LSTM Gate Disclosure as an Embedded AI Methodology for Wearable Fall-Detection Sensors
Open Access
Abstract
In this paper, the concept of symmetry is used to design the efficient inference of a fall-detection algorithm for elderly people on embedded processors—that is, there is a symmetric relation between the model’s structure and the memory footprint on the embedded processor. Artificial intelligence (AI) and, more particularly, Long Short-Term Memory (LSTM) neural networks are commonly used in the detection of falls in the elderly population based on acceleration measures. Nevertheless, embedded systems that may be utilized on wearable or wireless sensor networks have a hurdle due to the customarily massive dimensions of those networks. Because of this, the algorithms’ most popular implementation relies on edge or cloud computing, which raises privacy concerns and presents challenges since a lot of data need to be sent via a communication channel. The current work proposes a memory occupancy model for LSTM-type networks to pave the way to more efficient embedded implementations. Also, it offers a sensitivity analysis of the network hyper-parameters through a grid search procedure to refine the LSTM topology network under scrutiny. Lastly, it proposes a new methodology that acts over the quantization granularity for the embedded AI implementation on wearable devices. The extensive simulation results demonstrate the effectiveness and feasibility of the proposed methodology. For the embedded implementation of the LSTM for the fall-detection problem on a wearable platform, one can see that an STM8L low-power processor could support a 40-hidden-cell LSTM network with an accuracy of .
Keywords
Funding Information
- Fundação para a Ciência e a Tecnologia (UIDB/04111/2020, CEECINST/00147/2018/CP1498/CT0015, UIDB/05064/202, POCI-05-5762-FSE-000191, COFAC/ILIND/COPELABS/1/2020)
- Fundação para a Ciência e a Tecnologia (UIDB/04111/2020, CEECINST/00147/2018/CP1498/CT0015, UIDB/05064/202, POCI-05-5762-FSE-000191, COFAC/ILIND/COPELABS/1/2020)
- Instituto Lusófono de Investigação e Desenvolvimento (ILIND) (UIDB/04111/2020, CEECINST/00147/2018/CP1498/CT0015, UIDB/05064/202, POCI-05-5762-FSE-000191, COFAC/ILIND/COPELABS/1/2020)
This publication has 46 references indexed in Scilit:
- Application of ensemble RNN deep neural network to the fall detection through IoT environmentAlexandria Engineering Journal, 2021
- Elderly fall detection based on multi-stream deep convolutional networksMultimedia Tools and Applications, 2020
- Deep learning: RNNs and LSTM2020
- A comprehensive study on the use of artificial neural networks in wearable fall detection systemsExpert Systems with Applications, 2019
- Stochastic Quantization for Learning Accurate Low-Bit Deep Neural NetworksInternational Journal of Computer Vision, 2019
- Intelligence in Embedded Systems: Overview and Applications2018
- Revisit, Subsequent Hospitalization, Recurrent Fall, and Death Within 6 Months After a Fall Among Elderly Emergency Department PatientsAnnals of Emergency Medicine, 2017
- Decision tree analysis of construction fall accidents involving roofersExpert Systems with Applications, 2015
- A fall detection system using k-nearest neighbor classifierExpert Systems with Applications, 2010
- Fall Detection by Wearable Sensor and One-Class SVM Algorithm2006