"

EEG based Machine Control

A. Kavitha Rajesh
Assistant professor

Department of Electronics and Communication Engineering

Er. Perumal Manimekalai College of Engineering,Hosur,Tamil Nadu,India
AbstractIn the field of bio-medical, the brain interface is to create and adapt methods of human-computer
interaction. This is BCI. A variety of application domains to compare and validate BCI interaction, including
communication, environmental control, neural prosthetics and creative expression. EEG signals acts as a communication
between men and machines. The BCI-based control system for robots using the EEG has been suggested for mobile
robots and humanoids, and some other machines to control. In this project we do, the control interface to translate
human intentions into appropriate motion commands for robotic systems. The experimental procedures consist of
extraction of EEG signals, optimizing the exact signal, wireless transmission and machine control.
Index TermsBraincomputer interface (BCI), electroencephalograph (EEG), wireless communication, control robots.
I. INTRODUCTION
ONE of the most challenging goals of neural engineering is the development of Brain-Machine Interfaces (BMIs)
[6]. Then a novel interfacing technique used between humans and machines was intensively studied based on neural
responses to stimulation or thought, which is called braincomputer interface (BCI) [1], [2], [3], [4]. There exist
diseases of the nervous system that gradually cause the bodys motor neurons to degenerate, Example: Amyotrophic
Lateral Sclerosis (ALS). Eventually causes total paralysis. The affected individual becomes trapped in his own body,
unable to communicate.
A Brain-Computer Interface (BCI) enables communication under such circumstances. Using data recorded from the
brain, the BCI processes it, interprets the intention of the user, and acts on it. The BCI has a robust and flexible
design that can be expanded in the future to encompass more complex communication schemes. An
electroencephalogram (EEG) [7], [8] is a measure of the brain's voltage fluctuations as detected from brain signals.
It is an approximation of the cumulative electrical activity of neurons. BCI research programs have began and
encouraged new understanding of brain functions.
The advances in mechanics, electronics and computer science technology have allowed the development of machine
control. In this proposal extracted EEG signal can transmit human intentions into machines as a form of appropriate
command. The BCI methods using Electroencephalogy (EEG) have been extensively examined, because they are
applicable to healthy subjects for general purpose. The various types of extraction of signals from brain are invasive
techniques, ECOG (Electrocarticography), Functional MRI, EEG [16]. The best way for extraction of brain signals
are EEG based method. The EEG-based BCI system for robots has been suggested in robotics and neural
engineering fields because some elderly or disabled people can control robots naturally and intuitively by merely
thinking while using this system. After extraction of EEG signals digital version of EEG can be optimized by
suitable optimization algorithm. The algorithm used in this proposal is Fuzzy C Logic[13], [14]. After extraction of
optimized signals, it is given to ARM processor for transmission. ARM processor [17] has a 16 resolution of ADC
and it also has a inbuilt UART for transmitting and receiving data. The signal is transmitted from UART through
wireless for controlling the machine in receiver side. The wireless transmission used in this proposal is ZIGBEE.
The transmitted signal is received and it is given to PIC controller for machine control.
II. ELECTROENCEPHALOGRAPHY
Electroencephalography (EEG) is the recording of electrical activity along the scalp. EEG measures voltage
fluctuations resulting from ionic current flows within the neurons of the brain. In clinical contexts, EEG refers to the
recording of the brain's spontaneous electrical activity over a short period of time, usually 2040 minutes, as
recorded from multiple electrodes placed on the scalp. There are many types of materials used for manufacturing of
electrodes which may be dry electrodes, nickel electrodes, Ag/Ag Cl. For this system electrodes used is Ag/Ag Cl
which may be more effective than any other types of electrodes. Number of leads used for this system is only three
electrodes. The two leads are placed on forehead and another lead which is ground is placed in the right side of the
neck. Diagnostic applications generally focus on the spectral content of EEG, that is, the type of neural oscillations

'

&

"

that can be observed in EEG signals. Despite limited spatial resolution, EEG continues to be a valuable tool for
research and diagnosis, especially when millisecond-range temporal resolution (not possible with CT or MRI) is
required.
III. OVERVIEW OF PREVIOUS METHODS:
payam aghaei pour et al, the number of electrodes used is 32 electrodes. The signals are obtained using a specially
designed electrode cap and equipment, and send through a Bluetooth connection to a PC that processes it in real
time. The signals were then mapped on two control signals and send through wireless connection to a mobile
gaming device. Jos del R. Milln et al, Brain activity recorded noninvasively is sufficient to control a mobile robot
if advanced robotics is used in combination with asynchronous electroencephalogram (EEG) analysis and machine
learning techniques. Until now brain-actuated control has mainly relied on implanted electrodes, since EEG-based
systems have been considered too slow for controlling rapid and complex sequences of movements.
IV. BRAIN COMPUTER INTERFACE:
Brain-Computer Interface (BCI)[4], [5], technology is a new and fast evolving field that seeks direct interaction
between the human neural system and machines, aiming to augment human capabilities by enabling people
(especially disabled) to communicate and control devices by mere thinking or expressing intent. The increasing
success of BCI systems is partially due to a better understanding of the dynamics of brain oscillations that generate
EEG signals. In the brain, networks of neurons form feedback loops responsible for the oscillatory activity recorded
in the EEG.
EEG signals
Signal processsing

