Neuromorphic Neural Network Parallelization on CUDA Compatible GPU for EEG Signal Classification
The purpose of the project described in this paper is to implement a Spiking Neural Network, on a CUDA driven Nvidia video-card, which can learn predefined samples on images presented as input data. With experimental EEG signals pre-processed using the Wavelet transform into an image set, it can lea...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 364 |
|---|---|
| container_issue | |
| container_start_page | 359 |
| container_title | |
| container_volume | |
| creator | Bako, Laszlo Kolcsar, Arpad-Zoltan Brassai, Sandor-Tihamer Marton, Laszlo-Ferenc Losonczi, Lajos |
| description | The purpose of the project described in this paper is to implement a Spiking Neural Network, on a CUDA driven Nvidia video-card, which can learn predefined samples on images presented as input data. With experimental EEG signals pre-processed using the Wavelet transform into an image set, it can learn to classify inputs into a certain category by applying a proprietary algorithm, presented in the paper. The implementation of the spiking neural network is done in CUDA C, with the use of the card's inner GPU. The GPU has the functionality to parallelize multiple tasks, which can enable the neural network to do fast calculations even with large amounts of data. The application can be controlled with a GUI, in which the user can modify the base parameters of the system, make tests, or it can train the system. Performance results are given in terms of computation speed and classification accuracy. |
| doi_str_mv | 10.1109/EMS.2012.87 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6410177</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6410177</ieee_id><sourcerecordid>6410177</sourcerecordid><originalsourceid>FETCH-LOGICAL-i241t-c57d54790a38678ff56e8c145ba1324150c5191cc1c273ea35fbba12952a19953</originalsourceid><addsrcrecordid>eNotj0tPwzAQhI0QElB64sjFfyDB69faxyqEgFSgUum5OMYBQ9pUSVAFvx7zkFb6NDM7Ky0h58ByAGYvy7tlzhnw3OABOWWorZKWa3NIphYNSI1CWkR-TKbD8MYYA9RaojkhT_fho-82Xb97jZ7-CNcmjPuuf6cLl1Qb2vjlxthtaZpidTWjRbfZJaduA60WK9p0PS3Lii7jyza1i9YNQ2yi_y2dkaPGtUOY_nNCVtflY3GTzR-q22I2zyKXMGZe4bOSaJkTRqNpGqWD8SBV7UCkDcW8Agveg-coghOqqVPEreIOrFViQi7-7sYQwnrXx43rP9daQvoVxTdV8FNS</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Neuromorphic Neural Network Parallelization on CUDA Compatible GPU for EEG Signal Classification</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Bako, Laszlo ; Kolcsar, Arpad-Zoltan ; Brassai, Sandor-Tihamer ; Marton, Laszlo-Ferenc ; Losonczi, Lajos</creator><creatorcontrib>Bako, Laszlo ; Kolcsar, Arpad-Zoltan ; Brassai, Sandor-Tihamer ; Marton, Laszlo-Ferenc ; Losonczi, Lajos</creatorcontrib><description>The purpose of the project described in this paper is to implement a Spiking Neural Network, on a CUDA driven Nvidia video-card, which can learn predefined samples on images presented as input data. With experimental EEG signals pre-processed using the Wavelet transform into an image set, it can learn to classify inputs into a certain category by applying a proprietary algorithm, presented in the paper. The implementation of the spiking neural network is done in CUDA C, with the use of the card's inner GPU. The GPU has the functionality to parallelize multiple tasks, which can enable the neural network to do fast calculations even with large amounts of data. The application can be controlled with a GUI, in which the user can modify the base parameters of the system, make tests, or it can train the system. Performance results are given in terms of computation speed and classification accuracy.</description><identifier>ISBN: 9781467349772</identifier><identifier>ISBN: 1467349771</identifier><identifier>EISBN: 0769549268</identifier><identifier>EISBN: 9780769549262</identifier><identifier>DOI: 10.1109/EMS.2012.87</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Biological neural networks ; classification ; CUDA ; EEG ; Electroencephalography ; GPU ; Graphics processing units ; Neurons ; parallelization ; Spiking neural network ; Training ; Wavelet transforms</subject><ispartof>2012 Sixth UKSim/AMSS European Symposium on Computer Modeling and Simulation, 2012, p.359-364</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6410177$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6410177$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Bako, Laszlo</creatorcontrib><creatorcontrib>Kolcsar, Arpad-Zoltan</creatorcontrib><creatorcontrib>Brassai, Sandor-Tihamer</creatorcontrib><creatorcontrib>Marton, Laszlo-Ferenc</creatorcontrib><creatorcontrib>Losonczi, Lajos</creatorcontrib><title>Neuromorphic Neural Network Parallelization on CUDA Compatible GPU for EEG Signal Classification</title><title>2012 Sixth UKSim/AMSS European Symposium on Computer Modeling and Simulation</title><addtitle>ems</addtitle><description>The purpose of the project described in this paper is to implement a Spiking Neural Network, on a CUDA driven Nvidia video-card, which can learn predefined samples on images presented as input data. With experimental EEG signals pre-processed using the Wavelet transform into an image set, it can learn to classify inputs into a certain category by applying a proprietary algorithm, presented in the paper. The implementation of the spiking neural network is done in CUDA C, with the use of the card's inner GPU. The GPU has the functionality to parallelize multiple tasks, which can enable the neural network to do fast calculations even with large amounts of data. The application can be controlled with a GUI, in which the user can modify the base parameters of the system, make tests, or it can train the system. Performance results are given in terms of computation speed and classification accuracy.