06-04-2011, 04:01 PM
[attachment=11803]
“THE TONGUE DRIVE SYSTEM”
ASSISTIVE DEVICE
DEFINITION:
The "Tongue Drive System” is a tongue-operated assistive devise which helps individuals with physical disabilities such as spinal cord injuries.
This system is controlled by the movement of tongue.
The controlled devices may be wheelchair or computer system. Fig….
DEVELOPMENT:
This system was developed by the engineers of “Georgia Institute Of Technology , United States’’ in June 2008.
It is one of the nation's top research universities, distinguished by its commitment to improving the human condition .
WHY THE TONGUE?
Tongue movement is fast, accurate and does not require much concentration or effort.
Unlike hands and feet, which are controlled by the brain through the spinal cord, the tongue is directly connected to the brain by a cranial nerve.
It generally escapes in severe spinal cord injuries or other damages and it’s movement continues.
AN EXAMPLE:
COMPONENTS:
Permanent Magnetic Tracer -
A small permanent magnet is placed on the tongue by piercing, or tissue adhesives that is used as a tracer.
The movement of which is detected by an array of magnetic field sensors mounted on a headset outside the mouth.
Magnetic Sensor Module :
To receive the signals from from magnetic tracer a hall effect magnetic sensor is used. It is placed on headset around the mouth. It is used to measure the magnetic field generated by the magnetic tracer.
Control Unit : It is used to transmit the wireless signals.
Wireless Receiver :
Wireless signals are received by a wireless receiver which is called Personal Digital Assistance (PDA). The Sensor Signal processing algorithm runs on PDA.
• Driven System :
The driven system may be computer, wheelchair or motorized bed.
COMPONENT DIAGRAM:
HOW DOSE IT WORK?
To operate the TDS the motion of the tongue is traced by an array of magnetic sensors, which measure the magnetic field.
The magnetic field generated by the tracer varies as the tongue moves. This variation is detected by the sensor.
The sensor outputs is then digitized, modulated and transmitted across a wireless page link to an external controller, called Personal Digital Assistance (PDA).
A Sensor Signal Processing algorithm running on the PDA classifies the sensor signals and converts them into user control command.
A set of specific tongue movements can be tailored for each individuals.
Now the signals received by external controller are demodulated and demultiplexed to extract the individual sensor output.
By processing these outputs we can controlled the movement of the pointer on the screen.
Assigning a certain controller function to each tongue movement is done by the software.
There are six commands: right, left, up , down pointer movements, single and double clicks.
If the user quickly flicks the magnet towards one of the front sensors, it is considered a tongue click.
we had one sensor along the x-axis, one along the. y-axis, and two along the z-axis with respect to the imaginary coordinates of the face shield.
To minimize the effects of external magnetic field interference, including the earth magnetic field, we used a three-axis module as a reference electronic compass.
It is placed on top of the face shield.
SSP ALGORITHM :
The SSP algorithm running on the PC was developed in Lab VIEW and MATLAB environments.
Lab VIEW is a graphical programming environment to develop sophisticated measurement test and control system using graphical icons and wires.
MATLAB is a high level technical computing language and interactive environment for algorithm development.
SSP ALGORITHM :
It works in two phases: Training and Testing.
Training phase uses principal component analysis to extract the important features of the sensor out waveforms for each specific commands.
The user repeats each of the six designated
commands 10 times in 3-second intervals, while a total of 12 samples (3 per sensor) are recorded in 12-variable vectors for each repetition.
SSP ALGORITHM :
• The PCA based feature-extraction algorithm calculates the eigenvectors and Eigen values of the matrix in a three-dimensional (3-D) space based on the 12-variable vectors.
• Three eigenvectors with the largest Eigen values are then chosen to set up the feature matrix [v1, v2,v3].
• By multiplying the training vectors with the feature matrix, the SSP algorithm forms a cluster (class) of 10 data points from training for each specific command in the PCA virtual 3-D feature space.
