Non-Invasive BCI

Background: Brain-Computer Interface (BCI) is becoming more reliable, thanks to the advantages of Artificial Intelligence (AI). Recently, hybrid Deep Learning (hDL), which combines different DL algorithms, has gained momentum over the past five years. In this work, we proposed a review on hDL-based BCI starting from the seminal studies in 2015. Objectives: We have reviewed 47 papers that apply hDL to the BCI system published between 2015 and 2020 extracting trends and highlighting relevant aspects to the topic. Methods: We have queried four scientific search engines (Google Scholar, PubMed, IEEE Xplore and Elsevier Science Direct) and different data items were extracted from each paper such as the database used, kind of application, online/offline training, tasks used for the BCI, pre-processing methodology adopted, type of normalization used, which kind of features were extracted, type of DL architecture used, number of layers implemented and which optimization approach were used a...

Abstract: In this paper we focus on the most efficacious AI applications for life extension and anti-aging at three expected stages of AI development: narrow AI, AGI and superintelligence. First, we overview the existing research and commercial work performed by a select number of startups and academic projects. We find that at the current stage of “narrow” AI, the most promising areas for life extension are geroprotector-combination discovery, detection of aging biomarkers, and personalized anti-aging therapy. These advances could help currently living people reach longevity escape velocity and survive until more advanced AI appears. When AI comes close to human level, the main contribution to life extension will come from AI integration with humans through brain-computer interfaces, integrated AI assistants capable of autonomously diagnosing and treating health issues, and cyber systems embedded into human bodies. Lastly, we speculate about the more remote future, when AI reaches ...

A non-invasive blood glucose monitoring system with six laser diodes is used to obtain a total of 290 NIR spectra from the Oral Glucose Tolerance Test (OGTT) experiment with the participation of a healthy volunteer over 4 days. Each laser diode operates at the discrete wavelengths between 1500nm and 1800nm with the power of 6mW each. A comparative analysis using the Partial Least Squares (PLS) model and the Neural Network (NN) model is studied. The study shows that the NN model performs better than the PLS model due to the presence of nonlinearity in the collected data. The presence of the nonlinearity is tested by using the Durbin-Watson test. ©2009 IEEE.

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5384079

With the aid of a BCI conceived and developed by the
research team, EEG parameters are streamed from the
Emotiv EPOC headset to generate sound algorithmically.
Parameter translation is performed by eegOSC, and the
stage music is generated through EEGmus, two original
pieces of software developed within the project.

Experimental Setup
Five users, at the age of 23, 25 31, 42, and 46 participated in the experiment. Users sat comfortably in a chair. A green LED of a 1cm diameter was placed at a distance of about 1 meter from the eyes of a person. EEG signals were recorded using g.USBAmp with 16 active electrodes.
Users were stimulated with flickering LED light of frequencies: 5Hz, 6Hz, 7Hz and 8Hz. The stimulation lasted 30 seconds. All sessions took place at the same time of the day to avoid circadian influences on the measurements.
The electrodes were placed according to the international 10-20 system at positions: O2, AF3, AF4, P4, P3, F4, Fz, F3, FCz, Pz, C4, C3, CPz, Cz, Oz, O1. EEG sampling frequency was 256Hz. The signals were recorded using a Butterworth bandpass filter (0.1-100Hz) and notch filter (48-52Hz) to correct a technical artifact from the power network.
Format of the Data
  For every user there are 4 files (for the stimuli of 5Hz, 6Hz, 7Hz and 8Hz each). Data are provided in Matlab format (*.mat) as X variable containing raw EEG signals: the 16 EEG potentials acquired in  order: O2, AF3, AF4, P4, P3, F4, Fz, F3, FCz, Pz, C4, C3, CPz, Cz, Oz, O1.

The aim of this study is to control home devices
using a non invasive brain computer interface (BCI). The
Electroencephalographic signals (EEG) recorded from the brain
activity using the Emotiv EPOCH headset are interfaced with the
help of mouse emulator to a graphical user interface (GUI) on the
computer screen. The user will use this GUI to control various
devices in a smart home. This application will be very useful
especially for people with special needs.

Cyberspace has been called the "fifth," war fighting domain after land, sea, air, and space. As a logical extension, Neurospace should be considered as the sixth. If the hearts and minds cannot be won, perhaps they can be controlled. The brain is the summation of who and what we are. If the ultimate realization of victory in war is complete submission of the enemies' will, it is obvious to consider the gateway to one's inner thoughts as the final frontier of battle. Just as a Spaceforce became necessary to protect US assets in space, the formation of a Neuroforce as a branch of the US Armed Forces will be necessary to protect and defend US Neurosecurity in the context of a specific neuroscience biosecurity framework, both domestically and abroad.

Extracellularly recorded neural data from in-vivo experiments provide higher spatio-temporal resolution and SNR compared with non-invasive brain signal recordings. While the recorded data can be corrupted by artifacts and interferences, especially under a less constrained recording protocol, the detection and removal of artifacts as a part of neural signal preprocessing procedure without distorting the signal-of-interest, play an important role. However, due to very limited knowledge of the appeared artifacts and the broad spectral content of in-vivo neural data, it is difficult to apply available artifact removal algorithms directly on the in-vivo neural recordings and thus poses a great challenge to decode the underlying brain information properly. The first objective of this thesis is to investigate the artifacts that are usually found in the in-vivo neural recordings and then characterize them in a systematic way (which turns out to be the first ever such attempt to the best of our knowledge). Our second motivation of the thesis is to develop an algorithm for automatic artifact detection and removal without distorting the signals of interest. Apart from in-vivo neural recordings, EEG has been the most preferred way of brain recordings in clinical studies, lab experiments, patient health monitoring, diagnosis and many other applications due to its non-invasiveness and affordability benefits . In scalp EEG-based applications, as the electrodes are placed on the scalp, become most prone to external artifacts including physiological ones. Consequently artifact detection and removal also from EEG recordings becomes one of the most faced challenges and still is an open research problem in EEG signal processing community. Many attempts have been taken and still being made to develop suitable methods for artifact detection and removal with the help of recent advancement in signal processing techniques and algorithms. However, each of them lacks from some practical issues and there is no complete solution yet which indicates the future need for removal algorithms to be more application-specific; e.g. in brain-computer interface (BCI) or epilepsy seizure detection applications. This research gap motivates us to design artifact removal algorithms for two of the most popularly used EEG-based applications i.e. epilepsy seizure monitoring and brain-computer interface (BCI) studies. The proposed EEG artifact reduction method is automatic, independent of artifact types, doesn't require a reference channel, can work for both single and multi channels and most importantly application-specific (i.e. epilepsy seizure detection and BCI applications). In order to evaluate the proposed methods quantitatively in comparison with available state-of-the-art methods, different artifact types have been extracted from real recordings for simulating artifact templates and hence to build a synthesized neural database on which the methods are applied. In addition, the effects of artifact removal on the later-stage processing (e.g. neural spike detection, seizure detection and BCI classification performances) have also been evaluated resulting significant performance improvement which proofs the efficacy of the proposed methods. Thus this work is expected to provide a useful platform in neural signal analysis and processing area for future brain research.

Diverses méthodes d'interfaçage Homme/Machine, se confrontent et se complètent, suivant une gradation allant du peu invasif, le contact, jusqu'au totalement invasif, la greffe. Il ressort de cette recherche comparative portant sur le recours à des dispositifs implantés actifs comme sur l'utilisation de différentes prothèses détachables (membres bioniques, interfaces haptiques, informatique pervasive et systèmes de réalité augmentée), que l'implantation d'une endoprothèse est acceptée principalement parce qu'elle est perçue comme un moyen de prolonger l'espérance de vie ou d'améliorer significativement la qualité de vie. La pose des implants informatisés s'inscrit dans le contexte de l' « Humain réparé ». Dans ce domaine, des relations étroites entre patients, médecins, constructeurs d'implants et pouvoirs publics donnent lieu à la mise en place d'un accompagnement social structurant qui permet de limiter fortement de nombreuses dérives liées à un usage inapproprié. Cependant, il s'avère que l'essentiel de l'émergence actuelle de l' « Humain augmenté » ne découle pas du recours à des implants ni à des prothèses de membres, car la diffusion de ces appareils est limitée à un très faible effectif de la population mondiale. On assiste à un déferlement d'objets informatisés détachables (comme les smartphones et les tablettes tactile, par exemple). Ces outils, diffusés massivement, sont principalement des prothèses cognitives. Un marketing, très intense, présente ces dispositifs techniques comme des objets absolument sans danger. Or, l'usage fréquent de ces appareils semble pourtant en mesure d'exercer une forme de modification subtile de l'activité cognitive et peut transformer significativement les rapports sociaux ainsi que certains processus pédagogiques essentiels. Les prothèses informatiques cognitives détachables ne sont guère implantées mais notre recours constant, et très peu socialement régulé, à ces outils (souvent des gadgets), dans une certaine mesure, nous impose une activité cognitive particulière, liée à une rythmicité induite par des automates et une habituation à l'interaction constante avec des programmes et des bases de données. Summary: The research subject addresses the social use of man/machine interfaces. This thesis investigates invasive approaches (such as electronic surgical implants) as well as non-invasive approaches (nerve impulse detection using non-implanted sensors, haptic interfaces, augmented reality devices and ubiquitous computing). Such investigation aims at understanding the clinical and anthropological issues generated by the multiplication of self-animated devices in the environment as well as in the human body. A clear point that stands out of this research is the following. Implants are not the key element in the process of " enhanced human " being which, by the way, concerns only a tiny portion of the world population. Implanted computing devices are mainly used in a strictly regulated context of " repaired human " (to keep the patients alive or to restore significantly their quality of life). It is worth mentioning that we are witnessing a surge of computer objects (such as smartphones, tablet computers...) in our social world as never before. Instances of computerized removable (detachable) prostheses are deeply pervasive nowadays. An increasing part of them can be described as cognitive prosthetics. A marketing, very intense, presents this devices as fully harmless items. However, the way we constantly recourse (without clear social regulation) to these tools (or gadgets), the common daily exposure to different kinds of computer programs, raises fundamental pedagogic questions, causes upheavals in our relationship to our surrounding environment, let alone to man's cognitive activity.

A brain-computer interface (BCI) is a communication system that allows the use of brain activity to control computers or other external devices. It can, by bypassing the peripheral nervous system, provide a means of communication for people suffering from severe motor disabilities or in a persistent vegetative state. In this paper, brain-signal generation tasks, noise removal methods, feature extraction/selection schemes, and classification techniques for fNIRS-based BCI are reviewed. The most common brain areas for fNIRS BCI are the primary motor cortex and the prefrontal cortex. In relation to the motor cortex, motor imagery tasks were preferred to motor execution tasks since possible proprioceptive feedback could be avoided. In relation to the prefrontal cortex, fNIRS showed a significant advantage due to no hair in detecting the cognitive tasks like mental arithmetic, music imagery, emotion induction, etc. In removing physiological noise in fNIRS data, band-pass filtering was mostly used. However, more advanced techniques like adaptive filtering, independent component analysis, multi optodes arrangement, etc. are being pursued to overcome the problem that a band-pass filter cannot be used when both brain and physiological signals occur within a close band. In extracting features related to the desired brain signal, the mean, variance, peak value, slope, skewness, and kurtosis of the noised-removed hemodynamic response were used. For classification, the linear discriminant analysis method provided simple but good performance among others: support vector machine, hidden Markov model, artificial neural network, etc. fNIRS will be more widely used to monitor the occurrence of neuro-plasticity after neuro-rehabilitation and neuro-stimulation. Technical breakthroughs in the future are expected via bundled-type probes, hybrid EEG-fNIRS BCI, and through the detection of initial dips.

This paper represents a first attempt to perform a priori sample size determination from a "historic" Electroencephalography (EEG) dataset. The importance of adequate sample size is firstly highlighted, and evidence is given against the use of normal distribution for such computations, when the data cannot be assumed to be Gaussian. The "historic" dataset is then thoroughly examined to determine the least less likely underlying distribution for the desired phenomenon, in this case the spontaneous blinks potential. Two Monte Carlo simulations, using different distribution assumptions, are subsequently computed to estimate the a priori minimum sample size. Finally, these choices are discussed considering practical limitations, as well as the computational differences for other phenomena to study.

De acuerdo algunos investigadores el ruido es concebido típicamente como factor perjudicial en el desempeño cognitivo afectando la percepción, toma de decisiones y la función motora. No obstante, en estudios recientes se asocia al ruido blanco con la concentración y la calma, por lo tanto, esta investigación busca establecer el impacto del ruido blanco binaural en el desempeño de la memoria de trabajo y visual a corto plazo, la actividad cerebral alfa – beta y la atención – meditación, mediante el uso de dos estímulos auditivos con rangos de frecuencia de (100 a 450hz) y (100 a 750hz). Este estudio se realizó en la ciudad de Montes Claros, República de Brasil, donde se evaluó a siete participantes (n = 7) con una edad promedio de 36.71±, y dos grupos de edad (GP1) 21 a 30 y (GP2) 41 a 50 de escolaridad media a universitaria. Dentro del proceso experimental se realizaron pruebas de memoria visual a corto plazo mediante el uso de la batería de evaluación cognitiva general CAB de CogniFit™, así como el registro de actividades cerebrales mediante el uso de Electroencefalograma monopolar y los algoritmos eSense™. Con los resultados obtenidos y mediante el uso de pruebas estadísticas podemos inferir que el ruido blanco binaural con oscilaciones de 100 a 750 Hz contribuyeron con el rendimiento de la memoria visual de trabajo a corto plazo.

