PC AND POCKET PC BASED BRAIN COMPUTER INTERFACE ARCHITECTURES C. Guger, G. Edlinger, G. Krausz, F. Laundl, I. Niedermayer g.tec – medical engineering GmbH and Guger Technologies OEG Herbersteinstrasse 60, 8020 Graz Austria E-mail:
[email protected]
ABSTRACT EEG-based brain computer interface (BCI) systems measure brain activity in order to control a device just by thoughts. There are different demands depending on the application area. A PC based system allows the flexible design of feature extraction, classification methods and experimental paradigms. The key advantage of a Pocket PC based approach is its very small dimension and fully battery supply. Hence a truly mobile BCI system e.g. mounted on a wheelchair can be realized.
accuracy enhances to a certain degree, meaning the BCI system and the subject have adapted to each other for a better general system performance [1, 2].
brain computer interface (BCI), EEG, Pocket PC, rapid prototyping, information transfer rate
For this described scenario it is necessary to have a very flexible and easy extendable system architecture. It must be possible to use multiple EEG electrodes, to use and compare different feature extraction and classification methods and to develop different applications [1,2,4]. However, for the general usage outside the research lab new key features must additionally be realized: the BCI system must be as small as possible and very easy to use. Therefore, both a flexible research system and an embedded Pocket PC system are discussed.
1. Introduction
2. Systems
EEG based brain computer interface (BCI) systems can be used for people with disabilities to improve their quality of life. Applications of BCI systems comprise the restoration of movements, communication and environmental control [1]. General used parameters to quantify the performance of BCI systems are the accuracy and speed. Furthermore, a BCI approach should ensure that the user learn to control the system within a few training sessions. The level of control should be stable after initial learning and even improving in time [1, 2, 3]. BCI systems must also be able to operate without expert oversight. Family members must be able to help in operation of the BCI system on a daily basis. Therefore, the systems must be robust and easy to use. System appearance and how the users look like while using the device are also important issues when realizing the BCI system.
A Laboratory System
KEY WORDS
BCI systems have been successfully realized based on different EEG phenomena: (i) oscillatory EEG components in the mu and beta range, (ii) slow cortical potentials and (iii) evoked potentials. Depending on the BCI concept and control strategy different electrode montages are used for measuring EEG. Thereafter, feature extraction and classification is performed to get a reliable control signal. After some training sessions the BCI
Figure 1: PC/notebook based BCI system
As shown in Figure 1 the subject is connected via EEG electrodes to a biosignal amplifier. A data acquisition board (DAQ board) performs the analog to digital conversion with a user selectable sampling rate. For a PC system normally PCI boards and for notebook system PCMCIA boards are used. The advantage of extra DAQ boards is that other external sensors beside the EEG amplifier can be sampled together with the biosignal data. This is useful to acquire also trigger signals of external devices. On the other hand two DAQ boards are necessary to make the measurements with a notebook and/or with a PC. In this case a biosignal amplifier with an integrated analog to digital conversion is preferable. If the device sends the data over the USB bus to the notebook or PC the same device can be used. In order to control all hardware parameters, it is important to have a powerful software package that also includes the driver for the DAQ-boards. It is also important to choose a programming language that enables an easy setup or adaptation of the programs for the experimental paradigm, data acquisition and analysis. Such a rapid prototyping environment can be realized with MATLAB (MathWorks, Inc., Natick, USA), in combination with the signal flow oriented Simulink Toolbox. Simulink is used for the realtime calculation of different parameters, which describe the current state of the EEG (g.RTanalyze). The selection of the parameter estimation algorithm is mainly dependent on the application. A very robust method is the bandpower calculation in specific frequency ranges. Normally two bands are considered: (i) the alpha band between 8-12 Hz and (ii) the beta band from 16-24 Hz. Adaptive autoregressive methods on the other hand do not need a specific frequency band selection, but are considered less robust. After the parameter estimation a classification method is needed to translate the parameters into specific commands. Common methods are linear discriminant analysis, neural networks or Hidden Markov models. Beside the real-time parameter extraction and classification MATLAB handles the data acquisition, timing and presentation of the experimental paradigm. Thus, the system can be programmed graphically and it is also running in real-time under Windows [2]. Digital and analog outputs allow controlling external devices such as a hand orthosis or a stimulation unit to present different paradigms to the subject and enhance the BCI performance with feedback of the classification result. A personal area network is used to remotely control the BCI system for operation control, algorithm updates as well as BCI data transfer [2]. The rapid prototyping environment described above is well suited for experimental purposes in a laboratory. Such a system configuration can be used for the realization of a language supporting system where the patient can select letters or words on the display of the
notebook. But for assistive applications like a TV channel selection or a wheelchair mounted language supporting program, where the patient can also select letters or words, an embedded system including the processor board and DAQ board without mechanical disks and extra display is more suitable. Size, robustness, ease, and convenience of use are major considerations for assistive communication devices. The hardware must be fully portable, supplied by a battery and cheap [3].
