Roveri Maria Isabel, Manoel Edison de Jesus, Onodera Andrea Naomi, Ortega Neli R S, Tessutti Vitor Daniel, Vilela Emerson, Evêncio Nelson, Sacco Isabel C N
University of São Paulo, School of Medicine, Physical Therapy, Speech and Occupational Therapy dept., São Paulo, SP, Brazil.
Study Group in Action Development and Motor Intervention, School of Physical Education and Sport, University of São Paulo, São Paulo, SP, Brazil.
PLoS One. 2017 Aug 17;12(8):e0183389. doi: 10.1371/journal.pone.0183389. eCollection 2017.
The judgement of skill experience and its levels is ambiguous though it is crucial for decision-making in sport sciences studies. We developed a fuzzy decision support system to classify experience of non-elite distance runners. Two Mamdani subsystems were developed based on expert running coaches' knowledge. In the first subsystem, the linguistic variables of training frequency and volume were combined and the output defined the quality of running practice. The second subsystem yielded the level of running experience from the combination of the first subsystem output with the number of competitions and practice time. The model results were highly consistent with the judgment of three expert running coaches (r>0.88, p<0.001) and also with five other expert running coaches (r>0.86, p<0.001). From the expert's knowledge and the fuzzy model, running experience is beyond the so-called "10-year rule" and depends not only on practice time, but on the quality of practice (training volume and frequency) and participation in competitions. The fuzzy rule-based model was very reliable, valid, deals with the marked ambiguities inherent in the judgment of experience and has potential applications in research, sports training, and clinical settings.
技能经验及其水平的判断虽然在体育科学研究的决策中至关重要，但却模糊不清。我们开发了一个模糊决策支持系统来对非精英长跑运动员的经验进行分类。基于专业跑步教练的知识，开发了两个Mamdani子系统。在第一个子系统中，将训练频率和训练量的语言变量进行组合，其输出定义了跑步训练的质量。第二个子系统通过将第一个子系统的输出与比赛次数和训练时间相结合，得出跑步经验水平。模型结果与三位专业跑步教练的判断高度一致（r>0.88，p<0.001），也与其他五位专业跑步教练的判断高度一致（r>0.86，p<0.001）。从专家知识和模糊模型来看，跑步经验超出了所谓的“十年规则”，不仅取决于训练时间，还取决于训练质量（训练量和频率）以及比赛参与情况。基于模糊规则的模型非常可靠、有效，能够处理经验判断中固有的明显模糊性，并且在研究、运动训练和临床环境中具有潜在应用价值。
