MULTI-ADAPTIVE BCI · On-line adaptive classification for multi-class EEG-based brain-computer interfaces
6РП — Действия „Мария Кюри“
- Период
- 2006-11-01 → 2008-10-31
- Финансиране от ЕС
- 142 918 €
- Участници
- 1
- Схема
- EIF
Линиите свързват координатора с партньорите.
Накратко на български
Интерфейсите между мозъка и компютъра превръщат мозъчните сигнали (EEG) в команди за управление на устройства. Адаптивните системи помагат на хора без опит да контролират тези технологии, като се напасват към променливата им мозъчна активност.
Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.
Резултати накратко
Final Activity Report Summary - MULTI-ADAPTIVE BCI (On-line adaptive classification for multiclass EEG-based Brain-Computer Interfaces)
A Brain Computer Interface (BCI) is a system that translates human intentions into a technical control signal bypassing the classical neuromuscular output pathways. In this project electroencephalographic brain signals (EEG) were used. The EEG is known to be non-stationary and therefore, EEG based-BCI systems can benefit from adaptation of its components. Furthermore, acquiring knowledge of the changes in brain signals allows the design of tools invariant to these and make more robust BCI systems. This project has pursued the adaptation of a BCI system with the goal of training inexperienced or illiterate BCI subjects. It has been found that many illiterate subjects cannot produce stable mental patterns for the control of the system, thus, adaptation to the spatial distribution of their brain activity has been decisive for the successful completion of the study. The adaptation to this changing brain activity made necessary the design of new adaptive classifiers and both ingredients jointly have provided high quality feedback that allowed our illiterate subjects take control of the BCI system. Finally, new invariant techniques are developed for the design of a robust system partly invariant partly adaptive whose quality could bring BCI technology to society.
Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз
Цел на проекта
The two main objectives of the proposal are: - The study of man-machine interaction for the design of an appropriate online adaptative BCI - The development of an automated adaptive multiclass BCI using the results of the aforementioned topic for a high in formation transfer rate.They will be achieved:- Designing different automated adaptive BCI systems with different types of adaptation according to the analysis and assessment of the man-machine interaction (long-term changes, such as learning) with the aim to design a BCI which adapts where and when it is required.- Applying different feature extraction methods, which describe the classes of the system, focusing adaptive feature extraction to deal with short-term non-stationarities.- Using different adaptive classifiers to deal with long-term non-stationarities.The increase of classes will increase the dimensionality because more features will be necessary to describe them, but also the information transfer rate. This expertise is important in BCI research and the same techniques can be applied in related research areas (EEG analysis or fMRI analysis). The applicant is expert in online adaptation of statistical classifiers; she has much experience in univariate adaptive autoregressive parameters and band power estimates.The project will extend her knowledge to SVMs, which are also very powerful methods used in BCI research, with the aim of online adapt them. The application of the signal processing methods used in FIRST IDA will diversify her training in the feature extraction part. The knowledge acquired will be of great impact in her future career as well as in the development of BCI in Spain.Acquired training can be applied to analyse fMRI and EEG. Furthermore the machine learning and signal processing techniques that the applicant is trained in have a multitude of applications beyond biomedical data analysis; they will become more and more salient as key technologies for the European industry.
Оригинален текст от CORDIS (на английски).
Участници
- FRAUNHOFER GESELLSCHAFT ZUR FORDERUNG DER ANGEWANDTEN FORSCHUNG E.V.* · MÜNCHENКоординаторГермания
Връзки
Данни: CORDIS, © Европейски съюз