Upper Body Posture Recognition Using Inertial Sensors and Recurrent Neural Networks
Source abstract
Abstract
Inadequate sitting posture can cause imbalanced loading on the spine and result in abnormal spinal pressure, which serves as the main risk factor contributing to irreversible and chronic spinal deformity. Therefore, sitting posture recognition is important for understanding people’s sitting behaviors and for correcting inadequate postures. Recently, wearable devices embedded with microelectromechanical systems (MEMs) sensors, such as inertial measurement units (IMUs), have received increased attention in human activity recognition. In this study, a wearable device embedded with IMUs and a machine learning algorithm were developed to classify seven static sitting postures: upright, slump, lean, right and left bending, and right and left twisting. Four 9-axis IMUs were uniformly distributed between thoracic and lumbar regions (T1-L5) and aligned on a sagittal plane to acquire kinematic information about subjects’ backs during static-dynamic alternating motions. Time-domain features served as inputs to a signal-based classification model that was developed using long short-term memory-based recurrent neural network (LSTM-RNN) architecture, and the model’s classification performance was used to evaluate the relevance between sensor signals and sitting postures. Overall results from performance evaluation tests indicate that this IMU-based measurement and LSTM-RNN structural scheme was appropriate for sitting posture recognition.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ergonomics and Musculoskeletal Disorders · Balance, Gait, and Falls Prevention · Musculoskeletal pain and rehabilitation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical and Computer Engineering, University of California, La Jolla, San Diego, CA 92092, USA
School of Biomedical Engineering, College of Biomedical Engineering, Taipei Medical University, Taipei 11031, Taiwan
Department of Orthopedics, Shuang Ho Hospital, Taipei Medical University, Taipei 23561, Taiwan
Department of Orthopedics Surgery, School of Medicine, College of Medicine, Taipei Medical University, Taipei 23561, Taiwan
Center for Biomedical Engineering, Graduate Institute of Biomedical Engineering, College of Engineering, Chang Gung University, Taoyuan 33302, Taiwan
Bone and Joint Research Center, Department of Orthopedic Surgery, Chang Gung Memorial Hospital Linkou Branch, Taoyuan 33305, Taiwan
Funding
Ministry of Science and Technology of Taiwan
References (43)
Show source-provided references
1. Frost, B.A., Camarero-Espinosa, S., and Foster, E.J. (2019). Materials for the spine: Anatomy, problems, and solutions. Materials, 12.10.3390/ma12020253 ↗
2. Measurement of the Cobb angle on radiographs of patients who have10.2106/00004623-199072030-00002 ↗
3. Reliability assessment of Cobb angle measurements using manual and digital methods10.1016/j.spinee.2010.02.020 ↗
4. Muscles, testing and function
5. Incidence of common postural abnormalities in the cervical, shoulder, and thoracic regions and their association with pain in two age groups of healthy subjects10.1093/ptj/72.6.425 ↗
6. Effect of neck exercise on sitting posture in patients with chronic neck pain10.2522/ptj.20060009 ↗
7. A novel approach to managing graduated return to spinal loading in patients with low back pain using the Spineangel® device: A case series report
8. Using cineradiography for continuous dynamic-motion analysis of the lumbar spine10.1097/00007632-200109010-00008 ↗
9. Foubert, N., McKee, A.M., Goubran, R.A., and Knoefel, F. (2012, January 18–19). Lying and sitting posture recognition and transition detection using a pressure sensor array. Proceedings of the 2012 IEEE International Symposium on Medical Measurements and Applications Proceedings, Budapest, Hungary.10.1109/MeMeA.2012.6226630 ↗
10. Lumbar spine and pelvic posture between standing and sitting: A radiologic investigation including reliability and repeatability of the lumbar lordosis measure10.1016/j.jmpt.2009.11.008 ↗
11. Towards monitoring lumbo-pelvic posture in real-life situations: Concurrent validity of a novel posture monitor and a traditional laboratory-based motion analysis system10.1016/j.math.2011.09.006 ↗
12. Xu, W., Li, Z., Huang, M.-C., Amini, N., and Sarrafzadeh, M. (2011, January 23–25). ecushion: An etextile device for sitting posture monitoring. Proceedings of the 2011 International Conference on Body Sensor Networks, Dallas, TX, USA.10.1109/BSN.2011.24 ↗
13. Relationships between prolonged neck/shoulder pain and sitting spinal posture in male and female adolescents10.1016/j.math.2008.04.004 ↗
14. Wearable smart health advisors: An IMU-enabled posture monitor10.1109/MCE.2019.2956205 ↗
15. Petropoulos, A., Sikeridis, D., and Antonakopoulos, T. (2017, January 3–6). SPoMo: IMU-based real-time sitting posture monitoring. Proceedings of the 2017 IEEE 7th International Conference on Consumer Electronics-Berlin (ICCE-Berlin), Berlin, Germany.10.1109/ICCE-Berlin.2017.8210574 ↗
