Electroencephalogram-based cognitive performance evaluation for mental arithmetic task
| Autor: | Sanjoy Kumar Saha, Rahul Gavas, Roopkatha Samanta, Debatri Chatterjee |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
medicine.diagnostic_test
business.industry Brain activity and meditation Computer science Pattern recognition Electroencephalography Hjorth parameters Task (project management) Naive Bayes classifier ComputingMethodologies_PATTERNRECOGNITION medicine Feature (machine learning) Effects of sleep deprivation on cognitive performance Artificial intelligence business Statistical hypothesis testing |
| Zdroj: | Cognitive Computing for Human-Robot Interaction ISBN: 9780323857697 |
| Popis: | This study discusses an appropriate framework to assess participant’s cognitive performance-based on their brain activity dynamics recorded through an electroencephalogram (EEG) device. To this aim, we have used a publicly available EEG dataset. The dataset contains EEG recording of 36 subjects before and during a mental arithmetic task. The participants were divided into two subgroups (good and bad performers) based on the accuracy of task performed. Good performers were able to execute the task without difficulty whereas the second group struggled during the same task. In this work, we have dealt with conventional EEG time-domain and frequency-domain features like various energy band powers, Hjorth parameters, and engagement index. The discriminating capability of these features in categorizing good and bad performers has been validated by hypothesis test. We have proposed a simple but novel approach to summarize these window level features and formulate the signal level descriptor. The descriptor thus formed, captures the distribution of the feature values effectively. Experimental results suggest that the proposed descriptor, obtained after summarizing the window level EEG domain features, performs satisfactorily in discriminating between the two sets of performers. Mean classification accuracy obtained was about 85% using Gaussian naive Bayes classifier which outperformed EEG domain feature-based classification models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|