Exploring EMG and EEG signals for the development of a real-time control strategy for a robotic hand

Simple item page
dc.contributor.advisorFisher, Callenen_ZA
dc.contributor.advisorPerold, Willemen_ZA
dc.contributor.authorNieuwoudt, Loreleien_ZA
dc.contributor.otherStellenbosch University. Faculty of Engineering. Dept. of Electrical and Electronic Engineering.en_ZA
dc.date.accessioned2023-11-20T09:31:32Zen_ZA
dc.date.accessioned2024-01-08T20:04:37Zen_ZA
dc.date.available2023-11-20T09:31:32Zen_ZA
dc.date.available2024-01-08T20:04:37Zen_ZA
dc.date.issued2023-12en_ZA
dc.descriptionThesis (MEng)--Stellenbosch University, 2023.en_ZA
dc.description.abstractENGLISH ABSTRACT: Beyond the pronounced physical pain caused by amputation, amputees continue to struggle with their mental health on a daily basis. While being incapacitated as a result of having fewer limbs, navigating a new normal and becoming accustomed to the dependence on others to achieve simple daily tasks yields significant frustration, and deeper emotional turmoil. Furthermore, amputees strive to regain lost functionality in their bodies by seeking out various types of assistive devices. These devices encompass a spectrum, spanning from basic wooden or plastic prostheses primarily focused on aesthetics, to body-powered alternatives, and even to highly advanced and costly active prostheses. The array of available assistive devices for amputees, along with their corresponding price points, unfortunately fails to alleviate the emotional and physical challenges they face. This predicament arises due to financial constraints, often forcing them to settle for basic and less functional prosthetic options. In particular, the most functional and impressive active prostheses are severely unaffordable for those from middle or lower socioeconomic classes. This thesis therefore undertakes an exploration of the efficacy of employing realtime EMG and EEG signals in the development of control strategies for a robotic hand. The focus of this investigation is undertaken by classifying individual finger movements and arm flexion data, through the use of machine learning in real-time. Due to the different natures possessed by EMG and EEG signals, emphasis is placed on different aspects of the design of the two systems explored. In the case of the EMG system, focus is placed on obtaining the minimum number of EMG channels, an optimal window size to collect data, and data preprocessing measures required in order to achieve optimal classification accuracy. Emphasis is also placed on utilising multithreading in order to achieve parallel real-time signal sampling and classification, which is extended into use in the development of the EEG classifier. During the development of the EEG classifier, significant emphasis is directed towards the comparison of various classifier models, coupled with a meticulous fine-tuning of hyperparameters to attain optimal outcomes. The outcome of the developed EMG classifier yielded a real-time classification accuracy of 72.2% for grouped finger movements. The EEG classifier yielded a classification accuracy of 55% for arm flexion signals. As a result of the constraints imposed by the ethical clearance granted by the Research Ethics Committee for Social, Behavioral, and Educational Research (REC:SBER) of Stellenbosch University, the development of this system relied solely on data obtained from a single subject. Embark on a captivating intellectual journey as this thesis intricately unveils the expedition that reveals the meticulous processes developed, resulting in the realisation of the remarkable classifiers presented.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING: Buiten die uiterste fisiese pyn wat amputasie veroorsaak, sukkel lyers van hierdie tipe chirurgie ook met hulle geestesgesondheid op ’n daaglikse basis. Behalwe vir die feit dat sulke lyers fisies gestremd is, is dit uiters moeilik om ’n nuwe normaal te navigeer en om gewoond te raak daaraan om van ander afhanklik te wees om elke dag klein takies uit te voer. Hierdie lei gewoonlik tot uitermatige frustrasie en diep emosionele smart. Mense wat geamputeerd is, probeer om hulle verloorde liggaamlike funksionaliteit te herwin deur om gebruik te maak van verskeie bystandstoestelle. Hierdie toestelle bestaan uit ’n spektrum wat reeks van basiese hout of plastiek prostese, wat meestal gefokus is op estetiese voorkoms, tot liggaamsaangedrewe alternatiewe, en selfs tot die hoogs gevorderde en duur aktiewe prostese. Die verskeidenheid van beskikbare bystandstoestelle wat geamputeerdes het, sowel as hulle ooreenstemmende kostes misluk om enige fisiese of emosionele uitdagings te verbeter. Hierdie probleem bestaan meestal as gevolg van finansiele beperkinge, en forseer hierdie pasiente om baie basiese en minder funksionele prostese te kry. Ongelukkig is die mees funksionele en indrukwekkende prostese hoogs onbeskostigbaar vir die middle en laer sosio-ekonomiese klasse. Hierdie tesis onderneem dus ’n verkenning van die doeltreffendheid van die gebruik van intydse EMG- en EEG-seine in die ontwikkeling van beheerstrategie¨e vir ’n bestaande robotiese hand. Die fokus van hierdie ondersoek is onderneem deur individuele vingerbewegings en armsbuigingsdata te klassifiseer, deur die gebruik van masjienleer, in werklike tyd. As gevolg van die verskeie karakteristieke van EMG en EEG seine, word daar klem gelˆe op verskillende aspekte van die ontwerpe van die twee sisteme wat ondersoek word. Die fokus van die EMG sisteem is geplaas daarop om die minimum hoeveelheid EMG kanale te gebruik, ’n optimale venster grote vir die versameling van data, asook ander voorverwerkingsmaatre ¨els te vind om optimale klassifikasie akkuraatheid te bekom. Daar word ook klem gelˆe op die implementasie van ‘multithreading’ om intydse sein opneming en klassifikasie te bereik, wat ook gebruik word vir die EEG klassifiseerder. Gedurende die ontwikkeling van die EEG-klassifiseerder, word daar aansienlike klem geplaas op die vergelyking van verskeie klassifiseerdermodelle, saamgevoeg met ’n fynverstelling van hiperparameters om optimale resultate te bereik. Die uitkoms van die EMG klassifiseerder wat ontwikkel was in hierdie tesis het ’n intydse akkuraatheid van 72.2% bereik vir gegroepeerde vinger bewegings. Die EEG klassifiseerder het ’n akkuraatheid van 55% behaal vir seine wat van arm bewegings gemeet is. As gevolg van die beperkings wat ingestel is deur die Research Ethics Committee for Social, Behavioral, and Educational Research (REC:SBER) van Stellenbosch Universiteit, was hierdie navorsing net toegepas op een kandidaat. Maak ’n boeiende intellektuele reis terwyl hierdie tesis die onderneming onthul wat die prosesse ontwikkel het, wat gelei het tot die verwesenliking van die opmerklike klassifiseerders wat aangebied word.af_ZA
dc.description.versionMastersen_ZA
dc.format.extentxv. 111 pages : illustrationsen_ZA
dc.identifier.urihttps://scholar.sun.ac.za/handle/10019.1/129036en_ZA
dc.language.isoen_ZAen_ZA
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subject.lcshAmputation -- Complications en_ZA
dc.subject.lcshMyoelectric prosthesisen_ZA
dc.subject.lcshRobot handsen_ZA
dc.subject.lcshRobots -- Kinematicsen_ZA
dc.subject.lcshElectromyographyen_ZA
dc.subject.lcshElectroencephalogramen_ZA
dc.subject.lcshHuman-computer interactionen_ZA
dc.titleExploring EMG and EEG signals for the development of a real-time control strategy for a robotic handen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
nieuwoudt_exploring_2023.pdf
Size:
19.03 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Masters Degrees (Electrical and Electronic Engineering)