EMG Decoder

[kalarickal]

EMG Decoder
A Project Report
by
Sarath S.Nair
M105114
Department of Computer Science & Engineering
College of Engineering Trivandrum Kerala - 695016
2010-11

[attachment=8622]

Abstract
Many physically disabled individuals are deterred from using computers due to their inability
to utilize a hand-controlled mouse. However, if clicking or dragging of an icon can be achieved,
these individuals would be able to take on the functions of a mouse without the use of hands.
We propose to design and build an electromyogram (EMG) biopotential decoder in order to
decode a bio signal due to hand muscle movements and to use this signal to generate the mouse
click as well as drag actions. This design can also be used as a model for future advancements in
human-computer interactions. The EMG biopotential ampli er should be capable of detecting
frequencies between dc-10 Hz, the range at which most ocular movements operate. The EMG
signal is in the microvolt range (100-4500 V). Therefore, when the DC o set is removed, it will
be challenging to obtain a strong, usable signal given the minute nature of the recorded signal.
Our choice of an EMG over other possible methods was selected based on the ease of usage and
the low cost of production.

1 Introduction
With the ever increasing role of computerized machines in society, Human Computer Interac-
tion (HCI) system has become an increasingly important part of our daily lives. HCI determines
the e ective utilization of the available information
ow of the computing, communication, and
display technologies. In recent years, there has been a tremendous interest in introducing intu-
itive interfaces that can recognize the user's body movements and translate them into machine
commands. For the neural linkage with computers, various biomedical signals (bio signals) can
be used, which can be acquired from a specialized tissue, organ, or cell system like the nervous
system. Examples include Electro-Encephalogram (EEG), Electrooculogram (EOG), and Elec-
tromyogram (EMG).Such approaches are extremely valuable to physically disabled persons.
Many attempts have been made to use EMG signal from gesture for developing HCI. EMG
signal processing and controller work is currently proceeding in various directions including the
development of continuous EMG signal classi cation for graphical controller, that enables the
physically disabled to use word processing programs and other personal computer software,
internet. It also enable manipulation of robotic devices, prosthesis limb, I/O for virtual reality
games, physical exercise equipments etc. The EMG controller can be programmed to perform
gesture recognition based on signal analysis of groups of muscles action potential.
Many physically disabled individuals are deterred from using computers due to their inability
to utilize a hand-controlled mouse. The EMG signals generated in the human body can be used
to implement the mouse functions like click, drag, scroll etc. In fact, an input device developed
using EMGs is a natural means of HCI because the electrical activity induced by the human's
arm muscle movements can be interpreted and transformed into computer's control commands.
Furthermore, EMGs can be easily acquired on the surface of human skin through conveniently
attachable electrodes.EMG signals can be measured more conveniently and safely than other
neural signals. Furthermore, this non invasive monitoring method produces a good signal to
noise ratio. Hence, an EMG-based HCI is the most practical with current technology.
EMG measures electrical currents that are generated in a muscle during its contraction and
represent neuromuscular activities. EMG signals can be used for a variety of applications
including clinical applications, HCI and interactive computer gaming. Moreover, EMG can be
used to sense isometric muscular activity which does not translate into movement. This makes
it possible to classify subtle motionless gestures and to control interfaces without being noticed
and without disrupting the surrounding environment. On the other hand, one of the main
di culties in analyzing the EMG signal is due to its noisy characteristics. Compared to other
bio signals, EMG contains complicated types of noise that are caused by, for example, inherent
equipment noise, electromagnetic radiation, motion artifacts, and the interaction of di erent
tissues. Hence, pre-processing is needed to lter out the unwanted noises in EMG.

2 Methodology
2.1 Gesture selection
For controlling a mouse, four di erent gestures are required. These gestures should be equally
easy to perform and form patterns in the EMG signal which are as discriminative as possible.
Before the start and after the nish of each gesture, the hand should be situated in a posture
called the home position, in which hardly any signal amplitude occurs. The rst gesture, hold
(gesture 1), is a short and very light pressing of the st. Gesture Left (gesture 2) is performed
by a quick left motion of the wrist towards the inside of the forearm, followed by a straight
return into the home position. The motion directed towards the outside of the arm is called
gesture Right (gesture 3) and is supposed to be slow and smooth. A st should be formed in
this case. The fourth gesture, Circling (gesture 4), is a smooth circling movement of the wrist
starting with a swinging movement into the direction of the inside arm. Depending on the way
the executive user performs the motion, either a single or two consecutive circle movements
are possible. For the home position, a loose, relaxed st has been proven to be the best suited
position.
The choice of the performing hand is not an issue since the experiments showed that both
hands generate extremely similar EMG waveforms, except for unremarkable di erences in over-
all amplitude. As most users opt for the right hand, the names and descriptions of the gestures
refer to the right hand and have to be mirror-inverted for a left handed usage.