• Once a cluster is formed for each command, the testing phase can be executed.
During this phase a three-sample window is slid over the incoming sensor signals to reflect them onto the 3-D feature space as new data points by using the feature matrix.
We develop the GUI in lab VIEW environment.
GUI FOR TDS PROTOTYPE:
PERFORMANCE :
• Command time : shows how quickly a command is given to the computer by the user.
• The TDS response time : includes thinking about the command, its associated tongue movement and any delays associated with wireless transmission, and SSP computations.
• Obviously, the shorter the response time, the better.
We consider the percentage of correctly completed commands (CCC %) as an additional parameter along with the response time.
A GUI was developed for this experiment to randomly select one out of six direct commands and turn on its indicator.
The subject was asked to issue the indicated command within a specified time period T.
Information transfer rate :
ADVANTAGES :
The signals from the magnetic sensors are linear functions the magnetic field, which is a continuous position dependent property. Thus a few sensors are able to capture a wide variety of tongue movements.
This would provide a tremendous advantage over switch based devices.
These would offer smoother, faster, and more natural controls as the user is saved the trouble of multiple on/off switch operations.
In Tongue Drive system on the other hand, the additional switches are unnecessary since a specific tongue movement can be assigned to the button press.
The permanent magnet which generates the magnetic field is a small, passive, and inherently wireless component which leads to user convenience.
Due to the proximity of the magnet and Hall-effect sensors in the oral cavity, the Tongue Drive system is expected to be more robust against noise, interference, and involuntary movements compared to alternative technologies.
DISADVANTAGES :
Implementation is slightly harder.
Slightly costlier.
CONCLUSION:
Tongue drive system is a touch free , wireless & non-invasive technology that needs no surgery for its operation.
The result of the trial showed 100% of the command were accurate with the response time less than one second which equal to an information transfer rate of approximately 150 bits/min.
The next step of research is to develop software to connect the tongue drive system to a great number of devices such as text generators, speech synthesizers and readers.
“THE TONGUE DRIVE SYSTEM”
ASSISTIVE DEVICE
DEFINITION:
The "Tongue Drive System” is a tongue-operated assistive devise which helps individuals with physical disabilities such as spinal cord injuries.
This system is controlled by the movement of tongue.
The controlled devices may be wheelchair or computer system. Fig….
DEVELOPMENT:
This system was developed by the engineers of “Georgia Institute Of Technology , United States’’ in June 2008.
It is one of the nation's top research universities, distinguished by its commitment to improving the human condition .
WHY THE TONGUE?
Tongue movement is fast, accurate and does not require much concentration or effort.
Unlike hands and feet, which are controlled by the brain through the spinal cord, the tongue is directly connected to the brain by a cranial nerve.
It generally escapes in severe spinal cord injuries or other damages and it’s movement continues.
AN EXAMPLE:
COMPONENTS:
Permanent Magnetic Tracer -
A small permanent magnet is placed on the tongue by piercing, or tissue adhesives that is used as a tracer.
The movement of which is detected by an array of magnetic field sensors mounted on a headset outside the mouth.
Magnetic Sensor Module :
To receive the signals from from magnetic tracer a hall effect magnetic sensor is used. It is placed on headset around the mouth. It is used to measure the magnetic field generated by the magnetic tracer.
Control Unit : It is used to transmit the wireless signals.
Wireless Receiver :
Wireless signals are received by a wireless receiver which is called Personal Digital Assistance (PDA). The Sensor Signal processing algorithm runs on PDA.
• Driven System :
The driven system may be computer, wheelchair or motorized bed.
COMPONENT DIAGRAM:
HOW DOSE IT WORK?
To operate the TDS the motion of the tongue is traced by an array of magnetic sensors, which measure the magnetic field.
The magnetic field generated by the tracer varies as the tongue moves. This variation is detected by the sensor.
