Deep recurrent neural networks distributed on a Hadoop/Spark cluster for fall detection

Deep recurrent neural networks for fall detection


  • Monia Hamdi Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
  • Heni Bouhamed Advanced Technologies for Image and Signal Processing Unit (ATISP), Sfax University, Sfax, Tunisia
  • Fady Badreddine Advanced Technologies for Image and Signal Processing Unit (ATISP), Sfax University, Sfax, Tunisia
  • Reem Ibrahim Alkanhel Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University



big data, collaborative filtering, deep neural network, recommendation system.


Falls detection approaches struggle with both Big Data scalability and upholding individual privacy, this research work proposed a novel approach for posture recognition followed by fall detection, taking advantage of the synergy between Random Forests and Uniform Local Binary Patterns (uLBP) histograms for an accurate and fast posture identification while respecting privacy. Additionally, it referred to deep recurrent neural networks distributed on a Hadoop and Spark platform for time series analysis in fall detection. This combination of methods allowed us to achieve acceptable real-time monitoring precision. This study, therefore addressed two objectives simultaneously: efficiency and scalability in posture recognition using Random Forests and uLBP, and fall detection relying on the recurrent neural network (RNN) for time series processing. The suggested solution is designed for home telemonitoring, where scalability and effective data management are supported through Hadoop/Spark. The integration of these technologies promotes reliable detection without any privacy violation, paving the way for a wider adoption of home monitoring systems for an increasing population of dependent individuals.


S. Heinrich, K. Rapp, U. Rissmann, C. Becker, and H.-H. König, "Cost of falls in old age : A systematic review," Osteoporosis international : a journal established as result of cooperation between the European Foun- dation for Osteoporosis and the National Osteoporosis Foundation of the USA, vol. 21, pp. 891-902, 11 2009.

N. Noury, A. Fleury, P. Rumeau, A. Bourke, G. ÓLaighin, V. Rialle, and J.-E. Lundy, "Fall detection - principles and methods," Conference pro- ceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, vol. 2007, pp. 1663-6, 02 2007.

S. Herath, M. Harandi, and F. Porikli, "Going deeper into action recogni- tion : A survey," Image and Vision Computing, vol. 60, 05 2016.

J. Peña Queralta, T. Nguyen gia, H. Tenhunen, and T. Westerlund, "Edge- ai in lora-based health monitoring : Fall detection system with fog compu- ting and lstm recurrent neural networks," 07 2019.

D. Lie, B. Nukala, N. Shibuya, A. Rodriguez, J. Tsay, T. Nguyen, S. Zu- pancic, and D. Lie, "A wireless gait analysis sensor for real-time robust fall detection using an artificial neural network," 10 2014.

S. Gharghan, S. Mohammed, and A. A. Al-Naji, "Accurate fall detection and localization for elderly people based on neural network and energy- efficient wireless sensor network," Energies, vol. 11, p. 2866, 10 2018.

M. Majd and R. Safabakhsh, "A motion-aware convlstm network for ac- tion recognition," Applied Intelligence, vol. 49, pp. 1-7, 07 2019.

Y. Li, Y. Guanci, Z. Su, S. Li, and Y. Wang, "Human activity recognition based on multi environment sensor data," Information Fusion, vol. 91, pp. 47-63, 10 2022.

G. Diraco, A. Leone, and P. Siciliano, "Human posture recognition with a time-of-flight 3d sensor for in-home applications," Expert Systems with Applications, 02 2013.

F. Modarres and M. Soryani, "Body posture graph : A new graph-based posture descriptor for human behavior recognition," Computer Vision, IET, vol. 7, pp. 488-499, 12 2013.

B. Boulay and M. Thonnat, "Applying 3d human model in a posture re- cognition system," Pattern Recognition Letters, vol. 27, pp. 1788-1796, 11 2006.