Signal acquisi-tion

Wireless transmission

control devic-es

Normally the frequency of such oscillations becomes slower with increased synchronization. Sensorimotor activity
such as motor movements or motor imagery (e.g. imagining hand/feet movement) changes the oscillatory patterns
resulting in amplitude suppression (Event Related Desynchronization - ERD) or amplitude enhancement (Event
Related Synchronization - ERS) on the Rolandic mu rhythm (7-13 Hz) and the central beta rhythms above 13 Hz. A
second reason for the increased interest in BCI is the improved resolution and lower cost of recording equipment.
Current research aims at developing systems that use dry electrodes instead of the cumbersome golden or Ag/AgCl
electrodes, that require gel, glue and skin preparation. This technology, together with making the devices more
mobile, will allow BCI systems to be available for controlling the machine, humanoids, etc for various commands
through our thought.
In the brain computer interface system is the, People speculated that Electro Encephalographic (EEG) activity or
other measures of brain function might provide this new channel. BCI research programs have began and
encouraged new understanding of brain functions. Immediate goal is to provide communication capabilities so that
any subject can control the external world without using brains normal output pathways of peripheral nerves and
muscles. BCIs use EEG activity recorded at the signals. BCI operation depends on effective interaction between
two adaptive controllers. Current BCIs have maximum information transfer rates.
In this BCI has consists of the four types of main components (fig1 shown in their). They are Signal Acquisition,
Signal Processing, wireless transmission and Control Devices.
In this system the signal is extracted from the brain and it requires some amplification for strengthening the signal.
This module works as an interface between the recording device and the computer used for the recording. Then the
informative signal is extracted and it is transmitted and the machine is controlled.

'

&

"

V. EXPERIMENTAL SETUP:
In this an EEG based brain computer interface system is the proposed system has been implemented for making the
people by combining the brain commands to the machine. Hence, the machine can be controlled by the brain
commands (thoughts) which make the system move. The commands used in this proposal are right and left. The
system is designed with an aim of natural and direct navigational control of the machine. Hence, our system
employed thought-dependent control architecture that can perform right and left movements with respect to the
appropriate users intentions. The fig shows the schematic architecture of the proposal. This is the semi DSP system.
Three electrodes are used, in this 2 are placed on the forehead and another one which is ground is placed near the
right side of the neck for the user, the signal is extracted according to the thought through that device. The signals
from the electrodes are nearly a milli volt it is amplified in the first stage. Output of the amplifier selection, the
analog signal is formed. It is the first stage output in this system.

EEG signals

Transmitter

Amplifiers

Signal optimization

ARM processor

Receiver

PIC controller

H- bridge

Machine control

Architecture of this proposal

The output of the amplifier is given to the input of Analog to Digital Converter (ADC) [17]. It is inbuilt in the
ARMLPC2148 processor. LPC2148 is a 64 pin IC with 8 to 40 kB of on-chip static RAM and 32 to 512 kB of onchip flash program memory. It has 128 bit wide interface/accelerator enables high speed 60 MHz operation. One or
two (LPC2148) 10-bit A/D converters provide a total of 6/14 analog inputs, with conversion times as low as 2.44 s
per channel. Multiple serial interfaces including two UARTs (16C550), two Fast I2C-bus (400 k bit/s), SPI and SSP
with buffering and variable data length capabilities. The LPC2148 has the operating voltage of 3.0 V to 3.6 V. So
the milli volt is amplified to 3v and is digitize in the ARM processor. Digital EEG signal is optimized by suitable
optimization algorithm. In this system Fuzzy C logic algorithm is used. The output is given to MATLAB for
extracting the informative signal using Fuzzy C method. Then the ARM processor program is modified based on the
optimized value for right and left commands. The signal is again given to the ARM processor for further process
and then it is transmitted through ZIGBEE [15].
Types of wireless transmissions are IR, Bluetooth, WI-FI, ZIGBEE. IR light is electromagnetic radiation
with longer wave lengths. Its operating speed is 11500 bits/sec and now it is extended to 4 mbps. Bluetooth is to
exchanging a data over a short distance. It is a replaced model of RS232. Data transfer speed is 721 kbps. WI-FI, the
transmission area depends on the size of the antenna. Data transfer speed is 11 mbps.
ZIGBEE is IEEE 802 standards for personal area network (PAN). The data transfer rate is 20 to 250 k
bits/sec, and it is low cost. Then the signal is received and it is given to the PIC16F877A controller [18].
PIC16F877A has only 35 single-word instructions, and operating speed is DC 20 MHz clock input, DC 200 ns
instruction cycle to process the signal. It has Universal Synchronous Asynchronous Receiver Transmitter
(USART/SCI) with 9-bit address detection.
The output from the controller is given to machine or robot. The motor in the machine requires 12v to run
but the output from the controller is 3 to 5V. So it requires some methods to connect the controller and the machine.
There are three methods opto- isolation, H-bridge, transistor logic. In opto isolation the output from the controller is
given the led according to the light intensity the motor is controlled. Transistor logic works as a normal amplifier
using transistor. H-Bridge is the concept of using relays. Through relays the motor is controlled to move left and
right directions.

