No Access
Emotion Classification from EEG with a Low-Cost BCI Versus a High-End Equipment
https://doi.org/10.1142/S0129065722500411Cited by:7 (Source: Crossref)
Abstract
The assessment of physiological signals such as the electroencephalography (EEG) has become a key point in the research area of emotion detection. This study compares the performance of two EEG devices, a low-cost brain–computer interface (BCI) (Emotiv EPOC+) and a high-end EEG (BrainVision), for the detection of four emotional conditions over 20 participants. For that purpose, signals were acquired with both devices under the same experimental procedure, and a comparison was made under three different scenarios, according to the number of channels selected and the sampling frequency of the signals analyzed. A total of 16 statistical, spectral and entropy features were extracted from the EEG recordings. A statistical analysis revealed a major number of statistically significant features for the high-end EEG than the BCI device under the three comparative scenarios. In addition, different machine learning algorithms were used for evaluating the classification performance of the features extracted from high-end EEG and low-cost BCI in each scenario. Artificial neural networks reported the best performance for both devices with an F-score of 75.08% for BCI and 98.78% for EEG. Although the professional EEG outcomes were higher than the low-cost BCI ones, both devices demonstrated a notable performance for the classification of the four emotional conditions.
References
- 1. , A categorized list of emotion definitions, with suggestions for a consensual definition, Motiv. Emot. 5(4) (1981) 345–379. Crossref, Google Scholar
- 2. , The many meanings/aspects of emotion: Definitions, functions, activation, and regulation, Emot. Rev. 2(4) (2010) 363–370. Crossref, Google Scholar
- 3. ,
A framework for recognizing and regulating emotions in the elderly , in Ambient Assisted Living and Daily Activities, eds. L. Pecchia, L. L. Chen, C. Nugent and J. Bravo (Springer International Publishing, Cham, 2014), pp. 320–327. Crossref, Google Scholar - 4. , Deep support vector machines for the identification of stress condition from electrodermal activity, Int. J. Neural Syst. 30(07) (2020) 2050031. Link, Web of Science, Google Scholar
- 5. , Real-time multi-modal estimation of dynamically evoked emotions using EEG, heart rate and galvanic skin response, Int. J. Neural Syst. 30(04) (2020) 2050013. Link, Web of Science, Google Scholar
- 6. , Neural networks with emotion associations, topic modeling and supervised term weighting for sentiment analysis, Int. J. Neural Syst. 31(10) (2021) 2150013. Link, Web of Science, Google Scholar
- 7. , Upper limb movement classification via electromyographic signals and an enhanced probabilistic network, J. Med. Syst. 44(10) (2020) 1–12. Crossref, Web of Science, Google Scholar
- 8. , A circumplex model of affect, J. Pers. Soc. Psychol. 39(6) (1980) 1161. Crossref, Web of Science, Google Scholar
- 9. , Multiscale entropy analysis for recognition of visually elicited negative stress from EEG recordings, Int. J. Neural Syst. 29(02) (2019) 1850038. Link, Web of Science, Google Scholar
- 10. , Multi-lag analysis of symbolic entropies on EEG recordings for distress recognition, Front. Neuroinform. 13 (2019) 40. Crossref, Medline, Web of Science, Google Scholar
- 11. , Cortical asymmetries and connectivity patterns in the valence dimension of the emotional brain, Int. J. Neural Syst. 30(05) (2020) 2050021. Link, Web of Science, Google Scholar
- 12. , Recognition of emotional states from EEG signals with nonlinear regularity- and predictability-based entropy metrics, Cogn. Comput. 13 (2021) 403–417. Crossref, Web of Science, Google Scholar
- 13. , A review on nonlinear methods using electroencephalographic recordings for emotion recognition, IEEE Trans. Affect. Comput. 12(03) (2021) 801–820. Crossref, Web of Science, Google Scholar
