Abstract
The completely paralyzed and quadriplegic patients cannot communicate with others. However, the imagined thoughts of these patients can be used to drive assistive devices by brain-computer interfacing (BCI), the success of which relies on better classification accuracies. In this paper, we have performed an experiment for the classification of imagined words, which can provide an alternative neural path of speech communication for deprived people. A 32-channel industry-standard physiological signal system is used to measure imagined electroencephalogram (EEG) signals of five words (sos, stop, medicine, washroom, comehere) from 13 subjects. We have used the Hilbert transform to calculate time and joint time–frequency features from the imagined EEG signals. The above features are extracted individually in electrodes corresponding to nine brain regions. Each region of the brain is further analyzed in seven EEG frequency bands. The imagined speech features from each of the 63 combinations of brain region and frequency band are classified by the proposed deep architectures like long short term memory (LSTM), gated recurrent unit, and convolutional neural network (CNN). Some combinations are also classified by six traditional machine learning classifiers for performance comparison. In a five-class classification framework, we achieved the average and maximum accuracy of 71.75% and 94.29%. CNN gave high accuracy, but LSTM gave less network prediction time. Our results show that the alpha band can classify imagined speech better than other frequency bands. We have implemented subject-independent BCI, and the results are better than the state-of-the-art methods present in the literature.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
Agarwal P, Kumar S (2021) Transforming Imagined Thoughts into Speech Using a Covariance-Based Subset Selection Method. Indian J Pure Appl Phys; 59:180–3. http://nopr.niscair.res.in/handle/123456789/56517. Accessed 5 Jan 2022
Agarwal P, Kumar S (2022) Electroencephalography based imagined alphabets classification using spatial and time-domain features. Int J Imaging Syst Technol 32:111–122. https://doi.org/10.1002/ima.22655
Asghari Bejestani MR, Mohammad Khani GhR, Nafisi VR, Darakeh F (2022) EEG-Based Multiword Imagined Speech Classification for Persian Words. BioMed Res Int 2022:8333084. https://doi.org/10.1155/2022/8333084
Bakhshali MA, Khademi M, Ebrahimi-Moghadam A, Moghimi S (2020) EEG signal classification of imagined speech based on Riemannian distance of correntropy spectral density. Biomed Signal Process Control 59:101899. https://doi.org/10.1016/j.bspc.2020.101899
Cho K, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, et al. (2014) Learning phrase representations using rnn encoder-decoder for statistical machine translation. ArXiv:14061078 v3[CsCL]
D’Zmura M, Deng S, Lappas T, Thorpe S, Srinivasan R. (2009) Toward EEG Sensing of Imagined Speech. In: Jacko JA, editor. Human-Computer Interaction. New Trends, vol. 5610, Berlin, Heidelberg: Springer; p. 40–8
DaSalla CS, Kambara H, Sato M, Koike Y (2009) Single-trial classification of vowel speech imagery using common spatial patterns. Neural Netw 22:1334–1339. https://doi.org/10.1016/j.neunet.2009.05.008
Deng S, Srinivasan R, Lappas T, D’Zmura M (2010) EEG classification of imagined syllable rhythm using Hilbert spectrum methods. J Neural Eng 7:046006. https://doi.org/10.1088/1741-2560/7/4/046006
Dewan EM (1967) Occipital Alpha Rhythm Eye Position and Lens Accommodation. Nature 214:975–7. https://doi.org/10.1038/214975a0
Esfahani ET, Sundararajan V (2012) Classification of primitive shapes using brain-computer interfaces. Comput Aided Des 44:1011–1019. https://doi.org/10.1016/j.cad.2011.04.008
Fujimaki N, Takeuchi F, Kobayashi T, Kuriki S, Hasuo S (1994) Event-related potentials in silent speech. Brain Topogr 6:259–267. https://doi.org/10.1007/BF01211171
