Combining Classifiers

Nice article: but watch out: Math ahead !! read this first : pattern recognition tutorial

FAST ICA and beyond

ICA and GABA to keep You awake !

Explore this website by Mr. German Gomez-Herrero if You are interested in ICA , brain synchrony and EEGLab. Enjoy his (G) ABA synchrony

I very much enjoyed his crystal clear explanation on ICA principles in the EEGLab list Read here how Mr German Gomez-Herrero explains: Imagine that in an ERP or EEG experiment we have only 2 brain populations (P1,P2) that are active and whose bioelectrical activity are producing most of the variance in the scalp EEG. Let us call s1(t) and s2(t) the electrical activation patterns that are being generated at P1 and P2, respectively. Then, if we call x1(t) and x2(t) the signals acquired in two scalp electrodes we can write (based on the quasistatic approximation of brain volume conduction): EQUATION 1: x1(t) = a11*s1(t)+a12*s2(t) x2(t) = a21*s1(t)+a22*s2(t) where a11,a12,a21,a22 are just some scalar values modeling the electrical transfer from the locations P1,P2 to the electrodes locations (i.e. the volume conduction effects). Then, if we further assume that s1(t) and s2(t) are statistically independent from each other then, we can use ICA to estimate a (randomly scaled version of) the transfer coefficients a11,a12,a21,a22 as well as a (randomly scaled version of the) source activations s1(t) and s2(t) based on only on the observed scalp signals x1(t) and x2(t), that is: [a11/k, a12/k, a21/k, a22/k, k*s1(t), k*s2(t)] = ICA(x1(t),x2(t)) Where k is an unknown scaling factor. Since the brain generators P1,P2 are independent it makes sense to study each of them separately. Thanks to ICA we know all the variables involved in the system of equations above (EQUATION 1) except for the factor k. Then to study the contribution to the EEG of the first ICA component (s1(t)) we can just set to zero s2(t) and see that EQUATION 1 becomes: EQUATION 2: x1(t) = (a11/k)*(k*s1(t)) = a11*s1(t) x2(t) = (a21/k)*(k*s1(t)) = a21*s1(t) So this means that the scalp EEG at any electrode is just a scaled version of the source activation computed by ICA. Therefore, each independent component is identified by its (randomly scaled) activation k*s1(t) and the scaling factors for each electrode a11/k,a21/k. EEGLAB uses k*s1(t) to plot the spectrum and the component ERP (if epoched). Therefore the component spectrum plotted in EEGLAB does not correspond to any scalp location, it is just the spectrum of a randomly scaled version of the signal that is actually being generated inside the brain, in the brain population P1. When EEGLAB plots the scalp topography of component 1 it actually plots the values (a11/k),(a21/k). Note from EQUATION 2 that those values would be the values of the actual scalp potentials only when s1(t)=1/k. In what time instant does that happen? We can't know since the scaling factor k is unknown and therefore we can't know when s1(t) is going to take an unknown value :). However, note that that the ratio between the potentials at different scalp locations is constant at ANY time: x1(t)/x2(t) = [(a11/k)*(k*s1(t))] / [(a21/k)*(k*s1(t))] = a11/a21 These relative values x1(t)/x2(t) conceptually tell us whether component 1 was generated in an brain area closer to electrode x1 or closer to electrode x2. Thus, they are all we need for localizing in the brain the population P1 using any of the inverse methods available in the literature (e.g. LORETA or just your own intuition). Then to your question that at what time the scalp distribution is plotted you can say that the relative values of that scalp distribution x1(t)/x2(t) are the same for ANY time but the actual values x1(t),x2(t) are arbitrary and do not correspond to any certain time instant. So summarizing, you have to understand each ICA component as a signal generated inside the brain. Imagine that s1(t) would be a sinusoid generated somewhere in the temporal cortex, imagine also that electrode x1 is located in the temporal lobe and x2 in the occipital lobe. Then, component 1 has a single spectrum (an impulse at the frequency of the sinusoid). If only component 1 would be active, the signals acquired in the scalp would be just scaled sinusoids and so their spectrums would also be just scaled impulses at the frequency of that sinusoid. Furthermore, the fact that (a11/k)/(a21/k) is quite large tells you that component 1 might be located much closer to electrode x1 than to electrode x2, i.e. it is located in the temporal cortex. Note that we know this without knowing the actual values of a11 and a21 (i.e. we do not know k) but just from the fact that (a11/k)/(a21/k)=a11/a21 is large. My explanations above quite simplistic and discard many important issues but I think they capture the main idea. Probably other EEGLAB users or developers will tell you more. Hope that helps, Germán --------------------------------------------------------------------- Germán Gómez-Herrero M. Sc., Researcher Tampere University of Technology P.O. Box 553, FI-33101, Tampere, Finland Phone: +358 3 3115 4519 Mobile: +358 40 5011256 Fax: +358 3 3115 4989 http://www.cs.tut.fi/~gomezher/index.htm

More exoskeletons

Although targetted at the Military some more interesting medical applications spring to mind...