The sensor outputs is then digitized, modulated and transmitted across a wireless page link to an external controller, called Personal Digital Assistance (PDA).
A Sensor Signal Processing algorithm running on the PDA classifies the sensor signals and converts them into user control command.
A set of specific tongue movements can be tailored for each individuals.
Now the signals received by external controller are demodulated and demultiplexed to extract the individual sensor output.
By processing these outputs we can controlled the movement of the pointer on the screen.
Assigning a certain controller function to each tongue movement is done by the software.
There are six commands: right, left, up , down pointer movements, single and double clicks.
If the user quickly flicks the magnet towards one of the front sensors, it is considered a tongue click.
we had one sensor along the x-axis, one along the. y-axis, and two along the z-axis with respect to the imaginary coordinates of the face shield.
To minimize the effects of external magnetic field interference, including the earth magnetic field, we used a three-axis module as a reference electronic compass.
It is placed on top of the face shield.
SSP ALGORITHM :
The SSP algorithm running on the PC was developed in Lab VIEW and MATLAB environments.
Lab VIEW is a graphical programming environment to develop sophisticated measurement test and control system using graphical icons and wires.
MATLAB is a high level technical computing language and interactive environment for algorithm development.
SSP ALGORITHM :
It works in two phases: Training and Testing.
Training phase uses principal component analysis to extract the important features of the sensor out waveforms for each specific commands.
The user repeats each of the six designated
commands 10 times in 3-second intervals, while a total of 12 samples (3 per sensor) are recorded in 12-variable vectors for each repetition.
SSP ALGORITHM :
• The PCA based feature-extraction algorithm calculates the eigenvectors and Eigen values of the matrix in a three-dimensional (3-D) space based on the 12-variable vectors.
• Three eigenvectors with the largest Eigen values are then chosen to set up the feature matrix [v1, v2,v3].
• By multiplying the training vectors with the feature matrix, the SSP algorithm forms a cluster (class) of 10 data points from training for each specific command in the PCA virtual 3-D feature space.
• Once a cluster is formed for each command, the testing phase can be executed.
During this phase a three-sample window is slid over the incoming sensor signals to reflect them onto the 3-D feature space as new data points by using the feature matrix.
We develop the GUI in lab VIEW environment.
GUI FOR TDS PROTOTYPE:
PERFORMANCE :
• Command time : shows how quickly a command is given to the computer by the user.
• The TDS response time : includes thinking about the command, its associated tongue movement and any delays associated with wireless transmission, and SSP computations.
• Obviously, the shorter the response time, the better.
We consider the percentage of correctly completed commands (CCC %) as an additional parameter along with the response time.
A GUI was developed for this experiment to randomly select one out of six direct commands and turn on its indicator.
The subject was asked to issue the indicated command within a specified time period T.
Information transfer rate :
ADVANTAGES :
The signals from the magnetic sensors are linear functions the magnetic field, which is a continuous position dependent property. Thus a few sensors are able to capture a wide variety of tongue movements.
This would provide a tremendous advantage over switch based devices.
These would offer smoother, faster, and more natural controls as the user is saved the trouble of multiple on/off switch operations.
In Tongue Drive system on the other hand, the additional switches are unnecessary since a specific tongue movement can be assigned to the button press.
The permanent magnet which generates the magnetic field is a small, passive, and inherently wireless component which leads to user convenience.
Due to the proximity of the magnet and Hall-effect sensors in the oral cavity, the Tongue Drive system is expected to be more robust against noise, interference, and involuntary movements compared to alternative technologies.
DISADVANTAGES :
Implementation is slightly harder.
Slightly costlier.
CONCLUSION:
Tongue drive system is a touch free , wireless & non-invasive technology that needs no surgery for its operation.
The result of the trial showed 100% of the command were accurate with the response time less than one second which equal to an information transfer rate of approximately 150 bits/min.
The next step of research is to develop software to connect the tongue drive system to a great number of devices such as text generators, speech synthesizers and readers.