Brain-Computer Interface (BCI) technology is a promising research area in many domains. Brain activity can be interpreted through both invasive and non-invasive monitoring devices, allowing for novel, therapeutic solutions for individuals with disabilities and for other non-medical applications. However, a number of ethical issues have been identified from the use of BCI technology. In this paper, we review the academic discussion of the ethical implications of BCI technology in the last five years. We conclude that some emerging applications of BCI technology-including commercial ventures that seek to meld human intelligence with AI-present new and unique ethical concerns. Further, we seek to understand how academic literature on the topic of BCIs addresses these novel concerns. Similar to prior work, we use a limited sample to identify trends and areas of concern or debate among researchers and ethicists. From our analysis, we identify two key areas of BCI ethics that warrant further research: the physical and psychological effects of BCI technology. Additionally, questions of BCI policy have not yet become a frequent point of discussion in the relevant literature on BCI ethics, and we argue this should be addressed in future work. We provide guiding questions that will help ethicists and policy makers grapple with the most important issues associated with BCI technology.

This study was carried out to select EEG signal preprocessing methods to effectively detect and classify Steady State Visually Evoked Potentials (SSVEP). Algorithms, such as: Common Average Reference, Independent Component Analysis (in the task of electrooculography artifacts removing and SSVEP enhancement) and combinations of them were implemented and tested. The best classification accuracy improvement was obtained for CAR and ICA-SSVEP preprocessing methods. Experiments showed high usefulness of these methods in the context of SSVEP detection.

A traditional frequency analysis is not appropriate for observation of properties of
non-stationary signals. This stems from the fact that the time resolution is not defined in the
Fourier spectrum. Thus, there is a need for methods implementing joint time-frequency ...

The use of brain-computer interfaces for gaming-related purposes is usually limited to measuring brain signals with portable electroencephalographic equipment. It is only recently that game-related technological developments have experimented with the addition of brain stimulation through electricity and magnetism, the later being the most benign and scientifically supported. It then becomes relevant to think of design guidelines that could facilitate the creation of videogames that use transcranial magnetic stimulation (TMS). What minimum standards and failsafes should be taken in account before even starting to design such a game? What guidelines could benefit the game development community?

In order to answer these questions, I will make a survey of current commercial technologies available to measure brain signals, as well as technologies that are used and adapted to stimulate the brain using transcranial magnetic stimulation. I will then showcase a couple of examples that use TMS as a game mechanic. After I establish a state of the art, I will cite research, studies and conventions aimed at creating minimum medical safety and ethical standards for said technologies. Finally, I will suggest a set of best practices and guidelines for the game development industry regarding brain mapping, exposure safety and ethical limitations.

The goal of this thesis is to use scientific research, ethical precedent and ergonomics to create design guidelines for any future videogames that could be using transcranial magnetic stimulation as a part of their game mechanics, so as to ensure a safe and enjoyable experience to the player.

The main objective of this research is to generate an accurate, dynamic 3D Shape of a human subject in real-time and without
processing huge data sets. By doing this, the main obstacle is to handle missing data and pose ambiguities. So, the mission of this research is to find a solution to the problem of acquiring body shape and detecting posture of human subjects efficiently. Utilizing multiple Kinect cameras, human body pose and shape is scanned and the data is used to reconstruct the human body shape. So gathering all the data avails to reconstruct the Human Body Shape and produce an interactive real-time solution for virtual fitting of clothing's.

Se presenta una introducción a los conceptos básicos y tecnologías mínimas necesarias para la implementación de una BCI del tipo no-invasiva basada en actividad eléctrica cerebral. Se presentan experiencias recientes realizadas por la FIUNER en esta área junto a nuevas líneas de trabajo.

Invited talk, Friday August 12, 2016 during 'VII Simposio Argentino de Sistemas Embebidos', Ciudad Autónoma de Buenos Aires.

An approach to EEG signal classification for brain-computer interface (BCI) application using fuzzy standard additive model is introduced in this paper. The Wilcoxon test is employed to rank wavelet coefficients. Top ranking wavelets are used to form a feature set that serves as inputs to the fuzzy classifiers. Experiments are carried out using two benchmark datasets, Ia and Ib, downloaded from the BCI competition II. Prevalent classifiers including feedforward neural network, support vector machine, k-nearest neighbours, ensemble learning Adaboost and adaptive neuro-fuzzy inference system are also implemented for comparisons. Experimental results show the dominance of the proposed method against competing approaches.

