August 2015 - Comp-neuro - lists.cnsorg.org

The KARA ONE Database: Phonological Categories in imagined and articulated speech
by frank 03 Aug '15

03 Aug '15

We are making 24 GB of a new dataset, called Kara One, freely available. This database combines 3 modalities (EEG, face tracking, and audio) during imagined and articulated speech using phonologically-relevant phonemic and single-word prompts. It is the result of a collaboration between the Toronto Rehabilitation Institute (in the University Health Network) and the Department of Computer Science at the University of Toronto. In the associated paper (abstract below), we show how to accurately classify imagined phonological categories solely from EEG data. Specifically, we obtain up to 90% accuracy in classifying imagined consonants from imagined vowels and up to 95% accuracy in classifying stimulus from active imagination states using advanced deep-belief networks. Data from 14 participants are available here: http://www.cs.toronto.edu/~complingweb/data/karaOne/karaOne.html [1]. If you have any questions, please contact Frank Rudzicz at frank(a)cs.toronto.edu. Best regards, Frank PAPER Shunan Zhao and Frank Rudzicz (2015) Classifying phonological categories in imagined and articulated speech. _In Proceedings of ICASSP 2015_, Brisbane Australia ABSTRACT This paper presents a new dataset combining 3 modalities (EEG, facial, and audio) during imagined and vocalized phonemic and single-word prompts. We pre-process the EEG data, compute features for all 3 modalities, and perform binary classiﬁcation of phonological categories using a combination of these modalities. For example, a deep-belief network obtains accuracies over 90% on identifying consonants, which is signiﬁcantly more accurate than two baseline support vector machines. We also classify between the different states (resting, stimuli, active thinking) of the recording, achieving accuracies of 95%. These data may be used to learn multimodal relationships, and to develop silent-speech and brain-computer interfaces. Links: ------ [1] http://www.cs.toronto.edu/~complingweb/data/karaOne/karaOne.html

1 0

PhD Studentships – Centre for Robotics and Neural Systems (CRNS), Plymouth University, UK
by Roman Borisyuk 03 Aug '15

03 Aug '15

PhD Studentships – Centre for Robotics and Neural Systems (CRNS), Plymouth University, UK Following on the exceptional performance of Plymouth University in the UK Research Excellence Framework 2014, the university is now advertising the availability of 50 PhD studentships for study commencing in 2015/16. Of these studentships, at least two will be allocated to research projects and supervisors of the Centre for Robotics and Neural Systems (CRNS), within the Faculty of Science and Engineering. The first studentship can cover any topic within the CRNS research areas: * Cognitive and Humanoid Robotics * Computational Neuroscience * Artificial Intelligence The second studentship will focus on Autonomous Systems, possibly with relevance to unmanned marine systems, and will be in collaboration with the School of Marine Science and Engineering: For more details on the CRNS research projects, interests and supervisors, see: https://www1.plymouth.ac.uk/research/crns/Pages/default.aspx For general information on the studentships and application procedure, see: https://www.plymouth.ac.uk/student-life/your-studies/the-graduate-school/fu… We recommend that in the application form and cover letter you specify a research topic and preferred supervisor. You are also encouraged to contact the individual supervisors before applying, for informal discussion. The application deadline is 15 September 2015 Roman Borisyuk, DSc, PhD Professor of Computational Neuroscience School of Computing and Mathematics University of Plymouth A224, Portland Sq Plymouth, PL4 8AA UK Phone: +44 (0) 1752 584949 E-mail: RBorisyuk(a)plymouth.ac.uk<mailto:RBorisyuk@plymouth.ac.uk> ________________________________ [http://www.plymouth.ac.uk/images/email_footer.gif]<http://www.plymouth.ac.uk/worldclass> This email and any files with it are confidential and intended solely for the use of the recipient to whom it is addressed. If you are not the intended recipient then copying, distribution or other use of the information contained is strictly prohibited and you should not rely on it. If you have received this email in error please let the sender know immediately and delete it from your system(s). Internet emails are not necessarily secure. While we take every care, Plymouth University accepts no responsibility for viruses and it is your responsibility to scan emails and their attachments. Plymouth University does not accept responsibility for any changes made after it was sent. Nothing in this email or its attachments constitutes an order for goods or services unless accompanied by an official order form.

