Brain Computer interface

INTRODUCTION
Brain Computer interface (BCI) is a communication system that recognized users’ command only from his or her brainwaves and reacts according to them. For this purpose PC and subject is trained. Simple task can consist of desired motion of an arrow displayed on the screen only through subject's imaginary of something (e.g. motion of his or her left or right hand). As the consequence of imaging process, certain characteristics of the brainwaves are raised and can be used for user's command recognition, e.g. motor mu waves (brain waves of alpha range frequency associated with physical movements or intention to move). An Electroencephalogram based BrainComputer-Interface (BCI) provides a new communication channel between the human brain and a computer. Patients who suffer from severe motor impairments (late stage of Amyotrophic Lateral Sclerosis (ALS), severe cerebral palsy, head trauma and spinal injuries) may use such a BCI system as an alternative form of communication by mental activity. The use of EEG signals as a vector of communication between men and machines represents one of the current challenges in signal theory research. The principal element of such a communication system, more
Page | 1

Brain Computer interface known as “Brain Computer Interface”, is the interpretation of the EEG signals related to the characteristic parameters of brain electrical activity. The role of signal processing is crucial in the development of a real-time Brain Computer Interface. Until recently, several improvements have been made in this area, but none of them have been successful enough to use them in a real system. The goal of creating more effective classification extraction. The main objective of this project is the establishment of a Time – Frequency method, which allows EEG signal classification between two given tasks (“geometric figure rotation” and “mental letter composing”), as well as the familiarization with the state of the art in time-frequency and Brain Computer Interface. The extension of this method to a five-task classification problem will be also considered. The electrical nature of the human nervous system has been recognized for more Than a century. It is well known that the variation of the surface potential distribution on the scalp reflects functional activities emerging from the underlying brain [2.1]. This surface potential variation can be recorded by affixing an array of electrodes to the scalp, and measuring the voltage between
Page | 2

algorithms,

have

focused

numerous

investigations in the search of new techniques of feature

Brain Computer interface pairs of these electrodes, which are then filtered, amplified, and recorded. The resulting data is called the EEG. Fig. 1-1 shows waveforms of a 10 second EEG segment containing six recording channels, while the recording sites are illustrated in Fig. 2-2.

Figure 2-1. A segment of a multichannel EEG of an adult subject during a multiplication task.

Page | 3

Brain Computer interface

Each site has a letter (to identify the lobe) and a number or another letter to identify the hemisphere Location. The letters F, T, C, P, and O stand for Frontal, Temporal, Central, Parietal and Occipital. (Note that there is no “central”, but this is just used for identification process). Even numbers (2, 4, 6, and 8) refer to the right hemisphere and odd numbers (1, 3, 5, and 7) refer to the left hemisphere. The z refers to an electrode placed on the midline. Nasion: point between the forehead and nose. Inions: Bump at back of skull

Page | 4

neurological diseases. For example: • Bioengineering applications: assist devices for disabled people. • Human subject monitoring: sleep disorders. and/or overall "mental state".Brain Computer interface System overview A Brain-Computer Interface (BCI) is a system that acquires and analyzes neural Signals with the goal of creating a communication channel directly between the brain and the computer. Such a channel potentially has multiple uses. Page | 5 . attention Monitoring.

productive BCI research programs have begun. The immediate goal is to provide communication capabilities so that any subject can control the external world without using the brain's normal output pathways of peripheral nerves and muscles.Brain Computer interface • Neuroscience research: real-time methods for correlating observable behavior With recorded neural signals. Over the past decade. Nowadays. people have speculated that electroencephalographic (EEG) activity or other measures of brain function might provide this new channel. Facilitated and encouraged by the new understanding of brain functions and by the low-cost computer equipments. such activities drive their efforts in: • Brain (neural) signal acquisition: development of both invasive and non-invasive Techniques for high quality signal acquisition. • Algorithms and processing: advanced machine learning and signal processing Page | 6 . For many years. these programs have concentrated mainly in developing new communication and control technologies for people with severe neuromuscular disorders. • Man – Machine Interaction: Interface devices between human and computers. Machines.

which take advantage of cheap/fast computing power (i. Select letters or icons. The central element in each BCI is a translation devices. the physiology and how these are related to perception and Cognition. the functional neuro-anatomy. and the computer which recognizes the command contained in the input and expresses them in the device control. or operate a neuroprosthesis. enabling signals to be interpreted in the context of the neurobiology. Achievement of greater speed and accuracy depends on improvements in: • Signal acquisition: methods for increasing signal-to-noise ratio (SNR). Moore's Law2) to enable online real-time processing. his algorithm BCI or that converts on the electrophysiological input from the user into output that controls user external operation her depends in effective interaction between two adaptive controllers: the who encodes commands electrophysiological input provided to the BCI. signal-to interference ratio (S/I)) as well as optimally combining spatial and temporal Page | 7 .e. Current BCI’s have maximum information transfer rates of 5-25 bits/min.Brain Computer interface Algorithms. Present BCI’s use EEG activity recorded at the scalp to control cursor movement . • Underlying neuroscience: a better understanding of the neural code.

