izpis_h1_title_alt

Klasifikacija posnetkov elektroencefalograma med zamišljanjem motoričnih aktivnosti
ID PRESTOR, ADAM (Author), ID Jager, Franc (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (2,48 MB)
MD5: C2016B0C3FE5ED466D4F66891F18882C

Abstract
Metode za komunikacijo med možgani in računalnikom predstavljajo alternativno rešitev za upravljanje računalnika. Takšne rešitve pridejo prav ljudem, ki so fizično nezmožni uporabljati tipične mehanske vhodne naprave, kot sta tipkovnica in miška. V sklopu diplomske naloge smo razvili metodo za premikanje kazalca na računalniškem zaslonu na osnovi posnetkov elektroencefalograma (EEG) snemanih med zamišljanjem motoričnih aktivnosti, oziroma stiskanjem leve ali desne roke. Uporabili smo posnetke EEG javne, označene, podatkovne baze EEG Motor Movement Imagery DataSet (EEGMMI DS), ki je prosto dostopna na straneh Physionet. Razvita metoda vključuje postopke procesiranje signalov, postopke izločanja značilk, pristope strojnega učenja in klasifikacijo segmentov posnetkov z namenom klasifikacije med zamišljenimi ali dejanskimi akcijami leve in desne roke. Zelo pomemben rezultat raziskave je dala uporaba postopka sekvenčne izbire značilk v smeri naprej. Najvišje klasifikacijske točnosti so bile dosežene z uporabo izbranih značilk dobljenih s tistih signalov, ki ustrezajo elektrodam F7, F8, FT7 in FT8, in ne s signalov, ki ustrezajo tradicionalno uporabljenima elektrodama C3 in C4. V raziskavi nam je za vse posnetke podatkovne baze EEGMMI DS uspelo doseči povprečno klasifikacijsko točnost 66,78 %, pri čemer je bila najvišja klasifikacijska točnost za posnetke posameznega subjekta 97,62 %.

Language:Slovenian
Keywords:elektroencefalogram, procesiranje signalov, strojno učenje, podatkovna baza EEGMMI DS, vmesnik možgani računalnik
Work type:Bachelor thesis/paper
Organization:FRI - Faculty of Computer and Information Science
Year:2018
PID:20.500.12556/RUL-102246 This link opens in a new window
Publication date in RUL:26.07.2018
Views:1738
Downloads:540
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Classification of electroencephalographic records during motor movement imagery
Abstract:
The methods for communication between brain and computer represent an alternative solution for management of a computer. Such solutions are suitable for persons who are physically unable to use typical mechanical input devices such as keyboard and mouse. In the scope of diploma thesis, we developed a method for moving the cursor on a computer screen on the basis of the electroencephalographic (EEG) records recorded during motor movement imagery, and during actual closing of the left and right hand. We used the EEG records of the publicly available, annotated, EEG Motor Movement Imagery DataSet (EEGMMI DS) database, which is freely available on the Physionet pages. The developed method incorporates digital signal processing procedures, feature extraction procedures, machine learning approaches, and classification of the segments of the records with the aim to classify between the imagined or actual actions of the left and right hand. A very important result of the research gave the use of the sequential forward feature selection procedure. The highest classification accuracies were achieved using the selected features obtained from those signals which correspond to the electrodes F7, F8, FT7 and FT8, and not from the signals which correspond to the traditionally used electrodes C3 and C4. In the research, we achieved the average classification accuracy of 66.78 % for all records of the EEGMMI DS database, while the highest classification accuracy for the records of an individual subject was 97.62 %.

Keywords:electroencephalogram, signal processing, machine learning, EEGMMI DS database, brain computer interface

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back