- 14. , Brain functional connectivity patterns for emotional state classification in Parkinson’s disease patients without dementia, Behav. Brain Res. 298 (2016) 248–260. Crossref, Medline, Web of Science, Google Scholar
- 15. , Spotting psychopaths using technology, Rev. Neurosci. 26(6) (2015) 721–732. Crossref, Medline, Web of Science, Google Scholar
- 16. J. Bajada and F. B. Bonello, arXiv:2110.05635. Google Scholar
- 17. , Emotiv EPOC neuroheadset in brain-computer interface, in 15th Int. Carpathian Control Conf. (IEEE, 2014), pp. 149–152. Crossref, Google Scholar
- 18. BrainVision, BrainAmp MR (2020). Google Scholar
- 19. , Measuring concentration while programming with low-cost BCI devices: Differences between debugging and creativity tasks, in Int. Conf. Augmented Cognition (Springer, 2015), pp. 605–615. Crossref, Google Scholar
- 20. , A wearable home BCI system: Preliminary results with SSVEP protocol, in 2005 IEEE Engineering in Medicine and Biology 27th Annual Conf. (IEEE, 2006), pp. 5384–5387. Google Scholar
- 21. , An analysis of game-related emotions using Emotiv EPOC, in 2018 Federated Conf. Computer Science and Information Systems (IEEE, 2018), pp. 913–917. Google Scholar
- 22. , Neurological assessment of music therapy on the brain using Emotiv EPOC, in 2017 Internet Technologies and Applications (IEEE, 2017), pp. 259–263. Crossref, Google Scholar
- 23. , Commercial wireless versus standard stationary EEG systems for personalized emotional brain-computer interfaces: A preliminary reliability check, Neurosci. Res. Notes 2(1) (2019) 7–15. Crossref, Google Scholar
- 24. , Consumers’ cognitive, emotional and behavioral responses towards background music: An EEG study, in 15th Int. Conf. Web Information Systems and Technologies (Science and Technology Publications, 2019), pp. 314–318. Google Scholar
- 25. , Arousal detection in elderly people from electrodermal activity using musical stimuli, Sensors 20(17) (2020) 4788. Crossref, Web of Science, Google Scholar
- 26. , Implementation of SSVEP based BCI with Emotiv EPOC, in 2012 IEEE Int. Conf. Virtual Environments Human–Computer Interfaces and Measurement Systems (IEEE, 2012), pp. 34–37. Crossref, Google Scholar
- 27. ,
Towards low-cost P300-based BCI using Emotiv EPOC headset , UK Workshop on Computational Intelligence (Springer, 2017), pp. 239–244. Google Scholar - 28. , Cortically coupled computer vision with Emotiv headset using distractor variables, in 2013 IEEE 4th Int. Conf. Cognitive Infocommunications (IEEE, 2013), pp. 245–250. Crossref, Google Scholar
- 29. , Natural environment promotes deeper brain functional connectivity than built environment, BMC Neurosci. 16(1) (2015) 1–2. Crossref, Medline, Web of Science, Google Scholar
- 30. , Measuring brain signals using Emotiv devices, WSEAS Trans. Syst. Control 13 (2018) 537–542. Google Scholar
- 31. M. Lang, Investigating the Emotiv EPOC for cognitive control in limited training time (2012). Engineering Dissertation, University of Canterbury, New Zealand. Google Scholar
- 32. , Convolutional neural network for drowsiness detection using EEG signals, Sensors 21(5) (2021) 1734. Crossref, Web of Science, Google Scholar
- 33. , New EEG measure of the alertness analyzed by Emotiv EPOC in a real working environment, in Int. Congress on Neurotechnology, Electronics and Informatics, Vol. 2 (SCITEPRESS, 2016), pp. 35–42. Crossref, Google Scholar
- 34. , A novel method for sleep-stage classification based on sonification of sleep electroencephalogram signals using wavelet transform and recurrent neural network, Eur. Neurol. 83(5) (2020) 468–486. Crossref, Medline, Web of Science, Google Scholar
- 35. , Comparison of smoothing filters’ influence on quality of data recorded with the Emotiv EPOC flex brain–computer interface headset during audio stimulation, Brain Sci. 11(1) (2021) 98. Crossref, Medline, Web of Science, Google Scholar
