Abstract
Human falls are common source of injury among the elderly, because often the elderly person is injured and cannot call for help. In the literature this is addressed by various fall-detection systems, of which most common are the ones that use wearable sensors. This paper describes the winning method developed for the Challenge Up: Multimodal Fall Detection competition. It is a multi-sensor data-fusion machine-learning method that recognizes human activities and falls using 5 wearable inertial sensors: accelerometers and gyroscopes. The method was evaluated on a dataset collected by 12 subjects of which 3 were used as a test-data for the challenge. In order to optimally adapt the method to the 3 test subjects, we performed an unsupervised similarity search—that finds the three most similar users to the three users in the test data. This helped us to tune the method and its parameters to the 3 most similar users as the ones used for the test. The internal evaluation on the 9 users showed that with this optimized configuration the method achieves 98% accuracy. During the final evaluation for the challenge, our method achieved the highest results (82.5% F1-score, and 98% accuracy) and won the competition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The Challenge Up Multimodal Competition, available at: https://sites.google.com/up.edu.mx/challenge-up-2019/overview.
- 2.
The code developed for the challenge is available at: https://github.com/challengeupwinner/challengeupcode.
References
Asch, V.V.: Macro- and micro-averaged evaluation measures. Comput. Sci. (2013)
Aziz, O., Musungi, M., Park, E.J., Mori, G., 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. J. Med. Biol. Eng. Comput. 55(1), 45–55 (2017)
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J Mach. Learn. Res. 13, 281–305 (2012)
Bourbia, A.L., Son, H., Shin, B., Kim, T., Lee, D., Hyun, S.J.: Temporal dependency rule learning based group activity recognition in smart spaces (2016)
Chen, T., Guestrin, C.: XGBoost: A scalable tree boosting system. In: ACM SIGKDD International Conference, vol. 22, pp. 785–794 (2016)
Degen, T., Jaeckel, H., Rufer, M., Wyss, S.: SPEEDY: A fall detector in a wrist watch. In: Proceeding Seventh IEEE International Symposium on Wearable Computing, pp. 184–187 (2003)
Doughty, K., Lewis, R., McIntosh, A.: The design of a practical and reliable fall detector for community and institutional telecare. J. Telemed. Telecare 6, S150–S154 (2000)
Friedman, S.M., Munoz, B., West, S.K., Rubin, G.S., Fried, L.P.: Falls and fear of falling: Which comes first? A longitudinal prediction model suggests strategies for primary and secondary prevention. J. Am. Geriatr. Soc. 1329–1335 (2000)
Friedman, A., Chehade, N.H., Chien, C., Pottie, G.: Estimation of accelerometer orientation for activity recognition, pp. 2076–2079. Engineering in Medicine and Biology Society (EMBC) (2012)
Gillespie, L.D., Robertson, M.C., Gillespie, W.J., Lamb, S.E., Gates, S., Cumming, R.G., Rowe, B.H.: Interventions for preventing falls in older people living in the community (review). The Cochrane Library, 4 (2009)
Gislason, P.O., Benediktsson, J.A., Sveinsson, J.R.: Random forests for land cover classification. Pattern Recogn. Lett. 27(4), 294–300 (2006)
Gjoreski, H., Bizjak, J., Gams, M.: Using smartwatch as telecare and fall detection device. In: 12th International Conference on Intelligent Environments (IE), pp. 242–245 (2016a)
Gjoreski, M., Gjoreski, H., Luštrek, M., Gams, M.: How accurately can your wrist device recognize daily activities and detect falls? Sensors 16(6), 800 (2016b)
Gjoreskic, H., Gams, M., Luštrek, M.: Context-based fall detection and activity recognition using inertial and location sensors. J. Ambient Intell. Smart Env. 6(4), 419–433 (2014)
Gjoreski, H., Lustrek, M., Gams, M.: Accelerometer placement for posture recognition and fall detection. In: Seventh International Conference on Intelligent Environments, pp. 47–54 (2011)