'

&

"

VI. RESULT AND CONCLUSION:

In this proposal three electrodes are used instead of 32 electrodes. The subjects controlled the vehicle by using their
thoughts only up to 60% accuracy over controlling the target. By increasing the subjects more than 100 detection of
optimized signal will be more accurate. Use of DSP rather than semi-DSP will lead the proposed system for disabled
subjects. By use of DSP will increase the accuracy up to 80%.
REFERENCES

'

&

[13]
[14]
[15]
[16]
[17]
[18]

[12]

[11]

[10]

[9]

[8]

[7]

[5]
[6]

[4]

[3]

[2]

Payam Aghaei Pour, Tauseef Gulrez, Omar AlZoubi, Gaetano Gargiulo and Rafael A. Calvo Brain-Computer Interface: Next Generation
Thought ControlledDistributed Video Game Development Platform
J. R. Millan, F. Renkens, J. Mourino, and W. Gerstner, Noninvasivebrain-actuated control of a mobile robot by human eeg. IEEE
Transactionson Biomedical Engineering, pp. 10261033, 2004.
G. Pfurtscheller and et. al., 15 years of bci research at graz university of technology: current projects, IEEE Trans. on Neural Systems
and Rehabilitation Engineering, pp. 205210, 2006.
A. Kostov and M. Polak, Parallel man-machine training in development of eeg-based cursorcontrol, IEEE Trans. on Neural Systems and
Rehabilitation Engineering, pp.
203205, 2000.
J. R. Wolpaw and et. al., Brain-computer interfaces for communication and control, Clinical Neurophysiology, pp. 767791, 2002.
M. A. Lebedev, J. M. Carmena, J. E. ODoherty, M. Zacksenhouse, C. S. Henriquez, J. C. Principe, and M. A. Nicolelis, Cortical
ensemble adaptation to represent velocity of an artificial actuator controlled by a brain machine interface, Neuroscience, vol. 25(19), pp.
46814693, 2005.
T.-P. Jung, C. Humphries, T.-W. Lee, S. Makeig, M. McKeown, V. Iragui, and T. Sejnowski, Removing electroencephalographic artifacts:
comparison between icaand pca, in IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing VIII,Cambridge,
U.K, 1998.
C. W. Anderson, J. N. Knight, and et. al., Geometric subspace methods and time-delay embedding for eeg artifact removal and
classification, IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 14(2), pp. 142146, 2006.
D. J. McFarland, C. W. Anderson, and et. al., Bci meeting 2005 - workshop on bci signal processing: Feature extraction and translation,
IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 14(2), pp. 135138, 2006.
O. AlZoubi, I. Koprinska, and R. A. Calvo, Classification of braincomputer interface data, in AusDm08, The Australasian Data Mining
Conference: AusDM 2008 Stamford Grand, Glenelg, Adelaide, 27-28 November 2008.
A. Schloegl, K. Lugger, and G. Pfurtscheller, Using adaptive autoregressive parameters for a brain-computer-interface experiment, in
19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, USA, 1997.
M. Murugappan, M.Rizon, R.Nagarajan, S. Yaacob, D. Hazry and I. Zunaidi, time- frequency analysis of EEG signals for Human Emotion
Detection
James C. Bezdek, Robert Ehrlich, William Full FCM: The Fuzzy C-means clustering algorithm
Naoki Nitanda, Miki Haseyama, and Hideo Kitajima An Audio signal segmentation and classification using Fuzzy C-means clustering
zigbee communication en.wikipedia.org/wiki/ZigBee
G. Schalk, J. Mellinger, A practical guide to brain-computer interfacing with BCI2000.
PHILIPS LPC2148_UserManual
MICROCHIP pic16f877a datasheet

[1]