• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

HSE Team Wins International Hackathon with BCI Game

A team of post-graduate students and researchers from the HSE Centre for Cognition & Decision Making have invented a multiplayer BCI game, which is won by the player who best controls a robot with their mind.

The IEEE International Symposium on Video and Audio Signal Processing in the Context of Neurotechnologies took place in St. Petersburg, Russia, on June 26th and 27th and featured a hackathon, also called the IEEE Brain Data Bank Challenge. Representing HSE at the hackathon were Dmitry Altukhov, Nikolay Smetanin, and Alexandra Kuznetsova, all researchers with the HSE Centre for Cognition & Decision Making. The three are also part of a neurovisualization methods group headed by Alexey Ossadtchi.

The team developed a game in which two people compete to control a robot that is made from Legos and pours drinks into two glasses. After receiving commands from a player, the robot tilts the bottle over a glass. If the bottle is tipped enough, the drink is poured into the glass. The player’s goal is to pour the entire contents of the bottle into their glass. Players can send the robot three different commands: left, right, or stop.

The commands are given to the robot through a brain-computer interface that recognises imaginary movements of the left or right arm. For example, in order to command the robot to tilt the bottle to the left, the players have to think of themselves moving their left arm. In order to move to the right, the players think of moving their right arm, and in order to stop they just have to relax. The player who best concentrates on the thought-up movements pulls the bottle in their direction with the most strength and, as a result, wins.

HSE’s team placed first and took home the grand prize of $500.

 


Alexandra Kuznetsova

Despite the fact that the task is presented in the form of a game, multiplayer BCIs open up new areas of research and allow for important applications to be created.

By analysing the process of a game in which users can both compete against and cooperate with one another (by trying to tilt a glass fastest, for instance), we can study mechanisms of social collaboration from a new angle. And from a technical point of view, having several users allows for a larger number of distinct commands to be given and for complex devices to be co-controlled.

In our opinion, the most promising application lies in therapy for those whose motor functions have been impaired as a result of brain damage. As demonstrated in recent studies, using games to rehabilitate patients after a stroke leads to a quicker recovery of motor activity. Further, using a multiplayer BCI for rehabilitation not only requires significant involvement of the patient’s sensorimotor system in carrying out tasks, but it also fosters social collaboration among several patients in the form of a game, thereby positively impacting recovery.

 

See also:

Neural Prosthesis Uses Brain Activity to Decode Speech

Researchers from HSE University and the Moscow State University of Medicine and Dentistry have developed a machine learning model that can predict the word about to be uttered by a subject based on their neural activity recorded with a small set of minimally invasive electrodes. The paper 'Speech decoding from a small set of spatially segregated minimally invasive intracranial EEG electrodes with a compact and interpretable neural network' has been published in the Journal of Neural Engineering. The research was financed by a grant from the Russian Government as part of the 'Science and Universities' National Project.

Corpus Callosum Found to Switch Off Right Hemisphere During Speech

A study by the HSE Centre for Language and Brain has confirmed the role of the corpus callosum in language lateralisation, ie the distribution of language processing functions between the brain's hemispheres. The authors came up with an innovative language task for their study subjects and applied advanced neuroimaging methods to the data collected. A paper on their findings has been published in PLoS ONE.  The research was financed by a grant from the Russian government as part of the 'Science and Universities' National Project.

Ketamine Found to Increase Brain Noise

An international team of researchers including Sofya Kulikova, Senior Research Fellow at the HSE University-Perm, found that ketamine, being an NMDA receptor inhibitor, increases the brain's background noise, causing higher entropy of incoming sensory signals and disrupting their transmission between the thalamus and the cortex. This finding may contribute to a better understanding of the causes of psychosis in schizophrenia. An article with the study’s findings has been published in the European Journal of Neuroscience.

Speech Register Switching Causes Brain to Struggle with Comprehension

According to researchers at the HSE Centre for Language and Brain, processing a word which is markedly different in style from the rest of the sentence uses the same brain mechanisms as making sense of a semantically incongruent word. These mechanisms reflect the brain’s efforts to process an unexpected term. The study findings have been published in the Journal of Neurolinguistics. The research was financed by a grant from the Russian Government as part of the 'Science and Universities' National Project.

Only Left Hemisphere Involved in Action Naming

An international team including researchers from the HSE Centre for Language and Brain and the HSE Institute for Cognitive Neuroscience have demonstrated the critical role of the left, but not the right, inferior frontal gyrus in action naming. The study findings are published in Brain Structure and Function.

Machine Learning Predicts Epileptogenic Activity from High-Frequency Oscillation Rates

In an innovative study, researchers from HSE University, RAN Institute of Linguistics, and the National Medical and Surgical Centre named after N.I. Pirogov measured and analysed high-frequency oscillations (HFO) in different regions of the brain. An automated detector predicted seizure outcomes based on HFO rates with an accuracy rate of 85%, and by applying machine learning, made it possible to distinguish between epileptogenic and non-epileptogenic HFO. The study’s findings are published in Frontiers in Human Neurosciences.

HSE Researchers Caused People to Behave Less Rationally by Suppressing Activity in Specific Parts of the Brain

Researchers at the HSE Institute for Cognitive Neuroscience have shown experimentally that magnetic stimulation of the prefrontal cortex of the brain causes test subjects to act less rationally, changing how they assess possible outcomes at the moment they make risky decisions. The scientists believe that the discovery will provide a better understanding of the mechanisms that give rise to gaming addiction. The results of the study were published in the journal Scientific Reports.

Brain Found to Simultaneously Process Linguistic and Extralinguistic Information

An international team of scientists from the UK, Spain, Denmark and Russia (including researchers from the HSE Institute for Cognitive Neuroscience) conducted an experiment demonstrating that people automatically integrate extralinguistic information into grammatical processing during verbal communication. The study findings were published in the Scientific Reports Journal.

Early-Career HSE Researchers to Attend Neuroscience School

Two of the winners, Konstantin Sorokin, doctoral student and visiting lecturer of the HSE Faculty of Computer Science and research assistant at the HSE International Laboratory of Algebraic Topology and its Applications, and Daria Kleeva, doctoral student of the HSE Faculty of Social Sciences and research assistant at the HSE Institute of Cognitive Neuroscience Centre for Bioelectric Interfaces, spoke to the HSE News Service about why attending the School matters so much for them.

How Bilingual Brains Work: Cross-language Interplay and an Integrated Lexicon

An international team of researchers led by scientists from the HSE University have examined the interplay of languages in the brains of bilinguals. Using EEG data of Russian-English bilinguals, the authors were the first to demonstrate nearly instant and automatic detection of semantic similarity between words belonging to their two languages, suggesting the existence of an integrated bilingual lexicon in which words are activated in parallel in both languages. The study findings are published in Cortex.