it is necessary to clean them. 3) Signal Classification: once the signals are cleaned. electrodes). they will be processed and Page | 8 . 2) Signal Pre-Processing: once the signals are acquired. • Co-learning: jointly optimizing combined man-machine system and taking Advantage of feedback. After. 1) Signal Acquisition: the EEG signals are obtained from the brain through invasive or non-invasive methods (for example. The common structure of a Brain Computer Interface is the following.Brain Computer interface Information. • Single trial analysis: overcoming noise and interference in order to avoid Averaging and maximize bit rate. the signal is amplified and sampled. • Understanding algorithms and models within the context of the neurobiology: Building predictive models having neurophysiologic ally meaningful parameters And incorporating physically and biologically meaningful priors. • Experimental paradigms for interpretable readable signals: mapping the task to The brain state of the user (or vice versa).

BCI common structure. Usually.5 to 100 µV in amplitude. they will be used by an Appropriate algorithm for the development of a certain application. By means of Fourier transform power spectrum from the raw EEG signal is derived. In power spectrum contribution of sine waves with different frequencies are Page | 9 . 4) Computer Interaction: once the signals are classified. BRAIN SIGNALS Brain patterns form wave shapes that are commonly sinusoidal.Brain Computer interface Classified to find out which kind of mental task the subject is performing. they are measured from peak to peak and normally range from 0. which is about 100 times lower than ECG signals.

Alpha activity is induced by closing the eyes and by relaxation.Brain Computer interface visible. the brain state of the individual may make certain frequencies more dominant. BRAIN SIGNALS MEASUREMENT AND PROCESING Encephalographic measurements is consisted of • Electrodes with conductive media Page | 10 . It can be usually observed better in the posterior and occipital regions with typical amplitude about 50 µV (P-P). calculating). ranging from 0 Hz to one half of sampling frequency. • Beta (>10 Hz) • Alpha (8-13 Hz) • Theta (4-8 Hz) • Delta (0.5-4 Hz) The best . Although the spectrum is continuous.known and most extensively studied rhythm of the human brain is the normal alpha rhythm. Brain waves have been categorized into four basic groups. and abolished by eye opening or alerting by any mechanism (thinking.

Many types of electrodes exist. and personal computer process this data.Brain Computer interface • Amplifiers with filters • A/D converter Electrodes read signal from the head surface. electrode caps are preferred. 1 to 3 mm in diameter. Electrodes The EEG electrodes and their proper function are critical for acquiring appropriately high quality data for interpretation. Basically there are following types of electrodes: • Disposable (gel-less and pre-gelled types) • Reusable disc electrodes (gold. often with different characteristics. silver. Commonly used scalp electrodes consist of AgAgCl discs. amplifiers bring the microvolt signals into range where they can be digitalized accurately. AgCl electrodes can accurately record also very slow changes in potential. stainless steel or tin) • Headbands and electrode caps • Saline-based electrodes • Needle electrodes For multichannel montages. Page | 11 . with number of electrodes installed on this surface. converter changes signals from analog to digital form. with long flexible leads that be plugged into an amplifier.

Brain Computer interface Needle electrodes are used for long time recordings and are invasively inserted under scalp. pre auricural points and inions) to provide adequate coverage of all regions of the brain. Label 10-20 designates proportional distance on percents between ears and nose where points for electrodes are chosen. In 1958. International Federation on Electroencephalography and Clinical Neurophysiology adopted standardization for electrode placement called 10-20 electrode placement system. The head is divided into proportional distances from prominent skull landmarks (nasion. where electrodes are direct on the brain and are scanning only the small location. Best results are in with invasive measurement techniques. Picture above describes usual electrodes placement Amplifiers and filters Page | 12 . This system standardized physical placement and designations of electrodes an the scalp.

damages that migh result from high input voltages as they occur during the application of defibrillators or electrosurgical instrumentation.Brain Computer interface The signals need to be amplified to make them compatible with A/D converters. Amplifiers adequate to measure these signals have to satisfy very specific requirements. reject superimposed noise and interference signals. The basic requirements that a biopotential amplifier has no satisfy are: • The physiological process to be monitored should not be influenced in any way by the amplifier. from any hazard of electric shock. and guarantee protection from damages through voltage and current surges for both patients and electronic equipment. • • • The amplifier should provide the best possible The amplifier has to offer protection of the patient The amplifier itself has to be protected against separation of signal and interferences. Page | 13 . • The measured signal should not be distorted. They have to provide amplification selective to the physiological signal.

