基于加速度传感器的大学生自行车运动能耗预测模型研究

Forecasting model of college students' bicycle energy consumption based on acceleration sensor

目的:基于三轴加速度传感器,建立大学生自行车运动能量消耗预测方程。方法:选取101名在校大学生,按性别、年龄分成实验组(81人)和验证组(20人)。实验过程中受试者同时佩戴K4b^2气体代谢分析仪和GT3X加速度传感器(脚踝处),在功率自行车上依次进行不同强度(较低强度:37%～45%VO_2max;中等强度:46%～63%VO_2max;较大强度:64%～91%VO_2max)的骑行。采用逐步回归方法建立运动能量消耗预测模型。结果:1)ACz轴和VM轴的counts值与能量消耗存在较高的相关关系(P<0.01)。2)运动能量消耗(kcal/min)=0.000219×VM+0.065×BW+0.145×SE-2.032[VM为加速度传感器合轴counts值,BW为体重(kg),SE为性别(女=0,男=1)];R^2等于0.88,SEE和SEE/Y(%)分别为0.61和11.55%。3)经验证组数据回代检验,各强度水平下模型预测值与K4b^2实测值相关系数在0.82～0.86之间(P<0.01);绝对误差为0.38～0.61 kcal/min,相对误差为8.37%～10.54%;95%的残差均落在Bland-Altman散点图Mean±1.96SD的区间内。结论:自行车运动中,通过脚踝佩戴处加速度传感器合轴counts值、性别、体重三个变量建立的能量消耗预测方程,能够有效地预测不同强度水平下的运动能量消耗,预测精度较高,可为大学生自行车运动科学监测提供依据。

Objective:Based on the triaxial acceleration sensor,the energy consumption prediction equation of college students'bicycle movement is established.Methods:101 undergraduates were selected and divided into experimental group(81 persons)and validation group(20 persons)by gender and age.During the course of the experiment,subjects wear K4b2 gas metabolic analyzer and GT3X acceleration sensor(ankle)at the same time and take different intensity rides in the power of the bicycle(lower strength:37%~65%VO 2max;medium strength:46%~63%VO 2max;greater strength:64%~91%VO 2max);then establish the prediction model of motion energy consumption by using stepwise regression method.Results:1)There was a high correlation between the counts value of ACz axis and VM axis and energy consumption(P<0.01);2)exercise energyconsumption(kcal/min)=0.000219×VM+0.065×BW+0.145×SE-2.032(VM for the acceleration sensor coincidence counts value,BW for the weight(kg),SE for the gender(female=0,male=1));R2 is equal to 0.88,SEE and SEE/Y(%)are 0.61 and 11.55%,respectively.3)Through return test of the data of validation group,we can get that the correlation coefficient between the predicted values and the measured values of K4b2 is between 0.82 and 0.86 at different levels of strength(P<0.01).The absolute error is 0.38-0.61 kcal/min,the relative error is 8.37%-10.54%,and 95%of the residuals fall within the range of Mean±1.96SD of the Bland-Altman scatter plot.Conclusion:In the bicycle movement,through wearing the acceleration sensor in the ankle to accumulate three variables of counts value,gender,weight,and to establish the energy consumption prediction can predict the energy consumption under different intensity levels effectively and can get higher prediction accuracy,which can provide the basis for the scientific monitoring of cycling.