Methodology and validation for identifying gait type using machine learning on IMU data

References

• Busse ME, Van Deursen RW, Wiles CM. Real-life step and activity measurement: reliability and validity. J Med Eng Technol. 2009;33:33–41.
   PubMedGoogle Scholar
• Alsubheen SA, George AM, Baker A, Rohr LE, et al. Accuracy of the vivofit activity tracker. J Med Eng Technol. 2016;40:298–306.
   PubMedGoogle Scholar
• Noah JA, Spierer DK, Gu J, et al. Comparison of steps and energy expenditure assessment in adults of fitbit tracker and ultra to the actical and indirect calorimetry. J Med Eng Technol. 2013;37:456–462.
   PubMedGoogle Scholar
• Pober DM, Staudenmayer J, Raphael C, et al. Development of novel techniques to classify physical activity mode using accelerometers. Med Sci Sports Exerc. 2006;38:1626–1634.
   PubMed Web of Science ®Google Scholar
• Cleland I, Kikhia B, Nugent C, et al. Optimal placement of accelerometers for the detection of everyday activities. Sensors 2013;13:9183–9200.
   PubMed Web of Science ®Google Scholar
• Kwapisz JR, Weiss GM, Moore SA. Activity recognition using cell phone accelerometers. Sigkdd Explor Newsl. 2011;12:74–82.
   Google Scholar
• Leong JY, Wong JE. Accuracy of three android-based pedometer applications in laboratory and free-living settings. J Sports Sci. 2017;35:14–21.
   PubMed Web of Science ®Google Scholar
• Mannini A, Intille SS, Rosenberger M, et al. Activity recognition using a single accelerometer placed at the wrist or ankle. Med Sci Sports Exerc. 2013;45:2193.
   PubMed Web of Science ®Google Scholar
• Rhudy MB, Mahoney JM. A comprehensive comparison of simple step counting techniques using wrist-and ankle-mounted accelerometer and gyroscope signals. J Med Eng Technol. 2018;42:236–243.
   PubMedGoogle Scholar
• Gouwanda D, Senanayake SMNA. Periodical gait asymmetry assessment using real-time wireless gyroscopes gait monitoring system. J Med Eng Technol. 2011;35:432–440.
   PubMedGoogle Scholar
• Mannini A, Sabatini AM. Gait phase detection and discrimination between walking-jogging activities using hidden Markov models applied to foot motion data from a gyroscope. Gait Posture. 2012;36:657–661.
   PubMed Web of Science ®Google Scholar
• Pärkkä J, Ermes M, Korpipää P, et al. Activity classification using realistic data from wearable sensors. IEEE Trans Inform Technol Biomed. 2006;10:119–128.
   PubMed Web of Science ®Google Scholar
• Darji ST, Kher RK. Artificial neural network-based classification of body movements in ambulatory ECG signal. J Med Eng Technol. 2013;37:535–540.
   PubMedGoogle Scholar
• Dontje ML, de Groot M, Lengton RR, et al. Measuring steps with the fitbit activity tracker: an inter-device reliability study. J Med Eng Technol. 2015;39:286–290.
   PubMedGoogle Scholar
• Eisenmann JC, Laurson KR, Wickel EE, Gentile D, et al. Utility of pedometer step recommendations for predicting overweight in children. Int J Obes. 2007;31:1179–1182.
   PubMed Web of Science ®Google Scholar
• Feldman E. Running and health. Integr Med Alert 2018;21:52–54.
   Google Scholar
• Preece SJ, Goulermas JY, Kenney LPJ, et al. Activity identification using body-mounted sensors a review of classification techniques. Physiol Meas. 2009;30:R1–R33.
   PubMed Web of Science ®Google Scholar
• Mannini A, Sabatini AM. Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors 2010;10:1154–1175.
   PubMed Web of Science ®Google Scholar
• Pirttikangas S, Fujinami K, Nakajima T. Feature selection and activity recognition from wearable sensors. In: Third International Symposium on Ubiquitious Computing Systems; October 11–13, Seoul, Korea; Berlin, Heidelberg: Springer; 2006. p. 516–527. Available from: https://link.springer.com/book/10.1007/11890348#about
   Google Scholar
• Staudenmayer J, Pober D, Crouter S, et al. An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer. J Appl Physiol. 2009;107:1300–1307.
   PubMed Web of Science ®Google Scholar
• Jeong G-M, Truong PH, Choi S-I. Classification of three types of walking activities regarding stairs using plantar pressure sensors. IEEE Sens J. 2017;17:2638–2639.
   Web of Science ®Google Scholar
• Begg RK, Palaniswami M, Owen B. Support vector machines for automated gait classification. IEEE Trans Biomed Eng. 2005;52:828–838.
   PubMed Web of Science ®Google Scholar
• Begg R, Kamruzzaman J. A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data. J Biomech. 2005;38:401–408.