such as AC power line noise. The most common EEG artifact sources can be classified in following way: Patient related: • Any minor body movements • EMG • ECG (pulse.related artifacts are unwanted physiological signals that may significantly disturb the EEG. The artifact in the recorded EEG may be either patient. Usually it is a sequence with higher amplitude and different shape on comparison to signal sequences that doesn't suffer by anu large contamination. can be decreased by decreasing electrode impedance and by shorter electrode wires. Technical artifacts.Brain Computer interface Artifacts Among basic evaluation of the EEG traces belongs scanning for signal distortions called art effects. Patient . pace-maker) • Eye movements • sweating Technical • 50/60 Hz • Impedance fluctuation Page | 14 .related or technical.

Elliptic) with adjustable Page | 15 . Chebyshev.Brain Computer interface • Cable movements • Broken wire contacts • Too much electrode paste or dried pieces • Low battery Excluding the artifact segments from the EEG traces can be managed by the trained experts or automatically. prewhitening. In Brain science Institute RIKEN was developed the ICELAB for signal processing which is describing the picture below. filtering: High Pass Filtering (HPF). Sub band filters (Butterworth. The preprocessing tools include: Principal Component Analysis (PCA). For better discrimination of different physiological artifacts. and muscle activity may be important. ECG. additional electrodes for monitoring eye movement. Low Pass Filtering (LPF).

The successful and efficient use of the ICALAB vectors. Smooth Component Analysis (SmoCA). but rather mechanical procedures: There is not very much left for the user to do after the machinery has been optimally implemented. The algorithms can perform not only ICA . The post processing tools includes: Deflation and Reconstruction removing Moreover. Nonnegative Matrix Factorization (NMF). Strongly depends on a priori knowledge. Page | 16 .but also Second Order Statistics Blind Source Separation (BSS) Sparse Component Analysis (SCA). flexible extendable structure with. frequency sub bands and the number of sub bands. common sense and appropriate use of the preprocessing and post processing tools. the ("cleaning") ICALAB of original have raw or data by and undesirable components. the possibility to extend the toolbox by the users by adding their own algorithms. Factor Analysis (FA) and any other possible matrix factorization of the form X=HS+N or Y=WX where H=W+ is a mixing matrix or a matrix of basis He ICA/BSS algorithms are pure mathematical formulas. powerful.Brain Computer interface order of filters. Toolboxes noise artifacts.

they will be used by an appropriate algorithm for the development of a certain application. 2) Signal Pre-Processing: once the signals are acquired. Page | 17 . they will be processed and classified to find out which kind of mental task the subject is performing. 4) Computer Interaction: once the signals are classified. electrodes).Brain Computer interface STRUCTURE OF BRAIN-COMPUTER INTERFACE The common structure of a Brain-Computer Interface is the following: 1) Signal Acquisition: the EEG signals are obtained from the brain through invasive or non-invasive methods (for example. it is necessary to clean them. 3) Signal Classification: once the signals are cleaned.

and a feature extraction and recognition unit that identifies the command sent by the user to the BCI. Page | 18 . responsible for artifact detection.Brain Computer interface BRAIN-COMPUTER INTERFACE ARCHITECTURE The processing unit is subdivided into a preprocessing unit. The output subsystem generates an action associated to this command.

The information of these "mental states" can be recorded with different methods. Both evoked potential and operant conditioning methods are normally externallybased BCIs as the electrodes are located on the scalp. In a BCI.. They are usually obtained by averaging a number of brief EEG segments time-registered to a stimulus in a simple task. Describes the different signals in common use. etc.Brain Computer interface Neuropsychological signals used in BCI applications. single neural recordings may use operant conditioning in order to train neurons for control or may accept the natural occurring signals for control. the signal is described under the Implanted methods use signals from single or small groups of neurons in order to control a BCI. EPs may provide control when the BCI application Page | 19 . As an example. Where this occurs.. and operant conditioning. Neuropsychological signals can be generated by one or more of the following three: implanted methods. Interfaces based on brain signals require on-line detection of mental states from Spontaneous activity: different cortical areas are activated while thinking different things (i. a music composition. a mathematical computation. evoked potentials (also known as event related potentials).e. an imagined arm movement.). Evoked potentials (EPs) are brain potentials that are evoked by the occurrence of a sensory stimulus. It may be noted that some of the described signals fit into multiple categories.

