izpis_h1_title_alt

Simulacija premikanja grafičnega kazalca z zamišljanjem motoričnih aktivnosti : diplomsko delo
ID KAMENŠEK, MARTIN (Author), ID Jager, Franc (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (1,35 MB)
MD5: FFD5D171F36D8B20F410803D26EDB5D5
PID: 20.500.12556/rul/652995ba-ac2d-47b8-92f7-c5c06e8c3bd7

Abstract
Cilj diplomske naloge je bil narediti sistem, ki na podlagi posnetkov elektroencefalograma (EEG) premika grafični kazalec po zaslonu v štirih smereh. Uporabljeni so EEG posnetki, dobljeni med zamišljanjem motoričnih aktivnosti. Predstavljeni so trije protokoli obdelave EEG posnetkov in učenja nevronske mreže. Namen prvega protokola je iskanje enostavnih relacij med amplitudnima spektroma μ in β valov ter namišljenimi motoričnimi akcijami stiskanja leve in desne pesti. Z uporabo obeh amplitudnih spektrov kot vhoda nevronske mreže je bila dosežena klasifikacijska natančnost 52%. V drugem protokolu je uporabljeno le povprečje μ in β amplitudnih spektrov, učna množica je optimizirana, natančnost klasifikacij pa doseže 80%. S tretjim protokolom se je uporabilo tudi posnetke stiskov obeh pesti hkrati. Končna rešitev je uporabila dve nevronski mreži, kjer je prva enaka kot v drugem protokolu, druga pa je s klasifikacijo stiskov obeh pesti in mirovanja dosegla klasifikacijsko natančnost 69%.

Language:Slovenian
Keywords:elektroencefalogram, vmesnik možgani-računalnik, zamišljanje motoričnih aktivnosti, nevronska mreža, računalništvo, univerzitetni študij, diplomske naloge
Work type:Undergraduate thesis
Typology:2.11 - Undergraduate Thesis
Organization:FRI - Faculty of Computer and Information Science
Publisher:M. Kamenšek
Year:2014
Number of pages:47 str.
PID:20.500.12556/RUL-30039 This link opens in a new window
COBISS.SI-ID:1536163267 This link opens in a new window
Publication date in RUL:12.11.2014
Views:1629
Downloads:349
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Simulation of graphic cursor movement by motor movement imagery
Abstract:
The goal of this thesis was to create a system which moves a cursor on a computer monitor in four directions, based on electroencephalogram (EEG) recordings. The EEG recordings were recorded while imagining of motor activities. This thesis documents three different protocols for processing EEG records and training a neural network. The purpose of the first protocol is to search for simple relations between amplitude spectra of μ and β brainwaves and imaginary motor activities of opening and closing individual fists. Using the amplitude spectra of μ and β, the neural network achieved 52% accuracy. In the second protocol only the average of amplitude spectra of μ and β was used. Additionally the training set was optimized, resulting in 80% accuracy. The final solution used two neural networks, first one being identical to the one in second protocol and the second one being used to classify imaginary motor activities of opening and closing both fists individually, achieving 69% accuracy.

Keywords:electroencephalogram, Brain-computer interface, imagining motor activity, neural network, computer science, diploma

Similar documents

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

Back