Background: The fatigue that users suffer when using steady-state visual evoked\npotential (SSVEP)-based brain-computer interfaces (BCIs) can cause a number of serious\nproblems such as signal quality degradation and system performance deterioration, usersâ��\ndiscomfort and even risk of photosensitive epileptic seizures, posing heavy restrictions on\nthe applications of SSVEP-based BCIs. Towards alleviating the fatigue, a fundamental step\nis to measure and evaluate it but most existing works adopt self-reported questionnaire\nmethods which are subjective, offline and memory dependent. This paper proposes an\nobjective and real-time approach based on electroencephalography (EEG) spectral\nanalysis to evaluate the fatigue in SSVEP-based BCIs.\nMethods: How the EEG indices (amplitudes in d, ?, a and �Ÿ frequency bands),\nthe selected ratio indices (?/a and (? + a)/�Ÿ), and SSVEP properties (amplitude\nand signal-to-noise ratio (SNR)) changes with the increasing fatigue level are\ninvestigated through two elaborate SSVEP-based BCI experiments, one validates\nmainly the effectiveness and another considers more practical situations. Meanwhile, a\nself-reported fatigue questionnaire is used to provide a subjective reference. ANOVA is\nemployed to test the significance of the difference between the alert state and the\nfatigue state for each index.\nResults: Consistent results are obtained in two experiments: the significant increases in\na and (? + a)/�Ÿ, as well as the decrease in ?/a are found associated with the increasing\nfatigue level, indicating that EEG spectral analysis can provide robust objective\nevaluation of the fatigue in SSVEP-based BCIs. Moreover, the results show that the\namplitude and SNR of the elicited SSVEP are significantly affected by usersâ�� fatigue.\nConclusions: The experiment results demonstrate the feasibility and effectiveness of\nthe proposed method as an objective and real-time evaluation of the fatigue in\nSSVEP-based BCIs. This method would be helpful in understanding the fatigue problem\nand optimizing the system design to alleviate the fatigue in SSVEP-based BCIs.
Loading....