Neurosci. 2014 Jan 16;7:935 [PMID: 24474913]
  5. Biomed Opt Express. 2015 Sep 22;6(10):4063-78 [PMID: 26504654]
  6. Ann N Y Acad Sci. 2015 Mar;1337:7-15 [PMID: 25773611]
  7. Neuroimage. 2016 Jan 1;124(Pt A):536-549 [PMID: 26343322]
  8. Front Hum Neurosci. 2019 Sep 24;13:331 [PMID: 31607880]
  9. Neuroimage. 2009 Mar;45(1 Suppl):S199-209 [PMID: 19070668]
  10. Ear Hear. 2015 May-Jun;36(3):e76-85 [PMID: 25437140]
  11. Proc Natl Acad Sci U S A. 2014 Apr 22;111(16):5837-41 [PMID: 24706790]
  12. J Neural Eng. 2012 Apr;9(2):026011 [PMID: 22333135]
  13. Int J Neural Syst. 2020 Jan;30(1):1950018 [PMID: 31366249]
  14. Front Hum Neurosci. 2020 Aug 14;14:308 [PMID: 32922273]
  15. Front Hum Neurosci. 2020 Feb 20;14:34 [PMID: 32153375]
  16. Neuroimage. 2012 Mar;60(1):673-82 [PMID: 22230949]
  17. Hear Res. 2014 Mar;309:84-93 [PMID: 24342740]
  18. Int J Neural Syst. 2019 Nov;29(9):1950015 [PMID: 31262216]
  19. Front Hum Neurosci. 2015 Jan 06;8:1029 [PMID: 25646077]
  20. Front Psychol. 2015 Jun 02;6:709 [PMID: 26082733]
  21. J Biomed Opt. 2019 Feb;24(5):1-9 [PMID: 30734544]
  22. Nat Rev Neurosci. 2014 Jun;15(6):355-66 [PMID: 24840800]
  23. J Neural Eng. 2007 Jun;4(2):R1-R13 [PMID: 17409472]
  24. Front Hum Neurosci. 2019 Sep 06;13:317 [PMID: 31551741]
  25. Hear Res. 2010 Dec 1;270(1-2):39-47 [PMID: 20888894]
  26. J Speech Lang Hear Res. 2008 Aug;51(4):1026-41 [PMID: 18658069]
  27. Curr Alzheimer Res. 2020;17(13):1145-1160 [PMID: 33583382]
  28. Front Hum Neurosci. 2020 Sep 15;14:338 [PMID: 33100985]
  29. Front Neurorobot. 2019 Jul 11;13:50 [PMID: 31396070]
  30. Phys Med Biol. 1993 Dec;38(12):1859-76 [PMID: 8108489]
  31. Neuroimage. 2015 Dec;123:22-32 [PMID: 26306991]
  32. Front Neurosci. 2019 Nov 08;13:1120 [PMID: 31780879]
  33. Comput Biol Med. 2018 Aug 1;99:24-37 [PMID: 29807250]
  34. Front Hum Neurosci. 2019 Nov 22;13:408 [PMID: 31824275]
  35. Front Hum Neurosci. 2014 Apr 28;8:244 [PMID: 24808844]
  36. Neural Comput. 1997 Nov 15;9(8):1735-80 [PMID: 9377276]
  37. Nature. 2013 Oct 24;502(7472):428-30 [PMID: 24153277]
  38. PLoS Biol. 2012 Jan;10(1):e1001251 [PMID: 22303281]
  39. Nat Commun. 2019 Mar 21;10(1):1302 [PMID: 30899018]
  40. Neuroimage. 2013 Sep;78:249-60 [PMID: 23587693]
  41. Int J Neural Syst. 2019 Feb;29(1):1850014 [PMID: 29768971]
  42. PLoS One. 2015 Feb 18;10(2):e0117303 [PMID: 25692885]
  43. Front Hum Neurosci. 2020 May 15;14:164 [PMID: 32670034]
  44. Front Neurorobot. 2019 Jul 04;13:47 [PMID: 31333442]
  45. J Neuroeng Rehabil. 2009 Nov 09;6:39 [PMID: 19900285]
  46. J Med Internet Res. 2019 Jun 28;21(6):e13594 [PMID: 31254336]
  47. Front Hum Neurosci. 2019 Jan 11;12:505 [PMID: 30687038]
  48. Curr Biol. 2009 Mar 24;19(6):498-502 [PMID: 19268594]
  49. Front Neurosci. 2019 May 01;13:434 [PMID: 31118882]
  50. Front Aging Neurosci. 2020 May 21;12:141 [PMID: 32508627]
  51. Front Neurosci. 2020 Apr 09;14:251 [PMID: 32327965]
  52. Front Neurosci. 2019 Jul 09;13:692 [PMID: 31354409]
  53. Front Neurosci. 2015 Jun 12;9:217 [PMID: 26124702]
  54. Hear Res. 2016 Mar;333:157-166 [PMID: 26828741]
  55. Front Neurosci. 2020 Feb 07;14:26 [PMID: 32116494]
  56. Int J Neural Syst. 2019 Oct;29(8):1950006 [PMID: 30854906]
  57. Front Hum Neurosci. 2020 Apr 07;14:70 [PMID: 32317947]
  58. Hear Res. 2015 Jul;325:55-63 [PMID: 25819496]
  59. Front Neurorobot. 2019 Nov 15;13:95 [PMID: 31803041]
  60. Front Neurosci. 2019 Oct 04;13:1052 [PMID: 31636532]
  61. Nat Neurosci. 2007 Apr;10(4):420-2 [PMID: 17351633]
  62. Neuroimage. 2006 Aug 15;32(2):771-7 [PMID: 16829140]
  63. Hum Brain Mapp. 2004 Aug;22(4):341-9 [PMID: 15202112]
  64. Nat Rev Neurosci. 2004 Nov;5(11):887-92 [PMID: 15496866]
  65. Neuroimage. 2011 Apr 1;55(3):1200-7 [PMID: 21236348]
  66. Front Neurorobot. 2020 Sep 15;14:62 [PMID: 33041778]
  67. Front Neurorobot. 2019 Jun 28;13:40 [PMID: 31316366]
  68. Sci Rep. 2019 Dec 4;9(1):18262 [PMID: 31797878]
Journal Article
Article has an altmetric score of 1

Word Cloud

Created with Highcharts 10.0.0fNIRSsixsound-categoriesfunctionalnear-infraredspectroscopyauditorycortexshort-termLSTMclassificationstudyaimsdecodehemodynamicresponsesHRsevokedmultipleusingdifferentsoundsgivenstimuliEnglishnon-Englishannoyingnaturemusicgunshotoxy-hemoglobinHbOconcentrationchangesmeasuredhemispheres18healthysubjectslisten10-sblocksLongmemorynetworksusedclassifieraccuracy2038±463%classThoughnetworks'performancelittlehigherchancelevelsnoteworthyclassifydatasubject-wisewithoutfeatureselectionsDecodingMultipleSound-CategoriesAuditoryCortexNeuralNetworks:StudydecodingdeeplearninglongmemoriesLSTMs

Similar Articles

Cited By