H. Li and Q. Sun, "The recognition of moving human body posture based on combined neural network," pp. 1-5, 01 2013.

AlFayez, F.; Bouhamed, H. (2023). Machine learning and uLBP histograms for posture recognitionof dependent people via Big Data Hadoop and Spark platform,International Journal of ComputersCommunications & Control, 18(1), 4981, 2023.

D. Lord, C.J. ; Colvin, "Falls in the elderly : Detection and assessment," IEEE Annual International Conference of the IEEE Engineering in Medi- cine and Biology Society, vol. 13, p. 1938-1939, 02 1991.

G. Williams, K. Doughty, K. Cameron, and D. Bradley, "A smart fall and activity monitor for telecare applications," vol. 3, pp. 1151 - 1154 vol.3, 01 1998.

A. Bourke, J. O'Brien, and G. ÓLaighin, "Evaluation of a threshold-based tri-axial accelerometer," J Gait and Posture, vol. 26, pp. 194-199, 01 2006.

A. Bourke and G. ÓLaighin, "A threshold-based fall-detection algorithm using a bi-axial gyroscope sensor," Medical engineering physics, vol. 30, pp. 84-90, 02 2008.

P. Tsinganos and A. Skodras, "On the comparison of wearable sensor data fusion to a single sensor machine learning technique in fall detection," Sensors, vol. 18, p. 592, 02 2018.

Q. Li, J. Stankovic, M. Hanson, A. Barth, J. Lach, and G. Zhou, "Accurate, fast fall detection using gyroscopes and accelerometer-derived posture in- formation," pp. 138-143, 06 2009.

C. Rougier, J. Meunier, A. St-Arnaud, and J. Rousseau, "Robust video surveillance for fall detection based on human shape deformation," Circuits and Systems for Video Technology, IEEE Transactions on, vol. 21, pp. 611- 622, 06 2011.

G. Diraco, A. Leone, and P. Siciliano, "An active vision system for fall detection and posture recognition in elderly healthcare," pp. 1536-1541, 03 2010.

L. Xue, L. Nie, H. Xu, and X. Wang, "Collaborative fall detection using smart phone and kinect," Mobile Networks and Applications, vol. 23, 08 2018.

M. Saleh and R. Le Bouquin Jeannès, "Elderly fall detection using wea- rable sensors : A low cost highly accurate algorithm," IEEE Sensors Jour- nal, vol. PP, pp. 1-1, 01 2019.

T. Wu, Y. Gu, Y. Chen, Y. Xiao, and J. Wang, "A mobile cloud collabora- tion fall detection system based on ensemble learning," 07 2019.

Q. Han, H. Zhao, W. Min, H. Cui, X. Zhou, K. Zuo, and R. Liu, "A two- stream approach to fall detection with mobilevgg," IEEE Access, vol. PP, pp. 1-1, 01 2020.

A. Shojaei, P. Nasiopoulos, J. Little, and M. Pourazad, ""video-based hu- man fall detection in smart homes using deep learning"," pp. 1-5, 05 2018.

B. Kwolek and M. Kepski, "Human fall detection on embedded platform using depth maps and wireless accelerometer," Computer Methods and Programs in Biomedicine, vol. 117, p. 489-501, 10 2014.

E. Auvinet, C. Rougier, J. Meunier, A. St-Arnaud, and J. Rousseau, "Multiple cameras fall data set," 01 2011.

T. O. M. P. D. Harwood, "A comparative study of texture measures with classification based on featured distributions," Pattern Recognition, vol. 29, p. 51-59, 1996.

L. Breiman, "Random forests," Machine Learning, vol. 45, pp. 5-32, 10 2001.

L. MARKÉTA KRÚPOVÁ, Construction d'un modèle de Machine Lear- ning interprétable pour la tarification en assurance non-vie. PhD thesis, Université de Paris-Dauphine, 12 2022.

R. DE, H. GE, and W. RJ, Learning internal representations by error pro- pagation : Parallel Distributed Processing, Volume 1 : Foundations. 01 1986.

Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, pp. 436-44, 05 2015.

Y. Bengio, P. Simard, and P. Frasconi, "Learning long-term dependencies with gradient descent is difficult," IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council, vol. 5, pp. 157-66, 02 1994.

S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, pp. 1735-1780, 11 1997.

F. Gers, J. Schmidhuber, and F. Cummins, "Learning to forget : Continual prediction with lstm," Neural computation, vol. 12, pp. 2451-71, 10 2000.

c.-m. Own, F. Sha, and W. Tao, "Triplet decoders neural network ensemble system and tconversion for traffic speed sequence prediction," IEEE Ac- cess, vol. PP, pp. 1-1, 11 2019.

J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, "Empirical evaluation of gated recurrent neural networks on sequence modeling," 12 2014.

S. Abdulwahab, M. Jabreel, and D. Moreno, Deep Learning Models for Paraphrases Identification. PhD thesis, 09 2017.

"Hdfs," https :// dist/Hadoop hdfs/HdfsDesign.html. Consulté le 12/06/2023.

"Yarn," https :// yarn-site/YARN.html. Consulté le 12/06/2023.

"opencv," https :// Consulté le 12/06/2023.

scikit-image developers, "scikit-image : Image processing in python," 2023.

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, et al., "Tensorflow : A system for large- scale machine learning," in 12th USENIX Symposium on Operating Sys- tems Design and Implementation (OSDI 16), pp. 265-283, 2016.

F. Chollet et al., "Keras," GitHub, 2015.

M. Pumperla, "elephas," GitHub, 2015.

B.-H. Wang, J. Yu, K. Wang, X.-Y. Bao, and K.-M. Mao, "Fall detection based on dual-channel feature integration," IEEE Access, vol. PP, pp. 1-1, 06 2020.

F. Harrou, N. Zerrouki, Y. Sun, and A. Houacine, "An integrated vision- based approach for efficient human fall detection in a home environment," IEEE Access, vol. PP, pp. 1-1, 08 2019.

B. Dai, D. Yang, L. Ai, and P. Zhang, "A novel video-surveillance-based algorithm of fall detection," pp. 1-6, 10 2018.

M. Agrawal and S. Agrawal, "Enhanced deep learning for detecting suspicious fall event in video data," Intelligent Automation Soft Computing, vol. 36, pp. 2653-2667, 01 2023.

M. Mousse, C. Motamed, and E. Ezin, "Percentage of human-occupied areas

A., Raza, M. H., Yousaf, S. A., Velastin, & S. Viriri, (2023). Human Fall Detection from Sequences of Skeleton Features using Vision Transformer. In VISIGRAPP (5: VISAPP) (pp. 591-598) 2023.

X., Kan, S., Zhu, Y., Zhang, & C. Qian, (2023). A lightweight human fall detection network. Sensors, 23(22), 9069.

Y.,Wang, & T. Deng, (2024). Enhancing elderly care: Efficient and reliable real-time fall detection algorithm. Digital health, 10, 20552076241233690 2024.

C., Yuan, P., Zhang, Q., Yang, & J. Wang, (2022). Fall detection and direction judgment based on posture estimation. Discrete dynamics in nature and society, 2022.

S., Zou, W., Min, L., Liu, Q., Wang, & X., Zhou, (2021). Movement tube detection network integrating 3d cnn and object detection framework to detect fall. Electronics, 10(8), 898, 2021.

S., Chhetri, A., Alsadoon, T., Al-Dala'in, P. W. C., Prasad, T. A., Rashid, & A. Maag, (2021). Deep learning for vision-based fall detection system: Enhanced optical dynamic flow. Computational Intelligence, 37(1), 578-595.

P., Geng, H., Xie, H., Shi, R., Chen, & Y. Tong, (2022). Pedestrian Fall Event Detection in Complex Scenes Based on Attention-Guided Neural Network. Mathematical Problems in Engineering, 2022.

Additional Files



Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.