Improving the Performance of Electrotactile Brain–Computer Interface Using Machine Learning Methods on Multi-Channel Features of Somatosensory Event-Related Potentials
Abstract
1. Introduction
- A method for feature selection based on multi-EEG-channel features.
- A comparison of several systematically tested and optimized machine learning algorithms for classification of tactile attention.
- The detailed exploration of the ITR vs. accuracy trade-off, i.e., the possibility of reduction in the number of single evoked responses to increase the ITR while sustaining satisfactory accuracy.
2. Materials and Methods
2.1. Subjects
2.2. Instrumentation and Experimental Setup
2.3. Experimental Protocol
2.4. Data Processing
- Attended D location with stimulus delivered to D (ADSD);
- Attended D location with stimulus delivered to V (ADSV);
- Attended V location with stimulus delivered to D (AVSD);
- Attended V location with stimulus delivered to V (AVSV).
2.5. Feature Selection
2.6. Classification Approaches
- The training data is used for feature selection through SFS using nested 5-fold CV for feature evaluation and default classifier parameters.
- Using the selected feature subset, hyperparameters are optimized through grid search using the same inner-fold splits.
- The final model with selected features and optimized hyperparameters is evaluated on the held-out test data.
Algorithm 1. Classifier performance estimation |
Input: Dataset X, maximum features k = 40 Output: Selected features Y, Average accuracy (Acc) 1. Split X into 5 outer folds 2. For each outer fold: a. Set aside test data b. On training data: - Create inner 5-fold CV splits - Initialize empty feature set: Y = {} - While |Y| < k: * For each candidate feature f not in Y: - Using the created inner CV splits: * Evaluate Acc(Y ∪ {f}) using default parameters - Select f* = argmax(Acc) * Add f* to Y if improves performance - Using the created inner CV splits: * Perform hyperparameter tuning with selected features Y c. Evaluate final model on outer fold test data 3. Return averaged accuracy (Acc) across outer folds |
2.6.1. Logistic Regression (LR)
2.6.2. K-Nearest Neighbors (KNNs)
2.6.3. Support Vector Machine (SVM)
2.6.4. Random Forest (RF)
2.6.5. Artificial Neural Networks (ANNs)
3. Results
4. Discussion
- Finding the optimal subset of features: We implemented a sequential feature selection algorithm to extract the most important information from the signals. We extracted subsets of features that gave the highest accuracy during the selection process. The maximum size of the subset was set to 40 features. During the selection process, accuracy was obtained using 5-fold cross-validation.
- Comparison of classification approaches: We compared the performance of five different machine learning algorithms. To achieve the best performance, we optimized the most important hyperparameters of each algorithm. Classification accuracy was utilized as a performance metric and was obtained through 5-fold cross-validation.
- Testing the influence of α on BCI performance: We tested how the number of trials to be averaged influences the accuracy of classification and ITR. Parameter was changed in the range from 2 to 10, and for each value, the previous two steps were conducted.
4.1. Optimal Subset of Features
4.2. Influence of Classifier Selection on the BCI Performance
4.3. Influence of on the BCI Performance
4.4. Multi-Channel Approach
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Zander, T.O.; Kothe, C. Towards Passive Brain-Computer Interfaces: Applying Brain-Computer Interface Technology to Human-Machine Systems in General. J. Neural Eng. 2011, 8, 025005. [Google Scholar] [CrossRef] [PubMed]
- Abiri, R.; Borhani, S.; Sellers, E.W.; Jiang, Y.; Zhao, X. A Comprehensive Review of EEG-Based Brain-Computer Interface Paradigms. J. Neural Eng. 2019, 16, 011001. [Google Scholar] [CrossRef] [PubMed]
- Ramadan, R.A.; Vasilakos, A. V Brain Computer Interface Control Signals Review. Neurocomputing 2017, 223, 26–44. [Google Scholar] [CrossRef]
- Tufvesson, P.; Heskebeck, F. Automatic Control of Reactive Brain Computer Interfaces. IFAC J. Syst. Control 2024, 27, 100251. [Google Scholar] [CrossRef]
- Lee, S.H.; Lee, M.; Lee, S.W. Neural Decoding of Imagined Speech and Visual Imagery as Intuitive Paradigms for BCI Communication. IEEE Trans. Neural Syst. Rehabil. Eng. 2020, 28, 2647–2659. [Google Scholar] [CrossRef]
- Li, M.; He, D.; Li, C.; Qi, S. Brain–Computer Interface Speller Based on Steady-State Visual Evoked Potential: A Review Focusing on the Stimulus Paradigm and Performance. Brain Sci. 2021, 11, 450. [Google Scholar] [CrossRef]
- Nijboer, F.; Furdea, A.; Gunst, I.; Mellinger, J.; McFarland, D.J.; Birbaumer, N.; Kübler, A. An Auditory Brain-Computer Interface (BCI). J. Neurosci. Methods 2008, 167, 43–50. [Google Scholar] [CrossRef]
- Séguin, P.; Maby, E.; Fouillen, M.; Otman, A.; Luauté, J.; Giraux, P.; Morlet, D.; Mattout, J. The Challenge of Controlling an Auditory BCI in the Case of Severe Motor Disability. J. Neuroeng. Rehabil. 2024, 21, 9. [Google Scholar] [CrossRef]
- Brouwer, A.M.; van Erp, J.B.F. A Tactile P300 Brain-Computer Interface. Front. Neurosci. 2010, 4, 19. [Google Scholar] [CrossRef]
- Jin, J.; Chen, Z.; Xu, R.; Miao, Y.; Wang, X.; Jung, T.P. Developing a Novel Tactile P300 Brain-Computer Interface with a Cheeks-Stim Paradigm. IEEE Trans. Biomed. Eng. 2020, 67, 2585–2593. [Google Scholar] [CrossRef]
- Chu, C.; Luo, J.; Tian, X.; Han, X.; Guo, S. A P300 Brain-Computer Interface Paradigm Based on Electric and Vibration Simple Command Tactile Stimulation. Front. Hum. Neurosci. 2021, 15, 641357. [Google Scholar] [CrossRef] [PubMed]
- Li, J.; Pu, J.; Cui, H.; Xie, X.; Xu, S.; Li, T.; Hu, Y. An Online P300 Brain–Computer Interface Based on Tactile Selective Attention of Somatosensory Electrical Stimulation. J. Med. Biol. Eng. 2019, 39, 732–738. [Google Scholar] [CrossRef]
- Toleikis, J.R. Intraoperative Monitoring Using Somatosensory Evoked Potentials. A Position Statement by the American Society of Neurophysiological Monitoring. J. Clin. Monit. Comput. 2005, 19, 241–258. [Google Scholar] [CrossRef] [PubMed]
