Research Papers

Machine Learning-Based Pre-Impact Fall Detection Model to Discriminate Various Types of Fall

[+] Author and Article Information
Tae Hyong Kim

Department of Biomechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
2066 Seoburo,
Suwon, Gyeonggi 16419, South Korea
e-mail: sanctified@skku.edu

Ahnryul Choi

Department of Biomechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
2066 Seoburo,
Suwon, Gyeonggi 16419, South Korea;
Department of Biomedical Engineering,
College of Medical Convergence,
Catholic Kwandong University,
24, Beomil-ro 579 beon-gill,
Gangneung, Gangwon 25601, South Korea
e-mail: achoi@cku.ac.kr

Hyun Mu Heo

Department of Biomechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
2066 Seoburo,
Suwon, Gyeonggi 16419, South Korea
e-mail: hhmoo91@naver.com

Kyungran Kim

Agricultural Health and Safety Division,
Rural Development Administration,
300 Nongsaengmyeong-ro,
Jeonju, Jeollabuk 54875, South Korea
e-mail: kimgr@korea.kr

Kyungsuk Lee

Agricultural Health and Safety Division,
Rural Development Administration,
300 Nongsaengmyeong-ro,
Jeollabuk 54875, South Korea
e-mail: kyungsuk9903@gmail.com

Joung Hwan Mun

Department of Biomechatronic Engineering,
College of Biotechnology and Bioengineering,
Sungkyunkwan University,
2066 Seoburo,
Suwon, Gyeonggi 16419, South Korea
e-mail: jmun@skku.edu

1These authors made equal contributions to this work.

2Corresponding authors.

Manuscript received November 6, 2018; final manuscript received April 5, 2019; published online May 13, 2019. Assoc. Editor: Christian Puttlitz. This work was prepared while under employment by the Government of South Korea as part of the official duties of the author(s) indicated above, as such copyright is owned by that Government, which reserves its own copyright under national law.

J Biomech Eng 141(8), 081010 (May 13, 2019) (10 pages) Paper No: BIO-18-1483; doi: 10.1115/1.4043449 History: Received November 06, 2018; Revised April 05, 2019

Pre-impact fall detection can send alarm service faster to reduce long-lie conditions and decrease the risk of hospitalization. Detecting various types of fall to determine the impact site or direction prior to impact is important because it increases the chance of decreasing the incidence or severity of fall-related injuries. In this study, a robust pre-impact fall detection model was developed to classify various activities and falls as multiclass and its performance was compared with the performance of previous developed models. Twelve healthy subjects participated in this study. All subjects were asked to place an inertial measuring unit module by fixing on a belt near the left iliac crest to collect accelerometer data for each activity. Our novel proposed model consists of feature calculation and infinite latent feature selection (ILFS) algorithm, auto labeling of activities, and application of machine learning classifiers for discrete and continuous time series data. Nine machine-learning classifiers were applied to detect falls prior to impact and derive final detection results by sorting the classifier. Our model showed the highest classification accuracy. Results for the proposed model that could classify as multiclass showed significantly higher average classification accuracy of 99.57 ± 0.01% for discrete data-based classifiers and 99.84 ± 0.02% for continuous time series-based classifiers than previous models (p < 0.01). In the future, multiclass pre-impact fall detection models can be applied to fall protector devices by detecting various activities for sending alerts or immediate feedback reactions to prevent falls.

Copyright © 2019 by ASME
Your Session has timed out. Please sign back in to continue.