A novel hybrid brain-computer interface (BCI) based on the electroencephalogram (EEG) signal which consists of a motor imagery-(MI-) based online interactive brain-controlled switch, " teeth clenching " state detector, and a steady-state visual evoked potential-(SSVEP-) based BCI was proposed to provide multidimensional BCI control. MI-based BCI was used as single-pole double throw brain switch (SPDTBS). By combining the SPDTBS with 4-class SSEVP-based BCI, movement of robotic arm was controlled in three-dimensional (3D) space. In addition, muscle artifact (EMG) of " teeth clenching " condition recorded from EEG signal was detected and employed as interrupter, which can initialize the statement of SPDTBS. Real-time writing task was implemented to verify the reliability of the proposed noninvasive hybrid EEG-EMG-BCI. Eight subjects participated in this study and succeeded to manipulate a robotic arm in 3D space to write some English letters. The mean decoding accuracy of writing task was 0.93 ± 0.03. Four subjects achieved the optimal criteria of writing the word " HI " which is the minimum movement of robotic arm directions (15 steps). Other subjects had needed to take from 2 to 4 additional steps to finish the whole process. These results suggested that our proposed hybrid noninvasive EEG-EMG-BCI was robust and efficient for real-time multidimensional robotic arm control.

— Brain-computer interface (BCI) has changed the way to interact with external devices. Considering the role that computers and machines play in our daily life, recently, emotional interaction between human and machine has become an interesting area in BCI. Smart TVs, on the other hand, are becoming ubiquitous. Although recently a growing trend toward developing new features in Smart TVs has emerged, these devices are not yet aware of emotional states of audiences. This study aims at improving the quality of interaction between audiences and Smart TVs by establishing an emotional connection between them. In this work, 19 subjects aged 19-32 years participated in an EEG experiment, while watching a movie clip that evoked 3 emotional states: horror, neutral and relaxation. Firstly, the acquired EEG signals were denoised by stationary wavelet transform (SWT). For the majority of participants, a correlation mean energy of EEG sub-bands and between emotional states was observed for relaxing and scary movies. Thereby, the mean energy of EEG frequency bands 4-50Hz, were extracted so as to classify the emotional states. We managed to classify the EEG signals induced by relaxing and horror movies with average rate of 92% accuracy over all subjects using support vector machine (SVM). The classified data were then given to smart TV in order to establish interaction with audience based on his/her emotional state for each subject (subject-dependent classification).

The purpose of this study is to use OPENViBE, an open source signal processing software, for the Emotiv-EasyCap EEG system. In the previous study the Emotiv microprocessor was combined with EasyCap EEG cap and electrodes. The Motor Imagery BCI with Common Spatial Filter for hand motor imagery programs included in the software is used for cognitive command training. Six subjects were trained to execute left and right EEG commands with the Emotiv-EasyCap system and OPENViBE software. All trained subjects were successful on two cognitive commands with 65% and higher accuracy.

The light-bulb idea metaphor (a light bulb above
someone’s head that appears or switches on when they think of an
idea) is widespread in the literature and popular culture. But, to
the best of our knowledge, nobody has ever built an actual device
that implements this function. The “Inventometer” is a fun and
playful wearable device that measures and displays epiphanometric
data to a real light bulb, so its wearer and others in the
environment are alerted to “aha! moments” (“eureka moments”),
epiphanies, inventions, and idea formation in the brain/mind of
the wearer. It senses brainwave signals indicative of epiphanies,
and indicates to others a continuously varying epiphanometric
quantity by adjusting the light output of the bulb. It uses simple
machine learning on EEG (electroencephalogaph) brainwave
signals to automatically detect and quantify the novelty of ideas
formed in the brain. Long exposure photographs — made while
one or more Inventometer wearers walk around a room —
result in a Phenomenal Augmented Reality (Augmented Reality
of or pertaining to physical phenomena and phenomenology). In
particular, these “epiphanographs”, over time, indicate what sorts
of things in an environment tended to stimulate epiphanies and
to what degree — epiphanogrammetry as a possible new field of
study. Brain Games are designed so multiple people can compete
using their minds much like people competing using their bodies
(e.g. arm wrestling). The “brightest” people in a room become
visible by way of their epiphanographs. But with their wearable
display bulbs glowing brightly, they also serve as a distraction to
each other, thus introducing a richly complex and competitive
collective biofeedback gaming space. The device is meant to
appeal to people of all ages, from children to university students,
and thus forms a good teaching for making skills, science, and
engineering (e.g. power electronics, 3D printing, etc.). It is also
an ongoing research project