Key result
Combining spectral features from multiple EEG frequency bands improved mean verification accuracy to 95.7% (vs 91% for beta band alone), though performance dropped across different recording sessions.
Why the study?
The study investigated EEG-based people verification using shallow artificial neural networks to evaluate the impact of different spectral frequency bands, numbers of hidden neurons, and data separation scenarios on verification performance.
Combining spectral features from multiple EEG frequency bands improves person verification accuracy, though performance is overestimated when training and testing data originate from the same recording session.
Answers are grounded in this paper and cite their sources.
Multi-band EEG features boost verification accuracy but degrade across sessions; leaves open reliable biometric use in variable clinical settings.
The paper is devoted to the study of EEG-based people verification. Analyzed solutions employed shallow artificial neural networks using spectral EEG features as input representation. We investigated the impact of the features derived from different frequency bands and their combination on verification results. Moreover, we studied the influence of a number of hidden neurons in a neural network. The datasets used in the analysis consisted of signals recorded during resting state from 29 healthy adult participants performed on different days, 20 EEG sessions for each of the participants. We presented two different scenarios of training and testing processes. In the first scenario, we used different parts of each recording session to create the training and testing datasets, and in the second one, training and testing datasets originated from different recording sessions. Among single frequency bands, the best outcomes were obtained for the beta frequency band (mean accuracy of 91 and 89% for the first and second scenarios, respectively). Adding the spectral features from more frequency bands to the beta band features improved results (95.7 and 93.1%). The findings showed that there is not enough evidence that the results are different between networks using different numbers of hidden neurons. Additionally, we included results for the attack of 23 external impostors whose recordings were not used earlier in training or testing the neural network in both scenarios. Another significant finding of our study shows worse sensitivity results in the second scenario. This outcome indicates that most of the studies presenting verification or identification results based on the first scenario (dominating in the current literature) are overestimated when it comes to practical applications.
No takes yet. Share an insight, caveat, or question.
Plucińska et al. (2022) studied Healthy adults (EEG-based person verification) (n=29). Combined spectral features from multiple frequency bands vs. Single frequency band (beta band) was evaluated on Mean verification accuracy (first scenario). Combining spectral features from multiple EEG frequency bands improved mean verification accuracy to 95.7% (vs 91% for beta band alone), though performance dropped across different recording sessions.
Synapse has enriched 10 related papers. Consider them for comparative context: