Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/152349 |
Resumo: | In cycling, for cyclists to be able to keep track of their evolution, performance can be measured using tests of maximal effort or, when those cannot be performed, parameters obtained on submaximal efforts, such as power output. Usually, training programs with specific elevation gains are prescribed in order to increase training load. With that in mind, the purpose of this study was, through data analysis techniques, namely cluster analysis and linear mixed-effects models, to compare different elevation gain profiles and determine whether they had a significant effect on performance evolution or not. To accomplish that goal, a database, available on the internet with name GoldenCheetah Open Data was utilized. It contained 2681 athletes, to whom inclusion and exclusion criteria were applied, resulting in a final 1308 cyclists included. Inclusion criteria were being 10 to 90 years old and having at least cycling 20 activities recorded. Exclusion criteria were all activities have missing values and all activities had outlier observations. For descriptive analysis, summarytools from R software was used. Cyclists were 42 years old, on average, and, from the 1308 athletes, 32 were women. In cluster analysis, cluster, imputeTS, factoextra and clValid libraries from R were used to apply four clustering algorithms in order to test and compare with stability measures. Through this analysis we concluded K-means algorithm was the one that performed better, which is why it was analyzed, and two clusters were obtained as a result: the cluster with high elevation gains and the cluster with low elevation gains. Significance tests showed a significant difference on age between clusters, but not on the proportion of female gender. As for training parameters, all were significantly different between clusters, including the ones related to power output. At last, with rstatix and nlme libraries from R, a linear mixed-effects model was applied using all response variables. However, after a moderate correlation was found among some variables, using corrplot R library, a new model with age, gender, number of activity, elevation gain, average speed and average heart rate was applied. The last linear mixed-effects model for average power revealed a significant negative influence of female gender and a significant positive influence of elevation gain, number of activity, average speed, average heart rate and the interaction between elevation gain and the number of the activity. The linear mixed-effects model for peak power on both 5 and 30 minute efforts evinced a significant negative influence of both age and female gender and a significant positive influence of elevation gain, number of activity, average speed, average heart rate and the interaction between elevation gain and the number of the activity. It was possible to conclude that both cluster analysis and repeated measures analysis were effective establishing a relationship between including vertical climbing on training programs and better performance improvement. |
id |
RCAP_a753f295351f96460e0bc559a8fbbad3 |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/152349 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects ModelCycling performancePower outputCluster analysisRepeated measuresLinear mixed-effects modelDomínio/Área Científica::Ciências Naturais::MatemáticasIn cycling, for cyclists to be able to keep track of their evolution, performance can be measured using tests of maximal effort or, when those cannot be performed, parameters obtained on submaximal efforts, such as power output. Usually, training programs with specific elevation gains are prescribed in order to increase training load. With that in mind, the purpose of this study was, through data analysis techniques, namely cluster analysis and linear mixed-effects models, to compare different elevation gain profiles and determine whether they had a significant effect on performance evolution or not. To accomplish that goal, a database, available on the internet with name GoldenCheetah Open Data was utilized. It contained 2681 athletes, to whom inclusion and exclusion criteria were applied, resulting in a final 1308 cyclists included. Inclusion criteria were being 10 to 90 years old and having at least cycling 20 activities recorded. Exclusion criteria were all activities have missing values and all activities had outlier observations. For descriptive analysis, summarytools from R software was used. Cyclists were 42 years old, on average, and, from the 1308 athletes, 32 were women. In cluster analysis, cluster, imputeTS, factoextra and clValid libraries from R were used to apply four clustering algorithms in order to test and compare with stability measures. Through this analysis we concluded K-means algorithm was the one that performed better, which is why it was analyzed, and two clusters were obtained as a result: the cluster with high elevation gains and the cluster with low elevation gains. Significance tests showed a significant difference on age between clusters, but not on the proportion of female gender. As for training parameters, all were significantly different between clusters, including the ones related to power output. At last, with rstatix and nlme libraries from R, a linear mixed-effects model was applied using all response variables. However, after a moderate correlation was found among some variables, using corrplot R library, a new model with age, gender, number of activity, elevation gain, average speed and average heart rate was applied. The last linear mixed-effects model for average power revealed a significant negative influence of female gender and a significant positive influence of elevation gain, number of activity, average speed, average heart rate and the interaction between elevation gain and the number of the activity. The linear mixed-effects model for peak power on both 5 and 30 minute efforts evinced a significant negative influence of both age and female gender and a significant positive influence of elevation gain, number of activity, average speed, average heart rate and the interaction between elevation gain and the number of the activity. It was possible to conclude that both cluster analysis and repeated measures analysis were effective establishing a relationship between including vertical climbing on training programs and better performance improvement.No ciclismo, de modo que os ciclistas possam monitorizar a sua evolução, a performance é medida com testes de esforço máximo ou, quando a utilização destes não é adequada, parâmetros de esforços submáximos, como produção de potência. Normalmente são prescritos treinos com ganhos de elevação específicos, de forma a aumentar a carga de treino. Assim, o objetivo deste estudo foi, através de técnicas de análise de dados, nomeadamente análise de clusters e modelos lineares de efeitos mistos, comparar diferentes ganhos de elevação e determinar se o ganho de elevação tem efeito na evolução da performance. Para atingir este objetivo, utilizou-se uma base de dados, disponível na internet como GoldenCheetah Open Data, com 2681 atletas, que foram sujeitos a critérios de inclusão e exclusão, resultando num total de 1308 ciclistas. Os critérios de inclusão foram idades entre 10 e 90 anos e mínimo de 20 treinos