Time-frequency distribution analysis of electroencephalograms during mental arithmetic task performance

Noor Hazlan, Muhammad Nur Hazmi (2021) Time-frequency distribution analysis of electroencephalograms during mental arithmetic task performance. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

	Text (24 Pages) Time-frequency distribution analysis of electroencephalograms during mental arithmetic task performance.pdf - Submitted Version Download (773kB)
	Text (Full Text) Time-frequency distribution analysis of electroencephalograms during mental arithmetic task performance.pdf - Submitted Version Restricted to Repository staff only Download (3MB)

Abstract

Cognitive workload or mental workload refers to the sum of mental work needed to finish a job, such as problem-solving, reading, writing, and success of mental arithmetic. For the diagnosis and treatment of brain and mental illnesses, electroencephalograms (EEGs) have become an increasingly important measure of brain activity. EEGs recordings provide information regarding the brain's electrical activity. Through EEG records is one of the most important instruments for the detection of neurological disorders, such as epilepsy, brain tumor, head injury, sleep disturbance, etc, is base on the study of brain electrical activity.Feature extraction represents a distinguishing property, a familiar measurement, and a functional component obtained from a section of a pattern. Furthermore, they also simplify the sum of available resources to explain a large set of data accurately. The main aim of this project is to accurately evaluate the cognitive workload of EEG signals using the time-frequency distribution (TFD) during mental arithmetic task success. We can extract the EEG function by using time-frequency distribution (TFD) and use different types of classifiers, such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and several more, to use the signal in a real-time application that requires information on both time and frequency. By integrating the EEG signal it can help to increase or improve the diagnosis of neurological in the future.

Actions (login required)

View Item