Fall Detection using Deep Learning Algorithms and Analysis of Wearable Sensor Data by Presenting a New Sampling Method

Document Type : Original Article

Authors

Department of Computer Engineering, Islamic Azad University, Babol Branch, Babol, Iran

Abstract

Fall is one of the most critical health challenges in the community, which can cause severe injuries and even death. The primary purpose of this study is to develop a deep neural network using wearable sensor data to detect falls. Most datasets in this field suffer from the problem of data imbalance so that the instances belonging to the Fall classes are significantly less than the data of the normal class. This study offers a dynamic sampling technique for increasing the balance rate between the samples belonging to fall and normal classes to improve the accuracy of the learning algorithms. The Sisfall dataset was used in which human activity is divided into three categories: normal activity (BKG), moments before the fall (Alert), and role on the ground (Fall). Three deep learning models, CNN, LSTM, and a hybrid model called Conv-LSTM, were implemented on this dataset, and their performance was evaluated. Accordingly, the Conv-LSTM hybrid model presents 96.23%, 98.59%, and 99.38% in the Sensitivity parameter for the BKG, Alert, and Fall classes, respectively. For the accuracy parameter, we have managed to reach 97.12%. In addition, by using noise smoothing and removal techniques, we can hit a 97.83% accuracy rate. The results indicate the proposed model's superiority compared to other similar studies.