</description><subject>Biological neural networks</subject><subject>classification</subject><subject>CUDA</subject><subject>EEG</subject><subject>Electroencephalography</subject><subject>GPU</subject><subject>Graphics processing units</subject><subject>Neurons</subject><subject>parallelization</subject><subject>Spiking neural network</subject><subject>Training</subject><subject>Wavelet transforms</subject><isbn>9781467349772</isbn><isbn>1467349771</isbn><isbn>0769549268</isbn><isbn>9780769549262</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj0tPwzAQhI0QElB64sjFfyDB69faxyqEgFSgUum5OMYBQ9pUSVAFvx7zkFb6NDM7Ky0h58ByAGYvy7tlzhnw3OABOWWorZKWa3NIphYNSI1CWkR-TKbD8MYYA9RaojkhT_fho-82Xb97jZ7-CNcmjPuuf6cLl1Qb2vjlxthtaZpidTWjRbfZJaduA60WK9p0PS3Lii7jyza1i9YNQ2yi_y2dkaPGtUOY_nNCVtflY3GTzR-q22I2zyKXMGZe4bOSaJkTRqNpGqWD8SBV7UCkDcW8Agveg-coghOqqVPEreIOrFViQi7-7sYQwnrXx43rP9daQvoVxTdV8FNS</recordid><startdate>201211</startdate><enddate>201211</enddate><creator>Bako, Laszlo</creator><creator>Kolcsar, Arpad-Zoltan</creator><creator>Brassai, Sandor-Tihamer</creator><creator>Marton, Laszlo-Ferenc</creator><creator>Losonczi, Lajos</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201211</creationdate><title>Neuromorphic Neural Network Parallelization on CUDA Compatible GPU for EEG Signal Classification</title><author>Bako, Laszlo ; Kolcsar, Arpad-Zoltan ; Brassai, Sandor-Tihamer ; Marton, Laszlo-Ferenc ; Losonczi, Lajos</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i241t-c57d54790a38678ff56e8c145ba1324150c5191cc1c273ea35fbba12952a19953</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Biological neural networks</topic><topic>classification</topic><topic>CUDA</topic><topic>EEG</topic><topic>Electroencephalography</topic><topic>GPU</topic><topic>Graphics processing units</topic><topic>Neurons</topic><topic>parallelization</topic><topic>Spiking neural network</topic><topic>Training</topic><topic>Wavelet transforms</topic><toplevel>online_resources</toplevel><creatorcontrib>Bako, Laszlo</creatorcontrib><creatorcontrib>Kolcsar, Arpad-Zoltan</creatorcontrib><creatorcontrib>Brassai, Sandor-Tihamer</creatorcontrib><creatorcontrib>Marton, Laszlo-Ferenc</creatorcontrib><creatorcontrib>Losonczi, Lajos</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bako, Laszlo</au><au>Kolcsar, Arpad-Zoltan</au><au>Brassai, Sandor-Tihamer</au><au>Marton, Laszlo-Ferenc</au><au>Losonczi, Lajos</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Neuromorphic Neural Network Parallelization on CUDA Compatible GPU for EEG Signal Classification</atitle><btitle>2012 Sixth UKSim/AMSS European Symposium on Computer Modeling and Simulation</btitle><stitle>ems</stitle><date>2012-11</date><risdate>2012</risdate><spage>359</spage><epage>364</epage><pages>359-364</pages><isbn>9781467349772</isbn><isbn>1467349771</isbn><eisbn>0769549268</eisbn><eisbn>9780769549262</eisbn><coden>IEEPAD</coden><abstract>The purpose of the project described in this paper is to implement a Spiking Neural Network, on a CUDA driven Nvidia video-card, which can learn predefined samples on images presented as input data. With experimental EEG signals pre-processed using the Wavelet transform into an image set, it can learn to classify inputs into a certain category by applying a proprietary algorithm, presented in the paper. The implementation of the spiking neural network is done in CUDA C, with the use of the card's inner GPU. The GPU has the functionality to parallelize multiple tasks, which can enable the neural network to do fast calculations even with large amounts of data. The application can be controlled with a GUI, in which the user can modify the base parameters of the system, make tests, or it can train the system. Performance results are given in terms of computation speed and classification accuracy.</abstract><pub>IEEE</pub><doi>10.1109/EMS.2012.87</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9781467349772 |
| ispartof | 2012 Sixth UKSim/AMSS European Symposium on Computer Modeling and Simulation, 2012, p.359-364 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_6410177 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Biological neural networks classification CUDA EEG Electroencephalography GPU Graphics processing units Neurons parallelization Spiking neural network Training Wavelet transforms |
| title | Neuromorphic Neural Network Parallelization on CUDA Compatible GPU for EEG Signal Classification |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T02%3A27%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Neuromorphic%20Neural%20Network%20Parallelization%20on%20CUDA%20Compatible%20GPU%20for%20EEG%20Signal%20Classification&rft.btitle=2012%20Sixth%20UKSim/AMSS%20European%20Symposium%20on%20Computer%20Modeling%20and%20Simulation&rft.au=Bako,%20Laszlo&rft.date=2012-11&rft.spage=359&rft.epage=364&rft.pages=359-364&rft.isbn=9781467349772&rft.isbn_list=1467349771&rft.coden=IEEPAD&rft_id=info:doi/10.1109/EMS.2012.87&rft_dat=%3Cieee_6IE%3E6410177%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=0769549268&rft.eisbn_list=9780769549262&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6410177&rfr_iscdi=true |