3 System structure
In this section the single processing steps of the system, from the recording of a gesture to
mouse click control, are described. An overview is given in Figure 2.
Figure 2.General procedure of a biosignal based recognition system.
The EMG signal of the performing arm muscles is detected by electrodes connected to a
sensor. In order to qualify the incoming raw signal for further processing the signal is prepro-
cessed rst. Next, the incoming patterns, which represent a gesture movement in the signal, are
matched. To be able to distinguish patterns, the signi cant features of each pattern are rst
extracted. The resulting feature vector is used for the classi cation of the movement order.
3.1 Signal acquisition
For recording of the EMG signal, only one pair of pre-gelled single Ag/AgCl electrodes was
xed on the skin of the system user's inside forearm (Fig. 3). Usually, each pair of electrodes
is used to examine mainly one single muscle. Signal interferences of adjacent muscles, known
as crosstalk, are normally undesirable. Since we designed like only one channel sensor for
signal acquisition it was necessary to examine several muscles simultaneously with one pair
of electrodes. These observed muscles were mainly the
exor carpi radialis and the palmaris
longus, both of which are responsible for wrist movements, as well as the
exor digitorum
super cialis, which is used for nger movements. All three electrodes are situated in a line in
the middle of the forearm parallel to the length of the forearm muscle bers. By placing the
rst electrode near the wrist, it is possible to examine the muscles of the forearm between their
tendon insertions and their motor points, which seems to be the best location for a constant
measurement. The reference electrode is placed in the middle. The sampling rate of the EMG
signal in the system was set at 125 samples per second.
Figure 3. Position of the electrodes according to the muscle structure

3.2 Preprocessing
Fortunately, in this project, the common noises found in EMG signals, such as inherent equip-
ment noise, electromagnetic radiation, or moving artifacts, are hard to nd. However there will
be another problem hindering the raw signal from being subsequently processed. The incoming
signal will be extremely unstable baseline which is di cult to calculate reasonable values for
statistical and frequency features. As a consequence, the signal needs to be preprocessed rst to
be suitable for further processing. For this purpose, the raw signal values x should be detrended
with the following simple detrending function D:
3.3 Pattern extraction
To capture only relevant patterns in EMG waveforms, we need to design an adaptive thresh-
olding. Although the system should provide a default setting for the concrete threshold values
which normally provides comparatively accurate pattern boundaries, the best results are to be
achieved when the threshold values are individually adjusted to the user of the system. This
is due to the fact that the EMG signal of each person is slightly di erent. An incoming pre-
processed value is marked as the beginning of a pattern if a certain de ned threshold value
is reached. This boundary is found to be quite unproblematic, as there exists a considerable
di erence in the signal amplitude between staying in the home position and starting to perform
a gesture. The upper bound will be limited by the Press gesture which generally generates the
lowest amplitude and absolutely needed to be identi ed, while the lower bound will be limited
by noise, for example resulting from small unintended movements which must not be recognized
as patterns.
Detecting the ending of a pattern is more complicated. Here, a trade-o between two di erent
problems is to be found: First, the ending boundary should not be too high, otherwise the
pattern might not be caught completely. Second, the ending boundary should not be too low,
otherwise the end of a pattern might be detected much too late. A further complication may
results from the fact that some gestures can cause a reverberation e ect in the signal amplitude,
long after the motion had already stopped. If, because of the characteristic zigzag form of an
EMG signal, the examination of an incoming value does not make any sense, a couple of
consecutive values have to be observed. The best results for the detection of a pattern ending
in the system were achieved by observing the root mean square (RMS) of the last 16 incoming
values. If this RMS value fell twice in a row below two (possibly di erent) boundary values, it
was considered as being the end of a pattern.
3.4 Feature extraction
To classify a performed gesture some distinctive features have to be found and taken from
each matched pattern [19, 20]. Therefore several features were extracted, including common
statistical features like maximum, minimum, mean value, variance, signal length and root mean
square.In the frequency domain obtained by using typical fast Fourier transform (FFT), we can
calculate fundamental frequency (F0) and Fourier variance of the spectrum. Given the spectrum
of signal it can also be extracted the region length which is de ned as a partial length of the
spectrum containing greater magnitude than the mean value of total Fourier coe cients. This
feature should be an indicator for how periodic a signal is: the smaller the region the more
periodic the signal. In the cases where there is more than one region in the spectrum, the
lengths of these regions are added. First, the positions of the maximum and the minimum
which are de ned by the relative position (as a percentage) of the max. and min.