Abstract This paper proposes an integrative model of fall motion detection and fall severity level estimation. For the fall motion detection, a continuous stream of data representing time sequential frames of fifteen body joint positions was obtained from Kinect’s 3D depth camera. A set of features is then extracted and fed into the designated machine learning model. Compared with existing models that rely on the depth image inputs, the proposed scheme resolves background ambiguity of the human body. The experimental results demonstrated that the proposed fall detection method achieved accuracy of 99.97% with zero false negative and more robust when compared with the state-of-the-art approach using depth of image. Another key novelty of our approach is the framework, called Fall Severity Injury Score (FSIS), for determining the severity level of falls as a surrogate for seriousness of injury on three selected risk areas of body: head, hip and knee. The framework is based on two crucial pieces of information from the fall: 1) the velocity of the impact position and 2) the kinetic energy of the fall impact. Our proposed method is beneficial to caregivers, nurses or doctors, in giving first aid/diagnosis/treatment for the subject, especially, in cases where the subject loses consciousness or is unable to respond.

References

[1] Al-Najdawi N., Tedmori S., Edirisinghe E., and Bez H., An Automated Real-Time People Tracking System Based on KLT Features Detection, The International Arab Journal of Information Technology, vol. 9, no. 1, pp. 100- 107, 2012.

[2] Atanasijevic T., Savic S., Nikolic S., and Djokic V., Frequency and Severity of Injuries in Correlation with the Height of Fall, Journal of Forensic Sciences, vol. 50, no. 3, pp. 1-5, 2005.

[3] Baker S., O'Neill B., Haddon W., and Long W., The Injury Severity Score: a Method for Describing Patients with Multiple Injuries and Evaluating Emergency Care, Journal of Trauma and Acute Care Surgery, vol. 14, no. 3, pp. 187-196, 1974.

[4] Bevilacqua V., Nuzzolese N., Barone D., Pantaleo M., Suma M., D Ambruoso D., Loconsole C., Stroppa F., and Volpe A., Fall Detection in Indoor Environment with Kinect Sensor, in Proceedings of International Symposium on Innovations in Intelligent Systems and Applications, Alberobello, pp. 319-324, 2014.

[5] Bian Z., Hou J., Chau L., and Magnenat- Thalmann N., Fall Detection Based on Body Part Tracking Using a Depth Camera, Journal of Biomedical and Health Informatics, vol. 19, no. 2, pp. 430-439, 2015.

[6] Blake J., The Natural User Interface Revolution, Natural User Interfaces in .NET, Manning, 2012.

[7] Bourke A., O Brien J., and Lyons G., Evaluation of a Threshold-Based Tri-Axial Accelerometer Fall Detection Algorithm, Journal of Gait and Posture, vol. 26, no. 2, pp. 194-199, 2007.

[8] Bowers B., Lloyd J., Lee W., Powell-Cope G., and Baptiste A., Biomechanical Evaluation of Injury Severity Associated with Patient Falls from Bed, Rehabilitation Nursing : the Official Journal of the Association of Rehabilitation Nurses, vol. 33, no. 6, pp. 253-259, 2008.

[9] Box Plots, available at: http://onlinestatbook.com/2/graphing_distributio ns/boxplots.html, Last Visited, 2013.

[10] Center for Disease Control and Prevention, Hip Fractures among Older Adult, available at: http://www.cdc.gov/ncipc/factsheets/adulthipfx. htm, Last Visited, 2012. Fall Motion Detection with Fall Severity Level Estimation by ... 387

[11] Class Multilayer Perceptron, available at: http://weka.sourceforge.net/doc.dev/weka/classifi ers/functions/MultilayerPerceptron.html, Last Visited, 2014.

[12] Coordinate Geometry, available at: http://gmatclub.com/forum/math-coordinate- geometry-87652.html, Last Visited, 2013.

[13] Cory C., Jones M., James D., Leadbeatter S., and Nokes L., The Potential and Limitations of Utilising Head Impact Injury Models to Assess the Likelihood of Significant Head Injury in Infants after a Fall, Journal of Forensic Science International, vol. 123, no. 2-3, pp. 89-106, 2001.

[14] Cristianini N. and Shawe-Taylor J., An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods, Cambridge University Press, 2000.

[15] Curran G., Homework Helpers: Physics, The Career Press, 2012.

[16] Dai X., Wu M., Davidson B., Mahoor M., and Zhang J., Image-Based Fall Detection with Human Posture Sequence Modelling, in Proceedings of International Conference on Healthcare Informatics, Philadelphia, pp. 376- 381, 2013.

