Graz-BCI Team looking for New Members

The BCI Research Group from Graz University are looking for motivated students to work in their project. 

We are a group of students that it has set itself the goal, the team with paraplegic persons ("pilot") to develop a system which makes it possible to control with the power of thought, a (s) Computer (play). Our aim is to participate with our pilots in an international competition in 2016 in Zurich and to compete with more than 100 teams from around the world.

To sign up and get more information press here. 

Graz-BCI Team looking for New Members

The BCI Research Group from Graz University are looking for motivated students to work in their project. 

We are a group of students that it has set itself the goal, the team with paraplegic persons ("pilot") to develop a system which makes it possible to control with the power of thought, a (s) Computer (play). Our aim is to participate with our pilots in an international competition in 2016 in Zurich and to compete with more than 100 teams from around the world.

To sign up and get more information press here. 

Software for Visual Psychophysics

Prof. Hans Strasburger from Universität München brings together to this page the various existing tools to work with Psychophysics, divided by 15 topics:

• Libraries, Public Domain and Commercial Applications for Psychophysics;
• Psychophysical data analysis, SDT;
• Ophthalmology/Optometry/Neuroophthalmology;
• Psychological Experimenting Systems;
• Cognitive Neuroscience;
• (...)

How well do we see? How can visual function be described and which mechanisms can be thought to underly? Visual psychophysics tries to give answers to these general questions, and research in this area needs specialised software. This is an overview on what is available.

PsychToolbox, for Matlab or Octave, is one of tools example commonly used in SSVEP.

Singular Spectrum Analysis of Biomedical Signals

This book created by Saeid Sanei and Hossein Hassani covers new concepts of mathematical and signal processing providing new signal processing results in the form of signals, graphs, images, and tables.

"Recent advancements in signal processing and computerised methods are expected to underpin the future progress of biomedical research and technology, particularly in measuring and assessing signals and images from the human body. This book focuses on singular spectrum analysis (SSA), an effective approach for single channel signal analysis (...)"

It will be available at November, 2015 with a price of $110.

A Subject-independent Pattern-based BCI

A provisional PDF file corresponding to the article "A Subject-independent Pattern-based BCI", created by Andreas M. Ray,  Ranganatha Sitaram,  Mohit Rana,  Emanuele Pasqualotto,  Korhan Buyukturkoglu,  Cuntai Guan,  Kai Keng Ang, Cristián Tejos,  Francisco J. Zamorano, Francisco Aboitiz, Niels Birbaumer and Sergio Ruiz was published in Frontiers in Behavioral NeuroScience . 

"A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Traditional approaches to BCIs require the user to train for weeks or even months to learn to control the BCI. In contrast, BCIs based on machine learning only require a calibration session of less than an hour before the system can be used, since the machine adapts to the user's existing brain signals. However, this calibration session has to be repeated before each use of the BCI due to inter-session variability, which makes using a BCI still a time-consuming and an error-prone enterprise. In this work, we present a second-order baselining procedure that reduces these variations, and enables the creation of a BCI that can be applied to new subjects without such a calibration session. The method was validated with a motor-imagery classification task performed by 109 subjects. Results showed that our subject-independent BCI without calibration performs as well as the popular common spatial patterns (CSP)-based BCI that does use a calibration session."

For more information / read the (provisional) full text press here. 

BCI Research: A State-of-the-Art Summary 4

This new book "BCI Research: A State-of-the-Art Summary 4" edited by Christoph Guger, Gernot Muller-Putz and Bredan Allison, with a price of $55, is available for pre-order in January 2006 relating the most promising BCI projects.

BCI research is developing quickly, with many new ideas, research groups, and improved technologies. BCIs enable people to communicate just by thinking – without any movement at all. Several different groups have helped severely disabled users communicate with BCIs, and BCI technology is also being extended to facilitate recovery from stroke, epilepsy, and other conditions. (...) This book summarizes the 2014 BCI Award, including the ten projects that were nominated, the winner, and analyses and discussions of the submitted projects and how they reflect general trends in BCI development. 

The National Center for Adaptative Neurotechnologies (NCAN) located on New Scotland Avenue in Albany, New York, are building an infrastructure that supports real-time interactions with the central nervous system (CNS) helping to restore a skill such as locomotion.

"Progress in medical science now enables people with severe paralysis to live for many years. Many of these individuals have great difficulty in communicating. Some may even be entirely "locked in" to their bodies: their minds are functioning, but they cannot move a single muscle to communicate in any way. The capacity for simple communication could greatly improve the quality of their lives. The Center for Adaptive Neurotechnologies has addressed this problem by developing a new generation of brain-based communication devices (BCI) that can provide communication and control functions to people who have lost muscle control. By recording brain waves from the scalp and then decoding them, this system allows people to move a computer cursor up/down and left/right, to spell words, and to perform other simple control functions."

The research areas are divided by Guiding Beneficial Plasticity, Brain-Computer Interface (BCI) Based Rehabilitation and Characterizing and Interacting with Cortical Processes. During 2015 some papers have been published in peer-reviewed neuroscientic, neuroengineering and clinical journals related to this subjects:

• Cortical alpha activity predicts the confidence in an impending action;
• Brain-to-text: Decoding spoken sentences from phone representations (...);
• A general framework for dynamic cortical function:ons (FBO) hypothesis;
• The Plurality of Human Brain-Computer Interfacing;
• Electrocorticographic activity over sensorimotor cortex and motor function (...);
• Restoring walking after spinal cord injury (...);
• Word-level language for P300 spellers based on discriminative graphical models;
• NeuralAct: A Tool to Visualize Electrocortical (ECoG) Activity on a 3D Model (...);
• Targeted neuroplasticity for rehabilitation;
• Toward independent home use of BCIs: a decision algorithm (...);
• Electrocorticographic representations of segmental features in continuous speech.

For more informations about NCAN press here.

Identification of Motor Imagery Movements from EEG Signals Using Dual Tree Complex Wavelet Transform

Conference: 4th ICACCI ’15, Kerala, India
DOI: 10.1109/ICACCI.2015.7275623

Abstract: (...) Dual Tree Complex Wavelet Trans-form (DTCWT) domain based feature extraction method has been proposed to identify left and right hand motor imagery movements from EEG signals. After first performing auto-correlation of the EEG signals to enhance the weak brain signals and reduce noise, the EEG signals are decomposed into several bands of real and imaginary coefficients using DTCWT. The energy of the coefficients from relevant bands have been extracted as features and from the one way ANOVA analysis, scatter plots, box plots and histograms, this features are shown to be promising to distinguish various kinds of EEG signals. (...) K-nearest neighbor (KNN) classifiers have been shown to provide a good mean accuracy of 91.07% which is better than several existing techniques.

To read the full article click here.