Giyilebilir Minyatür Atalet ve Manyetik Sensörler (MIMU) Vasıtasıyla Alt Ekstremite Aktivitelerinin Makine Öğrenmesi Algoritmaları İle Sınıflandırılması

Year 2021, , 123 - 134, 31.12.2021

Beyda Taşar

https://doi.org/10.53433/yyufbed.931553

Abstract

Bu çalışmada, giyilebilir minyatür atalet sensör kullanılarak insan alt ekstremite aktivitelerinin sınıflandırılması çalışması gerçekleştirilmiştir. Çalışmada kullanılan atalet sensörü dokuz serbestlik dereceli olup bünyesinde üç eksenli bir jiroskop, üç eksenli bir ivmeölçer ve üç eksenli bir manyetometre barındırmaktadır. Gönüllü kişinin sağ ayak bileğine giydiği takılan bir adet atalet sensör vasıtasıyla kişin yürüme, koşma, merdiven çıkma, oturma hareketleri esnasında hareket verileri toplanmış ve kaydedilmiştir. İlk olarak kaydedilen bu üç sensör verisi sentezlenerek bacağın hareket esnasındaki kinematik yönelim açıları (yunuslama, yuvarlama, yalpa) hesaplanmıştır. Sonrasında bu yönelim açılarına ait iki adet özellik (enerji ve maksimum değer) matrisi hesaplanmıştır. Hesaplanan bu özellik matrisleri hareket sınıflandırma algoritmalarına girdi olarak verilmiştir. Çalışma kapsamında dört adet hareket sınıflandırma algoritması kullanılmıştır. Bunlar karar ağacı, k-en yakın komşu, destek vektör makinası ve rastgele orman sınıflandırma algoritmalarıdır. Tüm alt ekstremite hareket tiplerinde en yüksek sınıflandırma başarısı en yakın komşu sınıflandırıcısı ile elde edilmiş olup yürüme, koşma, oturma, merdiven çıkma hareketleri için sırası ile hareket sınıflandırma doğruluğu %83.3, %100, % 83.3ve %91.6’dir.

Keywords

MIMU, Alt ekstremite aktivitelerinin sınıflandırılması, Makina öğrenmesi

Classification of Lower Extremity Activities by Machine Learning Algorithms by Wearable Miniature Inertia and Magnetic Sensors (MIMU)

Abstract

In this study, a classification study of human lower extremity activities was carried out using a wearable miniature inertial sensor. The inertial sensor used in the study has nine degrees of freedom and includes a three-axis gyroscope, a three-axis accelerometer and a three-axis magnetometer. Movement data were collected and recorded during the walking, running, climbing stairs and sitting movements of the volunteer by means of an inertial sensor worn on the right ankle of the volunteer. Firstly, these three recorded sensor data were synthesized and the kinematic orientation angles (pitch, roll, yaw) of the leg during the movement were calculated. Then, two property (energy and maximum value) matrices of these orientation angles were calculated. These calculated feature matrices are given as input to motion classification algorithms. Within the scope of the study, four motion classification algorithms were used. These are decision tree, k-nearest neighbor, support vector machine and random forest classification algorithms. The highest classification success in all lower extremity motion types was obtained with the nearest neighbor classifier, and the motion classification accuracy was 83.3%, 100%, 83.3%, and 91.6% for walking, running, sitting, and climbing stairs, respectively.

