Brain-Computer Interface Based on Compressive Sensing and Steady-State Visual Evoked Potentials Applied to Command a Robotic Wheelchair
Name: HAMILTON RIVERA FLOR
Publication date: 21/09/2023
Advisor:
Name |
Role |
|---|---|
| RICARDO CARMINATI DE MELLO | Co-advisor * |
| TEODIANO FREIRE BASTOS FILHO | Advisor * |
Examining board:
| Name |
Role |
|---|---|
| ALAN SILVA DA PAZ FLORIANO | External Examiner * |
| DENIS DELISLE RODRIGUEZ | Co advisor * |
| RICARDO CARMINATI DE MELLO | Co advisor * |
| TEODIANO FREIRE BASTOS FILHO | Advisor * |
Summary: Peoplewithseverephysicaldisabilitiesareableofusingroboticwheelchairs,whichgenerallydemandsomemotorskills,andthereforetotalusageofassociatemuscles.Robotic wheelchairscommandedbyBrain-ComputerInterfaces(BCIs)basedonElectroencephalography(EEG)havedemonstratedtobeanalternativefortheseend-users,assuchsystems translatebrainpatternsongoingEEGsignalsintocontrolcommands.However,BCIs relyingonlocalprocessingencounterlimitationsinpower,scalability,andreal-time.In general,existingroboticwheelchairscommandedbyBCIsrequirepowerfulhardwarefor highspeedsignalprocessing.Ontheotherhand,end-usersneedalongtrainingprocess forsafelydrivingthesedevices.Asasolution,cloud-basedBCIsandcloudroboticshave emerged,leveragingcloudcomputingforhigh-performancedataprocessing,storage,and analysis.Thisintegrationempowersadvancedandadaptiveroboticassistance,transformingtele-rehabilitationande-healthapplicationsforpeoplewithdisabilities.However, integratingcloudcomputingwithBCIsintroducesitsownsetofchallenges.Theseinclude anefficientandreliabletransmissionoflargevolumesofdataandstablecommunication betweenthebrainsignalsensor,cloudinfrastructure,androboticwheelchair.Toaddress thesechallenges,thisthesisintroducesanovelCloud-BCISystemforwheelchaircommand throughtheuseofSteady-StateVisualEvokedPotential(SSVEP),CompressiveSensing (CS)techniques,andacommunicationframework.ThesystemenhancesInformationTransferRate,ensuringstablecommunicationamongtheBCI,cloudinfrastructure,androbotic wheelchair.LeveragingcloudService-OrientedarchitectureandRoboticOperatingSystem (ROS),thesystemallowsforeasyintegrationofdiverseroboticplatformsandprovides flexibilitytointegratevariousprotocols,classifiers,metrics,andcommandtechniques. Inconclusion,thecloud-BCIsystemdemonstratestobeanefficientandflexiblesolutionfor commandingaroboticwheelchair,makingitavaluabletoolforresearchersanddevelopers inthefieldofassistivetechnologies,tele-rehabilitationandtrainingscenarios.