   PubMed Web of Science ®Google Scholar
• Nakano T, Nukala BT, Tsay J, et al. Gaits classification of normal vs. patients by wireless gait sensor and support vector machine (SVM) classifier. Int J Software Innov (IJSI). 2017;5:17–29.
   Web of Science ®Google Scholar
• He B, Bai J, Zipunnikov VV, et al. Predicting human movement with multiple accelerometers using movelets. Med Sci. Sports Exerc. 2014;46:1859–1866.
   PubMed Web of Science ®Google Scholar
• Chowdhury AK, Tjondronegoro D, Chandran V, et al. Ensemble methods for classification of physical activities from wrist accelerometry. Med Sci. Sports Exerc. 2017;49(9):1965–1973.
   PubMed Web of Science ®Google Scholar
• Boulgouris NV, Plataniotis KN, Hatzinakos D. Gait recognition using dynamic time warping. In: 2004 IEEE 6th Workshop on Multimedia Signal Processing; 2004; Siena, Italy, IEEE: Piscataway, NJ. p. 263–266. Available from: https://ieeexplore.ieee.org/abstract/document/1436543
   Google Scholar
• Rong L, Zhiguo D, Jianzhong Z, et al. Identification of individual walking patterns using gait acceleration. In: The 1st International Conference on Bioinformatics and Biomedical Engineering, 2007. ICBBE 2007; Wuhan, China; IEEE: Piscataway, NJ, 2007. p. 543–546. Available from: https://ieeexplore.ieee.org/abstract/document/4272626
   Google Scholar
• Paiyarom S, Tungamchit P, Keinprasit R, et al. Activity monitoring system using dynamic time warping for the elderly and disabled people. In 2nd International Conference on Computer, Control and Communication, 2009; Karachi, Pakistan, IC4 2009; IEEE: Piscataway, NJ, 2009. p. 1–4. Available from: https://ieeexplore.ieee.org/abstract/document/4909158
   Google Scholar
• Tahir NM, Manap HH. Parkinson disease gait classification based on machine learning approach. J Appl Sci. 2012;12:180–185.
   Google Scholar
• Seifert AK, Zoubir AM, Amin MG. Radar classification of human gait abnormality based on sum-of-harmonics analysis. In Radar Conference (RadarConf18), Oklahoma City, OK; IEEE: Piscataway, NJ, 2018. p. 940–945. Available from: https://ieeexplore.ieee.org/abstract/document/8378687
   Google Scholar
• Preece S, Goulermas JY, Kenney LP, et al. A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Trans Biomed Eng. 2009;56:871–879.
   PubMed Web of Science ®Google Scholar
• Fathi A, Mori G, Action recognition by learning mid-level motion features. In IEEE Conference on Computer Vision and Pattern Recognition, 2008, Anchorage, AK (CVPR 2008); IEEE: Piscataway, NJ, 2008. p. 1–8. Available from: https://ieeexplore.ieee.org/abstract/document/4587735
   Google Scholar
• Fichou D, Morlock GE. Powerful artificial neural network for planar chromatographic image evaluation, shown for denoising and feature extraction. Anal Chem. 2018;90:6984–6991.
   PubMed Web of Science ®Google Scholar
• Lee J-A, Cho S-H, Lee Y-J, et al. Portable activity monitoring system for temporal parameters of gait cycles. J Med Syst. 2010;34:959–966.
   PubMed Web of Science ®Google Scholar
• Thorstensson A, Roberthson H. Adaptations to changing speed in human locomotion: speed of transition between walking and running. Acta Physiol. 1987;131:211–214.
   Web of Science ®Google Scholar
• O’Connor CM, Thorpe SK, O’Malley MJ, et al. Automatic detection of gait events using kinematic data. Gait Posture. 2007;25:469–474.
   PubMed Web of Science ®Google Scholar
• Abdi H. A neural network primer. J Biol Syst. 1994;2:247–281.
   Google Scholar
• Hansen LK, Salamon P. Neural network ensembles. IEEE Trans Pattern Anal Machine Intell. 1990;12:993–1001.
   Web of Science ®Google Scholar
• Hall P. Theoretical comparison of bootstrap confidence intervals. Ann Stat. 1988;16(3):927–953.
   Web of Science ®Google Scholar
• Efron B. Bootstrap methods: another look at the jackknife. In: Kotz S, Johnson NL, editors. Breakthroughs in statistics. Springer Series in Statistics (Perspectives in Statistics). New York: Springer; 1992. p. 569–593.
   Google Scholar
• Bao L, Intille SS. Activity recognition from user-annotated acceleration data. In Second International Conference on Pervasive Computing; Linz/Vienna, Austria, April 21-23. Berlin, Heidelberg: Springer; 2004. p. 1–17.
   Google Scholar