- 36. , A new dispersion entropy and fuzzy logic system methodology for automated classification of dementia stages using electroencephalograms, Clin. Neurol. Neurosurg. 201 (2021) 106446. Crossref, Medline, Web of Science, Google Scholar
- 37. , Emotion recognition with eigen features of frequency band activities embedded in induced brain oscillations mediated by affective pictures, Int. J. Neural Syst. 26(03) (2016) 1650013. Link, Web of Science, Google Scholar
- 38. , Discriminating multiple emotional states from EEG using a data-adaptive, multiscale information-theoretic approach, Int. J. Neural Syst. 26(02) (2016) 1650005. Link, Web of Science, Google Scholar
- 39. ,
Classification of basic human emotions from electroencephalography data , in Iberoamerican Congress on Pattern Recognition (Springer, 2015), pp. 108–115. Crossref, Google Scholar - 40. , An extension on “statistical comparisons of classifiers over multiple data sets” for all pairwise comparisons, J. Mach. Learn. Res. 9(12) (2008) 2677–2694. Google Scholar
- 41. , Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers, Expert Syst. Appl. 47 (2016) 35–41. Crossref, Web of Science, Google Scholar
- 42. , A hybrid-domain deep learning-based BCI for discriminating hand motion planning from EEG sources, Int. J. Neural Syst. 31(09) (2021) 2150038. Link, Web of Science, Google Scholar
- 43. , A prototype of EEG system for IoT, Int. J. Neural Syst. 30(07) (2020) 2050018. Link, Web of Science, Google Scholar
- 44. , Dyslexia diagnosis by EEG temporal and spectral descriptors: An anomaly detection approach, Int. J. Neural Syst. 30(07) (2020) 2050029. Link, Web of Science, Google Scholar
- 45. , Quantification of graph complexity based on the edge weight distribution balance: Application to brain networks, Int. J. Neural Syst. 28(01) (2018) 1750032. Link, Web of Science, Google Scholar
- 46. , An efficient deep learning paradigm for deceit identification test on EEG signals, ACM Trans. Manag. Inf. Syst. 12(3) (2021) 1–20. Crossref, Web of Science, Google Scholar
- 47. , Comparison of EEG microstates with resting state fMRI and FDG-PET measures in the default mode network via simultaneously recorded trimodal (PET/MR/EEG) data, Hum. Brain Mapp. 42(13) (2021) 4122–4133. Crossref, Medline, Web of Science, Google Scholar
- 48. , Validation of the Emotiv EPOC EEG system for research quality auditory event-related potentials in children, PeerJ 3 (2015) e907. Crossref, Medline, Web of Science, Google Scholar
- 49. , A P300-based quantitative comparison between the Emotiv EPOC headset and a medical EEG device, Biomed. Eng. 765(1) (2012) 2012–2764. Google Scholar
- 50. , A validation of Emotiv EPOC Flex saline for EEG and ERP research, PeerJ 8 (2020) e9713. Crossref, Medline, Web of Science, Google Scholar
- 51. , EEG wave identification in human brain with Emotiv EPOC for motor imagery, Procedia Comput. Sci. 72 (2015) 269–276. Crossref, Google Scholar
- 52. , Cognitive efficiency in robot control by Emotiv EPOC, in 2014 Int. Conf. Informatics, Electronics & Vision (IEEE, 2014), pp. 1–6. Crossref, Google Scholar
- 53. , Evaluation of consumer EEG device Emotiv EPOC, in MEi:CogSci Conf. (University of Vienna, 2011), p. 99. Google Scholar
- 54. Eprime, Eprime: Psychology Software tools (2020). Google Scholar
- 55. , International affective picture system (IAPS): Technical manual and affective ratings, NIMH Center Study Emotion Attention 1(39–58) (1997) 3. Google Scholar
- 56. , Observations SAM: The Self-Assessment Manikin — An efficient cross-cultural measurement of emotional response, J. Advert. Res. 35(6) (1995) 63–68. Web of Science, Google Scholar
- 57. , FASTER: Fully automated statistical thresholding for EEG artifact rejection, J. Neurosci. Methods 192(1) (2010) 152–162. Crossref, Medline, Web of Science, Google Scholar
- 58. , Adaptive Processing of Brain Signals (John Wiley & Sons, 2013). Crossref, Google Scholar