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS) 2010, vol. 9, Chia Laguna Resort, Sardinia, Italy: JMLR: W&CP 9; p. 249–56
Hahn SL (1996) Hilbert transforms in signal processing. eBook. Boston. Artech House, USA
Hochreiter S, Schmidhuber J (1997) Long Short-Term Memory. Neural Comput 9:1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Huang NE, Attoh-Okine (Eds.) NO (2005) The Hilbert-Huang Transform in Engineering. 1st ed. Boca Raton, Florida, USA: CRC Press; https://doi.org/10.1201/9781420027532
Huang NE, Samuel SPS (2014) Hilbert-Huang transform and its applications. vol. 16. 2nd ed. World Scientific. Singapore
Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q et al (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Math Phys Eng Sci 454:903–995. https://doi.org/10.1098/rspa.1998.0193
Kaushik P, Gupta A, Roy PP, Dogra DP (2019) EEG-Based Age and Gender Prediction Using Deep BLSTM-LSTM Network Model. IEEE Sens J 19:2634–2641. https://doi.org/10.1109/JSEN.2018.2885582
Khademi S, Neghabi M, Farahi M, Shirzadi M, Marateb HR. 2 - A comprehensive review of the movement imaginary brain-computer interface methods: Challenges and future directions. In: Bajaj V, Sinha GR, editors. Artificial Intelligence-Based Brain-Computer Interface, Academic Press; 2022, p. 23–74. https://doi.org/10.1016/B978-0-323-91197-9.00004-7
Kingma DP, Ba J (2014) Adam: A Method for Stochastic Optimization. ArXiv:14126980 [CsLG]
Klem GH, Lüders HO, Jasper HH, Elger C (1999) The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology. Electroencephalogr Clin Neurophysiol Suppl 52:3–6. https://doi.org/10.1080/00029238.1961.11080571
Kristensen AB, Subhi Y, Puthusserypady S (2020) Vocal Imagery vs Intention: Viability of Vocal-Based EEG-BCI Paradigms. IEEE Trans Neural Syst Rehabilitation Eng 28:1750–1759. https://doi.org/10.1109/TNSRE.2020.3004924
Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet Classification with Deep Convolutional Neural Networks. Commun ACM 60:84–90. https://doi.org/10.1145/3065386
Kumar P, Saini R, Roy PP, Sahu PK, Dogra DP (2018) Envisioned speech recognition using EEG sensors. Pers Ubiquitous Comput 22:185–199. https://doi.org/10.1007/s00779-017-1083-4
La Vaque TJ (1999) The History of EEG Hans Berger: Psychophysiologist. A Historical Vignette. J Neurother 3:1–9. https://doi.org/10.1300/J184v03n02_01
LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W et al (1989) Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput 1:541–551. https://doi.org/10.1162/neco.1989.1.4.541
Martin S, Brunner P, Iturrate I, Millán J del R, Schalk G, Knight RT, et al. (2016) Word pair classification during imagined speech using direct brain recordings. Sci Rep; 6. https://doi.org/10.1038/srep25803
Nguyen CH, Karavas GK, Artemiadis P (2017) Inferring imagined speech using EEG signals: a new approach using Riemannian manifold features. J Neural Eng 15:016002. https://doi.org/10.1088/1741-2552/aa8235
Nie K, Barco A, Zeng F-G (2006) Spectral and temporal cues in cochlear implant speech perception. Ear Hear 27:208–217. https://doi.org/10.1097/01.aud.0000202312.31837.25
Panachakel JT, Ramakrishnan AG, Ananthapadmanabha TV (2019) Decoding Imagined Speech using Wavelet Features and Deep Neural Networks. 2019 IEEE 16th India Council International Conference (INDICON), Rajkot, India: IEEE; p. 1–4. https://doi.org/10.1109/INDICON47234.2019.9028925
Porbadnigk A, Wester M, Calliess J, Schultz T. EEG-based speech recognition- impact of temporal effects. Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - BIOSIGNALS, (BIOSTEC 2009), Porto, Portugal: 2009, p. 376–81. https://doi.org/10.5220/0001554303760381
Qureshi MNI, Min B, Park H, Cho D, Choi W, Lee B (2018) Multiclass Classification of Word Imagination Speech With Hybrid Connectivity Features. IEEE Trans Biomed Eng 65:2168–2177. https://doi.org/10.1109/TBME.2017.2786251
