Radiosignaalien tunnistaminen neuroverkon avulla

Tekoäly on kehittynyt viime vuosina huimaa tahtia ja sitä on alettu soveltaa uusien haasteiden ratkaisemiseksi. Yksi tällainen haaste on pitkään ollut useiden radiosignaalien luokittelu toisistaan riittävällä tarkkuudella. Tehokkaalla radiosignaalien luokittelulla pysyttäisiin valvomaan alati kasvav...

Full description

Bibliographic Details
Main Author: Colliander, Jeremias
Other Authors: Informaatioteknologian tiedekunta, Faculty of Information Technology, Informaatioteknologia, Information Technology, Jyväskylän yliopisto, University of Jyväskylä
Format: Master's thesis
Language:fin
Published: 2022
Subjects:
Online Access: https://jyx.jyu.fi/handle/123456789/81397
_version_ 1826225701378850816
author Colliander, Jeremias
author2 Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä
author_facet Colliander, Jeremias Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä Colliander, Jeremias Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä
author_sort Colliander, Jeremias
datasource_str_mv jyx
description Tekoäly on kehittynyt viime vuosina huimaa tahtia ja sitä on alettu soveltaa uusien haasteiden ratkaisemiseksi. Yksi tällainen haaste on pitkään ollut useiden radiosignaalien luokittelu toisistaan riittävällä tarkkuudella. Tehokkaalla radiosignaalien luokittelulla pysyttäisiin valvomaan alati kasvavaa radioliikennettä sekä saamaan suurempi hyöty irti rajallisesta radiotaajuusspektristä. Aikaisemmat tutkimukset ovat luokitelleet radiosignaaleita käyttämällä keinotekoisesti luotua aineistoa, joka ei täysin vastaa oikean maailman haasteita ja ongelmia. Tämän tutkimuksen tarkoitus on kerätä oikeista signaaleista koostuva aineisto sekä rakentaa toimiva signaaleiden luokittelija syväoppimista (Deep Learning, DL) sekä hybridikuvia hyödyntämällä. Lisäksi tutkimuksessa tutkitaan tavallisen ohjelmistokehityksen sekä tekoälyn kehityksen eroavaisuuksia. Tutkimus tehtiin Jyväskylässä toimipistettään pitävälle yritys X:lle, jotka tarjosivat keinot signaalien tallentamiseen sekä resurssit mallien kouluttamiseen ja signaalien käsittelyyn. Tutkimustuloksista kävi ilmi, että radiosignaaleita on mahdollista luokitella hyvinkin tarkasti neuroverkkojen ja hybridikuvien avulla. Tutkimuksesta selvisi myös uusia haasteita, joita ei ollut otettu aikaisemmissa tutkimuksissa huomioon. Lisäksi selvisi, että ohjelmistokehitys ja tekoälyn kehitys eroavat toisistaan huomattavasti, jotka saattavat vaikuttaa suuresti AI projektien onnistumiseen. Toimiva ja skaalautuva malli tarvitsee itselleen paljon tukijärjestelmiä ja ohjelmia, jotta lopputuloksesta tulee helpommin ylläpidettävä ja käytettävä kokonaisuus. Artificial intelligence has developed at a rapid pace in recent years and has begun to be applied to meet new challenges. One such challenge has long been the classification of several radio signals with sufficient accuracy. Efficient classification of radio signals would make tracking and controlling of the ever-increasing radio traffic and make greater use of the limited radio frequency spectrum. Previous studies have classified radio signals using artificially generated data that does not fully meet the challenges and problems of the real world. The purpose of this study is to collect data consisting of real signals and to build a working signal classifier using deep learning and hybrid images. In addition, the study examines the differences between ordinary software development and the development of artificial intelligence. The study was carried out for Company X, which has an office in Jyväskylä. The Company X provided the means to record signals and resources for model training and signal processing. The results of the study showed that it is possible to classify radio signals very accurately using neural networks and hybrid images. The study also revealed new challenges that had not been addressed in the previous studies. In addition, it became clear that software development and the development of artificial intelligence differ significantly, and it may be a key factor in success of AI projects. A functional and scalable model needs a lot of support systems and programs to make the solution easier to maintain and use.
