Abstract
Event-related potentials (ERPs) can reflect the high-level thinking activities of the brain. In ERP analysis, the superposition and averaging method is often used to estimate ERPs. However, the single-trial ERP estimation can provide researchers with more information on cognitive activities. In recent years, more and more researchers try to find an effective method to extract single-trial ERPs, because most of the existing methods have poor generalization ability or suffer from strong assumptions about the characteristics of ERPs, resulting in unsatisfactory results under the condition of a very low signal-to-noise ratio. In this paper, an EEG classification-based method for single-trial ERP detection and estimation was proposed. This study used a linear generated EEG model containing templates of ERP local descriptors which include amplitude and latency, and this model can avoid the invalid assumption about ERPs taken by other methods. The purpose of this method is not to recover the whole ERP waveform but to model the amplitude and latency of ERP components. This method afterwards examined the three machine learning models including logistic regression, neural network, and support vector machine in the EEG signal classification for ERP detection and selected the best performed MLPNN model for detection. To get the utmost out of information produced in the classification process, this study also used extra information to propose a new optimization model, with which outperformed detection results were obtained. Performance of the proposed method is evaluated on simulated N170 and real P50 data sets, and the results show that the model is more effective than the Woody filter and the SingleTrialEM algorithm. These results are also consistent with the conclusion of sensory gating, which demonstrated good generalization ability.
Highlights
Electroencephalography (EEG) is a record of an electrogram of the electrical potentials on the scalp generated by the neurons of the brain
We examined the application of an artificial neural network (ANN) in EEG classification for Event-related potentials (ERPs) detection and compared the results obtained from logistic regression and support vector machine (SVM) and chose ANN as the most appropriate model for ERP detection
We only show the performance of multiple EEG classification methods including logistic regression, artificial neural networks, and support vector machine on simulated data because the results are similar on real data
Summary
Electroencephalography (EEG) is a record of an electrogram of the electrical potentials on the scalp generated by the neurons of the brain. Due to its advantages of high temporal resolution, relative noninvasiveness, and lower cost of equipment, it is widely used in research such as cognitive science, neuroscience, and neural engineering. Event-related potentials (ERPs) are a measurement of brain activities occurring in a brain structure. Differing from the EEG signals, ERPs can only be evoked a short time after the brain receives a stimulus or event [1]. The ERPs can be viewed as the EEG changes after the brain is exposed to cognitive, sensory, or motor events. Each of the component provides meaningful information to many research areas including neuroscience, cognitive science, and psychophysiological research. The P300 ERP component has a positive amplitude and exists with a latency of roughly 250 ms to 500 ms after decision-making, while the N170 ERP component has a negative amplitude and occurs with a latency of roughly 130 ms to 200 ms after the processing of familiar objects, faces, or words [3]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Computational and Mathematical Methods in Medicine
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.