- Petit, J.; Rouillard, J.; Cabestaing, F. EEG-Based Brain-Computer Interfaces Exploiting Steady-State Somatosensory-Evoked Potentials: A Literature Review. J. Neural Eng. 2021, 18, 051003. [Google Scholar] [CrossRef]
- Tobimatsu, S.; Zhang, M.; Kato, M. Steady-State Vibration Somatosensory Evoked Potentials: Physiological Characteristics and Tuning Function. Clin. Neurophysiol. 1999, 110, 1953–1958. [Google Scholar] [CrossRef]
- Josiassen, R.C.; Shagass, C.; Roemer, R.A.; Slepner, S.; Czartorysky, B. Early Cognitive Components of Somatosensory Event-Related Potentials. Int. J. Psychophysiol. 1990, 9, 139–149. [Google Scholar] [CrossRef]
- Novičić, M.; Savić, A.M. Somatosensory Event-Related Potential as an Electrophysiological Correlate of Endogenous Spatial Tactile Attention: Prospects for Electrotactile Brain-Computer Interface for Sensory Training. Brain Sci. 2023, 13, 766. [Google Scholar] [CrossRef]
- Savić, A.M.; Novičić, M.; Ðorđević, O.; Konstantinović, L.; Miler-Jerković, V. Novel Electrotactile Brain-Computer Interface with Somatosensory Event-Related Potential Based Control. Front. Hum. Neurosci. 2023, 17, 1096814. [Google Scholar] [CrossRef]
- Savić, A.M.; Novičić, M.; Miler-Jerković, V.; Djordjević, O.; Konstantinović, L. Electrotactile BCI for Top-Down Somatosensory Training: Clinical Feasibility Trial of Online BCI Control in Subacute Stroke Patients. Biosensors 2024, 14, 368. [Google Scholar] [CrossRef]
- Pudilr, P.; Ferrii, F.J.; Novovieov, J.; Kittler, J. Floating Search Methods for Feature Selection with Nammonotonic Criterion Functions. In Proceedings of the 12th IAPR International Conference on Pattern Recognition, Jerusalem, Israel, 9–13 October 1994; pp. 279–283. [Google Scholar]
- Hosmer, D.W., Jr.; Lemeshow, S.; Sturdivant, R.X. Applied Logistic Regression; John Wiley & Sons: Hoboken, NJ, USA, 2013. [Google Scholar]
- Bhatia, N. Survey of Nearest Neighbor Techniques. Int. J. Comput. Sci. Inf. Secur. 2010, 8, 302–305. [Google Scholar] [CrossRef]
- Hearst, M.A.; Dumais, S.T.; Osuna, E.; Platt, J.; Scholkopf, B. Support Vector Machines. IEEE Intell. Syst. Their Appl. 1998, 13, 18–28. [Google Scholar] [CrossRef]
- Belgiu, M.; Dragut, L. Random Forest in Remote Sensing: A Review of Applications and Future Directions. ISPRS J. Photogramm. Remote Sens. 2016, 114, 24–31. [Google Scholar] [CrossRef]
- Bishop, C.M. Neural Networks for Pattern Recognition; Oxford University Press: Oxford, UK, 1995. [Google Scholar]
- Wolpaw, J.R.; Birbaumer, N.; Mcfarland, D.J.; Pfurtscheller, G.; Vaughan, T.M. Brain-Computer Interfaces for Communication and Control. Clin. Neurophysiol. 2002, 113, 767–791. [Google Scholar] [CrossRef] [PubMed]
- Adams, M.S.; Niechwiej-Szwedo, E.; McIlroy, W.E.; Staines, W.R. A History of Concussion Affects Relevancy-Based Modulation of Cortical Responses to Tactile Stimuli. Front. Integr. Neurosci. 2020, 14, 33. [Google Scholar] [CrossRef]