Nanoskeleton

Now THAT is what I call an EXOSCELETON !!! sold by:

See through...

Wolf pack or miss Twiggy ?

Exosceleton

EXOSCELETON !!

No need to buy some CryTec shoot them up games anymore. Equipped with this stuff and some good old 10.000 RPM chain gun You could beat them all. More peacefull applications are of course more interesting: paralysed patients with this device and even added some BCI interface and intelligent peripheral robotics could be made to move again. Take a look at the video's how flexible this is ! Of course you could wait for the real CRYSIS stuff.....

Coffee anybody ?

Many researchers around the world have tried to build robotic devices able to help people with paralysis. Now, European researchers have developed a robot control system based on electroencephalogram (EEG). The patients using the Brain2Robot system might regain some of their lost autonomy. The users will control the robotic arm with their thoughts. To control the robotic arm, the Brain-Computer Interface (BCI) developed at one Fraunhofer Institute in Germany is combined with an eye tracker. The signals are sent to a computer which performs the main learning task. According to the researchers, the robotic arm could become commercially available in a few years.

read more

Chips growing axons ?

Not completely but take a look at these connecting nanotubes and tell me that they do not resemble some alien axons ?

read more...

Brain Imaging Conference

To review the most exciting developments in neuroimaging – from molecules to systems To highlight the recent work done in this field in the world renowned laboratories To identify some of the most exciting young investigators in this field To forge important collaborations between US-based scientists and investigators, which will promote scientific research and cooperation among the various institutions To disseminate the insights of the meeting to a broad audience via a powerful array of online outlets To view the complete programme, please visit www.nyas.org/imgconf.

Chess anybody ?

just for fun...

A new dimension in Neuronavigation: Visor (ANT)

A complete new dimension in neuronavigation. Do TMS simultaneously with EMG and EEG. Impossible ? Not a word in the ANT dictionary.

Neuroanatomy course

2nd - 4th April 2008

Institute of Child Health, London WC1

Course director: Dr Paul Johns BSc BM MSc

(Specialist Registrar, Institute of Neurology, Queen Square)

• 3-day programme
• Assumes minimal prior knowledge
• Emphasises functional and clinical neuroanatomy
• Includes dissecting room sessions examining real brains!

Three-day course: £200 (early bookings); £240 (late bookings)

Suitable for undergraduate / postgraduate students in medicine and biomedical sciences, neuroscience and psychology

Psychoacoustics Book

How hearing works and how the brain processes sounds entering the ear to provide the listener with useful information are of great interest to psychologists, cognitive scientists, and musicians. However, while a number of books have concentrated on individual aspects of this field, known as psychoacoustics, there has been no comprehensive introductory coverage of the multiple topics encompassed under the term. Music, Cognition, and Computerized Sound is the first book to provide that coverage. The book begins with introductory chapters on the basic physiology and functions of the ear and auditory sections of the brain, then proceeds to discuss numerous topics associated with the study of psychoacoustics, including cognitive psychology and the physics of sound. The book has a particular emphasis on music and computerized sound. An accompanying CD-ROM includes many sound examples to help explicate the text.

BCI Book

Toward Brain-Computer Interfacing Interest in developing an effective communication interface connecting the human brain and a computer has grown rapidly over the past decade. The brain-computer interface (BCI) would allow humans to operate computers, wheelchairs, prostheses, and other devices, using brain signals only. BCI research may someday provide a communication channel for patients with severe physical disabilities but intact cognitive functions, a working tool in computational neuroscience that contributes to a better understanding of the brain, and a novel independent interface for human-machine communication that offers new options for monitoring and control. This volume presents a timely overview of the latest BCI research, with contributions from many of the important research groups in the field. The book covers a broad range of topics, describing work on both noninvasive (that is, without the implantation of electrodes) and invasive approaches. Other chapters discuss relevant techniques from machine learning and signal processing, existing software for BCI, and possible applications of BCI research in the real world.