- 59. , DEAP: A database for emotion analysis using physiological signals, IEEE Trans. Affect. Comput. 3(1) (2012) 18–31. Crossref, Web of Science, Google Scholar
- 60. , Blinking artifact removal in cognitive EEG data using ICA, in 2006 Int. Conf. the IEEE Engineering in Medicine and Biology Society (IEEE, 2006), pp. 5273–5276. Crossref, Google Scholar
- 61. ,
MEG/EEG data analysis using EEGLAB , in Magnetoencephalography: From Signals to Dynamic Cortical Networks (Springer, 2019), pp. 391–406. Crossref, Google Scholar - 62. , EEGLAB: An open source toolbox for analysis of single-trial EEG dynamics including independent component analysis, J. Neurosci. Methods 134(1) (2004) 9–21. Crossref, Medline, Web of Science, Google Scholar
- 63. , One-dimensional convolutional neural networks for low/high arousal classification from electrodermal activity, Biomed. Signal Process. Control 71 (2022) 103203. Crossref, Web of Science, Google Scholar
- 64. , A sliding window common spatial pattern for enhancing motor imagery classification in EEG-BCI, IEEE Trans. Instrum. Meas. 70 (2021) 1–9. Crossref, Medline, Web of Science, Google Scholar
- 65. , The utility of EEG band power analysis in the study of infancy and early childhood, Dev. Neuropsychol. 37(3) (2012) 253–273. Crossref, Medline, Web of Science, Google Scholar
- 66. , Quantitative analysis of EEG power spectrum and EMG median power frequency changes after continuous passive motion mirror therapy system, Sensors 20(8) (2020) 2354. Crossref, Web of Science, Google Scholar
- 67. , A comparison between power spectral density and network metrics: An EEG study, Biomed. Signal Process. Control 57 (2020) 101760. Crossref, Web of Science, Google Scholar
- 68. , Power spectral density and coherence analysis of Alzheimer’s EEG, Cogn. Neurodyn. 9(3) (2015) 291–304. Crossref, Medline, Web of Science, Google Scholar
- 69. , Relative power and coherence of EEG series are related to amnestic mild cognitive impairment in diabetes, Front. Aging Neurosci. 6 (2014) 11. Crossref, Medline, Web of Science, Google Scholar
- 70. , Biomedical Engineering Handbook 2 (Springer Science & Business Media, 2000). Google Scholar
- 71. , Measuring instantaneous and spectral information entropies by Shannon entropy of Choi–Williams distribution in the context of electroencephalography, Entropy 16(5) (2014) 2530–2548. Crossref, Web of Science, Google Scholar
- 72. E. W. Weisstein, Bonferroni correction (2004). Google Scholar
- 73. R. Levesque et al., SPSS programming and data management (2007). Google Scholar
- 74. , IBM SPSS Statistics 25 Step by Step: A Simple Guide and Reference (Routledge, 2018). Google Scholar
- 75. MathWorks, Classification learner (2020). Google Scholar
- 76. ,
Stress identification from electrodermal activity by support vector machines , in Understanding the Brain Function and Emotions, eds. J. Ferrández, J. Álvarez-Sánchez, F. de la Paz, J. Toledo and H. Adeli (Springer, 2019), pp. 202–211. Google Scholar - 77. , Artificial neural networks to assess emotional states from brain–computer interface, Electronics 7(12) (2018) 384. Crossref, Web of Science, Google Scholar
- 78. , Detection of epileptic seizure using pretrained deep convolutional neural network and transfer learning, Eur. Neurol. 83(6) (2020) 602–614. Crossref, Medline, Web of Science, Google Scholar
- 79. , Topological inference for EEG and MEG, Ann. Appl. Stat. 4(3) (2010) 1272–1290. Crossref, Web of Science, Google Scholar
- 80. , Frontal EEG delta/alpha ratio and screening for post-stroke cognitive deficits: The power of four electrodes, Int. J. Psychophysiol. 94(1) (2014) 19–24. Crossref, Medline, Web of Science, Google Scholar
- 81. , EEG-based mild depressive detection using feature selection methods and classifiers, Comput. Methods Programs Biomed. 136 (2016) 151–161. Crossref, Medline, Web of Science, Google Scholar