- Schubert, R.; Ritter, P.; Wüstenberg, T.; Preuschhof, C.; Curio, G.; Sommer, W.; Villringer, A. Spatial Attention Related SEP Amplitude Modulations Covary with BOLD Signal in S1—A Simultaneous EEG—FMRI Study. Cereb. Cortex 2008, 18, 2686–2700. [Google Scholar] [CrossRef]
- Kida, T.; Wasaka, T.; Nakata, H.; Akatsuka, K.; Kakigi, R. Active Attention Modulates Passive Attention-Related Neural Responses to Sudden Somatosensory Input against a Silent Background. Exp. Brain Res. 2006, 175, 609–617. [Google Scholar] [CrossRef]
- Kida, T.; Nishihira, Y.; Hatta, A.; Wasaka, T.; Tazoe, T.; Sakajiri, Y.; Nakata, H.; Kaneda, T.; Kuroiwa, K.; Akiyama, S.; et al. Resource Allocation and Somatosensory P300 Amplitude during Dual Task: Effects of Tracking Speed and Predictability of Tracking Direction. Clin. Neurophysiol. 2004, 115, 2616–2628. [Google Scholar] [CrossRef]
- Desmedt, J.E.; Tomberg, C. Mapping Early Somatosensory Evoked Potentials in Selective Attention: Critical Evaluation of Control Conditions Used for Titrating by Difference the Cognitive P30, P40, P100 and N140 1. Electroencephalogr. Clin. Neurophysiol./Evoked Potentials Sect. 1989, 74, 321–346. [Google Scholar] [CrossRef]
- Grigoryan, R.; Goranskaya, D.; Demchinsky, A.; Ryabova, K.; Kuleshov, D.; Kaplan, A. Difference in Somatosensory Event-Related Potentials in the Blind Subjects Leads to Better Performance in Tactile P300 BCI. bioRxiv 2020, 12, 2825. [Google Scholar] [CrossRef]
- Ortner, R.; Lugo, Z.; Noirhomme, Q.; Laureys, S.; Guger, C. A Tactile Brain-Computer Interface for Severely Disabled Patients. In Proceedings of the 2014 IEEE Haptics Symposium (HAPTICS), Houston, TX, USA, 23–26 February 2014; pp. 235–237. [Google Scholar] [CrossRef]
- Pokorny, C.; Breitwieser, C.; Müller-Putz, G.R. The Role of Transient Target Stimuli in a Steady-State Somatosensory Evoked Potential-Based Brain-Computer Interface Setup. Front. Neurosci. 2016, 10, 152. [Google Scholar] [CrossRef]
- Kim, K.T.; Lee, J.; Kim, H.; Kim, C.H.; Lee, S.J. Classification of Selective Attention within Steady-State Somatosensory Evoked Potentials from Dry Electrodes Using Mutual Information-Based Spatio-Spectral Feature Selection. IEEE Access 2020, 8, 85464–85472. [Google Scholar] [CrossRef]
- Xu, R.; Dosen, S.; Jiang, N.; Yao, L.; Farooq, A.; Jochumsen, M.; Mrachacz-Kersting, N.; Dremstrup, K.; Farina, D. Continuous 2-D Control via State-Machine Triggered Endogenous Sensory Discrimination and a Fast Brain Switch. J. Neural Eng. 2019, 16, 056001. [Google Scholar] [CrossRef] [PubMed]
- Mao, Y.; Jin, J.; Li, S.; Miao, Y.; Cichocki, A. Effects of Skin Friction on Tactile P300 Brain-Computer Interface Performance. Comput. Intell. Neurosci. 2021, 2021, 6694310. [Google Scholar] [CrossRef] [PubMed]
Accuracy [%] | |||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
ID1 | ID2 | ID3 | ID4 | ID5 | ID6 | ID7 | ID8 | ID9 | ID10 | MV ± STD | MV ± STD | ||
LR | 2 | 69.87 | 65.71 | 71.20 | 70.86 | 71.22 | 70.99 | 76.12 | 77.20 | 64.96 | 68.39 | 70.65 ± 3.89 | 81.24 ± 8.38 |
3 | 71.66 | 67.38 | 79.41 | 71.13 | 76.95 | 76.99 | 80.35 | 83.33 | 66.69 | 74.65 | 74.85 ± 5.56 | ||
4 | 72.73 | 70.52 | 83.03 | 79.05 | 74.11 | 79.63 | 86.15 | 78.00 | 64.95 | 74.81 | 76.30 ± 6.20 | ||
5 | 78.25 | 77.80 | 83.85 | 77.65 | 81.96 | 86.48 | 83.38 | 89.21 | 71.97 | 75.06 | 80.56 ± 5.33 | ||
6 | 75.82 | 70.48 | 87.75 | 77.91 | 81.27 | 87.38 | 90.51 | 89.23 | 69.10 | 82.86 | 81.23 ± 7.72 | ||
7 | 80.74 | 80.47 | 93.15 | 81.01 | 87.17 | 84.31 | 84.29 | 92.73 | 78.18 | 82.29 | 84.43 ± 5.13 | ||
8 | 81.99 | 79.16 | 89.00 | 79.00 | 83.00 | 86.79 | 95.00 | 96.84 | 73.37 | 80.88 | 84.50 ± 7.40 | ||
9 | 88.97 | 82.35 | 90.92 | 80.92 | 90.98 | 89.80 | 98.18 | 97.57 | 82.48 | 91.32 | 89.35 ± 5.98 | ||
10 | 88.86 | 79.08 | 93.58 | 83.17 | 93.75 | 88.25 | 98.25 | 95.90 | 81.58 | 90.19 | 89.26 ± 6.37 | ||
KNN | 2 | 71.09 | 74.52 | 71.68 | 70.82 | 74.65 | 71.46 | 75.39 | 71.85 | 66.35 | 72.81 | 72.06 ± 2.58 | 83.68 ± 7.59 |
3 | 72.03 | 78.24 | 77.65 | 76.38 | 76.21 | 76.27 | 80.37 | 84.81 | 67.46 | 75.05 | 76.45 ± 4.62 | ||
4 | 76.32 | 76.52 | 79.80 | 81.43 | 75.03 | 81.08 | 86.15 | 84.00 | 72.61 | 83.33 | 79.63 ± 4.37 | ||
5 | 85.32 | 82.75 | 84.40 | 80.75 | 81.96 | 80.36 | 92.19 | 86.11 | 75.02 | 81.51 | 83.04 ± 4.48 | ||
6 | 86.06 | 82.76 | 87.70 | 80.90 | 84.95 | 79.97 | 92.94 | 89.23 | 80.16 | 81.29 | 84.60 ± 4.37 | ||
7 | 79.78 | 82.17 | 91.52 | 87.03 | 88.88 | 90.40 | 94.29 | 94.55 | 80.71 | 87.01 | 87.63 ± 5.34 | ||
8 | 90.47 | 78.16 | 96.00 | 89.00 | 91.00 | 80.74 | 93.33 | 95.79 | 81.53 | 85.09 | 88.11 ± 6.40 | ||
9 | 90.29 | 84.63 | 93.27 | 91.05 | 92.22 | 87.19 | 96.35 | 96.32 | 82.55 | 91.54 | 90.54 ± 4.58 | ||
10 | 91.62 | 85.58 | 93.58 | 91.08 | 88.67 | 90.83 | 97.78 | 94.57 | 87.00 | 90.29 | 91.10 ± 3.61 | ||
SVM | 2 | 70.11 | 72.14 | 76.51 | 70.13 | 73.97 | 72.64 | 76.09 | 70.86 | 66.82 | 71.81 | 72.11 ± 2.92 | 84.78 ± 7.50 |
3 | 76.11 | 73.89 | 79.04 | 75.36 | 78.36 | 80.94 | 80.37 | 75.56 | 71.28 | 79.49 | 77.04 ± 3.11 | ||
4 | 78.27 | 75.52 | 82.58 | 80.48 | 82.03 | 77.74 | 84.62 | 82.50 | 79.84 | 79.22 | 80.28 ± 2.72 | ||
5 | 82.08 | 88.88 | 88.00 | 81.35 | 85.58 | 82.78 | 86.33 | 82.92 | 83.56 | 85.28 | 84.68 ± 2.55 | ||
6 | 88.25 | 83.28 | 91.27 | 86.80 | 84.18 | 86.64 | 90.51 | 90.77 | 83.89 | 82.86 | 86.84 ± 3.25 | ||
7 | 84.20 | 81.19 | 91.38 | 87.90 | 89.75 | 84.23 | 97.14 | 93.64 | 84.31 | 89.74 | 88.35 ± 4.95 | ||
8 | 90.47 | 84.26 | 92.00 | 88.00 | 92.00 | 85.84 | 98.32 | 92.57 | 85.74 | 90.41 | 90.02 ± 4.31 | ||
9 | 89.19 | 89.26 | 96.54 | 88.50 | 93.33 | 90.65 | 98.95 | 97.57 | 86.08 | 87.87 | 91.68 ± 4.31 | ||
10 | 91.71 | 80.58 | 91.08 | 94.83 | 93.75 | 94.83 | 97.78 | 95.90 | 88.08 | 91.52 | 92.01 ± 4.88 | ||
RF | 2 | 70.11 | 70.24 | 73.74 | 65.99 | 72.37 | 70.29 | 74.28 | 71.12 | 62.64 | 70.59 | 70.14 ± 3.49 | 81.69 ± 7.81 |
3 | 72.04 | 73.51 | 75.57 | 71.14 | 75.53 | 76.27 | 80.37 | 77.41 | 69.14 | 72.40 | 74.34 ± 3.32 | ||
4 | 75.73 | 77.93 | 77.87 | 70.00 | 76.41 | 78.14 | 83.85 | 78.50 | 74.56 | 78.21 | 77.12 ± 3.50 | ||
5 | 77.68 | 78.45 | 83.81 | 76.56 | 79.50 | 80.97 | 85.33 | 82.82 | 74.36 | 81.51 | 80.10 ± 3.43 | ||
