Cognitive Workload Detection Using EEG Images

Cognitive demand refers to the quantity of mental work needed to complete a given task and it is undergone a major role in executing a task effectively and efficiently. In recent years it is becoming more widely accepted in several fields including education and health care. By measuring or evaluating cognitive workload certain things can be designed to decrease stress and boost performance. The detection of cognitive workload using electroencephalography (EEG) images can result in a potentially valuable tool and it can help in ensuring tasks are done both effectively and with efficiency. Deep learning a subset of machine learning can be used to monitor operator mental states and recognize cognitive workloads using electroencephalograms (EEG). While several machine learning algorithms have been presented for identifying cognitive stress using EEG there is currently no comprehensive assessment of their applicability. Data used in this research is collected through multiple video sessions. Experimental results conducted on 14 channels of EEG indicates that the proposed method accurately detects cognitive workload and has significant scope of improvement.