Keywords

MIMU, Classification of lower extremity activities, Machine Learning

References

• Aggarwal, J. K., & Cai, Q., (1999), Human motion analysis: a Review, Computer Vision Image Understanding, 73(3), 428–440, doi:10.1006/cviu.1998.0744.
• Allen, F. R., Ambikairajah, E., Lovell, N. H., & Celler, B. G., (2006), Classification of a known sequence of motions and postures from accelerometry data using adapted Gaussian mixture models, Physiological Measurement, 27(10), 935–951, doi:10.1088/0967-3334/27/10/001.
• Altun, K., Barshan, B., & Tunçel, O., (2010), Comparative study on classifying human activities with miniature inertial and magnetic sensors'', Pattern Recognition, 43(10), 3605-3620,doi: DOI:10.1016/j.patcog.2010.04.019.
• Altun, K., & Barshan, B., (2010, Agustos), Human activity recognition using inertial/magnetic sensor units, First International Workshop on Human Behavior Understanding, Istanbul, Turkey.
• Aminian, K., Robert, P., Buchser, E. E., Rutschmann, B., Hayoz, D., & Depairon, M., (1999), Physical activity monitoring based on accelerometry: validation and comparison with video observation, Medical & Biological Engineering & Computing, 37(1), 304–308, doi: 10.1007/BF02513304.
• Ang, W. T., Khosla, P. K., & Riviere, C. N., (2003), Design of all-accelerometer inertial measurement unit for tremor sensing in hand-held microsurgical instrument, IEEE International Conference on Robotics and Automation, The Grand Hotel, Taipei, Taiwan.
• Aristidou A. and Lasenby, J., (2013), “Real-time marker prediction and CoR estimation in optical motion capture,” The Visual Computer, 29(1), 7-26.
• Audigie´, F., Pourcelot, P., Degueurce, C., Geiger, D., & Denoix, J. M., (2002), Fourier analysis of trunk displacements: a method to identify the lame limb in trotting horses, Journal of Biomechanics, 35(9), 1173–1182, doi: 10.1016/s0021-9290(02)00089-1.
• Aylward, R., & Paradiso, J. A., (2006, June), Sensemble: a wireless, compact, multi-user sensor system for interactive dance, in: Proceedings of the Conference on New Interfaces for Musical Expression, Paris, France.
• Bao, L., & Intille, S. S., (2004), Activity recognition from user-annotated acceleration data, in Ferscha A, Mattern F (Eds.), Pervasive Computing, New York, USA, Springer-Verlag Berlin Heidelberg Press, (pp. 1-17).
• Barshan, B., & Durrant-Whyte, H. F., (1995), Inertial navigation systems for mobile robots, IEEE Trans. Robotics Automation, 11(3), 328–342, doi: 0.1109/70.388775.
• Barshan, B., & Durrant-Whyte, H. F., 1995, Evaluation of a solid-state gyroscope for robotics applications, IEEE Transaction Instrumentation Measurement, 44(1), 61–67, doi: 10.1109/19.368102.
• Barshan, B. and Yurtman, A., (2020), Classifying daily and sports activities invariantly to the positioning of wearable motion sensor units, IEEE Internet Things J.,7,4801-4815.
• Barshan, B., & Yüksek, M. C., (2014), Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units, The Computer Journal, 57(11), 649-1667, doi: 10.1093/comjnl/bxt075.
• Blank, P.; Hoßbach, J.; Schuldhaus, D.; Eskofier, B.M., (2015), Sensor-based stroke detection and stroke type classification in table tennis. In Proceedings of the 2015 ACM International Symposium on Wearable Computers, Osaka, Japan, 7–11 September 2015; pp. 93–100.
• Bussmann, J. B., Reuvekamp, P. J., Veltink, P. H., Martens, W. L., & Stam, H. J., (1998), Validity and reliability of measurements obtained with an ‘activity monitor in people with and without transtibial amputation, Physical Therapy, 78(9), 989–998, doi: 10.1093/ptj/78.9.989 .
• Chen, Y.L. Yang, I.J Fu, LC., Lai, JS, Liang HW. and Lu L, (2021), IMU-based Estimation of Lower Limb Motion Trajectory with Graph Convolution Network, IEEE Sensors, DOI 10.1109/JSEN.2021.3115105, IEEE Sensors
• Dias, J., Vinzec, M., Corke, P., & Lobo, J., (2007), Special issue:2nd Workshop on Integration of Vision and Inertial Sensors , The International Journal of Robotics Research, 26(6), 515-517, doi: 10.1177/0278364907079903.
