Wearable sensors show great potential for exercise energy management. This paper addresses the issues of insufficient sample data and low estimation accuracy in existing studies. First, an exercise training monitoring system with real-time capabilities is implemented utilizing multi-modal wearable sensors, and the monitoring data are preprocessed to remove redundant features by the regression coefficient method. The preprocessed data are augmented in light of an enhanced generative adversarial network to expand the sample data. Then an improved residual neural network model is proposed to reduce the computational complexity by decomposition convolution and group regularization, and finally the motion energy estimation results are obtained by softmax. Simulation results indicate that the measurement error of the proposed method is within 8% for each physiological index, and the accuracy of energy consumption estimation is 92.71%, which significantly improves the management effect of exercise energy consumption.
Mielgo AyusoJMaroto SanchezBLuzardo SocorroR, et al.Evaluation of nutritional status and energy expenditure in athletes. Nutr Hosp2015; 31: 227–236.
2.
YangCMingH. Detection of sports energy consumption based on IoTs and cloud computing. Sustain Energy Technol Assessments2021; 46: 12–24.
3.
QiuYLiuGMuthuBA, et al.Design of an energy‐efficient IoT device with optimized data management in sports person health monitoring application. Trans Emerging Tel Tech2022; 33: 42–58.
4.
StaudenmayerJPoberDCrouterS, et al.An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer. J Appl Physiol2009; 107: 1300–1307.
5.
NathanDHuynhDQRubensonJ, et al.Estimating physical activity energy expenditure with the Kinect sensor in an exergaming environment. PLoS One2015; 10: 27–34.
6.
SladePKochenderferMJDelpSL, et al.Sensing leg movement enhances wearable monitoring of energy expenditure. Nat Commun2021; 12: 43–61.
7.
O’DriscollRTuricchiJHopkinsM, et al.Improving energy expenditure estimates from wearable devices: a machine learning approach. J Sports Sci2020; 38: 1496–1505.
8.
WangS. Sports training monitoring of energy-saving IoT wearable devices based on energy harvesting. Sustain Energy Technol Assessments2021; 45: 17–34.
9.
PreatoniENodariSLopomoNF. Supervised machine learning applied to wearable sensor data can accurately classify functional fitness exercises within a continuous workout. Front Bioeng Biotechnol2020; 8: 36–47.
10.
VyasNFarringdonJAndreD, et al.Machine learning and sensor fusion for estimating continuous energy expenditure. AI Mag2012; 33: 55.
11.
Sadat-MohammadiMShakerianSLiuY, et al.Non-invasive physical demand assessment using wearable respiration sensor and random forest classifier. J Build Eng2021; 44: 13–36.
12.
SazonovEHegdeNBrowningRC, et al.Posture and activity recognition and energy expenditure estimation in a wearable platform. IEEE J Biomed Health Inform2015; 19: 1339–1346.
13.
EomHRohJHariyaniYS, et al.Deep learning-based optimal smart shoes sensor selection for energy expenditure and heart rate estimation. Sensors2021; 21: 58–72.
14.
YanYChenQ. Energy expenditure estimation of tabata by combining acceleration and heart rate. Front Public Health2022; 9: 44–50.
15.
LopesJMFigueiredoJFonsecaP, et al.Deep learning-based energy expenditure estimation in assisted and non-assisted gait using inertial, EMG, and heart rate wearable sensors. Sensors2022; 22: 79–82.
16.
ParaschiakosSDe SaCROkaiJ, et al.A recurrent neural network architecture to model physical activity energy expenditure in older people. Data Min Knowl Discov2022; 36: 477–512.
17.
AlghamdiWY. A novel deep learning method for predicting athletes’ health using wearable sensors and recurrent neural networks. Decision Analytics Journal2023; 7: 21–36.
18.
LiDShenCDaiX, et al.Research on data fusion of adaptive weighted multi-source sensor. Comput Mater Continua (CMC)2019; 61: 1217–1231.
19.
VonderHLElviraTOchoaO. An analysis of explainability methods for convolutional neural networks. Eng Appl Artif Intell2023; 117: 56–73.
20.
LiuMShiJLiZ, et al.Towards better analysis of deep convolutional neural networks. IEEE Trans Vis Comput Graph2016; 23: 91–100.
21.
FangWYuZChenY, et al.Deep residual learning in spiking neural networks. Adv Neural Inf Process Syst2021; 34: 21056–21069.
22.
ChengZQuAHeX. Contour-aware semantic segmentation network with spatial attention mechanism for medical image. Vis Comput2022; 38: 749–762.
23.
MiJMaCZhengL, et al.WGAN-CL: a wasserstein GAN with confidence loss for small-sample augmentation. Expert Syst Appl2023; 233: 12–25.
24.
FengJSimonN. Gradient-based regularization parameter selection for problems with nonsmooth penalty functions. J Comput Graph Stat2018; 27: 426–435.
25.
MoradiRBerangiRMinaeiB. A survey of regularization strategies for deep models. Artif Intell Rev2020; 53: 3947–3986.
26.
HarindranathAAroraM. Effect of sensor noise characteristics and calibration errors on the choice of IMU-sensor fusion algorithms. Sensor Actuator Phys2024; 379: 42–53.
