Efficient Brain-Computer Interface for Attention Detection in Health Care Industry

A cognitive component of brain activity is attention. The effectiveness of other activities, including the learning process and crucial ones, are greatly impacted. Here, several methods are employed to categorize human attention according to ERP. The Electroencephalography (EEG) signal known as the Event-Related Potential (ERP) P300 is an evoked potential that has been linked to a number of cognitive functions, including response choice and attention. This study utilize the MOABB ERP Dataset bi2013a in this case. This was derived from a study conducted at GIPSA-lab in 2013 by the University of Grenoble Alpes, the CNRS, and Grenoble-INP. With the use of statistical Time domain analysis techniques like means and standard deviation of the filtered EEG data, the P300 ERP may be recovered from the raw EEG signal. Distinct P300 classifiers were utilized in this study, four of which were based on Riemannian geometry: CSP LDA, ERPCov TS LR, ERPCov MDM, as well as LR, LDA, and SVM classifiers. By analysing the data, it is concluded that LR performs better than the competition and generates positive test results on categorising the p300 ERP, which directly indicates the attention of the individual individuals.