Fuzzy Inference Based Pre-impact Fall Detection System Using Dynamic Threshold
Article Sidebar
Main Article Content
Abstract
Problems of falling are particularly vital safety in seniors. For these reasons, increasing a useful fall prevention approach is necessary to relieve the infliction of falls. This study focuses on a dynamic threshold model for real-time pre-impact fall detection that enables the falls to be identified before the body crashes to the ground. The velocity of head and chest position and the center of gravity of the subject body used for the feature combination classified by fuzzy inference for pre-impact fall detection. It only needs subjects to wear some tiny coin-size sensors that combine with the Kinect sensor, vision-based, without recording any data due to privacy issue. The dynamic threshold-based model with stereotypes suitable for an individual one, is applied for real-time fall and non-fall classification for the longest lead time of
pre-impact fall detection. Moreover, the various kinds of integration of single, multiple, and triple Kinect combined with and without the wearable device are evaluated. The 14 rules of Sugeno fuzzy set defining the falling posture, movement transitions, and comparison of the different combination of devices are inferred first, whereas the final decision is produced through thinking and trigger on such fuzzy sets. The experimentation result found that the highest lead-time of pre-impact fall detection is 549.83 ms. However, the integration method that combined multiple Kinect with the wearable device can reduce camera overlapping and obscurity with the highest accuracy about 98.09 percent. Vice versa, the method using only multiple Kinect without the wearable device provide lower accuracy than 93.00 percent.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Bagala, F., Becker, C., Cappello, A., Chiari, L., Aminian, K., Hausdorff, J. M., Zijlstra, W., & Klenk, J. (2012). Evaluation of Accelerometer-based Fall Detection Algorithms on Real-world Falls. PloS One, 7(5), e37062.
Rougier, C., Meunier, J., St-Arnaud, A., & Rousseau, J. (2011). Robust Video Surveillance for Fall Detection Based on Human Shape Deformation. IEEE Transactions on Circuits and Systems for Video Technology, 21(5), 611-622.
Liu, J., & Lockhart, T. E. (2009). Age-related Joint Moment Characteristics during Normal Gait and Successful Reactiverecovery from Unexpected Slip Perturbations. Gait & Posture, 30(3), 276-281.
Abbate, S., Avvenuti, M., Bonatesta, F., Cola, G., Corsini, P., & Vecchio, A. (2012). A Smartphone-based Fall Detection System. Pervasive and Mobile Computing, 8(6), 883-899.
Otanasap, N. & Boonbrahm, P. (2015). Multiple Kinect for 3D Human Skeleton Posture using Axis Replacement Method. In The 14th IEEE International Symposium on Mixed and Augmented Reality (ISMAR 2015). September 29 October 3, 2015, Fukuota: Japan.
Otanasap, N., & Boonbrahm, P. (2017). Pre-impact Fall Detection System using Dynamic Threshold and 3D Bounding Box. In The 8th International Conference on Graphic and Image Processing (ICGIP 2016) 10225, 102250D. October 29 -31, 2016, Tokyo: Japan.
Otanasap, N., & Boonbrahm, P. (2017). Pre-impact Fall Detection Approach using Dynamic Threshold Based and Center of Gravity in Multiple Kinect Viewpoints. In The 2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE). 1-6. July 12-14, 2017, Nakhon Si Thammarat: IEEE.
Rougier, C., Meunier, J., St-Arnaud, A., & Rousseau, J. (2006). Monocular 3D Head Tracking to Detect Falls of Elderly People. In The 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. 6384-6387. August 30 – September 3, 2006, New York : IEEE.
Stone, E. E., & Skubic, M. (2015). Fall Detection in Homes of Older Adults using the Microsoft Kinect. IEEE Journal of Biomedical and Health Informatics, 19(1), 290-301.
InvenSense (2014). Introduces the World’s First Motion Apps Platform™ for Embedded System Developers (Online). Retrieved 5 March 2018, from https://ir.invensense.com/phoenix.zhtml? c=237953 &p=irol-newsArticle&ID=1587324.
