Deep Recurrent Neural Networks for Edge Monitoring of Personal Risk and Warning Situations

Accidental falls are the main cause of fatal and nonfatal injuries, which typically lead to hospital admissions among elderly people. A wearable system capable of detecting unintentional falls and sending remote notifications will clearly improve the quality of the life of such subjects and also helps to reduce public health costs. In this paper, we describe an edge computing wearable system based on deep learning techniques. In particular, we give special attention to the description of the classification and communication modules, which have been developed by keeping in mind the limits in terms of computational power, memory occupancy, and power consumption of the designed wearable device. The system thus developed is capable of classifying 3D-accelerometer signals in real-time and to issue remote alerts while keeping power consumption low and improving on the present state-of-the-art solutions in the literature.

[1]  B. Hu,et al.  Machine learning algorithms based on signals from a single wearable inertial sensor can detect surface- and age-related differences in walking. , 2018, Journal of biomechanics.

[2]  Gaetano Patti,et al.  Multi-Hop Real-Time Communications Over Bluetooth Low Energy Industrial Wireless Mesh Networks , 2018, IEEE Access.

[3]  Adrian Burns,et al.  SHIMMER™ – A Wireless Sensor Platform for Noninvasive Biomedical Research , 2010, IEEE Sensors Journal.

[4]  Jaouhar Mouine,et al.  Design and implementation of a fall detection system on a Zynq board , 2016, 2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA).

[5]  M N Nyan,et al.  A wearable system for pre-impact fall detection. , 2008, Journal of biomechanics.

[6]  Giuseppe Lami,et al.  Deep Learning in Automotive Software , 2017, IEEE Software.

[7]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[8]  Hannu Tenhunen,et al.  Energy efficient wearable sensor node for IoT-based fall detection systems , 2018, Microprocess. Microsystems.

[9]  Vangelis Metsis,et al.  SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning , 2018, Sensors.

[10]  Ahmed Nait Aicha,et al.  Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry , 2018, Sensors.

[11]  Mirto Musci,et al.  Embedded Real-Time Fall Detection with Deep Learning on Wearable Devices , 2018, 2018 21st Euromicro Conference on Digital System Design (DSD).

[12]  Dan Milea,et al.  Embedded deep learning in ophthalmology: making ophthalmic imaging smarter , 2018, Therapeutic advances in ophthalmology.

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  Suparna Biswas,et al.  On Fall Detection Using Smartphone Sensors , 2018, 2018 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET).

[15]  Daniele De Martini,et al.  Fall Detection with Supervised Machine Learning using Wearable Sensors , 2019, 2019 IEEE 17th International Conference on Industrial Informatics (INDIN).

[16]  Inmaculada Plaza,et al.  Challenges, issues and trends in fall detection systems , 2013, Biomedical engineering online.

[17]  Ki-Hyung Kim,et al.  A real-time fall detection system based on the acceleration sensor of smartphone , 2017 .

[18]  Tzyy-Ping Jung,et al.  Fall Prediction and Prevention Systems: Recent Trends, Challenges, and Future Research Directions , 2017, Sensors.

[19]  Danilo Pau,et al.  Efficient light harvesting for accurate neural classification of human activities , 2018, 2018 IEEE International Conference on Consumer Electronics (ICCE).

[20]  Md. Zahurul Islam,et al.  A direction-sensitive fall detection system using single 3D accelerometer and learning classifier , 2016, 2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec).

[21]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[22]  Dae-Hyeong Kim,et al.  Wearable Fall Detector using Integrated Sensors and Energy Devices , 2015, Scientific Reports.

[23]  Yakup Genc,et al.  Applying Deep Learning in Augmented Reality Tracking , 2016, 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[24]  Fu-Shan Jaw,et al.  Smartphone-based fall detection algorithm using feature extraction , 2016, 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[25]  Maurizio Rebaudengo,et al.  A Neural Network Model Based on Co-occurrence Matrix for Fall Prediction , 2016, MobiHealth.

[26]  Madhushee Gangali,et al.  Getting started with Bluetooth , 2002 .

[27]  Daniele De Martini,et al.  Online Fall Detection Using Recurrent Neural Networks on Smart Wearable Devices , 2018, IEEE Transactions on Emerging Topics in Computing.

[28]  M. A. Saleem Durai,et al.  Intelligent video surveillance: a review through deep learning techniques for crowd analysis , 2019, Journal of Big Data.