it is used to train the patients to control their EEG. as EPs are an inherent response. and a reinforce to change the probability of a response occurring again in a given situation. Operant conditioning is a method for modifying the behavior (an operant).as it is presented in table shown in below. an operant response.Brain Computer interface produces the appropriate stimuli. several methods use operant conditioning on spontaneous EEG signals for BCI control. Page | 20 . This paradigm has the benefit of requiring little to no training to use the BCI at the cost of having to make users wait for the relevant stimulus presentation. The main feature of this kind of signals is that it enables continuous rather than discrete control. This feature may also serve as a drawback: continuous control is fatiguing for subjects and fatigue may cause changes in performance since control is learned. In the BCI framework. which Utilizes contingencies between a discriminative stimulus. EPs offer discrete control for almost all users.

Brain Computer interface Common neuropsychological signals used in BCIs Page | 21 .

the implant allowed Jerry to see shades of grey in a limited field of vision at a low frame-rate. being interviewed about his vision BCI on CBS's The Early Show In vision science. but shrinking Page | 22 . direct brain implants have been used to treat non-congenital (acquired) blindness. Dobelle's first prototype was implanted into "Jerry. causing the signal to become weaker or even lost as the body reacts to a foreign object in the brain.Brain Computer interface Human BCI research Invasive BCIs Invasive BCI research has targeted repairing damaged sight and providing new functionality to paralyzed people." a man blinded in adulthood. the sensation of seeing light. Invasive BCIs are implanted directly into the grey matter of the brain during neurosurgery. invasive devices produce the highest quality signals of BCI devices but are prone to scar-tissue build-up. The system included cameras mounted on glasses to send signals to the implant. Initially. Jens Naumann. This also required him to be hooked up to a two-ton mainframe. As they rest in the grey matter. in 1978. One of the first scientists to come up with a working brain interface to restore sight was private researcher William Dobelle. a man with acquired blindness. A single-array BCI containing 68 electrodes was implanted onto Jerry’s visual cortex and succeeded in producing phosphates.

also blinded in adulthood. Jens Naumann.Brain Computer interface electronics and faster computers made his artificial eye more portable and now enable him to perform simple tasks unassisted. Jens was able to use his imperfectly restored vision to drive slowly around the parking area of the research institute. became the first in a series of 16 paying patients to receive Dobelle’s second generation implant. Phosphenes are spread out across the visual field in what researchers call the starry-night effect. Immediately after his implant. BCIs focusing on motor neuroprosthetics aim to either restore movement in paralyzed individuals or provide Page | 23 . marking one of the earliest commercial uses of BCIs. Dummy unit illustrating the design of a BrainGate interface In 2002. The second generation device used a more sophisticated implant enabling better mapping of phosphenes into coherent vision.

such as interfaces with computers or robot arms.Brain Computer interface devices to assist them. Implanted in Nagle’s right precentral gyrus (area of the motor cortex for arm movement). Researchers at Emory University in Atlanta led by Philip Kennedy and Roy Bakay were first to install a brain implant in a human that produced signals of high enough quality to simulate movement. Page | 24 . Ray’s implant was installed in 1998 and he lived long enough to start working with the implant. They produce better resolution signals than noninvasive BCIs where the bone tissue of the cranium deflects and deforms signals and have a lower risk of forming scartissue in the brain than fully-invasive BCIs. suffered from ‘locked-in syndrome’ after suffering a brainstem stroke. eventually learning to control a computer cursor. Johnny Ray. the 96-electrode Brain Gate implant allowed Nagle to control a robotic arm by thinking about moving his hand as well as a computer cursor. Partially-invasive BCIs Partially invasive BCI devices are implanted inside the skull but rest outside the brain rather than within the grey matter. lights and TV. Tetraplegic Matt Nagle became the first person to control an artificial hand using a BCI in 2005 as part of the first nine-month human trial of Cyberkinetics Neurotechnology’s BrainGate chip-implant. Their patient.

Brain Computer interface Electro cortico graphy (ECoG) measures the electrical activity of the brain taken from beneath the skull in a similar way to non-invasive electroencephalography (see below). It has not been studied extensively until recently due to the limited access of subjects. the laser light pattern and wavelengths it reflects would change slightly. In a later trial. Currently. The laser would be trained on a single neuron and the neuron's reflectance measured by a separate sensor. the only manner to acquire the signal for study is through the use of patients requiring Page | 25 . but is not taken from within the brain parenchyma itself. beneath the dura mater. These would involve implanting a laser inside the skull. When the neuron fires. the researchers enabled a teenage boy to play Space Invaders using his ECoG implant. but the electrodes are embedded in a thin plastic pad that is placed above the cortex. This would allow researchers to monitor single neurons but require less contact with tissue and reduce the risk of scartissue build-up. This research indicates that it is difficult to produce kinematic BCI devices with more than one dimension of control using ECoG. ECoG technologies were first trialed in humans in 2004 by Eric Leuthardt and Daniel Moran from Washington University in St Louis. Light Reactive Imaging BCI devices are still in the realm of theory. This signal can be either subdural or epidural.