Brain Modelling

Signal processing and neural computation have separately and significantly influenced many disciplines, but the cross-fertilization of the two fields has begun only recently. Research now shows that each has much to teach the other, as we see highly sophisticated kinds of signal processing and elaborate hierachical levels of neural computation performed side by side in the brain. In New Directions in Statistical Signal Processing, leading researchers from both signal processing and neural computation present new work that aims to promote interaction between the two disciplines. The book's 14 chapters, almost evenly divided between signal processing and neural computation, begin with the brain and move on to communication, signal processing, and learning systems. They examine such topics as how computational models help us understand the brain's information processing, how an intelligent machine could solve the "cocktail party problem" with "active audition" in a noisy environment, graphical and network structure modeling approaches, uncertainty in network communications, the geometric approach to blind signal processing, game-theoretic learning algorithms, and observable operator models (OOMs) as an alternative to hidden Markov models (HMMs).

Brain Storm

A bold scheme to map the entire human brain has become the mission of many scientists from a host of different fields. Paul Smaglik tracks the interdisciplinary career implications.

IMAGE SOURCE/CORBIS

A major goal for neuroscientists is to build a complete wiring diagram of the human brain. Such a feat has already been achieved for the nematode worm Caenorhabditis elegans. But going from worm to human requires a serious leap: C. elgans has 302 neurons connected together through 7,000 synapses; the human brain has an estimated 10 billion neurons, each of which has an average of 10,000 synaptic connections.

Undaunted, many neuroscientists are pursuing at least part of the problem, and...read on

Bioexplorer

I (sigh) Robot

Reminds me of Alien. As long as the makers of this stuff do not forget that geriatric grandma's tend to suffer from osteoporosis and carrying this thing could be a bone breaker... PS It's a Honda Jim, but not as we know it... TOKYO (AFP) - As Japan greys, who will look after the elderly? Maybe one day their aging children -- in robot suits -- if technology under development comes out of the laboratory and into the home

Among the array of futuristic products for the senior citizens or their caregivers on display at a trade fair this week in Tokyo was a power assist suit that makes it easier to lift an elderly person out of a wheelchair or bed.

The suit looks clunky, takes 10 minutes to put on, weighs thirty kilos (66 pounds) and has blinking lights and wires reminiscent of a robot in a sci-fi movie.

But it allows the wearer to lift a person as heavy as 100 kilos as if they were carrying only half that weight.

"I don't feel heavy at all. Because of air pumped in the suit, I just feel like I'm carrying a normal backpack," said Hiroi Tsukui, a participant in the project as she carried a young man onto a table to demonstrate to onlookers.

For now the suit, developed by Kanagawa Institute of Technology, is only made to order and generally targeted at nursing homes and hospitals.

But Tsukui hopes it will be used in ordinary homes in the future.

"Of course 80-year-olds won't be able to wear this. But perhaps for their children who are in their 50s and need to take care of their parents, this could prove to be useful," she added.

Japan, which has one of the world's lowest birth rates and yet forbids immigration, is increasingly turning to robots to take care of rudimentary tasks in hospitals and nursing homes as the young population dwindles.

Researchers are also looking to improve "robot suits" for the elderly to wear themselves for more autonomy, instead of relying on caregivers or their children.

A "muscle suit" developed by Tokyo University of Science also allows the wearer to lift heavy objects.

The half-body suit incorporates artificial muscles made of elastic rubber and nylon and air pumps for the arms.

Hiroshi Kobayashi, an associate professor at the university that spearheaded the project, admitted that hurdles remain before it could be easily used.

The suit, which weighs four kilos, presents "some safety concerns for elderly people," he said.

"So for now we have limited the suit to caretakers or even construction workers whom I think would benefit greatly from this. But we hope in the future this will give old people more mobility with their arms," he added.

Another product designed to give elderly greater mobility is auto giant Honda Motor's "Walking Assist" product which can help the elderly walk independently without the help of a cane, walking frame or arm of a carer.

It's a chunky belt with sensors and leg straps that monitor leg movements to help the user walk correctly.

As the person walks, a device behind the thigh pushes the leg forward and once he or she steps on the ground, another one at the front of the thigh pushes inwards, stabilising the user.

The belt is currently only a prototype, as its three-kilo weight could be a little too heavy for a frail elderly man or woman.

Taiji Koyama, an assistant chief designer at Honda R&D Co., hopes that in the near future his team, which has spent eight years on the project, will be able to make the belt lighter and easier for the elderly.

"We hope to roll this out as a product as soon as possible so people will be able to use it," the engineer said.

"It is a lot lighter than 'muscle suits' that use artificial muscle. They still have a long way to go to become mainstream as they remain difficult to wear," he added.

Keep on smiling

Why is this lady smiling ? not because she is high but because her EEG does not consume any (battery) power. Just body heath that keeps the brain going.. made in Flanders by IMEC. Boy are we good... More of this on Medgadget Thanks to Greg for sending this link.