Keywords

Main Subjects

References

  1. Florence, C.S., Bergen, G., Atherly, A., Burns, E., Stevens, J. and Drake, C., "Medical costs of fatal and nonfatal falls in older adults", Journal of the American Geriatrics Society, Vol. 66, No. 4, (2018), 693-698. doi: 10.1111/jgs.15304.
  2. Qiu, H. and Xiong, S., "Center-of-pressure based postural sway measures: Reliability and ability to distinguish between age, fear of falling and fall history", International Journal of Industrial Ergonomics, Vol. 47, (2015), 37-44. doi: 10.1016/j.ergon.2015.02.004.
  3. Organization, W.H., Ageing, W.H.O. and Unit, L.C., "Who global report on falls prevention in older age, World Health Organization, (2008).
  4. Zhang, D., Wang, H., Wang, Y. and Ma, J., "Anti-fall: A non-intrusive and real-time fall detector leveraging csi from commodity wifi devices", in International Conference on Smart Homes and Health Telematics, Springer., (2015), 181-193.
  5. Santos, G.L., Endo, P.T., Monteiro, K.H.d.C., Rocha, E.d.S., Silva, I. and Lynn, T., "Accelerometer-based human fall detection using convolutional neural networks", Sensors, Vol. 19, No. 7, (2019), 1644. doi: 10.3390/s19071644.
  6. Casilari, E., Lora-Rivera, R. and García-Lagos, F., "A study on the application of convolutional neural networks to fall detection evaluated with multiple public datasets", Sensors, Vol. 20, No. 5, (2020), 1466. doi: 10.3390/s20051466.
  7. Pannurat, N., Thiemjarus, S. and Nantajeewarawat, E., "Automatic fall monitoring: A review", Sensors, Vol. 14, No. 7, (2014), 12900-12936. doi: 10.3390/s140712900.
  8. Xu, T., Zhou, Y. and Zhu, J., "New advances and challenges of fall detection systems: A survey", Applied Sciences, Vol. 8, No. 3, (2018), 418. doi: 10.3390/app8030418.
  9. Chen, X., Xue, H., Kim, M., Wang, C. and Youn, H.Y., "Detection of falls with smartphone using machine learning technique", in 2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI), IEEE., (2019), 611-616.
  10. Özdemir, A.T., "An analysis on sensor locations of the human body for wearable fall detection devices: Principles and practice", Sensors, Vol. 16, No. 8, (2016), 1161. doi: 10.3390/s16081161.
  11. Ren, L. and Peng, Y., "Research of fall detection and fall prevention technologies: A systematic review", IEEE Access, Vol. 7, (2019), 77702-77722. doi: 10.1109/ACCESS.2019.2922708.
  12. Liang, S., Chu, T., Lin, D., Ning, Y., Li, H. and Zhao, G., "Pre-impact alarm system for fall detection using mems sensors and hmm-based svm classifier", in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE., (2018), 4401-4405.
  13. Wu, Y., Su, Y., Feng, R., Yu, N. and Zang, X., "Wearable-sensor-based pre-impact fall detection system with a hierarchical classifier", Measurement, Vol. 140, (2019), 283-292. doi: 10.1016/j.measurement.2019.04.002.
  14. Aziz, O., Musngi, M., Park, E.J., Mori, G. and Robinovitch, S.N., "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", Medical & Biological Engineering & Computing, Vol. 55, No. 1, (2017), 45-55. doi: 10.1007/s11517-016-1504-y.
  15. Özdemir, A.T. and Barshan, B., "Detecting falls with wearable sensors using machine learning techniques", Sensors, Vol. 14, No. 6, (2014), 10691-10708. doi: 10.3390/s140610691.
  16. Wang, J., Chen, Y., Hao, S., Peng, X. and Hu, L., "Deep learning for sensor-based activity recognition: A survey", Pattern Recognition Letters, Vol. 119, (2019), 3-11. doi: 10.1016/j.patrec.2018.02.010.
  17. LeCun, Y., Bengio, Y. and Hinton, G., "Deep learning", nature, Vol. 521, No. 7553, (2015), 436-444. doi: 10.1038/nature14539.
  18. Ordóñez, F.J. and Roggen, D., "Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition", Sensors, Vol. 16, No. 1, (2016), 115. doi: 10.3390/s16010115.
  19. Chen, Y. and Xue, Y., "A deep learning approach to human activity recognition based on single accelerometer", in 2015 IEEE international conference on systems, man, and cybernetics, IEEE., (2015), 1488-1492.
  20. Tao, X. and Yun, Z., "Fall prediction based on biomechanics equilibrium using kinect", International Journal of Distributed Sensor Networks, Vol. 13, No. 4, (2017), doi: 10.1177/1550147717703257.
  21. Torti, E., Fontanella, A., Musci, M., Blago, N., Pau, D., Leporati, F. and Piastra, M., "Embedding recurrent neural networks in wearable systems for real-time fall detection", Microprocessors and Microsystems, Vol. 71, (2019), 102895. doi: 10.1016/j.micpro.2019.102895.
  22. Musci, M., De Martini, D., Blago, N., Facchinetti, T. and Piastra, M., "Online fall detection using recurrent neural networks", arXiv preprint arXiv:1804.04976, (2018). doi: 10.48550/arXiv.1804.04976.
  23. Sucerquia, A., López, J.D. and Vargas-Bonilla, J.F., "Sisfall: A fall and movement dataset", Sensors, Vol. 17, No. 1, (2017), 198. doi: 10.3390/s17010198.
  24. Rastogi, S. and Singh, J., "A systematic review on machine learning for fall detection system", Computational Intelligence, Vol. 37, No. 2, (2021), 951-974. doi: 10.1111/coin.12441.
  25. Usmani, S., Saboor, A., Haris, M., Khan, M.A. and Park, H., "Latest research trends in fall detection and prevention using machine learning: A systematic review", Sensors, Vol. 21, No. 15, (2021), 5134. doi: 10.3390/s21155134.
  26. Syed, A.S., Sierra-Sosa, D., Kumar, A. and Elmaghraby, A., "A deep convolutional neural network-xgb for direction and severity aware fall detection and activity recognition", Sensors, Vol. 22, No. 7, (2022), 2547. doi: 10.3390/s22072547.
  27. Bourjandi, M., Yadollahzadeh Tabari, M. and Golsorkhtabaramiri, M., "Fuzzy centralized coordinate learning and hybrid loss for human activity recognition", International Journal of Engineering, Transactions A: Basics,, Vol. 35, No. 1, (2022), 130-141. doi: 10.5829/IJE.2022.35.01A.12.
  28. Siddharth, D., Saini, D. and Singh, P., "An efficient approach for edge detection technique using kalman filter with artificial neural network", International Journal of Engineering, Transactions C: Aspects,, Vol. 34, No. 12, (2021), 2604-2610. doi: 10.5829/IJE.2021.34.12C.04.
  29. Bourjandi, M., Yadollahzadeh‐Tabari, M. and Golsorkhtabaramiri, M., "Combined deep centralized coordinate learning and hybrid loss for human activity recognition", Concurrency and Computation: Practice and Experience, (2022), e6870. doi: 10.1002/cpe.6870.
  30. Bourjandi, M., Yadollahzadeh‐Tabari, M. and GolsorkhtabariAmiri, M., "Predicting user's movement path in indoor environments using the stacked deep learning method and the fuzzy soft‐max classifier", IET Signal Processing, (2022). doi: 10.1049/sil2.12125.
  31. Yu, X., Qiu, H. and Xiong, S., "A novel hybrid deep neural network to predict pre-impact fall for older people based on wearable inertial sensors", Frontiers in Bioengineering and Biotechnology, Vol. 8, (2020), 63. doi: 10.3389/fbioe.2020.00063.
International Journal of Engineering
Volume 35, Issue 10
TRANSACTIONS A: Basics
October 2022
Pages 1941-1958

Files

Cited by

Share

How to cite

Statistics