Figure 2: Pocket PC BCI system components. B Mobile System For the embedded BCI a standard IPAQ Pocket PC from HP is used as portable host and is connected via a serial cable to an embedded target computer system g.MOBIlab (see Figure 2 and 3). The serial interface has a data transfer rate of 115 kBaud. The embedded system consists of a µC operating at 12 MHz to optimize the power consumption. A 16 Bit analog to digital converter (ADC) samples 8 analog channels with 256 Hz each. The module is equipped with 4 EEG channels, 2 ECG channels and 2 analog inputs for external sensors. Two digital inputs and 2 digital outputs allow controlling external devices. Two AA batteries power the embedded system. The Pocket PC operating system is Pocket PC 2003 and the BCI system was programmed in Embedded Visual C++. The integrated Wireless LAN (WLAN) module of the Pocket PC can be used for wireless data transmission. Data are stored on the internal 64 MByte storage or streamed to a Compact Flash card (512 MByte) for later analysis. Subject Training For BCI training two different paradigms are implemented. In order to acquire EEG data the first
experiment is made without feedback. Therefore, an arrow pointing to the left or right side of the computer monitor is shown. Depending on the direction of the arrow the subject has to imagine a specific kind of movement. If the arrow is pointing to the left hand side the subject should imagine a left hand movement, if the arrow is pointing to the right side the subject should imagine a right hand movement. This is repeated 160 times to acquire the thoughts of 80 right and 80 left hand movements. Then from this data specific parameters are estimated and classified and this gives a subject specific classifier. Then the next experiment can be performed with feedback. The classifier weights the parameters calculated from the EEG data in such a way that the thoughts are translated into a right or left cursor movement in real-time.
Both systems have standard digital I/Os for communication with the external world but can also use a network connection. The Pocket PC is equipped with a Wireless LAN or Bluetooth interface for wireless operation.
4. Acknowledgements This project is funded by the European Union project PRESENCIA, IST-2001-37927.
References: [1] G. Pfurtscheller, C. Guger, G. Müller, G. Krausz, & C. Neuper, Brain oscillations control hand orthosis in a tetraplegic, Neuroscience Letters, 292, 2000, 211-214. [2] C. Guger, Real-time data processing under Windows for an EEG-based brain-computer interface (Dissertation, University of Technology, 1999). [3] T.M. Vaughan, J.R. Wolpaw, & E. Donchin, EEGbased communication: prospects and problems, IEEE Transactions Rehabilitation Engineering, 4(4), 1996, 425430. [4] C. Guger, et al, How many people are able to operate an EEG-based brain-computer interface (BCI) ?, IEEE Transactions Rehabilitation Engineering, 11(2), 2003, 145-147.
Figure 3: Pocket PC based BCI system
3. Discussion The PC based BCI system allows a very flexible design of BCI experiments concerning electrode configuration, utilized algorithms and applications. The rapid prototyping environment speeds up the development cycle significantly. On the other hand the embedded BCI with its compact dimension allows the usage of the BCI outside the research lab for patient training and (as Pocket PC CPUs are getting more and more powerful) also for many sophisticated applications. The system can be mounted easily on a wheelchair or beside the bed and is fully battery powered. A big advantage is that the Pocket PC BCI operates immediately after switching it on without booting of the operating system. The PC based BCI system was used for example in a Virtual Environment to walk around a virtual street [5]. A limitation was the size of the BCI system which required that the subject is sitting throughout the experiment in a chair. The Pocket PC BCI system would allow the subject to move more flexible through the virtual world.
[5] R. Leeb & G. Pfurtscheller, Walking through a Virtual City by Thought. Proc. 26th IEEE Engineering in Medicine and Biology Society (EMBS), San Francisco, CA, 2004, 4503-4506.