first_indexed 2022-06-01T20:04:23Z
format Pro gradu
free_online_boolean 1
fullrecord [{"key": "dc.contributor.advisor", "value": "Lehto, Martti", "language": "", "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.advisor", "value": "P\u00f6l\u00f6nen, Ilkka", "language": "", "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Colliander, Jeremias", "language": "", "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2022-06-01T08:29:11Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2022-06-01T08:29:11Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2022", "language": "", "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/81397", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Teko\u00e4ly on kehittynyt viime vuosina huimaa tahtia ja sit\u00e4 on alettu soveltaa uusien haasteiden ratkaisemiseksi. Yksi t\u00e4llainen haaste on pitk\u00e4\u00e4n ollut useiden radiosignaalien luokittelu toisistaan riitt\u00e4v\u00e4ll\u00e4 tarkkuudella. Tehokkaalla radiosignaalien luokittelulla pysytt\u00e4isiin valvomaan alati kasvavaa radioliikennett\u00e4 sek\u00e4 saamaan suurempi hy\u00f6ty irti rajallisesta radiotaajuusspektrist\u00e4. Aikaisemmat tutkimukset ovat luokitelleet radiosignaaleita k\u00e4ytt\u00e4m\u00e4ll\u00e4 keinotekoisesti luotua aineistoa, joka ei t\u00e4ysin vastaa oikean maailman haasteita ja ongelmia. T\u00e4m\u00e4n tutkimuksen tarkoitus on ker\u00e4t\u00e4 oikeista signaaleista koostuva aineisto sek\u00e4 rakentaa toimiva signaaleiden luokittelija syv\u00e4oppimista (Deep Learning, DL) sek\u00e4 hybridikuvia hy\u00f6dynt\u00e4m\u00e4ll\u00e4. Lis\u00e4ksi tutkimuksessa tutkitaan tavallisen ohjelmistokehityksen sek\u00e4 teko\u00e4lyn kehityksen eroavaisuuksia. Tutkimus tehtiin Jyv\u00e4skyl\u00e4ss\u00e4 toimipistett\u00e4\u00e4n pit\u00e4v\u00e4lle yritys X:lle, jotka tarjosivat keinot signaalien tallentamiseen sek\u00e4 resurssit mallien kouluttamiseen ja signaalien k\u00e4sittelyyn. Tutkimustuloksista k\u00e4vi ilmi, ett\u00e4 radiosignaaleita on mahdollista luokitella hyvinkin tarkasti neuroverkkojen ja hybridikuvien avulla. Tutkimuksesta selvisi my\u00f6s uusia haasteita, joita ei ollut otettu aikaisemmissa tutkimuksissa huomioon. Lis\u00e4ksi selvisi, ett\u00e4 ohjelmistokehitys ja teko\u00e4lyn kehitys eroavat toisistaan huomattavasti, jotka saattavat vaikuttaa suuresti AI projektien onnistumiseen. Toimiva ja skaalautuva malli tarvitsee itselleen paljon tukij\u00e4rjestelmi\u00e4 ja ohjelmia, jotta lopputuloksesta tulee helpommin yll\u00e4pidett\u00e4v\u00e4 ja k\u00e4ytett\u00e4v\u00e4 kokonaisuus.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Artificial intelligence has developed at a rapid pace in recent years and has begun to be applied to meet new challenges. One such challenge has long been the classification of several radio signals with sufficient accuracy. Efficient classification of radio signals would make tracking and controlling of the ever-increasing radio traffic and make greater use of the limited radio frequency spectrum. Previous studies have classified radio signals using artificially generated data that does not fully meet the challenges and problems of the real world. The purpose of this study is to collect data consisting of real signals and to build a working signal classifier using deep learning and hybrid images. In addition, the study examines the differences between ordinary software development and the development of artificial intelligence. The study was carried out for Company X, which has an office in Jyv\u00e4skyl\u00e4. The Company X provided the means to record signals and resources for model training and signal processing. The results of the study showed that it is possible to classify radio signals very accurately using neural networks and hybrid images. The study also revealed new challenges that had not been addressed in the previous studies. In addition, it became clear that software development and the development of artificial intelligence differ significantly, and it may be a key factor in success of AI projects. A functional and scalable model needs a lot of support systems and programs to make the solution easier to maintain and use.