A Mental Fatigue Detection Research Based On Eeg Signals

Mental fatigue is a common physiological phenomenon which caused by a high load work or study. If people still forced the brain to work, the efficiency of work and study will be lower and lower. What is more, this inattention seriously threat people’s health and life. Electroencephalogram (EEG) signals can directly reflect the activity of brain tissue. Using it to evaluate mental fatigue has become a hot topic in the research of the mental fatigue detection.At present, mental fatigue detection based on EEG signals using multi-channel EEG acquisition equipment is widely used. However, this mental fatigue detection method can only be operated in the laboratory conditions because of the limitations of the devices. In order to overcome the limitations of the multi-channel EEG acquisition equipment such as poor portability, operational complexity and high cost, this paper discusses the use of portable EEG acquisition equipment for which use single-channel EEG signals to detect the mental fatigue.The main research tasks of the thesis which are based on previous studies are as follows:1. This article describes in detail to the research status including EEG acquisition equipment, electrode selection and feature extraction method on the study of mental fatigue detection based on EEG signals.2. In order to overcome the issue of frequency aliasing in the fast wavelet packet algorithm, this paper proposes an Improved Single Sub-band Reconstruction of Wavelet Packet Algorithm (ISSBR-WPA). The algorithm design thought is to introduce two operators to eliminate wavelet packet decomposition and reconstruction process in excess of each sub-band frequency components, so as to effectively overcome frequency aliasing generation. The results show that ISSBR-WPA can extract more accurate the four rhythms of δ,θ, α, β in EEG signals and it provides a guarantee to accurately calculate the mental fatigue feature parameters.3. This papers use two feature parameters to assess the state of the brain fatigue. Two feature parameters are8energy ratios of the EEG four rhythms and the variance of various sub-bands wavelet packet coefficients. The feature parameters of the EEG signals at the brain FP1lead in portable equipment acquisition. The experimental results show that F2, F3, F4, F6and F7in8energy radios can be used as an effective indice to assess mental fatigue, in which feature F2is more effective. The variance of the low-frequency sub-bands wavelet packet coefficients can effectively distinguish the awake and mental fatigue states.4. In order to verify the validity of the results of feature extraction based on portable EEG acquisition equipment, this paper use multi-channel EEG acquisition equipment to extract and analysis the EEG signals feature parameters at brain FP1lead and O1lead at the same way. The experimental results show that mental fatigue assessment of these feature parameters are the same with the portable device. This shows that the use of the portable EEG acquisition equipment collect EEG signals from the brain FP1lead can detecte mental fatigue. The multi-channel equipment which collects EEG signals from the brain O1lead can also be used as detected mental fatigue.