Gjoreski, H., Gams, M., Lutrek, M.: Human activity recognition: from controlled lab experiments to competitive live evaluation. In: IEEE International Conference on Data Mining Workshop (ICDMW), pp. 139–145 (2015)
Hammerla, N.Y., Halloran, S., Plotz, T.: Deep, convolutional, and recurrent models for human activity recognition using wearables (2016)
Hardjianto, M., Istiyanto, J.E., Putra, A.E.: Fall detection on humans using threshold method based on smartphone accelerometer data (2017)
Janko, V., Gjoreski, M., Slapničar, G., Mlakar, M., Reščič, N., Bizjak, J., Drobnič, V., Marinko, M., Mlakar, N., Gams, M., Luštrek, M.: Winning the Sussex-Huawei locomotion-transportation recognition challenge. In: Kawaguchi, N., Nishio, N., Roggen, D., Inoue, S., Pirttikangas, S., Van Laerhoven, K. (eds.) Human Activity Sensing. Springer Series in Adaptive Environments. Springer, Cham (2019)
Kozina, S., Gjoreski, H., Gams, M., Luštrek, M.: Three-layer activity recognition combining domain knowledge and meta- classification. JMBE 33(4), 406–414 (2013)
Lai, C., Huang, Y.M., Park, J.H., Chao, H.C.: Adaptive body posture analysis for elderly-falling detection with multisensors. IEEE Intell. Syst. 25, 2–11 (2010)
Lustrek, M., Gjoreski, H., Vega, N.G., Kozina, S., Cvetkovic, B., Mirchevska, V., Gams, M.: Fall detection using location sensors and accelerometers. IEEE Pervas. Comput. 14(4), 72–79 (2015)
Miguel, K., Brunete, A., Hernando, M., Gambao, E.: Home camera-based fall detection system for the elderly. Sensors (2017)
Putra, I., Brusey, J., Gaura, E., Vesilo, R.: An event-triggered machine learning approach for accelerometer-based fall detection (2017a)
Putra, P., Brusey, J., Gaura, E., Vesilo, R.: An event-triggered machine learning approach for accelerometer-based fall detection (2017b)
Ren, L., Shi, W.: Chameleon: Personalised and adaptive fall detection of elderly people in home-based environments (2016)
Ronao, C.A., Cho, S.-B.: Human activity recognition with smartphone sensors using deep learning neural networks. Expert Syst. Appl. 59, 235–244 (2016)
Tinetti, M.E., Williams, C.S.: Falls, injuries due to falls, and the risk of admission to a nursing home. The New England J Medicine 337, 1279–1284 (1997)
Wang, Y., Witten, I.H.: Induction of model trees for predicting continuous classes. Eur. Conf. Mach. Learn. 9, 128–137 (1996)
Ward, J.A., Lukowicz, P., Gellersen, H.W.: Performance metrics for activity recognition. ACM transactions on intelligent systems and technology (2011)
Williams, G., Doughty, K., Cameron, K., Bradley D.A: A smart fall and activity monitor for telecare applications. In: Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (1998)
World Health Organization (WHO): Global brief for World Health Day, Good health adds life to years. (2012) http://whqlibdoc.who.int/hq/2012/WHO_DCO_WHD_2012.2_eng.pdf
Wu, F., Zhao, H., Zhao, Y., Zhong, H.: Development of a wearable-sensor-based fall detection system. Int. J. Telemed. Appl. (2015)
Zhang, S., Wei, Z., Nie, J., Huang, L., Wang, S., Li1, Z.: A review on human activity recognition using vision-based method. J Healthcare Eng (2017)
Acknowledgements
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. The authors declare that they have no conflict of interest.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic Supplementary Material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Gjoreski, H. et al. (2020). Wearable Sensors Data-Fusion and Machine-Learning Method for Fall Detection and Activity Recognition. In: Ponce, H., Martínez-Villaseñor, L., Brieva, J., Moya-Albor, E. (eds) Challenges and Trends in Multimodal Fall Detection for Healthcare. Studies in Systems, Decision and Control, vol 273. Springer, Cham. https://doi.org/10.1007/978-3-030-38748-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-38748-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-38747-1
Online ISBN: 978-3-030-38748-8
eBook Packages: EngineeringEngineering (R0)