People with impaired motor function could be helped by an effective brain–computer interface (BCI) based on a real-time electroencephalogram (EEG) and artificial intelligence algorithms. However, current methodologies for interpreting patient instructions from an EEG are not accurate enough to be completely safe in a real-world situation , where a poor decision would place their physical integrity at risk, such as when traveling in an electric wheelchair in a city. For various reasons, such as the low signal-to-noise ratio of portable EEGs or the effects of signal contamination (disturbances due to user movement, temporal variation of the features of EEG signals, etc.), a long short-term memory network (LSTM) (a type of recurrent neural network) that is able to learn data flow patterns from EEG signals could improve the classification of the actions taken by the user. In this paper, the effectiveness of using an LSTM with a low-cost wireless EEG device in real time is tested, and the time window that maximizes its classification accuracy is studied. The goal is to be able to implement it in the BCI of a smart wheelchair with a simple coded command protocol, such as opening or closing the eyes, which could be executed by patients with reduced mobility. Results show a higher resolution of the LSTM with an accuracy range between 77.61 and 92.14% compared to traditional classifiers (59.71%), and an optimal time window of around 7 s for the task done by users in this work. In addition, tests in real-life contexts show that a trade-off between accuracy and response times is necessary to ensure detection.

The performance of an EEG-based brain-computer interface (BCI) system is highly dependent on signal preprocessing. This manuscript presents a filtering method to improve the feature classification algorithms typically used in BCI. Methods: A graph Laplacian quadratic form using the Phase Locking Value (PLV) is applied to generate a new filtered signal in the preprocessing stage. Results: The accuracy of the classification algorithms improved significantly (up to 27.18% in the BCI Competition IV dataset, and up to 42.56% with records made with an Emotiv EPOC+). In addition, the proposed filtering algorithm has similar or better results when compared with the Filter Bank Common Spatial Pattern (FBCSP), which has disadvantages in a multiclass classification. Conclusion: This paper shows how our PLVbased filtering between EEG channels could improve the performance of a BCI.

Brain-computer interface applications for biometric person identification have increased their interest in recent years since they are potentially more secure and more difficult to counterfeit than traditional biometric techniques. However, it is necessary to consider how brain waves are acquired for this purpose, not only in terms of efficiency but also of practical comfort for the user and the affordability degree of the biosignal acquisition device so that their everyday application can become a realistic possibility. In this context, this paper presents the capabilities of using a non-expensive wireless electroencephalogram (EEG) device to extract spectral-related and functional connectivity information of brain activity. The proposed method achieved a sufficient biometric identification with two datasets of 13 and 109 subjects when comparing the performance of a sizeable classification algorithm set. In addition, a novel feature in EEG biometric identification, called asymmetry index, is introduced here. Furthermore, this is the first study in this field to consider the effect of the time-lapse between different recording sessions on the system's behaviour when using a low-cost EEG device with identification accuracy rates of up to 100%. K E Y W O R D S biometrics brain-computer interface (BCI), classification, electroencephalogram (EEG) | INTRODUCTIONThe extraction of information from human brain electrical biosignals has been the subject of much attention in recent years. The electroencephalogram, encephalogram, or EEG is a non-invasive measure used to study the central nervous system's functioning, specifically the cerebral cortex's electrical activity [1]. EEG analysis has been widely used during the last century in medicine and as a basis for interfaces between brain and machine (BMI) [2,3]. In this context, the application of feature extraction techniques and automatic classification algorithms to the EEG signals has served as support tools in various utilities such as diagnosing neurological disorder diseases [4,5], since BMIs provide their users with an alternativeThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

No abstract

No abstract