Sattin, R. W. , 1992, “Falls Among Older Persons: A Public Health Perspective,” Annu. Review Public Health, 13(1), pp. 489–508. [CrossRef]
Berg, W. P. , Alessio, H. M. , Mills, E. M. , and Tong, C. , 1997, “Circumstances and Consequences of Falls in Independent Community-Dwelling Older Adults,” Age Ageing, 26(4), pp. 261–268. [CrossRef] [PubMed]
Hu, X. , and Qu, X. , 2016, “ Pre-Impact Fall Detection,” Biomed. Eng. Online, 15(1), p. 61. [CrossRef] [PubMed]
Rajagopalan, R. , Litvan, I. , and Jung, T. P. , 2017, “Fall Prediction and Prevention Systems: Recent Trends, Challenges, and Future Research Directions,” Sensors, 17(11), p. 2509. [CrossRef]
Noury, N. , Fleury, A. , Rumeau, P. , Bourke, A. K. , Laighin, G. O. , Rialle, V. , and Lundy, J. E. , 2007, “Fall Detection—Principles and Methods,” Engineering in Medicine and Biology Society (EMBS),” 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), Lyon, France, Aug. 22–26, pp. 1663–1666.
Tamura, T. , Yoshimura, T. , Sekine, M. , Uchida, M. , and Tanaka, O. , 2009, “A Wearable Airbag to Prevent Fall Injuries,” IEEE Trans. Inf. Technol. Biomed., 13(6), pp. 910–914. [CrossRef] [PubMed]
Kong, K. , Bae, J. , and Tomizuka, M. , 2012, “A Compact Rotary Series Elastic Actuator for Human Assistive Systems,” IEEE/ASME Trans. Mechatronics, 17(2), pp. 288–297. [CrossRef]
Monaco, V. , Tropea, P. , Aprigliano, F. , Martelli, D. , Parri, A. , Cortese, M. , Molino-Lova, R. , Vitiello, N. , and Micera, S. , 2017, “An Ecologically-Controlled Exoskeleton Can Improve Balance Recovery After Slippage,” Sci. Rep., 7, p. 46721. [CrossRef] [PubMed]
DeGoede, K. M. , Ashton-Miller, J. A. , and Schultz, A. B. , 2003, “ Fall-Related Upper Body Injuries in the Older Adult: A Review of the Biomechanical Issues,” J. Biomech., 36(7), pp. 1043–1053. [CrossRef] [PubMed]
Rubenstein, L. Z. , 2006, “Falls in Older People: Epidemiology, Risk Factors and Strategies for Prevention,” Age Ageing, 35(Suppl. 2), pp. ii37–ii41. [CrossRef] [PubMed]
Nevitt, M. C. , and Cummings, S. R. , 1993, “Type of Fall and Risk of Hip and Wrist Fractures: The Study of Osteoporotic Fractures,” J. Am. Geriatr. Soc., 41(11), pp. 1226–1234. [CrossRef] [PubMed]
Kelly, D. W. , and Kelly, B. D. , 2012, “A Novel Diagnostic Sign of Hip Fracture Mechanism in Ground Level Falls: Two Case Reports and Review of the Literature,” J. Med. Case Rep., 6(1), p. 136. [CrossRef] [PubMed]
Merrill, Z. , Chambers, A. J. , and Cham, R. , 2017, “Arm Reactions in Response to an Unexpected Slip—Impact of Aging,” J. Biomech., 58, pp. 21–26. [CrossRef] [PubMed]
Tolkiehn, M. , Atallah, L. , Lo, B. , and Yang, G. Z. , 2011, “Direction Sensitive Fall Detection Using a Triaxial Accelerometer and a Barometric Pressure Sensor,” Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), Boston, MA, Aug. 30–Sept. 3, pp. 369–372.
Lindemann, U. , Hock, A. , Stuber, M. , Keck, W. , and Becker, C. , 2005, “Evaluation of a Fall Detector Based on Accelerometers: A Pilot Study,” Med. Biol. Eng. Comput., 43(5), pp. 548–551. [CrossRef] [PubMed]
Bourke, A. K. , O'donovan, K. J. , and Olaighin, G. , 2008, “The Identification of Vertical Velocity Profiles Using an Inertial Sensor to Investigate Pre-Impact Detection of Falls,” Med. Eng. Phys., 30(7), pp. 937–946. [CrossRef] [PubMed]
Liu, J. , and Lockhart, T. E. , 2014, “Development and Evaluation of a Prior-to-Impact Fall Event Detection Algorithm,” IEEE Trans. Biomed. Eng., 61(7), pp. 2135–2140. [CrossRef] [PubMed]
Sabatini, A. M. , Ligorio, G. , Mannini, A. , Genovese, V. , and Pinna, L. , 2016, “Prior-to-and Post-Impact Fall Detection Using Inertial and Barometric Altimeter Measurements,” IEEE Trans. Neural Syst. Rehabil. Eng., 24(7), pp. 774–783. [CrossRef] [PubMed]
Zhao, G. , Mei, Z. , Liang, D. , Ivanov, K. , Guo, Y. , Wang, Y. , and Wang, L. , 2012, “Exploration and Implementation of a Pre-Impact Fall Recognition Method Based on an Inertial Body Sensor Network,” Sensors, 12(11), pp. 15338–15355. [CrossRef] [PubMed]
Tong, L. , Song, Q. , Ge, Y. , and Liu, M. , 2013, “ HMM-Based Human Fall Detection and Prediction Method Using Tri-Axial Accelerometer,” IEEE Sens. J., 13(5), pp. 1849–1856. [CrossRef]
Kangas, M. , Konttila, A. , Lindgren, P. , Winblad, I. , and Jämsä, T. , 2008, “Comparison of Low-Complexity Fall Detection Algorithms for Body Attached Accelerometers,” Gait Posture, 28(2), pp. 285–291. [CrossRef] [PubMed]
Otanasap, N. , 2016, “ Pre-Impact Fall Detection Based on Wearable Device Using Dynamic Threshold Model,” 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT), Guangzhou, China, Dec. 16–18, pp. 362–365.
Wu, G. , 2000, “Distinguishing Fall Activities From Normal Activities by Velocity Characteristics,” J. Biomech., 33(11), pp. 1497–1500. [CrossRef] [PubMed]
Aziz, O. , Musngi, M. , Park, E. J. , Mori, G. , and Robinovitch, S. N. , 2017, “A Comparison of Accuracy of Fall Detection Algorithms (Threshold-Based Vs. Machine Learning) Using Waist-Mounted Tri-Axial Accelerometer Signals From a Comprehensive Set of Falls and Non-Fall Trials,” Med. Biol. Eng. Comput., 55(1), pp. 45–55. [CrossRef] [PubMed]