de ciclismo registados. Os critérios de exclusão foram atletas com valores em falta em todas as atividades registadas ou todos os seus treinos terem observações outliers. Para a análise descritiva, utilizou-se a biblioteca summarytools do software R. Os ciclistas apresentaram média de 42 anos e 32 dos 1308 atletas eram mulheres. Na análise de clusters utilizaram-se as bibliotecas cluster, imputeTS, factoextra e clValid do R para aplicar quatro algoritmos de modo a testar e comparar com medidas de estabilidade. Nesta análise, concluímos que o algoritmo K-means obteve uma melhor performance, pelo que foi o que foi analisado, tendo sido obtidos dois clusters: cluster com grandes ganhos de elevação e cluster com pequenos ganhos de elevação. Testes de significância demonstraram diferenças significativas na idade entre clusters, embora não tenham sido detetadas diferenças na proporção de atletas do sexo feminino. Quanto aos parâmetros de treino, todos demonstraram ser significativamente diferentes entre os dois clusters, incluindo os relativos à produção de potência. Por último, com as bibliotecas rstatix e nlme do software R, aplicou-se um modelo linear de efeitos mistos utilizando todas as variáveis resposta. Contudo, após ter sido detetada uma correlação moderada entre algumas variáveis, com recurso à biblioteca corrplot do R, foi aplicado novo modelo com as variáveis idade, género, número do treino, ganho de elevação, velocidade média e frequência cardíaca média. O último modelo linear de efeitos mistos para a potência média revelou influência negativa significativa do género feminino e influência positiva significativa do ganho de elevação, número do treino, velocidade média, frequência cardíaca média e da interação entre ganho de elevação e número do treino. O modelo linear de efeitos mistos para os picos de potência a 5 e 30 minutos evidenciaram influência negativa significativa da idade e género feminino e influência positiva significativa do ganho de elevação, número do treino, velocidade média, frequência cardíaca média e da interação entre ganho de elevação e número do treino. Foi possível concluir que tanto a análise de clusters como a análise de medidas repetidas foram eficazes no estabelecimento de uma relação entre incluir ganho de elevação nos planos de treino e melhor evolução da performance.Dias, SaraMartins, Maria do RosárioRUNFerreira, Martina Lopes2023-05-03T09:58:29Z2022-012022-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/152349enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:34:41Zoai:run.unl.pt:10362/152349Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:54:52.691548Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model |
title |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model |
spellingShingle |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model Ferreira, Martina Lopes Cycling performance Power output Cluster analysis Repeated measures Linear mixed-effects model Domínio/Área Científica::Ciências Naturais::Matemáticas |
title_short |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model |
title_full |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model |
title_fullStr |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model |
title_full_unstemmed |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model |
title_sort |
Longitudinal Study of Effects of Elevation Training on Cycling Performance: Cluster Analysis and Linear Mixed Effects Model |
author |
Ferreira, Martina Lopes |
author_facet |
Ferreira, Martina Lopes |
author_role |
author |
dc.contributor.none.fl_str_mv |
Dias, Sara Martins, Maria do Rosário RUN |
dc.contributor.author.fl_str_mv |
Ferreira, Martina Lopes |
dc.subject.por.fl_str_mv |
Cycling performance Power output Cluster analysis Repeated measures Linear mixed-effects model Domínio/Área Científica::Ciências Naturais::Matemáticas |
topic |
Cycling performance Power output Cluster analysis Repeated measures Linear mixed-effects model Domínio/Área Científica::Ciências Naturais::Matemáticas |
description |
In cycling, for cyclists to be able to keep track of their evolution, performance can be measured using tests of maximal effort or, when those cannot be performed, parameters obtained on submaximal efforts, such as power output. Usually, training programs with specific elevation gains are prescribed in order to increase training load. With that in mind, the purpose of this study was, through data analysis techniques, namely cluster analysis and linear mixed-effects models, to compare different elevation gain profiles and determine whether they had a significant effect on performance evolution or not. To accomplish that goal, a database, available on the internet with name GoldenCheetah Open Data was utilized. It contained 2681 athletes, to whom inclusion and exclusion criteria were applied, resulting in a final 1308 cyclists included. Inclusion criteria were being 10 to 90 years old and having at least cycling 20 activities recorded. Exclusion criteria were all activities have missing values and all activities had outlier observations. For descriptive analysis, summarytools from R software was used. Cyclists were 42 years old, on average, and, from the 1308 athletes, 32 were women. In cluster analysis, cluster, imputeTS, factoextra and clValid libraries from R were used to apply four clustering algorithms in order to test and compare with stability measures. Through this analysis we concluded K-means algorithm was the one that performed better, which is why it was analyzed, and two clusters were obtained as a result: the cluster with high elevation gains and the cluster with low elevation gains. Significance tests showed a significant difference on age between clusters, but not on the proportion of female gender. As for training parameters, all were significantly different between clusters, including the ones related to power output. At last, with rstatix and nlme libraries from R, a linear mixed-effects model was applied using all response variables. However, after a moderate correlation was found among some variables, using corrplot R library, a new model with age, gender, number of activity, elevation gain, average speed and average heart rate was applied. The last linear mixed-effects model for average power revealed a significant negative influence of female gender and a significant positive influence of elevation gain, number of activity, average speed, average heart rate and the interaction between elevation gain and the number of the activity. The linear mixed-effects model for peak power on both 5 and 30 minute efforts evinced a significant negative influence of both age and female gender and a significant positive influence of elevation gain, number of activity, average speed, average heart rate and the interaction between elevation gain and the number of the activity. It was possible to conclude that both cluster analysis and repeated measures analysis were effective establishing a relationship between including vertical climbing on training programs and better performance improvement. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-01 2022-01-01T00:00:00Z 2023-05-03T09:58:29Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10362/152349 |
url |
http://hdl.handle.net/10362/152349 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799138137246531584 |