[17] Elert G., The Physics Hypertextbook, available at: http://www.physics.info, Last Visited, 2012.

[18] Fischer I., Krauss M., Dunagan W., Birge S., Hitcho E., Johnson S., Costantinou E., and Fraser J., Patterns and Predictors of Inpatient Falls and Fall-Related Injuries in a Large Academic Hospital, Infection Control and Hospital Epidemiology, vol. 26, no. 10, pp. 822-827, 2005.

[19] Han J. and Kamber M., Data Mining Concepts and Techniques, Morgan Kaufmann Publishers, 2011.

[20] Haykin S., Neural Networks and Learning Machines, Prentice Hall, 2008.

[21] Jacob J., Nguyen T., Lie D., Zupancic S., Bishara J., Dentino A., and Banister R., A Fall Detection Study on the Sensors Placement Location and a Rule-Based Multi-Thresholds Algorithm Using both Accelerometer and Gyroscopes, in Proceedings of International Conference on Fuzzy Systems, Taipei, pp. 666-671, 2011.

[22] Jain Y. and Bhandare S., Min Max Normalization Based Data Perturbation Method for Privacy Protection, International Journal of Computer and Communication Technology, vol. 2, no. 8, pp. 45-50, 2011.

[23] Kangas M., Konttila A., Winblad I., and J ms T., Determination of Simple Thresholds for Accelerometry-Based Parameters for Fall Detection, in Proceedings of the 29th Annual International Conference of Engineering in Medicine and Biology Society, Lyon, pp. 1367- 1370, 2007.

[24] Kawatsu C., Li J., and Chung C., Development of a Fall Detection System with Microsoft Kinect, in Proceedings of the 1st International Conference on Robot Intelligence Technology and Applications, Gwangju, pp. 623-630, 2013.

[25] Kim K. and Ashton-Miller J., Biomechanics of Fall Arrest Using the Upper Extremity: Age Differences, Journal of Clinical Biomechanics, vol. 18, no. 4, pp. 311-318, 2003.

[26] Knee Pain Health Center, available at: http://www.webmd.com/pain-management/knee- pain/knee-problems-and-injuries-topic-overview, Last Visited, 2015.

[27] Kwolek B. and Kepski M., Human Fall Detection on Embedded Platform Using Depth Maps and Wireless Accelerometer, Computer Methods and Programs in Biomedicine, vol. 117, no. 3, pp. 489-501, 2014.

[28] Leskovec J., Rajaraman A., and Ullman J., Mining of Massive Datasets, Stanford, 2014.

[29] Ma X., Wang H., Xue B., Zhou M., Ji B., and Li Y., Depth-Based Human Fall Detection Via Shape Features and Improved Extreme Learning Machine, Journal of Biomedical and Health Informatics, vol. 18, no. 6, pp. 1915-1922, 2014.

[30] Magaziner J., Hawkes W., Hebel J., Zimmerman S., Fox K., Dolan M., Felsenthal G., and Kenzora J., Recovery from Hip Fracture in Eight Areas of Function, Journal of Gerontology, vol. 55, no. 9, pp. 498-507, 2000.

[31] Marjoux D., Baumgartner D., Deck C., and Willinger R., Head Injury Prediction Capability of the HIC, HIP, SIMon and ULP Criteria, Accident; Analysis and Prevention, vol. 40, no. 3, pp. 1135-1148, 2008.

[32] Mastorakis G. and Makris D., Fall Detection System Using Kinect s Infrared Sensor, Journal of Real-Time Image Processing, vol. 9, no. 4, pp. 635 - 646, 2014.

[33] Murthy C., Harish S., and Chandra Y., The Study of Pattern of Injuries in Fatal Cases of Fall from Height, Journal of Medical Sciences, vol. 5, no. 1, pp. 45-52, 2012.

[34] Nghiem A., Auvinet E., Meunier J., Head Detection Using Kinect Camera and Its Application to Fall Detection, in Proceedings of the 11th International Conference on Information Science, Signal Processing and their Applications, Montreal, pp. 164-169, 2012.

[35] Noury N., Fleury A., Rumeau P., Bourke A., Laighin G., Rialle V., and Lundy J., Fall Detection-Principles and Methods, in Proceedings of the 29th International Conference of the Engineering in Medicine and Biology Society, Lyon, pp. 1663-1666, 2007.

