EEG Brainwave Data Classification of a Confused Student Using Moving Average Feature
Jay Mehta, H. Lakhani, Harsh Dave, Sheshang Degadwala, Dhairya Vyas
Abstract
The measurement of electrical activity in the brain, known as Electroencephalogram (EEG), is a common non-invasive diagnostic method used to detect neurological disorders and investigate cognitive processes such as memory, attention, and learning. Nonetheless, classifying and interpreting EEG data can be challenging due to the signals' complex and noisy nature. This research study examines the classification of EEG data from a student whose brainwave patterns were irregular during academic challenges. The proposed study has first processed the data by smoothing the signals using a moving average feature, and then a variety of deep and machine learning methods are used to categorize the data. Our results demonstrate that the student's EEG data was unique and did not fit within established categories. Our analysis also revealed that the technology used to collect the data may have contributed to the irregular patterns. However, the data can be accurately classified by utilizing a deep learning approach. In addition to highlighting the value of properly processing the data to remove noise and artefacts, this research study demonstrates the potential of both deep learning and machine learning techniques in the interpretation of EEG data. Additionally, the research findings suggest that EEG data classification should consider individual brain activity differences rather than solely relying on existing categories.