• Ermes, M., Parkkaa, J., Mantyjarvi, J., & Korhonen, I., (2008), Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions, IEEE Transactions on Information Technology, 12(1), 20–26, doi: 10.1109/TITB.2007.899496.
• Foerster, F., Smeja, M., & Fahrenberg, J., (1999), Detection of posture and motion by accelerometry: a validation study in ambulatory monitoring, Computers in Human Behavior, 15(5), 571–583, doi: 10.1016/S0747-5632(99)00037-0.
• Hauer, K., Lamb, S. E., Jorstad, E. C., Todd, C., Becker, C., (2006), Systematic review of definitions and methods of measuring falls in randomized controlled fall prevention trials, Age Ageing, 35(1),5–10, doi: 10.1093/ageing/afi218.
• Hyeon-Kyu, L., Kim, J. H., (1999), An HMM-based threshold model approach for gesture recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(10), 961–973, doi: 10.1109/34.799904 .
• Jovanov, E., Milenkovic, A., Otto, C., & De Groen, P. C., (2005), A wireless body area network of intelligent motion sensors for computer assisted physical rehabilitation, Journal of Neuro Engineering and Rehabilitation, 2(6), 1-10, doi: 10.1186/1743-0003-2-6.
• Junker, H., Amft, O., Lukowicz, P., & Troester, G., (2008), Gesture spotting with body-worn inertial sensors to detect user activities, Pattern Recognition, 41(6), 2010–2024, doi: 10.1016/j.patcog.2007.11.016 .
• Kangas, M., Konttila, A., Lindgren, P., Winblad, I., & Jamsa, T., (2008), Comparison of low complexity fall detection algorithms for body attached accelerometers, Gait Posture, 28(2), 285–291, doi: 10.1016/j.gaitpost.2008.01.003.
• Karantonis, D.M., Narayanan, M.R., Mathie, M., Lovell, N. H., & Celler, B.G., (2006), Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring, IEEE Transactions on Information Technology, B10(1), 156–167, doi: 10.1109/titb.2005.856864.
• Kautz, T.; Groh, B.H.; Hannink, J.; Jensen, U.; Strubberg, H.; Eskofier, B.M. (2017), Activity recognition in beach volleyball using a Deep Convolutional Neural Network. Data Min. Knowl. Discov. 31, 1678–1705.
• Kern, N., Schiele, B., & Schmidt, A., (2003, November), Multi-sensor activity context detection for wearable computing, European Symposium on Ambient Intelligence, Veldhoven, The Netherlands, doi: 10.1007/978-3-540-39863-9_17.
• Kiani, K., Snijders, C. J., Gelsema, E. S., (1997), Computerized analysis of daily life motor activity for ambulatory monitoring, Technology and Health Care, 5(4), 307–318, PMID: 9429271.
• Kuritsky, M.M., & Golstein, M.S., (1990), Section on inertial navigation in Cox IJ, Wilfong GT (Eds.), Autonomous Robot Vehicles, New York, USA, Springer-Verlag Press, (pp.96-117).
• LaBelle, K. (2011), Evaluation of Kinect joint tracking for clinical and in-home stroke rehabilitation tools, Undergraduate Thesis, University of Notre Dame.
• Lariviere, S., Ward, N.S and Boudrias, MH, (2018), Disrupted functional network integrity and flexibility after stroke: Relation to motor impairments Neuroimage-Clinical, 19,883-891.
• Lee, J., & Ha, I., (2001), Real-time motion capture for a human body using accelerometers, Robotica, 19(6), 601–610, doi: doi:10.1017/S0263574701003319.
• Lementec, J.C., & Bajcsy, P., (2004, November), Recognition of arm gestures using multiple orientation sensors: gesture classification, 7th International Conference on Intelligent Transportation Systems, Washington, DC, USA, doi: 10.1109/ITSC.2004.1399037.
• Lin, P. C., Komsuoglu, H., & Koditschek, D. E., (2006), Sensor data fusion for body state estimation in a hexapod robot with dynamical gaits, IEEE Transactions on Robotics, 22(5), 932–943.
• Ma, R.; Yan, D.; Peng, H.; Yang, T.; Sha, X.; Zhao, Y.; Liu, L., (2018), Basketball movements recognition using a wrist wearable inertial measurement unit. In Proceedings of the 2018 IEEE 1st International Conference on Micro/Nano Sensors for AI, Healthcare, and Robotics (NSENS), Shenzhen, China, 5–7 December 2018; 73–76.