Mastorakis, G., & Makris, D. (2014). Fall Detection System using Kinect’s Infrared Sensor. Journal of Real-Time Image Processing, 9(4), 635-646.
Wu, G. (2000). Distinguishing Fall Activities from Normal Activities by Velocity Characteristics. Journal of Biomechanics, 33(11), 1497-1500.
Kim, E., Helal, S., & Cook, D. (2010). Human Activity Recognition and Pattern Discovery. IEEE Pervasive Computing/IEEE Computer Society [and] IEEE Communications Society, 9(1), 48.
Luinge, H. J., & Veltink, P. H. (2005). Measuring Orientation of Human Body Segments using Miniature Gyroscopes and Accelerometers. Medical and Biological Engineering and Computing, 43(2), 273-282.
Bourke, A. K., O’Donovan, K. J., Nelson, J., & OLaighin, G. M. (2008). Fall-detection through Vertical Velocity Thresholding using a Tri-axial Accelerometer Characterized using an Optical Motion-capture System. In The 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2832-2835. August 20-25, 2008, Vancouver, BC, Canada: IEEE.
Kwolek, B., & Kepski, M. (2016). Fuzzy Inference-based Fall Detection using Kinect and Body-worn Accelerometer. Applied Soft Computing, 40, 305-318.
Zadeh, L. A. (1976). A Fuzzy-algorithmic Approach to the Definition of Complex or Imprecise Concepts. In Systems Theory in the Social Sciences. 202-282. Basel, Switzerland: Birkhäuser, Basel.
Sugeno, M. (1985). Industrial Applications of Fuzzy Control. Amsterdam : Elsevier Science Ltd.
Otanasap, N. & Boonbrahm, P. (2015, July). Real Time Action Detection from 3D Skeleton Data Using Multiple Kinects. In Proceeding of the 7th Walailak Research National Conference. 188. July 2, 2018. Nakhon Si Thammarat : Walailuk University.
Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., & Blake, A. (2011). Real-time Human Pose Recognition in Parts from Single Depth Images. In The Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. 1297-1304. June 20 – 25, 2011, Washington, DC, USA : IEEE.
Patel, S., Park, H., Bonato, P., Chan, L., & Rodgers, M. (2012). A Review of Wearable Sensors and Systems with Application in Rehabilitation. Journal of Neuroengineering and Rehabilitation, 9(1), 21.
Sabatini, A. M., Ligorio, G., Mannini, A., Genovese, V., & Pinna, L. (2016). Prior-to-and Post-impact Fall Detection using Inertial and Barometric Altimeter Measurements. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 24(7), 774-783.
Djurić-Jovičić, M. D., Jovičić, N. S., & Popović, D. B. (2011). Kinematics of Gait: New Method for Angle Estimation Based on Accelerometers. Sensors, 11(11), 10571-10585.
Noury, N., Rumeau, P., Bourke, A. K., ÓLaighin, G., & Lundy, J. E. (2008). A Proposal for the Classification and Evaluation of Fall Detectors. Irbm, 29(6), 340-349.
Maki, B. E., & McIlroy, W. E. (2003). Effects of Aging on Control of Stability. A Textbook of Audiological Medicine: Clinical Aspects of Hearing and Balance, London: Martin Dunitz Publishers.
Otanasap, N. & Boonbrahm, P. (2014). Falling Pattern Analysis Based on 3D Euclidean Distance of Human Skeleton Joints. In Proceedings of The International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES 2014). (N/A). January 23-25, 2014, Ayutthaya : Thammasat and Kasetsart University.
Hirata, Y., Komatsuda, S., & Kosuge, K. (2008). Fall Prevention Control of Passive Intelligent Walker Based on Human Model. In The 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems. 1222-1228. September 22-26, 2008, Acropolis Convention Center. Nice, France: IEEE.