Aziz, O. , Russell, C. M. , Park, E. J. , and Robinovitch, S. N. , 2014, “The Effect of Window Size and Lead Time on Pre-Impact Fall Detection Accuracy Using Support Vector Machine Analysis of Waist Mounted Inertial Sensor Data,” 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), Chicago, IL, Aug. 26–30, pp. 30–33.
Shi, G. , Chan, C. S. , Li, W. J. , Leung, K. S. , Zou, Y. , and Jin, Y. , 2009, “Mobile Human Airbag System for Fall Protection Using MEMS Sensors and Embedded SVM Classifier,” IEEE Sens. J., 9(5), pp. 495–503. [CrossRef]
Shan, S. , and Yuan, T. , 2010, “A Wearable Pre-Impact Fall Detector Using Feature Selection and Support Vector Machine,” IEEE 10th International Conference on Signal Processing (ICSP), Beijing, China, Oct. 24–28, pp. 1686–1689.
Noury, N. , Rumeau, P. , Bourke, A. K. , ÓLaighin, G. , and Lundy, J. E. , 2008, “A Proposal for the Classification and Evaluation of Fall Detectors,” IRBM, 29(6), pp. 340–349. [CrossRef]
Lee, J. K. , Robinovitch, S. N. , and Park, E. J. , 2015, “Inertial Sensing-Based Pre-Impact Detection of Falls Involving Near-Fall Scenarios,” IEEE Trans. Neural Syst. Rehabil. Eng., 23(2), pp. 258–266. [CrossRef] [PubMed]
O'Haver, T. , 1997, “A Pragmatic Introduction to Signal Processing,” University of Maryland at College Park, College Park, MD, accessed Jan. 14, 2018, https://terpconnect.umd.edu/~toh/spectrum/index.html
Pannurat, N. , Thiemjarus, S. , and Nantajeewarawat, E. , 2014, “Automatic Fall Monitoring: A Review,” Sensors, 14(7), pp. 12900–12936. [CrossRef] [PubMed]
Saeys, Y. , Inza, I. , and Larrañaga, P. , 2007, “A Review of Feature Selection Techniques in Bioinformatics,” Bioinformatics, 23(19), pp. 2507–2517. [CrossRef] [PubMed]
Roffo, G. , Melzi, S. , Castellani, U. , and Vinciarelli, A. , 2017, “Infinite Latent Feature Selection: A Probabilistic Latent Graph-Based Ranking Approach,” IEEE International Conference on Computer Vision (ICCV), Venice, Italy, Oct. 22–29, pp. 1398–1406.
Kim, K. S. , Choi, H. H. , Moon, C. S. , and Mun, C. W. , 2011, “Comparison of k-Nearest Neighbor, Quadratic Discriminant and Linear Discriminant Analysis in Classification of Electromyogram Signals Based on the Wrist-Motion Directions,” Curr. Appl. Phys., 11(3), pp. 740–745. [CrossRef]
Youn, S. H. , Sim, T. , Choi, A. , Song, J. , Shin, K. Y. , Lee, I. K. , Heo, H. M. , Lee, D. , and Mun, J. H. , 2015, “ Multi-Class Biological Tissue Classification Based on a Multi-Classifier: Preliminary Study of an Automatic Output Power Control for Ultrasonic Surgical Units,” Comput. Biol. Med., 61, pp. 92–100. [CrossRef] [PubMed]
Bosch, A. , Zisserman, A. , and Munoz, X. , 2007, “Image Classification Using Random Forests and Ferns,” IEEE 11th International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, Oct. 14–21, pp. 1–8.
Oh, S. E. , Choi, A. , and Mun, J. H. , 2013, “Prediction of Ground Reaction Forces During Gait Based on Kinematics and a Neural Network Model,” J. Biomech., 46(14), pp. 2372–2380. [CrossRef] [PubMed]
Mei, J. , Liu, M. , Wang, Y. F. , and Gao, H. , 2016, “Learning a Mahalanobis Distance-Based Dynamic Time Warping Measure for Multivariate Time Series Classification,” IEEE Trans. Cybern., 46(6), pp. 1363–1374. [CrossRef] [PubMed]
Hochreiter, S. , and Schmidhuber, J. , 1997, “Long Short-Term Memory,” Neural Comput., 9(8), pp. 1735–1780. [CrossRef] [PubMed]
Vedaldi, A. , and Lenc, K. , 2015, “Matconvnet: Convolutional Neural Networks for Matlab,” 23rd ACM International Conference on Multimedia, Brisbane, Australia, Oct. 26–30, pp. 689–692. http://www.vlfeat.org/matconvnet/matconvnet-manual.pdf
Xi, X. , Keogh, E. , Shelton, C. , Wei, L. , and Ratanamahatana, C. A. , 2006, “Fast Time Series Classification Using Numerosity Reduction,” 23rd International Conference on Machine Learning, Pittsburgh, PA, June 25–29, pp. 1033–1040.
Belgiu, M. , and Drăguţ, L. , 2016, “Random Forest in Remote Sensing: A Review of Applications and Future Directions,” ISPRS J. Photogramm. Remote Sens., 114, pp. 24–31. [CrossRef]
Chutia, D. , Bhattacharyya, D. K. , Sarma, K. K. , Kalita, R. , and Sudhakar, S. , 2016, “Hyperspectral Remote Sensing Classifications: A Perspective Survey,” Trans. GIS, 20(4), pp. 463–490. [CrossRef]
Wang, X. , Mueen, A. , Ding, H. , Trajcevski, G. , Scheuermann, P. , and Keogh, E. , 2013, “Experimental Comparison of Representation Methods and Distance Measures for Time Series Data,” Data Min. Knowl. Discovery, 26(2), pp. 275–309. [CrossRef]
Ordóñez, F. J. , and Roggen, D. , 2016, “Deep Convolutional and Lstm Recurrent Neural Networks for Multimodal Wearable Activity Recognition,” Sensors, 16(1), p. 115. [CrossRef]
Yin, W. , Kann, K. , Yu, M. , and Schütze, H. , 2017, “Comparative Study of CNN and RNN for Natural Language Processing,” arXiv preprint arXiv:1702.01923. https://arxiv.org/abs/1702.01923
Johansson, S. , 2015, “A Machine-Learning Based Approach to Pre-Impact Fall Detection With Wearable Devices: Motion Monitoring Using Sensor Fusion and the Support Vector Machine,” M.Sc. thesis, KTH Royal Institute of Technology, Stockholm, Sweden. http://www.diva-portal.org/smash/get/diva2:840157/FULLTEXT01.pdf
Ronao, C. A. , and Cho, S. B. , 2016, “Human Activity Recognition With Smartphone Sensors Using Deep Learning Neural Networks,” Expert Syst. Appl., 59, pp. 235–244. [CrossRef]