• Mackenzie, D.A., (1990), Inventing Accuracy: A Historical Sociology of Nuclear Missile Guidance, 1st ed. Cambridge, MA, USA, MIT Press.
• Mathie, M.J., Coster, A.C.F., Lovell, N.H., & Celler, B.G., (2004), Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement, Physiological Measurement, 25(2), 1–20, doi: 10.1088/0967-3334/25/2/r01.
• Mathie, M.J., Celler, B.G., Lovell, N.H., & Coster, A.C.F, (2004), Classification of basic daily movements using a triaxial accelerometer, Medical & Biological Engineering & Computing, 42(5), 679–687, doi: 10.1007/BF02347551.
• Moeslund, T. B., & Granum, E., (2001), A survey of computer vision-based human motion capture, Computer Vision Image Understanding, 81(3), 231–268, doi: 10.1006/cviu.2000.0897 .
• Moeslund, T. B., Hilton, A., & Kruger, V., (2006), A survey of advances in vision-based human motion capture and analysis, Computer Vision Image Understanding, 104,(2–3), 90–126, doi: 10.1016/j.cviu.2006.08.002.
• Mousavi Hondori H. and Khademi, M., (2014), A review on technical and clinical impact of microsoft kinect on physical therapy and rehabilitation, Journal of medical engineering, 2014.
• Najafi, B., Aminian, K., Loew, F., Blanc, Y., Robert, P., (2002), Measurement of stand-sit and sit-stand transitions using a miniature gyroscope and its application in fall risk evaluation in the elderly, IEEE Transactions on Biomedical Engineering, 49(8), 843–851, doi: 10.1109/TBME.2002.800763.
• Najafi, B., Aminian, K., Paraschiv-Ionescu, A., Loew, F., Bula, C.J., & Robert, P., (2003), Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly, IEEE Transactions on Biomedical Engineering, 50(6), 711–723, doi: 10.1109/TBME.2003.812189.
• Nichol, J.G., Singh, S.P.N., Waldron, K.J., Palmer, L. R., & Orin, D.E., (2004), System design of a quadrupedal galloping machine, The International Journal of Robotics Research, 23(10–11), 1013–1027, doi: 10.1177/0278364904047391.
• Noury, N., Fleury, A., Rameau, P., Bourke, A. K., Laighin, G. O., Rialle, V., & Lundy, J. E., (2007), Fall detection principles and methods, 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Lyon, France, doi: 10.1109/IEMBS.2007.4352627.
• Pärkkä, J., Ermes, M., Korpipää, P., Mäntyjärvi, J., Peltola, J., & Korhonen, I. (2006). Activity classification using realistic data from wearable sensors. IEEE Transactions on Information Technology in Biomedicine, 10(1), 119-128, doi: 10.1109/TITB.2005.856863.
• Punchihewa, N.G.; Yamako, G.; Fukao, Y.; Chosa, E., (2019), Identification of key events in baseball hitting using inertial measurement units. J. Biomech. 87, 157–160.
• Luinge, H. and Slycke, P., (2009), Xsens MVN: Full 6DOF human motion tracking using miniature inertial sensors, Xsens Motion Technologies BV, Tech. Rep, 1(2009).
• Roetenberg D, Slycke P.J, & Veltink P.H., (2007Ambulatory position and orientation tracking fusing magnetic and inertial sensing. IEEE Transaction Biomed Eng., 54(5):883-90, doi: 10.1109/TBME.2006.889184.
• Sabatini, A.M., (2006), Inertial sensing in biomechanics: a survey of computational techniques bridging motion analysis and personal navigation, in Begg R, Palaniswami M, (Eds.) Computational Intelligence for Movement Sciences: Neural Networks and Other Emerging Techniques, Hershey, PA, USA, Idea Group Publishing, (pp.70–100).
• Shiratori, T., Hodgins, J. K., (2008), Accelerometer-based user interfaces for the control of a physically simulated character, ACM Trans. Graphics (SIGGRAPH Asia 2008), 27(5), 1-9, doi: 10.1145/1457515.1409076.
• Struzik, A. Konieczny, G. Grzesik, K. Stawarz, M. Winiarski, S. and Rokita, A., (2015), Relationship between lower limbs kinematic variables and effectiveness of sprint during maximum velocity phase, Acta of Bioengineering and Biomechanics, 17(4), 131-138.
• Tan, C.W., & Park, S., (2005), Design of accelerometer-based inertial navigation systems, IEEE Transaction Instrumentation Measurement, 54(6), 2520–2530, doi: 10.1109/TIM.2005.858129.