[36] O'Keefe G. and Jurkovich G., Injury Control a Guide to Research and Program Evaluation, Cambridge University Press, 2000. 388 The International Arab Journal of Information Technology, Vol. 15, No. 3, May 2018

[37] OpenNI, available at: https://github.com/OpenNI/OpenNI, Last Visited, 2014.

[38] Patsadu O., Nukoolkit C., and Watanapa B., Survey of Smart Technologies for Fall Motion Detection: Techniques, Algorithms and Tools, in Proceedings of the 5th International Conference on Advances in Information Technology, Bangkok, pp. 137-147, 2012.

[39] Planinc R. and Kampel M., Introducing the Use of Depth Data for Fall Detection, Journal of Personal and Ubiquitous Computing, vol. 17, no. 6, pp. 1063-1072 , 2013.

[40] Rougier C., Auvinet E., Rousseau J., Mignotte M., and Meunier J., Fall Detection from Depth Map Video Sequences, in Proceedings of the 9th International Conference on Smart Homes and Health Telematics, Montreal, pp. 121-128, 2011.

[41] Schneider E., Shubert T., and Harmon K., Addressing the Escalating Public Health Issue of Falls Among Older Adults, Medical Society of the State of North Carolina, vol. 71, no. 6, pp. 547-552, 2010.

[42] Schulz B., Lee W., and Lloyd J., Estimation, Simulation, and Experimentation of a Fall from Bed, Journal of Rehabilitation Research and Development, vol. 45, no. 8, pp. 1227-1236, 2008.

[43] Stone E. and Skubic M., Fall Detection in Homes of Older Adults Using the Microsoft Kinect, Journal of Biomedical and Health Informatics, vol. 19, no. 1, pp. 290-301, 2015.

[44] Tran T., Le L., and Morel J., An Analysis on Human Fall Detection Using Skeleton from Microsoft Kinect, in Proceedings of the 5th International Conference on Communications and Electronics, Danang, pp. 484-489, 2014.

[45] Uddin M., Kim D., and Kim T., A Human Activity Recognition System Using HMMs with GDA on Enhanced Independent Component Features, The International Arab Journal of Information Technology, vol. 12, no. 3, pp. 304- 310, 2015.

[46] Versace J., A Review of the Severity Index, in Proceedings of the 15th Stapp Car Crash Conference, Coronado, pp. 771-796, 1971.

[47] Yu X., Approaches and Principles of Fall Detection for Elderly and Patient, in Proceedings of the 10th International Conference on E-health Networking, Applications and Services, Singapore, pp. 42-47, 2008. Orasa Patsadu received her B.B.A. degree in Computer Information Systems from Rajamangala University of Technology Krungthep, Thailand, in 2007 and M.Sc. in Software Engineering from King Mongkut's University of Technology Thonburi, Thailand in 2010. Since April 2011, she has been pursuing the Ph.D. in School of Information Technology, King Mongkut's University of Technology Thonburi. Her research interests include data mining and software engineering. Bunthit Watanapa received his B.Eng. in Computer Engineering from King Mongkut's Institute of Technology Ladkrabang, Thailand, in 1987 and M.Eng. and Ph.D. in Industrial Engineering from Asian Institute of Technology (AIT), Thailand, in 1990 and 2003, respectively. Currently he is the chairperson of the Business Information System program at the School of Information Technology, King Mongkut's University of Technology Thonburi, Thailand. His research interests are in the area of Decision Support System, Optimization, and Project Management. Piyapat Dajpratham received her M.D. from Mahidol University, Bangkok, Thailand in 1992 and Diplomat Thai Board of Rehabilitation Medicine from Faculty of Medicine Siriraj Hospital in 1997. She had fellowship training in Neurorehabilitation & Geriatric Rehabilitation from Northwestern Healthcare Network, University of Melbourne, Australia in 1998 and 1999 respectively. Currently she is an Associate Professor in Rehabilitation Medicine, Faculty of Medicine Siriraj Hospital, Bangkok, Thailand. Her research interests are stroke rehabilitation and falling in the elderly. Chakarida Nukoolkit received her B.Sc. in Computer Science from Thammasat Univerisity, Thailand in 1992 and M.Sc. in Computer Science from Vanderbilt University, U.S.A. in 1995 and Ph.D. in Computer Science from University of Alabama, U.S.A. in 2001. Previously she had led the Data and Knowledge Engineering Lab at the School of Information Technology, King Mongkut's University of Technology Thonburi, Thailand. Her current research interests are in the area of data mining, data science, visualizations, creative computing, bioinformatics, and artificial intelligence.