16. Ma, S., Cho, W.-H., Quan, C.-H., and Lee, S. (2016, January 5–7). A sitting posture recognition system based on 3 axis accelerometer. Proceedings of the 2016 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Chiang Mai, Thailand.10.1109/CIBCB.2016.7758131 ↗
17. Detecting spinal posture change in sitting positions with tri-axial accelerometers10.1016/j.gaitpost.2007.03.001 ↗
18. Sousa Lima, W., Souto, E., El-Khatib, K., Jalali, R., and Gama, J. (2019). Human activity recognition using inertial sensors in a smartphone: An overview. Sensors, 19.10.3390/s19143213 ↗
19. Human activity recognition using inertial, physiological and environmental sensors: A comprehensive survey10.1109/ACCESS.2020.3037715 ↗
20. Human activity recognition with smartphone sensors using deep learning neural networks10.1016/j.eswa.2016.04.032 ↗
21. Attention-based convolutional neural network for weakly labeled human activities’ recognition with wearable sensors10.1109/JSEN.2019.2917225 ↗
22. Santos, G.L., Endo, P.T., Monteiro, K.H.d.C., Rocha, E.d.S., Silva, I., and Lynn, T. (2019). Accelerometer-based human fall detection using convolutional neural networks. Sensors, 19.10.3390/s19071644 ↗
23. Sequential human activity recognition based on deep convolutional network and extreme learning machine using wearable sensors10.1155/2018/8580959 ↗
24. Pienaar, S.W., and Malekian, R. (2019, January 18–20). Human activity recognition using LSTM-RNN deep neural network architecture. Proceedings of the 2019 IEEE 2nd wireless africa conference (WAC), Pretoria, South Africa.10.1109/AFRICA.2019.8843403 ↗
25. Steven Eyobu, O., and Han, D.S. (2018). Feature representation and data augmentation for human activity classification based on wearable IMU sensor data using a deep LSTM neural network. Sensors, 18.10.3390/s18092892 ↗
26. Ordóñez, F.J., and Roggen, D. (2016). Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors, 16.10.3390/s16010115 ↗
27. Deep recurrent neural network for mobile human activity recognition with high throughput10.1007/s10015-017-0422-x ↗
28. Murad, A., and Pyun, J.-Y. (2017). Deep recurrent neural networks for human activity recognition. Sensors, 17.10.3390/s17112556 ↗
29. Training unsupported sitting does not improve ability to sit in people with recently acquired paraplegia: A randomised trial10.1016/S1836-9553(11)70018-2 ↗
30. Severin, I.-C. (2020, January 29–30). Head Posture monitor based on 3 IMU sensors: Consideration toward Healthcare application. Proceedings of the 2020 International Conference on e-Health and Bioengineering (EHB), Iasi, Romania.10.1109/EHB50910.2020.9280106 ↗
31. Segmentation and recognition of human motion sequences using wearable inertial sensors10.1007/s11042-017-5573-1 ↗
32. Zimmermann, T., Taetz, B., and Bleser, G. (2018). IMU-to-segment assignment and orientation alignment for the lower body using deep learning. Sensors, 18.10.3390/s18010302 ↗
33. Brugarolas, R., Roberts, D., Sherman, B., and Bozkurt, A. (September, January 28). Posture estimation for a canine machine interface based training system. Proceedings of the 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, CA, USA.10.1109/EMBC.2012.6346964 ↗
34. A CNN-LSTM neural network for recognition of puffing in smoking episodes using wearable sensors10.1007/s13534-020-00147-8 ↗
35. Harmonic loss function for sensor-based human activity recognition based on LSTM recurrent neural networks10.1109/ACCESS.2020.3003162 ↗
36. Human activity recognition and classification using of convolutional neural networks and recurrent neural networks10.18100/ijamec.803105 ↗
37. Learning long-term dependencies with recurrent neural networks10.1016/j.neucom.2007.12.036 ↗
38. Zheng, J., Xu, C., Zhang, Z., and Li, X. (2017, January 22–24). Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network. Proceedings of the 2017 51st Annual Conference on Information Sciences and Systems (CISS), Baltimore, MD, USA.
39. Zhao, R., Wang, J., Yan, R., and Mao, K. (2016, January 11–13). Machine health monitoring with LSTM networks. Proceedings of the 2016 10th international conference on sensing technology (ICST), Nanjing, China.10.1109/ICSensT.2016.7796266 ↗
40. Recognition of human hand activities based on a single wrist imu using recurrent neural networks
41. The instant axis of rotation influences facet forces at L5/S1 during flexion/extension and lateral bending10.1007/s00586-005-0935-1 ↗
42. Beil, J., Ehrenberger, I., Scherer, C., Mandery, C., and Asfour, T. (2018, January 1–5). Human Motion Classification Based on Multi-Modal Sensor Data for Lower Limb Exoskeletons. Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.10.1109/IROS.2018.8594110 ↗
43. “Non-invasive hydration level estimation in human body using galvanic skin response10.1109/JSEN.2020.2965892 ↗