A Novel Method for Assessing Cycling Movement Status: an Exploratory Study Integrating Deep Learning and Signal Processing Technologies

Overview

Journal BMC Med Inform Decis Mak

Publisher Biomed Central

Specialty Medical Informatics

Date 2025 Feb 11

PMID 39934805

Authors

Yingchun He

Yi-Haw Jan

Fan Yang

Yunru Ma

Chun Pei

Affiliations

Soon will be listed here.

Abstract

This study proposes a deep learning-based motion assessment method that integrates the pose estimation algorithm (Keypoint RCNN) with signal processing techniques, demonstrating its reliability and effectiveness.The reliability and validity of this method were also verified.Twenty college students were recruited to pedal a stationary bike. Inertial sensors and a smartphone simultaneously recorded the participants' cycling movement. Keypoint RCNN(KR) algorithm was used to acquire 2D coordinates of the participants' skeletal keypoints from the recorded movement video. Spearman's rank correlation analysis, intraclass correlation coefficient (ICC), error analysis, and t-test were conducted to compare the consistency of data obtained from the two movement capture systems, including the peak frequency of acceleration, transition time point between movement statuses, and the complexity index average (CIA) of the movement status based on multiscale entropy analysis.The KR algorithm showed excellent consistency (ICC=0.988) between the two methods when estimating the peak acceleration frequency. Both peak acceleration frequencies and CIA metrics estimated by the two methods displayed a strong correlation (r > 0.70) and good agreement (ICC>0.750). Additionally, error values were relatively low (MAE = 0.001 and 0.040, MRE = 0.00% and 7.67%). Results of t-tests showed significant differences (p = 0.003 and 0.030) for various acceleration CIAs, indicating our method could distinguish different movement statuses.The KR algorithm also demonstrated excellent intra-session reliability (ICC = 0.988). Acceleration frequency analysis metrics derived from the KR method can accurately identify transitions among movement statuses. Leveraging the KR algorithm and signal processing techniques, the proposed method is designed for individualized motor function evaluation in home or community-based settings.

References

Huo C, Zheng Y, Lu W, Zhang T, Wang D, Xu D . Prospects for intelligent rehabilitation techniques to treat motor dysfunction. Neural Regen Res. 2020; 16(2):264-269. PMC: 7896219. DOI: 10.4103/1673-5374.290884. View

Zhao J, She J, Fukushima E, Wang D, Wu M, Pan K . Muscle Fatigue Analysis With Optimized Complementary Ensemble Empirical Mode Decomposition and Multi-Scale Envelope Spectral Entropy. Front Neurorobot. 2020; 14:566172. PMC: 7674835. DOI: 10.3389/fnbot.2020.566172. View

Bini R, Serrancoli G, Pereira Santiago P, Pinto A, Moura F . Validity of Neural Networks to Determine Body Position on the Bicycle. Res Q Exerc Sport. 2022; 94(4):905-912. DOI: 10.1080/02701367.2022.2070103. View

He K, Gkioxari G, Dollar P, Girshick R . Mask R-CNN. IEEE Trans Pattern Anal Mach Intell. 2018; 42(2):386-397. DOI: 10.1109/TPAMI.2018.2844175. View

Pfister A, West A, Bronner S, Noah J . Comparative abilities of Microsoft Kinect and Vicon 3D motion capture for gait analysis. J Med Eng Technol. 2014; 38(5):274-80. DOI: 10.3109/03091902.2014.909540. View

Yamamoto M, Shimatani K, Hasegawa M, Kurita Y, Ishige Y, Takemura H . Accuracy of Temporo-Spatial and Lower Limb Joint Kinematics Parameters Using OpenPose for Various Gait Patterns With Orthosis. IEEE Trans Neural Syst Rehabil Eng. 2021; 29:2666-2675. DOI: 10.1109/TNSRE.2021.3135879. View

Marotta L, Scheltinga B, van Middelaar R, Bramer W, van Beijnum B, Reenalda J . Accelerometer-Based Identification of Fatigue in the Lower Limbs during Cyclical Physical Exercise: A Systematic Review. Sensors (Basel). 2022; 22(8). PMC: 9025833. DOI: 10.3390/s22083008. View

Pincus S . Approximate entropy as a measure of system complexity. Proc Natl Acad Sci U S A. 1991; 88(6):2297-301. PMC: 51218. DOI: 10.1073/pnas.88.6.2297. View

Takeda I, Yamada A, Onodera H . Artificial Intelligence-Assisted motion capture for medical applications: a comparative study between markerless and passive marker motion capture. Comput Methods Biomech Biomed Engin. 2020; 24(8):864-873. DOI: 10.1080/10255842.2020.1856372. View

10.

Schober P, Boer C, Schwarte L . Correlation Coefficients: Appropriate Use and Interpretation. Anesth Analg. 2018; 126(5):1763-1768. DOI: 10.1213/ANE.0000000000002864. View

11.

Inturi A, Manikandan V, Kumar M, Wang S, Zhang Y . Synergistic Integration of Skeletal Kinematic Features for Vision-Based Fall Detection. Sensors (Basel). 2023; 23(14). PMC: 10385725. DOI: 10.3390/s23146283. View

12.

Cao Z, Hidalgo G, Simon T, Wei S, Sheikh Y . OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields. IEEE Trans Pattern Anal Mach Intell. 2019; 43(1):172-186. DOI: 10.1109/TPAMI.2019.2929257. View

13.

Koo T, Li M . A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research. J Chiropr Med. 2016; 15(2):155-63. PMC: 4913118. DOI: 10.1016/j.jcm.2016.02.012. View

14.

Sato K, Nagashima Y, Mano T, Iwata A, Toda T . Quantifying normal and parkinsonian gait features from home movies: Practical application of a deep learning-based 2D pose estimator. PLoS One. 2019; 14(11):e0223549. PMC: 6855634. DOI: 10.1371/journal.pone.0223549. View

15.

Bini R, Serrancoli G, Pereira Santiago P, Pinto A, Moura F . Criterion validity of neural networks to assess lower limb motion during cycling. J Sports Sci. 2023; 41(1):36-44. DOI: 10.1080/02640414.2023.2194725. View

16.

Duarte M, Sternad D . Complexity of human postural control in young and older adults during prolonged standing. Exp Brain Res. 2008; 191(3):265-76. DOI: 10.1007/s00221-008-1521-7. View

17.

Richman J, Moorman J . Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol Heart Circ Physiol. 2000; 278(6):H2039-49. DOI: 10.1152/ajpheart.2000.278.6.H2039. View

18.

Washabaugh E, Shanmugam T, Ranganathan R, Krishnan C . Comparing the accuracy of open-source pose estimation methods for measuring gait kinematics. Gait Posture. 2022; 97:188-195. DOI: 10.1016/j.gaitpost.2022.08.008. View

19.

Lu L, Tan Y, Klaic M, Galea M, Khan F, Oliver A . Evaluating Rehabilitation Progress Using Motion Features Identified by Machine Learning. IEEE Trans Biomed Eng. 2020; 68(4):1417-1428. DOI: 10.1109/TBME.2020.3036095. View

20.

Liao Y, Vakanski A, Xian M . A Deep Learning Framework for Assessing Physical Rehabilitation Exercises. IEEE Trans Neural Syst Rehabil Eng. 2020; 28(2):468-477. PMC: 7032994. DOI: 10.1109/TNSRE.2020.2966249. View