Wearable PPG sensor based alertness scoring system
Authors:
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Vol. 2017 (1557170X) , 2422-2425
Abstract
Quantifying mental alertness in today's world is important as it enables the person to adopt lifestyle changes for better work efficiency. Miniaturized sensors in wearable devices have facilitated detection/monitoring of mental alertness. Photoplethysmography (PPG) sensors through Heart Rate Variability (HRV) offer one such opportunity by providing information about one's daily alertness levels without requiring any manual interference from the user. In this paper, a smartwatch based alertness estimation system is proposed. Data collected from PPG sensor of smartwatch is processed and fed to machine learning based model to get a continuous alertness score. Utility functions are designed based on statistical analysis to give a quality score on different stages of alertness such as awake, long sleep and short duration power nap. An intelligent data collection approach is proposed in collaboration with the motion sensor in the smartwatch to reduce battery drainage. Overall, our proposed wearable based system provides a detailed analysis of alertness over a period in a systematic and optimized manner. We were able to achieve an accuracy of 80.1% for sleep/awake classification along with alertness score. This opens up the possibility for quantifying alertness levels using a single PPG sensor for better management of health related activities including sleep.Keywords
This publication has 11 references indexed in Scilit:
- Cuff-less PPG based continuous blood pressure monitoring — A smartphone based approach2016
- Time-frequency analysis of heart rate variability for sleep and wake classification2012
- Automatic recognition of alertness level by using wavelet transform and artificial neural networkJournal of Neuroscience Methods, 2004
- Comparison of detrended fluctuation analysis and spectral analysis for heart rate variability in sleep and sleep apneaIEEE Transactions on Biomedical Engineering, 2003
- Atlas, rules, and recording techniques for the scoring of cyclic alternating pattern (CAP) in human sleepSleep Medicine, 2001
- PhysioBank, PhysioToolkit, and PhysioNetCirculation, 2000
- Development of the polysomnographic database on CD‐ROMPsychiatry and Clinical Neurosciences, 1999
- A Tutorial on Support Vector Machines for Pattern RecognitionData Mining and Knowledge Discovery, 1998
- Fluctuations in autonomic nervous activity during sleep displayed by power spectrum analysis of heart rate variabilityNeurology, 1995
- A Real-Time QRS Detection AlgorithmIEEE Transactions on Biomedical Engineering, 1985