and lesser training requirements than scalp-recorded EEG. Non-invasive BCIs As well as invasive experiments. This feature profile and recent evidence of the high level of control with minimal training requirements shows potential for real world application for people with motor disabilities. Animal BCI research Page | 26 . and probably superior long-term stability than intracortical single-neuron recording. Although they are easy to wear. Although the waves can still be detected it is more difficult to determine the area of the brain that created them or the actions of individual neurons. non-invasive implants produce poor signal resolution because the skull dampens signals. dispersing and blurring the electromagnetic waves created by the neurons. lower clinical risk. there have also been experiments in humans using non-invasive neuroimaging technologies as interfaces. ECoG is a very promising intermediate BCI modality because it has higher spatial resolution. better signal-tonoise ratio.Brain Computer interface invasive monitoring for localization and resection of an epileptogenic focus. Signals recorded in this way have been used to power muscle implants and restore partial movement in an experimental volunteer. and at the same time has lower technical difficulty. wider frequency range.

He also found that dispersed groups of neurons in different areas of the brain collectively controlled motor commands but was only able to record the firings of neurons in one area at a time because of technical limitations imposed by his equipment. date back to the 1970s. Apostolos Georgopoulos at Johns Hopkins University found a mathematical relationship between the electrical responses of single motor-cortex neurons in rhesus macaque monkeys and the direction that monkeys moved their arms (based on a cosine function). Early work Studies that developed algorithms to reconstruct movements from motor cortex neurons.Brain Computer interface Several laboratories have managed to record signals from monkey and rat cerebral cortexes in order to operate BCIs to carry out movement. Other research on cats has decoded visual signals. Work by groups led by Schmidt. a training method using punishment and rewards. Monkeys have navigated computer cursors on screen and commanded robotic arms to perform simple tasks simply by thinking about the task and without any motor output. Fetz and Baker in the 1970s established that monkeys could quickly learn to voluntarily control the firing rate of individual neurons in the primary motor cortex via closed-loop operant conditioning. Page | 27 . In the 1980s. which control movement.

Miguel Nicolelis. John Donohue. bottom row: recording) In 1999. researchers led by Yang Dan at University of California. and Andrew Schwartz. Prominent research successes Phillip intracortical Kennedy and colleagues interface built by the first brain-computer implanting neurotrophic-cone electrodes into monkeys.Brain Computer interface There has been rapid development in BCIs since the mid-1990s. The team used an array of electrodes embedded in the thalamus (which integrates all of the Page | 28 . including research groups led by Richard Andersen. Berkeley decoded neuronal firings to reproduce images seen by cats. Phillip Kennedy. Yang Dan and colleagues' recordings of cat vision using a BCI implanted in the lateral geniculate nucleus (top row: original image. Several groups have been able to capture complex brain motor centre signals using recordings from neural ensembles (groups of neurons) and use these to control external devices.

Using mathematical filters. Similar results in humans have been since then achieved by researchers in Japan (see below). By 2000. which decodes signals from the retina. Researchers targeted 177 brain cells in the thalamus lateral geniculate nucleus area. and their neuron firings were recorded. The cats were shown eight short movies. which could make it difficult to operate a BCI. Such neural ensembles are said to reduce the variability in output produced by single electrodes. Monkeys have advanced reaching and grasping abilities and good hand manipulation skills. making them ideal test subjects for this kind of work. the researchers decoded the signals to generate movies of what the cats saw and were able to reconstruct recognizable scenes and moving objects. Miguel Nicolelis has been a prominent proponent of using multiple electrodes spread over a greater area of the brain to obtain neuronal signals to drive a BCI. the group succeeded in building a BCI that reproduced owl monkey movements while the monkey operated a joystick or reached for food. After conducting initial studies in rats during the 1990s. Nicolelis and his colleagues developed BCIs that decoded brain activity in owl monkeys and used the devices to reproduce monkey movements in robotic arms.Brain Computer interface brain’s sensory input) of sharp-eyed cats. The BCI operated in Page | 29 .

