Assessment of visual fatigue in SSVEP-based brain-computer interface: a comprehensive study.

Fatigue deteriorates the performance of a brain-computer interface (BCI) system; thus, reliable detection of fatigue is the first step to counter this problem. The fatigue evaluated by means of electroencephalographic (EEG) signals has been studied in many research projects, but widely different results have been reported. Moreover, there is scant research when considering the fatigue on steady-state visually evoked potential (SSVEP)-based BCI. Therefore, nowadays, fatigue detection is not a completely solved topic. In the current work, the issues found in the literature that led to the differences in the results are identified and saved by performing a new experiment on an SSVEP-based BCI system. The experiment was long enough to produce fatigue in the users, and different SSVEP stimulation ranges were used. Additionally, the EEG features commonly reported in the literature (EEG rhythms powers, SNR, etc.) were calculated as well as newly proposed features (spectral features and Lempel-Ziv complexity). The analysis was carried out on O1, Oz and O2 channels. This work found a tendency of displacement from high-frequency rhythms to low-frequency ones, and thus, better EEG features should present a similar behaviour. Then, the 'relative power' of EEG rhythms, the rates (θ + α)/ß, α/ß and θ/ß, some spectral features (central and mean frequencies, asymmetry and kurtosis coefficients, etc.) and Lempel-Ziv complexity are proposed as reliable EEG features for fatigue detection. Hence, this set of features may be used to construct a more trustworthy fatigue index.

Attention-level transitory response: a novel hybrid BCI approach.

OBJECTIVE: People with disabilities may control devices such as a computer or a wheelchair by means of a brain-computer interface (BCI). BCI based on steady-state visual evoked potentials (SSVEP) requires visual stimulation of the user. However, this SSVEP-based BCI suffers from the 'Midas touch effect', i.e., the BCI can detect an SSVEP even when the user is not gazing at the stimulus. Then, these incorrect detections deteriorate the performance of the system, especially in asynchronous BCI because ongoing EEG is classified. In this paper, a novel transitory response of the attention-level of the user is reported. It was used to develop a hybrid BCI (hBCI). APPROACH: Three methods are proposed to detect the attention-level of the user. They are based on the alpha rhythm and theta/beta rate. The proposed hBCI scheme is presented along with these methods. Hence, the hBCI sends a command only when the user is at a high-level of attention, or in other words, when the user is really focused on the task being performed. The hBCI was tested over two different EEG datasets. MAIN RESULTS: The performance of the hybrid approach is superior to the standard one. Improvements of 20% in accuracy and 10 bits min(-1) are reported. Moreover, the attention-level is extracted from the same EEG channels used in SSVEP detection and this way, no extra hardware is needed. SIGNIFICANCE: A transitory response of EEG signal is used to develop the attention-SSVEP hBCI which is capable of reducing the Midas touch effect.

Automatic detection of epileptic seizures in long-term EEG records.

Epilepsy is a neurological disorder which affects nearly 1.5% of the world׳s total population. Trained physicians and neurologists visually scan the long-term electroencephalographic (EEG) records to identify epileptic seizures. It generally requires many hours to interpret the data. Therefore, tools for quick detection of seizures in long-term EEG records are very useful. This study proposes an algorithm to help detect seizures in long-term iEEG based on low computational costs methods using Spectral Power and Wavelet analysis. The detector was tested on 21 invasive intracranial EEG (iEEG) records. A sensitivity of 85.39% was achieved. The results indicate that the proposed method detects epileptic seizures in long-term iEEG records successfully. Moreover, the algorithm does not require long processing time due to its simplicity. This feature will allow significant time reduction of the visual inspection of iEEG records performed by the specialists.

Automatic detection of drowsiness in EEG records based on multimodal analysis.

Drowsiness is one of the main causal factors in many traffic accidents due to the clear decline in the attention and recognition of danger drivers, diminishing vehicle-handling abilities. The aim of this research is to develop an automatic method to detect the drowsiness stage in EEG records using time, spectral and wavelet analysis. A total of 19 features were computed from only one EEG channel to differentiate the alertness and drowsiness stages. After a selection process based on lambda of Wilks criterion, 7 parameters were chosen to feed a Neural Network classifier. Eighteen EEG records were analyzed. The method gets 87.4% and 83.6% of alertness and drowsiness correct detections rates, respectively. The results obtained indicate that the parameters can differentiate both stages. The features are easy to calculate and can be obtained in real time. Those variables could be used in an automatic drowsiness detection system in vehicles, thereby decreasing the rate of accidents caused by sleepiness of the driver.

An automatic detector of drowsiness based on spectral analysis and wavelet decomposition of EEG records.

An algorithm to detect automatically drowsiness episodes has been developed. It uses only one EEG channel to differentiate the stages of alertness and drowsiness. In this work the vectors features are building combining Power Spectral Density (PDS) and Wavelet Transform (WT). The feature extracted from the PSD of EEG signal are: Central frequency, the First Quartile Frequency, the Maximum Frequency, the Total Energy of the Spectrum, the Power of Theta and Alpha bands. In the Wavelet Domain, it was computed the number of Zero Crossing and the integrated from the scale 3, 4 and 5 of Daubechies 2 order WT. The classifying of epochs is being done with neural networks. The detection results obtained with this technique are 86.5 % for drowsiness stages and 81.7% for alertness segment. Those results show that the features extracted and the classifier are able to identify drowsiness EEG segments.

Multiparametric detection of epileptic seizures using Empirical Mode Decomposition of EEG records.

Epilepsy is a neurological disorder that affects around 50 million people worldwide. The seizure detection is an important tool for the diagnosis of epilepsy. In this study, an epileptic seizure classification method based on features of the Empirical Mode Decomposition (EMD) of EEG records is proposed. The Intrinsic Mode Functions (IMFs) of EEG records are first computed, and then several time and frequency features of IMFs are extracted. A features selection based on a Mann-Whitney test and Lambda of Wilks criterion is performed, then these parameters are used in a linear discriminant analysis (LDA) to classify epileptic seizure and normal EEG segments. The algorithm was tested in 3 intracranial channels EEG records acquired in 21 patients with refractory epilepsy and validated by the Epilepsy Center of the University Hospital of Freiburg. The signal was divided in 15 s segments. In 45517 segments analyzed (689 with epileptic seizures) the sensitivity and specificity obtained with this method were 69.4% and 69.2% respectively. It could be concluded that the developed method could be a promising tool for epileptic seizure detection in EEG records.