| fullrecord |
[{"key": "dc.contributor.advisor", "value": "Piirainen, Jarmo", "language": null, "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.advisor", "value": "Cronin, Neil", "language": null, "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Virtanen, Lauri", "language": null, "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2021-07-01T07:51:05Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2021-07-01T07:51:05Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2021", "language": null, "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/76932", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "M\u00e4kihyppy on Suomessa perinteik\u00e4s laji, jossa on totuttu kansainv\u00e4liseen menestykseen arvokisoissa. M\u00e4kihyppy\u00e4 on tutkittu jo 1900-alkupuolelta alkaen ja vilkkain tutkimusaikakausi sijoittunee v\u00e4h\u00e4n 2000-luvun molemmin puolin. M\u00e4kihyppysuoritus jakaantuu nelj\u00e4\u00e4n vaiheeseen: yl\u00e4m\u00e4en vauhdinottoon, ponnistukseen, ilmalentoon sek\u00e4 alastuloon. Eniten lienee tutkittu ponnistusta, sill\u00e4 se n\u00e4hd\u00e4\u00e4n hypyn pituuden kannalta kaikkein kriittisimp\u00e4n\u00e4.\r\n\r\nTyypillisesti ponnistuksesta tutkitaan liikkeen ajoitusta, nivelkulmia ja kulmanopeuksia, hypp\u00e4\u00e4j\u00e4n nopeutta, voiman tuottoa, lihasaktivaatiota ja hypp\u00e4\u00e4j\u00e4\u00e4n kohdistuvia voimia.\r\n\r\nPerinteinen liikeanalyysi ei sovellu m\u00e4kihyppyyn. Se on operatiivisesti raskasta ja markkereiden kiinnitt\u00e4minen pukuun aiheuttaa ep\u00e4tarkkuutta tuloksiin ja riskej\u00e4 hypp\u00e4\u00e4j\u00e4lle.\r\n\r\nT\u00e4m\u00e4n Pro gradu -tutkielman tarkoituksena oli selvitt\u00e4\u00e4 koneoppimiseen perustuvan sovelluksen AlphaPosen ja sen p\u00e4\u00e4lle rakennetun sovelluksen suoriutumista ponnistusvaiheen analyysist\u00e4, kun vertailtavana menetelm\u00e4n\u00e4 oli perinteinen kuva kuvalta tehty analyysi. Tutkimus suoritettiin Vuokatissa K-100 m\u00e4est\u00e4 syyskuussa 2020, jossa videoitiin kahdeksan (15-26-v.) yhdistetyn urheilijan suorittamat 40 hyppy\u00e4. Tilastolliseen vertailu tehtiin 10:lle ponnistukselle. ICC testi (N=376) osoitti erinomaista toistettavuutta sek\u00e4 lantio- (ICC: 0.988, 95% CI[0.984,0.991]), polvi- (ICC: 0.982, 95% CI[0.898,0.993]) ett\u00e4 s\u00e4\u00e4rikulmille (ICC: 0.936, 95% CI[0.911,0.952]). Yl\u00e4vartalonkulman osalta tuloshajontaa esiintyi merkitt\u00e4v\u00e4sti (ICC:0.889, 95% CI[0.506,0.955]). Korrelaatioanalyysi osoitti eritt\u00e4in vahvan korrelaation lantio- (\ud835\udc5f\ud835\udc60=0.975, p=0.000***), polvi- (\ud835\udc5f\ud835\udc60=0.931, p=0.000***) ja yl\u00e4vartalokulman (\ud835\udc5f\ud835\udc60=0.882, p=0.000***) sek\u00e4 vahvan korrelaation s\u00e4\u00e4rikulman (\ud835\udc5f\ud835\udc60=0.882, p=0.000***) osalta. AlphaPose yliarvioi yl\u00e4vartalo- ja aliarvioi polvikulmaa laskun loppuvaiheessa. Parillinen t testi osoitti hyv\u00e4n vastaavuuden menetelmien v\u00e4lill\u00e4 ponnistuksen kestolle (sovellus: M=0.269\u00b10.463s; perinteinen: M=0.272\u00b10.162s, p=0.831) ja lantion kulmanopeudelle keulalla (sovellus: M=9.319\u00b11.230rad/s; perinteinen: M=9.417\u00b11.165rad/s, p=0.791,).\r\n\r\nKoneoppimispohjainen liikeanalyysi vaikuttaa lupaavalta ja operatiivisesti kustannustehokkaalta. Mittausmenetelm\u00e4ss\u00e4 oli selke\u00e4sti havaittavissa toistettavuutta ja validiteettia monilta osin, mutta my\u00f6s mittausarvojen hajontaa. Mittausasetelmaa ja mallia kehitt\u00e4m\u00e4ll\u00e4 on mahdollista p\u00e4\u00e4st\u00e4 viel\u00e4kin tarkempaan sovelluspohjaiseen analyysiratkaisuun.