国内大学生关于心肺耐力室外估测还有待于进一步研究，采用文献资料研究、实验、数理统计和计算机编程等方法，随机选择80名大学生（男、女各40人，年龄19～23岁），以实验室跑台心肺代谢仪直接测试作为研究标准，参考国外经典1 mi跑测试方程，利用 Neu‐roph Studio构建BP人工神经网络最大摄氧量估测模型。研究结果显示，BP人工神经网络输入变量确定为年龄、性别、体重、1600 m跑时间和跑后即刻心率，三层网络层级结构具体为5‐9‐1，通过2．198万次反复训练及验证，将模型输出的错误率控制在0．001，进一步统计分析模型估测与实验室测试值的相关系数 r为0．923，P＜0．01，对两个样本进行 t检验，t＝0．06，P＞0．05，显示没有显著性差异。可见，采用BP人工神经网络进行最大摄氧量估测具有快速、有效、精确等特点。%Domestic Students cardiorespiratory endurance outdoor estimation method needs fur‐ther study ,this paper ,using the literature review ,experiment ,mathematical statistics and com‐puter programming method ,randomly selected 80 college students (40 male and 40 female , aged 19~ 23 years old ) ,taking laboratory testing as a research standard ,with reference to foreign classical equation 1 mile run test ,use NeurophStudio builds BP artificial neural network model to estimate maximal oxygen uptake .The results showed that BP artificial neural network input variable to be age ,gender ,weight ,1600‐meter run time and heart rate ,the three‐tier network hierarchy 5‐9‐1 specifically by 21980 times repeated training and validation the error rate in the output of the model control thousandth correlation coefficient r further statistical model to estimate the value of laboratory testing and is 0 .923 ,P< 0 .01 ,two sample T‐test , t=0 .06 ,P>0 .05 ,There were no significant differences in the display ,showing the use of BP artificial neural network to estimate maximal oxygen uptake is fast ,efficient ,accurate .
展开▼