- 82. , Methods to improve the spatial resolution of EEG, Int. J. Bioelectromagn. 1(1) (1999) 102–111. Google Scholar
- 83. , Deep EEG super-resolution: Upsampling EEG spatial resolution with generative adversarial networks, in 2018 IEEE EMBS Int. Conf. Biomedical & Health Informatics (IEEE, 2018), pp. 100–103. Crossref, Google Scholar
- 84. , Balanced communication-avoiding support vector machine when detecting epilepsy based on EEG signals, Eng. Technol. Appl. Sci. Res. 10(6) (2020) 6462–6468. Crossref, Web of Science, Google Scholar
- 85. , Universum based Lagrangian twin bounded support vector machine to classify EEG signals, Comput. Methods Programs Biomed. 208 (2021) 106244. Crossref, Medline, Web of Science, Google Scholar
- 86. , Classification of EEG signals using neural network and logistic regression, Comput. Methods Programs Biomed. 78(2) (2005) 87–99. Crossref, Medline, Web of Science, Google Scholar
- 87. , EEG based multi-class seizure type classification using convolutional neural network and transfer learning, Neural Netw. 124 (2020) 202–212. Crossref, Medline, Web of Science, Google Scholar
- 88. , Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals, Comput. Biol. Med. 100 (2018) 270–278. Crossref, Medline, Web of Science, Google Scholar
- 89. , A deep convolutional neural network model for automated identification of abnormal EEG signals, Neural Comput. Appl. 32 (2018) 1–12. Web of Science, Google Scholar
- 90. , A deep fourier neural network for seizure prediction using convolutional neural network and ratios of spectral power, Int. J. Neural Syst. 31(8) (2021) 2150022. Link, Web of Science, Google Scholar
- 91. , 3D-convolutional neural network with generative adversarial network and autoencoder for robust anomaly detection in video surveillance, Int. J. Neural Syst. 30(06) (2020) 2050034. Link, Web of Science, Google Scholar
- 92. , Epileptic EEG classification by using time-frequency images for deep learning, Int. J. Neural Syst. 31(8) (2021) 2150026. Link, Web of Science, Google Scholar
- 93. , One dimensional convolutional neural networks for seizure onset detection using long-term scalp and intracranial EEG, Neurocomputing 459 (2021) 212–222. Crossref, Web of Science, Google Scholar
- 94. , MI-EEG temporal information learning based on one-dimensional convolutional neural network, in 35th Youth Academic Annual Conf. Chinese Association of Automation (IEEE, 2020), pp. 499–504. Crossref, Google Scholar
- 95. , Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals, Comput. Biol. Med. 106 (2019) 71–81. Crossref, Medline, Web of Science, Google Scholar
- 96. , Recurrent neural networks employing Lyapunov exponents for EEG signals classification, Expert Syst. Appl. 29(3) (2005) 506–514. Crossref, Web of Science, Google Scholar
- 97. , Enhanced probabilistic neural network with local decision circles: A robust classifier, Integr. Comput. -Aided Eng. 17(3) (2010) 197–210. Crossref, Web of Science, Google Scholar
- 98. , A new neural dynamic classification algorithm, IEEE Trans. Neural Netw. Learn. Syst. 28(12) (2017) 3074–3083. Crossref, Medline, Web of Science, Google Scholar
- 99. , FEMa: A finite element machine for fast learning, Neural Comput. Appl. 32(10) (2020) 6393–6404. Crossref, Web of Science, Google Scholar
- 100. , A dynamic ensemble learning algorithm for neural networks, Neural Comput. Appl. 32(12) (2020) 8675–8690. Crossref, Web of Science, Google Scholar
- 101. , Validation of the mobile emotiv device using a neuroscan event-related potential system, J. Med. Imaging Health Inform. 5(7) (2015) 1553–1557. Crossref, Web of Science, Google Scholar
- 102. ,
Emotiv-based low-cost brain computer interfaces: A survey , in Advances in Neuroergonomics and Cognitive Engineering (Springer, 2017), pp. 133–142. Crossref, Google Scholar
| Remember to check out the Most Cited Articles! |
|---|
|
Check out our titles in neural networks today! |