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Ski jumping has long traditions in Finland and the country has enjoyed notable success in the history of Ski jumping events. Research work around ski jumping started in the early 20th century and the busiest era took place at the turn of the millennium. Ski jump performance is divided into in-run, take-off, flight and landing phases. Take-off might be the most actively researched topic as it is widely regarded as the most critical phase as it has the greatest effect on jump length. Typically, researchers investigate take-off timing, joint angles, angular velocities of joint angles, the speed of a jumper, power generation, muscle activity and forces acting on the jumper from the take-off phase. Traditional motion analysis is not suitable for ski jumping due to operative costs. It is also inaccurate method as markers are difficult to place reliably on loose jump suit. This Master\u2019s thesis is about investigating how well a machine learning based AlphaPose and an analysis software built on top of it performs in a take-off analysis compared to a traditional image by image performed analysis.\r\n\r\nResearch took place in Vuokatti HS-100 hill on September 2020 where total of 40 jumps from 8 Nordic combined athletes (15-26y) were video recorded. Statistical analysis was eventually performed for 10 take-offs. ICC test (N=376) showed excellent reliability for hip (ICC: 0.988, 95% CI[0.984,0.991]), knee (ICC: 0.982, 95% CI[0.898,0.993]) and shank-ski angles (ICC: 0.936, 95% CI[0.911,0.952]). Upper body angle showed significant deviation in results (ICC:0.889, 95% CI[0.506,0.955]). Correlation analysis showed very strong correlation for hip (\ud835\udc5f\ud835\udc60=0.975, p=0.000***), knee (\ud835\udc5f\ud835\udc60=0.931, p=0.000***) and upper body (\ud835\udc5f\ud835\udc60=0.882, p=0.000***) angles and strong correlation for shank-ski angle (\ud835\udc5f\ud835\udc60=0.882, p=0.000***). AlphaPose overestimated upper body and underestimated knee angles during late in-run. Paired samples t-test showed good equivalency for jump duration (software: M=0.269\u00b10.463s; traditional: M=0.272\u00b10.162s, p=0.831), and hip angular velocity at the time of release (software: M=9.319\u00b11.230rad/s; traditional: M=9.417\u00b11.165rad/s, p=0.791).\r\n\r\nMachine learning based software is promising as a motion analysis method and also operatively cost effective. Reliability and validity were recognized to some extent, but some high deviation was also observed in certain parameters. By enhancing the video shooting setup and analyzing software with dedicated ski jumping training data it is very likely to find even more reliable and valid motion analysis method for ski jumping.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by Miia Hakanen (mihakane@jyu.fi) on 2021-07-01T07:51:05Z\r\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2021-07-01T07:51:05Z (GMT). No. of bitstreams: 0\r\n Previous issue date: 2021", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "93", "language": null, "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": "asennon arviointi", "language": null, "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.title", "value": "M\u00e4kihypyn ponnistusvaiheen biomekaniikka hahmon asennon tunnistamiseen perustuvalla liikeanalyysill\u00e4", "language": null, "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-202107014120", "language": null, "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": "Liikuntatieteellinen tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Sport and Health Sciences", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Liikunta- ja terveystieteet", "language": "fi", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Sport and Health Sciences", "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": "Liikuntateknologia", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Sports Technology", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "yvv.contractresearch.funding", "value": "0", "language": null, "element": "contractresearch", "qualifier": "funding", "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": "5014", "language": null, "element": "subject", "qualifier": "oppiainekoodi", "schema": "dc"}, {"key": "dc.subject.yso", "value": "konen\u00e4k\u00f6", "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": "m\u00e4kihyppy", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "hahmontunnistus", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "liikeanalyysi", "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": "markkerit", "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"}]
|