Grahic Jump Location
Fig. 1

Custom-designed IMU sensor placed on the left anterior iliac crest of the pelvis of the subject. Tri-axial accelerometer data are sent and received from a Bluetooth module and receiver.

Grahic Jump Location
Fig. 2

Experimental protocol of ten types of fall and 14 types of ADL results in 3062 datasets. N represents the number of subjects and n represents the number of trials for each activity.

Grahic Jump Location
Fig. 3

Tri-axial accelerometer data of fall phase for slipping

Grahic Jump Location
Fig. 4

Fall indicators. A total of 182 feature candidates were extracted within the window by calculating maximum, minimum, average, median, variance, skewness, and kurtosis of fall indicators from tri-axial accelerometer data for single frame.

Grahic Jump Location
Fig. 5

Flow chart showing the proposed pre-impact fall detection model

Grahic Jump Location
Fig. 6

The average classification accuracy of multiclass pre-impact fall detection model depending on the number of features

Grahic Jump Location
Fig. 7

Overall performance of our two proposed multiclass pre-impact fall detection model using discrete data and continuous time-series data

Grahic Jump Location
Fig. 8

Confusion matrix of our two our proposed multiclass pre-impact fall detection model. Bolded number in the confusion matrix represents each type of activity (1–10 are ADLs activities and 11–24 are different types of falls).



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In