基于特征工程和深度学习方法估算体力消耗的模型有效性研究  

Model Validation of Physical Activity Energy Expenditure Based on Feature Engineering and Deep Learning

作　　者：王丕坤 孙倩 刘毅[1] 马宏伟[1] 高永艳 杨东强 WANG Pikun;SUN Qian;LIU Yi;MA Hongwei;GAO Yongyan;YANG Dongqiang(School of Computer Science and Technology,Shandong Jianzhu University,Jinan 250101,Shandong,China;Physical Education Department,Shandong Jianzhu University,Jinan 250101,Shandong,China)

机构地区：[1]山东建筑大学计算机科学与技术学院,山东济南250101 [2]山东建筑大学体育教学部,山东济南250101

出　　处：《上海体育学院学报》2022年第10期52-64,共13页Journal of Shanghai University of Sport

摘　　要：目的探究不同佩戴部位、不同惯性测量装置(IMU)(加速度计和陀螺仪)以及不同机器学习方法对人体走、跑活动能量消耗预测准确性的影响。方法对IMU的原始信号进行预处理并提取多种活动特征,采用交叉验证的方式分别对基于特征工程的机器学习方法和基于深度学习的卷积神经网络方法进行建模。结果在走、跑活动中,对于IMU的不同佩戴部位,踝部模型的性能整体上优于髋部模型;对于不同IMU获取的运动信号,加速度计模型的性能整体上优于陀螺仪模型;对于不同的机器学习模型,基于特征工程的机器学习方法普遍优于基于深度学习的卷积神经网络方法。结论基于多信号融合的人工神经网络模型在不同运动强度下的稳定性和泛化能力均优于其他3种模型,建议使用该模型对走、跑活动的能量消耗进行估算。Objective To investigate the effect of wearing positions,inertial measurement unit(IMU)(accelerometers and gyroscopes),and machine learning methods on the prediction of human energy expenditure in walking and running.Methods The original signal of IMU was preprocessed and a variety of activity features were extracted.The machine learning method based on feature engineering and the convolutional neural network method based on deep learning were modeled by cross-validation.Results In walking and running activities,the performance of ankle model was better than that of hip model for different wearing parts of IMU.For different types of motion signals,the performance of accelerometer model was better than that of gyroscope model.For different machine learning models,machine learning methods based on feature engineering were generally superior to convolutional neural network methods based on deep learning.Conclusion The artificial neural network model based on multi-signal fusion can generalize and stabilize better than the other models under different exercise intensities,which is recommended to estimate energy expenditure for walking and running activities.

关 键 词：体力活动能量消耗 惯性测量装置 加速度计 陀螺仪 机器学习 深度学习 

分 类 号：G804.49[文化科学—运动人体科学]