Currently, 35.2% of mothers suffer from hand and wrist pain after giving birth. Their physical problems are often related to the posture in which they carry their baby. Therefore, correct posture when carrying the baby is important to avoid postpartum physical problems such as tendonitis. However, determining the infant-carrying posture requires feedback from an expert, (e.g., a midwife), and is time-consuming. To overcome this problem, an infant-carrying posture determination (ICPD) method is proposed using an RGB camera and the BlazePose pose estimation model. With the ICPD method, a person carrying an infant can easily determine the quality of their posture when carrying an infant. To achieve a more accurate determination, the ICPD method normalizes the infant-carrying posture and selects features based on the area under the receiver operating characteristic curve, which is a widely used performance measure in classification models. The postures of 28 mothers while carrying infants was experimentally determined to validate the proposed system. The experimental results confirmed that ICPD was more accurate on the test dataset than conventional methods, both with and without feature selection.

1. [1] H. D. Skoff, ““Postpartum/newborn” de Quervain’s tenosynovitis of the wrist,” American J. of Orthopedics, Vol.30, No.5, pp. 428-430, 2001.
2. [2] T. Satoh, L. R. H. Cadillo, A. Nakagawa, A. Sakakibara, and K. Ohasi, “Hand and wrist pain and its related factors in postpartum women,” J. of Japan Academy of Midwifery, Vol.31, No.1, pp. 63-70, 2017. https://doi.org/10.3418/jjam.31.63
3. [3] F. Wuytack, E. Curtis, and C. Begley, “The health-seeking behaviours of first-time mothers with persistent pelvic girdle pain after childbirth in Ireland: A descriptive qualitative study,” Midwifery, Vol.31, No.11, pp. 1104-1109, 2015. https://doi.org/10.1016/j.midw.2015.07.009
4. [4] C.-L. Dennis and L. Chung-Lee, “Postpartum Depression Help-Seeking Barriers and Maternal Treatment Preferences: A Qualitative Systematic Review,” Birth, Vol.33, No.4, pp. 323-331, 2006. https://doi.org/10.1111/j.1523-536x.2006.00130.x
5. [5] T. Satoh, L. R. H. Cadillo, K. Ohashi, and T. Onishi, “Self-assessed hand and wrist pain and quality of life for postpartum mothers in Japan,” British J. of Midwifery, Vol.30, No.8, pp. 467-475, 2022. https://doi.org/10.12968/bjom.2022.30.8.467
6. [6] V. Bazarevsky and I. Grishchenko. “On-Device, Real-Time Body Pose Tracking with MediaPipe BlazePose.” https://ai.googleblog.com/2020/08/on-device-real-time-body-pose-tracking.html [Accessed October 1, 2024]
7. [7] C. Cortes and M. Mohri, “AUC Optimization vs. Error Rate Minimization,” S. Thrun, L. Saul, and B. Schölkopf (Eds.), “Advances in Neural Information Processing Systems,” Vol.16, pp. 313-320. MIT Press, 2003.
8. [8] C. X. Ling, J. Huang, and H. Zhang, “AUC: A better measure than accuracy in comparing learning algorithms,” Advances in Artificial Intelligence, pp. 329-341, 2003. https://doi.org/10.1007/3-540-44886-1_25
9. [9] L. Yan, R. H. Dodier, M. Mozer, and R. H. Wolniewicz, “Optimizing Classifier Performance via an Approximation to the Wilcoxon-Mann-Whitney Statistic,” Proc. of the Twentieth Int. Conf. on Machine Learning, pp. 848-855. AAAI Press, 2003.
10. [10] V. M. Conroy, B. N. Murray, Q. T. Alexopulos, and J. McCreary, “Kendall’s Muscles: Testing and Function with Posture and Pain,” Wolters Kluwer Health, 6 edition, 2023.
11. [11] T. Hastie, R. Tibshirani, and J. Friedman, “The Elements of Statistical Learning,” Springer, 2 edition, 2009.
12. [12] “MediaPipe Solutions guide.” https://ai.google.dev/edge/mediapipe/solutions/guide [Accessed October 1, 2024]
13. [13] J. F. Soechting and B. Ross, “Psychophysical determination of coordinate representation of human arm orientation,” Neuroscience, Vol.13, No.2, pp. 595-604, 1984. https://doi.org/10.1016/0306-4522(84)90252-5
14. [14] J. Soechting, F. Lacquaniti, and C. Terzuolo, “Coordination of arm movements in three-dimensional space. Sensorimotor mapping during drawing movement,” Neuroscience, Vol.17, No.2, pp. 295-311, 1986. https://doi.org/10.1016/0306-4522(86)90248-4
15. [15] N. A. Borghese, L. Bianchi, and F. Lacquaniti, “Kinematic determinants of human locomotion,” J. of Physiology, Vol.494, No.3, pp. 863-879, 1996. https://doi.org/10.1113/jphysiol.1996.sp021539
16. [16] F. Wilcoxon, “Individual Comparisons by Ranking Methods,” Biometrics Bulletin, Vol.1, No.6, pp. 80-83, 1945. https://doi.org/10.2307/3001968
17. [17] “Scikit-learn webpage.” https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html [Accessed October 1, 2024]
18. [18] Y. S. Ambarwati and S. Uyun, “Feature Selection on Magelang Duck Egg Candling Image Using Variance Threshold Method,” 2020 3rd Int. Seminar on Research of Information Technology and Intelligent Systems (ISRITI), pp. 694-699, 2020. https://doi.org/10.1109/ISRITI51436.2020.9315486
19. [19] D. Kong, C. Ding, H. Huang, and H. Zhao, “Multi-label ReliefF and F-statistic feature selections for image annotation,” 2012 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2352-2359, 2020. https://doi.org/10.1109/CVPR.2012.6247947
20. [20] P. A. Estevez, M. Tesmer, C. A. Perez, and J. M. Zurada, “Normalized mutual information feature selection,” IEEE Trans. on Neural Networks, Vol.20, No.2, pp. 189-201, 2009. https://doi.org/10.1109/TNN.2008.2005601
21. [21] A. Altmann, L. Toloşi, O. Sander, and T. Lengauer, “Permutation importance: a corrected feature importance measure,” Bioinformatics, Vol.26, pp. 1340-1347, 2010. https://doi.org/10.1093/bioinformatics/btq134
22. [22] F. G. Blanchet, P. Legendre, and D. Borcard, “Forward selection of explanatory variables,” Ecology, Vol.89, No.9, pp. 2623-2632, 2008. https://doi.org/10.1890/07-0986.1