Information Technology Reference
In-Depth Information
The data collecting process was divided into two parts. In each of the parts, the pa-
tients are asked to perform distinct inputs:
•
Perform obligatory inputs, including a complete set of a previously specified pro-
tocol: voice commands; facial expressions; head, arm and hand movements. The ob-
jective of this protocol is to make a profile of the users.
•
Perform free inputs, which enable the patient to perform some given tasks but
using its own and completely free preferred process.
The inputs are performed in distinct environmental conditions: noise and lighting
variations; distinct pavement and wheelchair movements; tasks performed in parallel
(such as maintaining a conversation). Tracing a user diagnostic can be very useful to
adjust certain settings allowing for an optimized configuration and improved interac-
tion between the user and the multimodal interface.
Accordingly, the Intellwheels Multimodal Interface contains a module capable of
performing series of training sessions, composed of small tests for each input modali-
ty. These tests may consist, for example, of asking the user to press a certain sequence
of buttons on the gamepad, or to move one of the gamepads' joysticks to a certain
position. Another test may consist in asking the user to pronounce a set of voice
commands, or to perform a specific head movement.
The tests should be performed sequentially and should have an increasing difficul-
ty. Additionally, the tests should be reconfigurable and extensible. Finally, the tests
sets and theirs results should be saved on a database, accessible by the Intellwheels
Multimodal Interface. Therefore, the following user characteristics should be ex-
tracted and these characteristics can be separated in two different types: quantitative
and qualitative. The quantitative measures consist of: the time taken to perform a full
button sequence; the average time between pressing two buttons; the average time to
place a gamepad analogical switch on a certain position; the average time to position
the head on a certain position; the trust level of speech recognition; maximum ampli-
tude achieved with the gamepad analogical switches in different directions; maximum
amplitude achieved with the head in different directions and number of errors made
using the gamepad. Using the quantitative measures, the following qualitative meas-
ures should be estimated: user ability to use the gamepad buttons; user ability to per-
form head movements and user ability to pronounce voice commands.
At the end of the training session, the tracked user information should be saved to
an external database, containing the users' profile. The user profile can be used to
improve security, by defining, for each user, a global trust level for each input modali-
ty. The trust level can be used to advice the user of which modality to use, at the crea-
tion of a new association. Also, it could be useful to activate confirmation events
whenever a user requests a certain output action using an input level with a low trust
level.
Another functionality of the user´s profile is capturing the EEG signals using a
brain computer interface [27] for using as input facial expressions and thoughts.
The users will be asked to fill a complete questionnaire about the experiment and
their preferences regarding each control method for each task in each environmental
condition.
