DeepEmote: Towards multi-layer neural networks in a low power wearable multi-sensors bracelet
Authors:
- 1 June 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 45, 32-37
Abstract
Wearable smart sensing is a promising technology to enhance user experience that has already been exploited in sport/fitness, as well as health and human monitoring. Wearable sensing systems not only provide continuous data monitoring and acquisition, but are also expected to process, and make sense of the acquired data by classification in similar ways as human experts do. Supporting continuous operation on ultra-small batteries poses unique challenges in energy efficiency. In this paper, we present an ultra-low-power bracelet with several sensors that is able to run multi-layer neural networks learning algorithms to process data efficiently. The design combines low-power design, energy efficient algorithms and makes this bracelet suitable for long-term uninterrupted usage with small coin batteries. We demonstrate in-field measurement results that prove that neural networks applications can fit within the mW power and memory envelope of a commercial ARM Cortex M4F microcontroller. We show that a fully connected network of 26 neurons achieve an accuracy of 100% on emotion detection, using only 2% of memory available. Field trials demonstrate that the wearable device can achieve a 2-month lifetime while performing one emotion detection classification every 10 minutes.Keywords
This publication has 10 references indexed in Scilit:
- Accelerated Visual Context Classification on a Low-Power SmartwatchIEEE Transactions on Human-Machine Systems, 2016
- InfiniTime: Multi-sensor wearable bracelet with human body harvestingSustainable Computing: Informatics and Systems, 2016
- Artificial Neural Network2016
- Microcontroller-Implemented Artificial Neural Network for Electrooculography-Based Wearable Drowsiness Detection System2015
- A wearable device for physical and emotional health monitoring2015
- The Internet of Things for Health Care: A Comprehensive SurveyIEEE Access, 2015
- A low power wireless node for contact and contactless heart monitoringMicroelectronics Journal, 2014
- Ultra low-power signal processing in wearable monitoring systemsACM Transactions on Embedded Computing Systems, 2013
- Towards Measuring Stress with Smartphones and Wearable Devices During Workday and SleepBioNanoScience, 2013
- A 470mV 2.7mW feature extraction-accelerator for micro-autonomous vehicle navigation in 28nm CMOS2013