Brain Computer interface real time and could also control a separate robot remotely over Internet protocol. Diagram of the BCI developed by Miguel Nicolelis and colleagues for use on Rhesus monkeys Later experiments by Nicolelis using rhesus monkeys. succeeded in closing the feedback loop and reproduced monkey reaching and grasping movements in a robot arm. But the monkeys could not see the arm moving and did not receive any feedback. With their deeply cleft and furrowed brains. Other labs that develop BCIs and algorithms that decode neuron signals include John Donohue from Brown Page | 30 . a so-called open-loop BCI. The monkeys were later shown the robot directly and learned to control it by viewing its movements. The monkeys were trained to reach and grasp objects on a computer screen by manipulating a joystick while corresponding movements by a robot arm were hidden. The BCI used velocity predictions to control reaching movements and simultaneously predicted hand gripping force. rhesus monkeys are considered to be better models for human neurophysiology than owl monkeys.

The group created headlines when they demonstrated that a monkey could feed itself pieces of zucchini using a robotic arm controlled by the animal's own brain signals. In addition of to limb predicting kinematic BCIs and that kinetic predict parameters movements. Donoghue's group reported training rhesus monkeys to use a BCI to track visual targets on a computer screen with or without assistance of a joystick (closed-loop BCI). Such BCIs could be used to restore mobility in paralyzed limbs by electrically stimulating muscles. These researchers were able to produce working BCIs even though they recorded signals from far fewer neurons than Nicolelis (15–30 neurons versus 50–200 neurons). Commercialization and companies Page | 31 . Andersen's group used recordings of premovement activity from the posterior parietal cortex in their BCI. including signals created when experimental animals anticipated receiving a reward. Schwartz's group created a BCI for three-dimensional tracking in virtual reality and also reproduced BCI control in a robotic arm.Brain Computer interface University. electromyography or electrical activity of muscles are being developed. Andrew Schwartz from the University of Pittsburgh and Richard Andersen from Caltech.

which has not yet received FDA approval for human implantation. and Stony Brook University is continuing development of the implant. Using signal Page | 32 . the company also sells an implant to restore speech. Now listed on a US stock exchange and known as Cyber kinetic Neurotechnology Inc. the company markets its electrode arrays under the Brain Gate product name and has set the development of practical BCIs for humans as its major goal. Philip Kennedy founded Neural Signals in 1987 to develop BCIs that would allow paralyzed patients to communicate with the outside world and control external devices. Avery Biomedical Devices. The Audio is being developed to create a humancomputer interface for communication without the need of physical motor control or speech production. As well as an invasive BCI. A company controlled by Dobelle. at a TI developer’s conference in early 2008. Neural Signals' Brain Communicator BCI device uses glass cones containing microelectrodes coated with proteins to encourage the electrodes to bind to neurons. Ambient. demoed a product they have in development call The Audeo. Although 16 paying patients were treated using William Dobelle's vision BCI. The Brain Gate is based on the Utah Array developed by Dick Norman.Brain Computer interface John Donoghue and fellow researchers founded Cyber kinetics. new implants ceased within a year of Do belle’s death in 2004.

constructing basic computers neurons and manipulating on robotic devices. Interactive Product line is a Swedish company whose objective is to develop and sell easy understandable EEG products that train the ability to relax and focus. There are three main consumer-devices commercial- competitors in this area . Cell-culture BCIs Researchers have built devices to interface with neural cells and entire neural networks in cultures outside animals. As well as furthering research on animal implantable devices. Mind ball is a product developed and commercialized by Interactive Productline in which players compete to control a ball's movement across a table by becoming more relaxed and focused.and pc-users. unpronounced speech representing the thought of the mind can be translated from intercepted neurological signals. chips is Research into techniques for stimulating and recording from individual grown semiconductor sometimes referred to as neuroelectronics or neurochips. Page | 33 . experiments on cultured neural tissue have focused on building problem-solving networks.Brain Computer interface processing.which are going to launch such devices primarily for g aiming.

The Caltech chip had room for 16 neurons. Page | 34 . The hippocampus was chosen because it is thought to be the most ordered and structured part of the brain and is the most studied area. In 2003. a team led by Theodore Berger at the University of Southern California started work on a neurochip designed to function as an artificial or prosthetic hippocampus. The neurochip was designed to function in rat brains and is intended as a prototype for the eventual development of higher-brain prosthesis. Its function is to encode experiences for storage as long-term memories elsewhere in the brain.Brain Computer interface World first: Neurotic developed by Caltech researchers Jerome Pine and Michael Maher Development of the first working neurotic was claimed by a Caltech team led by Jerome Pine and Michael Maher in 1997.