• Tao, Y., Hu, H., & Zhou, H., (2007), Integration of vision and inertial sensors for 3D arm motion tracking in home-based rehabilitation, The International Journal of Robotics Research, 26(6), 607–624, doi: 10.1177/0278364907079278.
• Titterton D. H. & Weston, J. L. (2004), Strapdown Inertial Navigation Technology, 2nd Edition, AIAA and IEE, Sevenage, doi:10.1049/PBRA017E.
• Tunçel, O., Altun, K., & Barshan, B., (2009), Classifying human leg motions with uniaxial piezoelectric gyroscopes, Sensors, 9(11), 8508–8546, doi: 10.3390/s91108508.
• Uiterwaal, M., Glerum, E.B.C., Busser, H.J., & Van Lummel, R.C., (1998), Ambulatory monitoring of physical activity in working situations, a validation study, Journal of Medical Engineering & Technology, 22(4), 168–172, doi: 10.3109/03091909809032535.
• Veltink, P.H., Bussmann, H.B.J., De Vries, W., Martens, W.L.J., & Van Lummel, R.C., (1996), Detection of static and dynamic activities using uniaxial accelerometers, IEEE Transactions on Rehabilitation Engineering, 4(4), 375–385, doi: 10.1109/86.547939.
• Vleugels , R., Herbruggen B.V , Fontaine J. and Poorter, E., (2021), Ultra-Wideband Indoor Positioning and IMU-Based Activity Recognition for Ice Hockey Analytics, Sensors, (21), 4650. https://doi.org/10.3390/s21144650
• Vie´ville, T., & Faugeras, O. D., Cooperation of the inertial and visual systems, Editors: Henderson TC, Traditional and Non-Traditional Robotic Sensors, Compurer Science, Springer-Verlag, Berlin, Germany, 59, (pp.339–350), doi: 10.1007/978-3-642-75984-0_22 .
• Wang, L., Hu, W., & Tan, T. (2003). Recent developments in human motion analysis. Pattern Recognit., 36, 585-601, doi: 10.1016/S0031-3203(02)00100-0.
• Wei, C., Wang H., Hu F., Chen, J., Lu, Y. and Qi, Y., (2021), Feature Selection and Reduction of Lower Limb Activity Recognition Based on Surface Electromyography and Motion, AICS 2021 AICS 2021 Journal of Physics: Conference Series Journal of Physics: Conference Series, 012006 ,IOP Publishing ,doi:10.1088/1742-6596/2025/1/012006
• Wong, W.Y., Wong, M.S., & Lo, K.H., (2007), Clinical applications of sensors for human posture and movement analysis: a review, Prosthetics and Orthotics International, 31(1), 62–75, doi: 10.1080/03093640600983949.
• Wu, W.H., Bui, A.A.T., Batalin, M.A., Liu, D., & Kaiser, W.J., (2007), Incremental diagnosis method for intelligent wearable sensor system, IEEE Transactions on Information Technology, B11(5), 553–562, doi: 10.1109/titb.2007.897579.
• Xia , S., Pei, L., Zhang, Z. Yu, W. and Qiu, RC.,(2021), Learning Disentangled Representation for Mixed- Reality Human Activity Recognition With a Single IMU Sensor, IEE Transactions On Instrumentation And Measurement, 70( 2514314),
• Yu, G. Jang, Y. J. Kim, J. Kim, J. H. Kim, H. Y. Kim, K. and Panday, S. B., (2016), Potential of IMU sensors in performance analysis of professional alpine skiers, Sensors, 16(4), 463.
• Yun, X., Bachmann, E. R., Moore, H., & Calusdian, J., (2007, May), Self-contained position tracking of human movement using small inertial/magnetic sensor modules, IEEE International Conference on Robotics and Automation, Rome, Italy, doi: 10.1109/ROBOT.2007.363845 .
• Zhang, Z.; Xu, D.; Zhou, Z.; Mai, J.; He, Z.; Wang, Q., (2017), IMU-based underwater sensing system for swimming stroke classification and motion analysis. In Proceedings of the 2017 IEEE International Conference on Cyborg and Bionic Systems (CBS), Beijing, China, 17–19 October 2017; pp. 268–272.
• Zhu, R., & Zhou, Z., (2004), A real-time articulated human motion tracking using tri-axis inertial/magnetic sensors package, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 12(2), 295–302, doi: 10.1109/TNSRE.2004.827825.
• Zijlstra, W., & Aminian, K., (2007), Mobility assessment in older people: new possibilities and challenges, European Journal of Ageing, 4(1), 3–12, doi: 10.1007/s10433-007-0041-9.