EEG-Based Mental Workload Estimation Using Bidirectional LSTM

This article gives a thorough investigation of the data processing method used to determine mental effort levels in electroencephalography (EEG). The Egg data was analyzed using a bidirectional Long Short-Term Memory (LSTM) neural network. With the help of this neural network, precise classification was made possible by its ability to capture the intricate temporal correlations seen in the brainwave patterns. By employing a meticulous to-fold cross-validation process, the model exhibited a noteworthy accuracy rate of 80.02% in accurately differentiating between various degrees of mental effort. The use of EEG data to access mental workload is very pertinent to a number of industries, including human-computer interface, aviation, and healthcare. Bidirectional LSTM achieves an 80.02% accuracy rate, demonstrating the strategy's robustness in precisely and consistently recognizing mental strain situations. In addition to making a significant contribution to the quickly developing field of brain signal processing, the current study offers important new understandings into the real-world applications of electroencephalography (EEG)-based mental workload detection systems. There is a great deal of potential to develop human capacities in a variety of sectors and advance general welfare through the investigation of further advancements and useful applications in real-life situations.