Such classification can be utilized to enable a patient to communicate without any overt physical movement. After collection. the cortical neurons were cultured in a Petri dish and rapidly began to reconnect themselves to form a living neural network. The cells were arranged over a grid of 60 electrodes and used to control the pitch and yaw functions of the simulator. The study's focus was on understanding how the human brain performs and learns computational tasks at a cellular level. This is done just by the computer processing of the patient’s brain waves as can be seen in the block diagram of Figure 1. This accuracy is affected by the quality of EEG signal and the Page | 35 . So far the accuracy of classification has been one of the main pitfalls of the developed BCI systems which directly affect the decisions made as the BCI output. Mental Task Classification for Brain Computer Interface Applications Mental task classification by recognizing Electroencephalographic (EEG) patterns is an important and challenging biomedical signal processing problem.000 neurons taken from a rat's brain to fly an F-22 fighter jet aircraft simulator. Developments of faster digital computers and better EEG devices have motivated many researchers to work on BCI systems.Brain Computer interface Thomas Demarest at the University of Florida used a culture of 25.

the effects of different types of classifiers on the accuracy of classification are investigated and compared. the classification of mental tasks using the Purdue University .Brain Computer interface processing algorithms. The same extracted features for all classifiers facilitated the comparison of classifiers efficiencies. University of Technology Graz are investigated. Bayesian quadratic. Density models. In the current work. In our previous research the effect of different feature extraction algorithms and different number of EEG channels [4] on classification accuracy was investigated. The Gaussian mixture Page | 36 In the present research. EEG dataset and the EEG Dataset from Department of Medical Informatics. The classifiers are intentionally chosen to cover both linear and nonlinear methods. The main focus was on investigation The main focus was on investigation and comparison of feed forward neural network. Both datasets are known and well established datasets in the BCI field and are accessible from internet. The processing algorithms include preprocessing. which is the classifier. Fisher linear classifier and Hidden Markov Models (HMM) in mental task classification. Autoregressive (AR) and adaptive autoregressive coefficients (AAR) were extracted from the EEG windows for all classifiers. Bayesian network. These extracted features were inputted to the next stage of BCI. feature extraction and feature classification. These classifiers are known methods in the machine learning literature.

Flow of the methodology Military applications The United States military has begun to explore possible applications of BCIs beginning in 2008 to enhance troop performance as well as a possible development by adversaries. They are comprised of a number of component functions that in our case were Gaussians. Mixture models are a type of density models.Brain Computer interface model is represented as a Bayesian network and this is the first time that such a classifier is used for the EEG signal classification [7]. Page | 37 . We trained the Bayesian network and Hidden Markov model using expectation maximization (EM) algorithm. As one report concluded. Figure1. These component functions are combined to provide a multimodal density.

The relationship between the time courses of the signals coming from different electrodes serves as an indication of motor activities. Adversarial actions using this approach to implement enhanced. BCI ANDIT'S APPLICATIONS In the context of BCI. Most of the research groups work in the frequency domain and extract the information characterizing mental activities from the nonparametric and parametric spectral representations of EEG. Useful information can alos be extracted from particular brain configurations that can be interpreted in terms of brain states. specialized sensory functions could be possible in limited form now. and with developing capability in the future. Such threat potential would be limited to adversaries with access to advanced medical technology. Also joint spectral properties of the EEG components are analyzed do detecting particular emotional states. EEG signals are mainly analyzed in time. frequency. and time-frequency domains.Brain Computer interface The most successful implementation of invasive interfaces has occurred in medical applications in which nerve signals are used as the mechanism for information transfer. Time-frequency and time-scale representations of EEG signals were exploited for finding those neuronal groups Page | 38 .

This technology uses the Page | 39 . They are already working on Direct Brain Interface that recognizes voluntary activity within the brain and can be used to control assistive technologies without requiring any physical movement. or control of a prosthesis or orthosis. as input and provides a control option by its output. recorded during specific mental activity. display a picture that illustrates the cooperative activity consists in analyzing the joint time-frequency-space correlations between the components of an EEG signal. The Brain Communicator is well-suited for patients who are severely paralyzed or locked-in. There are many applications that are still in developement but also some of them are quite useful. At Graz University of technology was developed BCI that uses oscillatory EEG signals. From that above considerations it can be stated that mental activities. such as ALS (Amyotrophic Lateral Sclerosis) patients on a ventilator. such as cursor control. when mapped onto the timefrequency representation of EEG signals. The obtained output signals are presently evaluated for different purposes. Patients must be cognitively intact with no history of epilepsy. and who therefore have very limited options in their communications with others. selection of letters or words.Brain Computer interface that synchronize their activity as a response to a particular stimulus.