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by Miia Hakanen (mihakane@jyu.fi) on 2022-06-01T08:29:11Z\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2022-06-01T08:29:11Z (GMT). No. of bitstreams: 0\n Previous issue date: 2022", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "58", "language": "", "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.format.mimetype", "value": "application/pdf", "language": null, "element": "format", "qualifier": "mimetype", "schema": "dc"}, {"key": "dc.language.iso", "value": "fin", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "In Copyright", "language": "en", "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.subject.other", "value": "radiosignaalit", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "luokittelu", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.title", "value": "Radiosignaalien tunnistaminen neuroverkon avulla", "language": "", "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "master thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-202206013021", "language": "", "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Pro gradu -tutkielma", "language": "fi", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Master\u2019s thesis", "language": "en", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Informaatioteknologian tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Information Technology", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Informaatioteknologia", "language": "fi", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Information Technology", "language": "en", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "Jyv\u00e4skyl\u00e4n yliopisto", "language": "fi", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "University of Jyv\u00e4skyl\u00e4", "language": "en", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Tietoj\u00e4rjestelm\u00e4tiede", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Information Systems Science", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "yvv.contractresearch.collaborator", "value": "business", "language": "", "element": "contractresearch", "qualifier": "collaborator", "schema": "yvv"}, {"key": "yvv.contractresearch.funding", "value": "0", "language": "", "element": "contractresearch", "qualifier": "funding", "schema": "yvv"}, {"key": "yvv.contractresearch.initiative", "value": "student", "language": "", "element": "contractresearch", "qualifier": "initiative", "schema": "yvv"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_bdcc", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "masterThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.subject.oppiainekoodi", "value": "601", "language": "", "element": "subject", "qualifier": "oppiainekoodi", "schema": "dc"}, {"key": "dc.subject.yso", "value": "syv\u00e4oppiminen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "teko\u00e4ly", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "tutkimus", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "neuroverkot", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "koneoppiminen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "kehitys", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "kehitt\u00e4minen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "signaalit", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "ohjelmistokehitys", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.format.content", "value": "fulltext", "language": null, "element": "format", "qualifier": "content", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://rightsstatements.org/page/InC/1.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}, {"key": "dc.type.okm", "value": "G2", "language": null, "element": "type", "qualifier": "okm", "schema": "dc"}]
id jyx.123456789_81397
language fin
last_indexed 2025-02-18T10:55:52Z
main_date 2022-01-01T00:00:00Z
main_date_str 2022
online_boolean 1
online_urls_str_mv {"url":"https:\/\/jyx.jyu.fi\/bitstreams\/52fad48c-9a6e-4ad7-9d8b-45445c854c45\/download","text":"URN:NBN:fi:jyu-202206013021.pdf","source":"jyx","mediaType":"application\/pdf"}
publishDate 2022
record_format qdc
source_str_mv jyx
spellingShingle Colliander, Jeremias Radiosignaalien tunnistaminen neuroverkon avulla radiosignaalit luokittelu Tietojärjestelmätiede Information Systems Science 601 syväoppiminen tekoäly tutkimus neuroverkot koneoppiminen kehitys kehittäminen signaalit ohjelmistokehitys
title Radiosignaalien tunnistaminen neuroverkon avulla
title_full Radiosignaalien tunnistaminen neuroverkon avulla
title_fullStr Radiosignaalien tunnistaminen neuroverkon avulla Radiosignaalien tunnistaminen neuroverkon avulla
title_full_unstemmed Radiosignaalien tunnistaminen neuroverkon avulla Radiosignaalien tunnistaminen neuroverkon avulla
title_short Radiosignaalien tunnistaminen neuroverkon avulla
title_sort radiosignaalien tunnistaminen neuroverkon avulla
title_txtP Radiosignaalien tunnistaminen neuroverkon avulla
topic radiosignaalit luokittelu Tietojärjestelmätiede Information Systems Science 601 syväoppiminen tekoäly tutkimus neuroverkot koneoppiminen kehitys kehittäminen signaalit ohjelmistokehitys
topic_facet 601 Information Systems Science Tietojärjestelmätiede kehittäminen kehitys koneoppiminen luokittelu neuroverkot ohjelmistokehitys radiosignaalit signaalit syväoppiminen tekoäly tutkimus
url https://jyx.jyu.fi/handle/123456789/81397 http://www.urn.fi/URN:NBN:fi:jyu-202206013021
work_keys_str_mv AT collianderjeremias radiosignaalientunnistaminenneuroverkonavulla