6 | 81.20 | 76.52 | 86.30 | 77.12 | 80.61 | 83.62 | 95.15 | 89.23 | 79.39 | 83.60 | 83.27 ± 5.73 | ||
7 | 83.51 | 79.57 | 89.67 | 80.25 | 87.97 | 80.59 | 94.29 | 90.91 | 78.97 | 85.19 | 85.09 ± 5.39 | ||
8 | 82.98 | 80.21 | 90.00 | 86.00 | 90.00 | 84.74 | 96.67 | 92.63 | 77.74 | 85.15 | 86.61 ± 5.77 | ||
9 | 88.09 | 84.71 | 92.16 | 83.99 | 92.16 | 84.97 | 98.00 | 98.75 | 82.61 | 86.76 | 89.22 ± 5.79 | ||
10 | 87.81 | 84.08 | 92.33 | 83.25 | 85.83 | 89.42 | 95.78 | 94.67 | 85.75 | 94.48 | 89.34 ± 4.68 | ||
ANN | 2 | 63.97 | 66.90 | 66.37 | 63.41 | 65.90 | 65.11 | 71.28 | 67.73 | 59.34 | 63.94 | 65.40 ± 3.13 | 71.81 ± 5.21 |
3 | 66.82 | 65.60 | 71.74 | 66.20 | 69.24 | 65.84 | 73.03 | 72.96 | 60.29 | 66.03 | 67.78 ± 3.99 | ||
4 | 68.63 | 67.10 | 72.69 | 66.67 | 68.87 | 72.86 | 73.85 | 73.50 | 63.94 | 68.69 | 69.68 ± 3.38 | ||
5 | 70.50 | 67.37 | 73.46 | 65.70 | 74.12 | 72.86 | 72.57 | 75.91 | 62.22 | 73.08 | 70.78 ± 4.32 | ||
6 | 73.48 | 69.03 | 79.71 | 71.35 | 71.16 | 72.36 | 76.18 | 79.23 | 64.81 | 74.09 | 73.14 ± 4.53 | ||
7 | 73.25 | 72.25 | 80.18 | 70.65 | 76.81 | 71.15 | 78.57 | 82.73 | 67.39 | 73.25 | 74.62 ± 4.79 | ||
8 | 71.29 | 72.74 | 77.00 | 75.00 | 77.00 | 73.63 | 78.33 | 81.87 | 68.21 | 74.50 | 74.96 ± 3.85 | ||
9 | 72.06 | 70.37 | 76.34 | 68.04 | 78.63 | 74.18 | 81.27 | 83.01 | 67.58 | 74.49 | 74.60 ± 5.29 | ||
10 | 75.14 | 73.50 | 77.17 | 71.42 | 79.58 | 75.08 | 76.44 | 81.24 | 69.83 | 73.81 | 75.32 ± 3.48 |
Classifier | Optimal Accuracy [%] MV ± STD | Optimal ITR [bmp] | |
---|---|---|---|
LR | 6 | 81.23 ± 7.72 | 6.67 |
KNN | 6 | 84.60 ± 4.37 | 6.67 |
SVM | 6 | 86.84 ± 3.25 | 6.67 |
RF | 6 | 83.27 ± 5.73 | 6.67 |
ANN | 5 | 70.78 ± 4.32 | 8 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Novičić, M.; Djordjević, O.; Miler-Jerković, V.; Konstantinović, L.; Savić, A.M. Improving the Performance of Electrotactile Brain–Computer Interface Using Machine Learning Methods on Multi-Channel Features of Somatosensory Event-Related Potentials. Sensors 2024, 24, 8048. https://doi.org/10.3390/s24248048
Novičić M, Djordjević O, Miler-Jerković V, Konstantinović L, Savić AM. Improving the Performance of Electrotactile Brain–Computer Interface Using Machine Learning Methods on Multi-Channel Features of Somatosensory Event-Related Potentials. Sensors. 2024; 24(24):8048. https://doi.org/10.3390/s24248048
Chicago/Turabian StyleNovičić, Marija, Olivera Djordjević, Vera Miler-Jerković, Ljubica Konstantinović, and Andrej M. Savić. 2024. "Improving the Performance of Electrotactile Brain–Computer Interface Using Machine Learning Methods on Multi-Channel Features of Somatosensory Event-Related Potentials" Sensors 24, no. 24: 8048. https://doi.org/10.3390/s24248048
APA StyleNovičić, M., Djordjević, O., Miler-Jerković, V., Konstantinović, L., & Savić, A. M. (2024). Improving the Performance of Electrotactile Brain–Computer Interface Using Machine Learning Methods on Multi-Channel Features of Somatosensory Event-Related Potentials. Sensors, 24(24), 8048. https://doi.org/10.3390/s24248048