rather like a very pricise EEG (electroencephalogram). The neural signals are transmitted to and processed by a computer to activate a switch or drive a cursor and hence provide communication. whereby the electrode tip is implanted 5mm under the surface of the brain and the outer end is attached to amplifiers and FM transmitters located on the skull. recorded from implanted electrodes which are placed directly on the cortex. No wires or batteries are used. There Neurotrophic are two choices.Brain Computer interface electrocorticogram (ECoG). These signals can be used to activate a switch and hence provide communication. One is the patented Electrode. The system is also used at surgery to guide the surgeon onto target for accurate implantation. It records from local field potentials over the surface of the cortex. This determines if there is brain activity even when there is no movement. The other option is to implant a patented conductive skull screw that does not enter the brain. The combination of EEG Page | 40 . The Army is also interested in using BCI to make faster responses possible for figter pilots. The implant target is thus chosen. Power is provided by a power induction system similar to your toothbrush holder that charges the toothbrush overnight. Before implantation. This implantation requires major surgery lasting about 10 hours. the subject undergoes a functional MRI. under the scalp.

Brain Computer interface signals and artifacts combine to create a signal that can be used to fly a virtual plane. The goal of the ACT program is to enable communication with computers while the computer users’ hands are busy with other tasks. the main focus of Air Force research is for Alternative Control Technology (ACT). One can imagine that the military would have multiple uses for a system that speeds up response times in areas as tactical maneuvering and even targeting and firing weapons. Currently. Page | 41 .

Rehabilitation specialists.Brain Computer interface Present and Future The practical use of BCI technology depends on an interdisciplinary engineers. and to pay careful attention to the needs and desires of Individual users. The prospects for controlling computers through neural signals are indeed Difficult to judge because the field of research is still in its infancy. psychologists. direct neural communication between humans and computers may ultimately mature and find widespread use. Perhaps newly purchased computers will one day arrive with biological signal sensors and thought-recognition software built in. If the advances of the 21st century match the strides of the past few decades. just as keyboard and mouse are commonly found on today's units. but the search for new and more useful signals still continues. cooperation between neuroscientists. Much progress has been made in taking advantage of the power of personal computers to perform the operations needed to recognize patterns in biological impulses. in order to develop appropriate applications. and computer programmers. Page | 42 . to identify appropriate users groups.

Brain Computer interface Page | 43 .

The goal of creating more effective classification algorithms. several improvements have been made in this area. Last are are the applications for making our lives easier. mental letter composing.machine interface. A BCI has to be useful for a wide variety of tasks.Brain Computer interface CONCLUSION As we can see there are many useful applications of brain computer interface. geometric figure rotation. So one day maybe all people are wearing bci-caps and using hands only for eating. But it can be also used for control of human body muscles. multiplication problem solving. two (“rotation” and “letter”) had been problematic in a previous Page | 44 . Or even without caps but with implants right in CNS. Until recently. There are also many possibilities in military domain. It can be very helpful for people with moving disabilities as human . but none of them has been entirely successful.To bring this in reality it has to been d The role of signal processing is crucial in the development of a real-time Brain Computer Interface. visual counting. signals from five different tasks were used as the basis for tests. and A baseline task where the subject was instructed to think about nothing in particular. Among the five tasks. In this study. for instance. have focused numerous investigations in the search of new techniques of feature extraction. when a BCI is used as the main control device for a handicapped individual.

but also for future research.Brain Computer interface classification method based on autoregressive models. Page | 45 . The discovery of a new method founded on Time Frequency Representations was of vital importance not only for these two tasks.

Future Publishing Co. v. Nature. Ghanayim. pp. T. "Conscious mental tasks and their . "An EEG-based Brain-computer interface for cursor control". pp. 1999. J. D. and C.. v. Clan. Medical and Biol. and M. Flor. 1991. Flotzinger. G.31. McFarland. Forneris. and C Liou. Ch.A. B. Schiffman (editors). Neuper. 297— 298. Wolpaw. 252—258. "On-line EEG classification during externallypaced hand movements using a neural network basedClassify er".W. Armonk. "A Spelling Device for the Paralysed". 1996. Page | 46 . v. J.99. [N. Kotchoubey.M. 416—425. J. Neurophysiology. D. Belsh and P. I. Lin. Hinterberger.". Y Tsai. Neat. Electroenceph. 421— 425. Kubler. Pregenzer. EEG signals". Neurophysiol. Inc. H. 1993. Birbaumer. v.R. Engineering and Comput. N.Brain Computer interface BIBILOGRAPHY J. E. pp. G. Amyotrophic lateral sclerosis: diagnosis and management for the clinician. A..398. Pfurtscheller. Taub. Iversen. 1996.L.78. Cline. Electroenceph.J. NY. S.. pp. Kalcher. Perelmouter.

Brain Computer interface Page | 47 .

Sign up to vote on this title
UsefulNot useful