1 0

Call for participation NEUROMOD'2015, Neurotechnix'2015, 16-17 November, Lisbon
by Jaime Ibánez Pereda 02 Aug '15

02 Aug '15

(Please accept our apologies if you receive multiple copies of this call) ******************************************************************************************* Dear colleagues, We are pleased to invite you to participate in the upcoming “Symposium on Neuromodulation-based Approaches for Neural Rehabilitation - NEUROMOD 2015”, to be held on November 16-17, at the Neurotechnix 2015 conference, in Lisbon. NEUROMOD website: http://www.neurotechnix.org/neuromod.aspx IMPORTANT DATES: Paper Submission: September 10, 2015 Authors Notification: September 25, 2015 Camera Ready and Registration: October 6, 2015 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - DESCRIPTION Neuromodulation is a rapidly-growing field, encompassing the application of targeted electrical/chemical/biological stimuli to the nervous system in order to improve function and quality of life. At present, an increasing number of implantable and non-invasive techniques are being proposed and made available to the clinicians, to stimulate CNS plasticity and foster recovery from motor, neurological and psychiatric disorders. Advancing in the field of neuromodulation represents challenges to build accurate neurophysiological models, understanding mechanisms of neuromodulation at cellular and systems levels, defining optimal engineering methodologies, and developing clinical application to treat patients. This session provides an opportunity for researchers/engineers/clinicians to present and discuss novel neurorehabilitation paradigms based on neuromodulation targeted at the spinal and/or supraspinal level. Top quality papers at NEUROMOD will be eligible for inclusion in the post-congress IOP journal of best papers or even for the best-paper award to be presented at the main congress, NEUROTECHNIX. This special session/symposium is part of the International Congress on Neurotechnology, Electronics and Informatics (NEUROTECHNIX - http://www.neurotechnix.org/) which is sponsored by the Institute for Systems and Technologies of Information and Control and Communication (INSTICC) and held in Cooperation with the Associacao Portuguesa de EEG e Neurofisiologia ClÌnica (APEEGNC), Neurotech Network, International Neural Network Society (INNS), Nansen Neuroscience Network, World Federation for NeuroRehabilitation (WFNR), Sociedade Portuguesa de Neurologia (SPN), International Neuromodulation Society (INS), International Federation of Clinical Neurophysiology (IFCN) and International Brain Research Organization (IBRO). All accepted Extended Abstracts will be published in the Book of Abstracts of the congress and on CD-ROM support, without ISBN. All accepted Complete Papers (full and short) will be published in the Congress Proceedings, under an ISBN reference, on paper and on CD-ROM support. All papers presented at the congress venue will also be available at the SCITEPRESS Digital Library. SCITEPRESS is a member of CrossRef and every paper is given a DOI (Digital Object Identifier). The Congress Proceedings will be submitted to appropriate indexes for indexation. A short list of presented papers will be selected so that revised and extended versions of these papers may be published by IOP Publishing on Journal of Neural Engineering. With this workshop we would like to bring together different researchers already active in the development of new neuromodulation techniques and protocols, with the goal of identifying the optimal developments and assessment strategies to be targeted in future studies and applications. Please check further details at the Special Session website available at: http://www.neurotechnix.org/neuromod.aspx Should you have any question or suggestions please don't hesitate to contact us. CO-CHAIRS: Stefano Piazza, Neural Rehabilitation Group, CSIC, Spain Jaime Ibanez, Neural Rehabilitation Group, CSIC, Spain Julian Taylor, HNP Toledo, Spain and Stoke Mandeville Spinal Research, United Kingdom

1 0