Ramadan RA, Vasilakos AV (2017) Brain computer interface: control signals review. Neurocomputing 223:26–44. https://doi.org/10.1016/j.neucom.2016.10.024
Recio-Spinoso A, Fan Y-H, Ruggero MA (2011) Basilar-Membrane Responses to Broadband Noise Modeled Using Linear Filters With Rational Transfer Functions. IEEE Trans Biomed Eng 58:1456–1465. https://doi.org/10.1109/TBME.2010.2052254
Rezazadeh Sereshkeh A, Trott R, Bricout A, Chau T (2017) EEG Classification of Covert Speech Using Regularized Neural Networks. IEEE/ACM Trans Audio, Speech, Language Process 25:2292–2300. https://doi.org/10.1109/TASLP.2017.2758164
Roy AM (2022) An efficient multi-scale CNN model with intrinsic feature integration for motor imagery EEG subject classification in brain-machine interfaces. Biomed Signal Process Control 74:103496. https://doi.org/10.1016/j.bspc.2022.103496
Roy Y, Banville H, Albuquerque I, Gramfort A, Falk TH, Faubert J (2019) Deep learning-based electroencephalography analysis: a systematic review. J Neural Eng 16:051001. https://doi.org/10.1088/1741-2552/ab260c. Accessed 5 Jan 2022
Saxe AM, McClelland JL, Ganguli S (2013) Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. ArXiv:13126120 [CsNE]
Sereshkeh AR, Trott R, Bricout A, Chau T (2017) Online EEG Classification of Covert Speech for Brain-Computer Interfacing. Int J Neural Syst 27:1750033. https://doi.org/10.1142/S0129065717500332
Sreeja SR, Himanshu, Samanta D (2020) Distance-based weighted sparse representation to classify motor imagery EEG signals for BCI applications. Multimed Tools Appl 79:13775–93. https://doi.org/10.1007/s11042-019-08602-0
Torres-García AA, Reyes-García CA, Villaseñor-Pineda L, García-Aguilar G (2016) Implementing a fuzzy inference system in a multi-objective EEG channel selection model for imagined speech classification. Expert Syst Appl 59:1–12. https://doi.org/10.1016/j.eswa.2016.04.011
Wang L, Liu X, Liang Z, Yang Z, Hu X (2019) Analysis and classification of hybrid BCI based on motor imagery and speech imagery. Measurement 147:106842. https://doi.org/10.1016/j.measurement.2019.07.070
Xu F, Xu X, Sun Y, Li J, Dong G, Wang Y et al (2022) A framework for motor imagery with LSTM neural network. Comput Methods Programs Biomed 218:106692. https://doi.org/10.1016/j.cmpb.2022.106692
Zhang Y, Zhang S, Ji X (2018) EEG-based classification of emotions using empirical mode decomposition and autoregressive model. Multimed Tools Appl 77:26697–26710. https://doi.org/10.1007/s11042-018-5885-9
Zhao S, Rudzicz F (2015) Classifying phonological categories in imagined and articulated speech. 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, Australia: IEEE; p. 992–6. https://doi.org/10.1109/ICASSP.2015.7178118
Author information
Authors and Affiliations
Contributions
1) Prabhakar Agarwal: Conceptualization, Formal Analysis, Investigation, Methodology, Software, Visualization, Writing- Original Draft
2) Sandeep Kumar: Data Curation, Investigation, Project Administration, Resources, Supervision, Writing- Reviewing and Editing
Corresponding author
Ethics declarations
Research involving Human Participants and/or Animals
The subjects voluntarily participated and submitted written consent for the experiment. Their identity was maintained confidential throughout the work.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Conflicts of interest
There is no conflict of interest between the authors regarding the manuscript preparation and submission.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Agarwal, P., Kumar, S. EEG-based imagined words classification using Hilbert transform and deep networks. Multimed Tools Appl 83, 2725–2748 (2024). https://doi.org/10.1007/s11042-023-15664-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15664-8