Accidental falls have an enormous human cost, especially for elderly people, so there is need for automatic fall detection techniques for timely warnings.

We have used smart wearable devices and deep learning on embedded to detect falls with recurrent neural networks. The implementation challenge was due to limited computing and memory resources and to the necessity of battery life for continuous use (24x7).



Datasets with simulated falls by volunteers have been collected: seven carry positions, seventeen different activities, forty volunteers, over five thousands tracks. Manual annotations on videos, basic for training, have been done.

 

Related publications

• Mirto Musci, Marco Piastra (2021). Recurrent Neural Networks Architectures for Accidental Fall Detection on Wearable Embedded Devices, in M. Elloumi (ed.), Deep Learning for Biomedical Data Analysis, pp. 81-98, Springer, Cham, DOI:10.1007/978-3-030-71676-9_4.
• Mirto Musci, Daniele De Martini, Nicola Blago, Tullio Facchinetti, Marco Piastra (2020). Online Fall Detection using Recurrent Neural Networks on Smart Wearable Devices, in IEEE Transactions on Emerging Topics in Computing, DOI:10.1109/TETC.2020.3027454.
• Emanuele Torti, Alessandro Fontanella, Mirto Musci, Nicola Blago, Danilo Pau, Francesco Leporati, Marco Piastra (2019). Embedding Recurrent Neural Networks in Wearable Systems for Real-Time Fall Detection, in Microprocessors and Microsystems, Elsevier, DOI:10.1016/j.micpro.2019.102895
• Emanuele Torti, Mirto Musci, Federico Guareschi, Francesco Leporati, Marco Piastra (2019). Deep Recurrent Neural Networks for Edge Monitoring of Personal Risk and Warning Situations, in Scientific Programming, Wiley Online Library, DOI:10.1155/2019/9135196
• Torti Emanuele, Fontanella Alessandro, Musci Mirto, Blago Nicola, Pau Danilo, Leporati Francesco, Piastra Marco (2018). Embedded Real-Time Fall Detection with Deep Learning on Wearable Devices, 21^st Euromicro Conference on Digital System Design (DSD), August 2018, DOI:10.1109/DSD.2018.00075