Accurate and efficient estimation of caloric expenditure during daily activities is desirable in tracking personal activity and health. Kinetic energy harvesting (KEH) has created an opportunity for wearable devices with limited battery power to realize long-term human health monitoring. We postulate to utilize KEH device for calorie estimation instead of accelerometer considering that the kinetic energy is produced when the user expends some calories by doing the bodily movement. In this paper, we propose to use the output voltage of KEH for activity intensity classification and develop activity-specific regression models combined with anthropometric characteristics for caloric expenditure estimation by random forest. To validate our approach, we build a KEH hardware platform and collect the dataset of seven different activities in free-living conditions from ten participants. Experiment results show that our approach achieves an accuracy of 95. 7% to classify intensity of activity and yields a $R^2$ coefficient of 0.93 for regression model and a root mean square error (RMSE) of 1.09 kcal/min to estimate calorie expenditure by only using the output voltage of KEH. The comparison experiments validate the effectiveness of KEH device for caloric expenditure estimation act as a substitute for accelerometer in terms of estimation accuracy and energy saving.

在跟踪个人活动和健康时，需要在日常活动中准确有效地估算热量消耗。动能收集（KEH）为电池电量有限的可穿戴设备创造了实现长期人体健康监测的机会。考虑到当用户通过身体运动消耗一些卡路里时会产生动能，因此我们假设将KEH装置用于卡路里估算，而不是加速度计。在本文中，我们建议使用KEH的输出电压进行活动强度分类，并开发结合人类活动特征的特定活动回归模型，以估算随机森林的热量支出。为了验证我们的方法，我们建立了KEH硬件平台，并从十个参与者那里收集了七种不同活动的数据集。实验结果表明，我们的方法对活动强度进行分类可达到95. 7％的准确度，并产生${\mathrm{[R}}^2$回归模型的系数为0.93，均方根误差（RMSE）为1.09 kcal / min，仅通过使用KEH的输出电压即可估算卡路里消耗。比较实验验证了KEH装置在热量支出估算方面的有效性，在估算精度和节能方面可以替代加速度计。