Next Article in Journal
Complex Wavelet-Based Image Watermarking with the Human Visual Saliency Model
Next Article in Special Issue
Brain Computer Interface-Based Action Observation Game Enhances Mu Suppression in Patients with Stroke
Previous Article in Journal
The P-Type Module with Virtual DC Links to Increase Levels in Multilevel Inverters
Previous Article in Special Issue
Decoding EEG in Motor Imagery Tasks with Graph Semi-Supervised Broad Learning
Open AccessArticle

Deep-ACTINet: End-to-End Deep Learning Architecture for Automatic Sleep-Wake Detection Using Wrist Actigraphy

1
Department of Intelligent Information and Embedded Software Engineering, Kwangwoon University, Seoul 01897, Korea
2
Department of Computer Engineering, Kwangwoon University, Seoul 01897, Korea
3
Biointelligence Laboratory, Seoul National University, Seoul 08826, Korea
4
Department of Neurology, Asan Medical Center, Ulsan University College of Medicine, Seoul 05505, Korea
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Electronics 2019, 8(12), 1461; https://doi.org/10.3390/electronics8121461
Received: 18 October 2019 / Revised: 20 November 2019 / Accepted: 26 November 2019 / Published: 2 December 2019
Sleep scoring is the first step for diagnosing sleep disorders. A variety of chronic diseases related to sleep disorders could be identified using sleep-state estimation. This paper presents an end-to-end deep learning architecture using wrist actigraphy, called Deep-ACTINet, for automatic sleep-wake detection using only noise canceled raw activity signals recorded during sleep and without a feature engineering method. As a benchmark test, the proposed Deep-ACTINet is compared with two conventional fixed model based sleep-wake scoring algorithms and four feature engineering based machine learning algorithms. The datasets were recorded from 10 subjects using three-axis accelerometer wristband sensors for eight hours in bed. The sleep recordings were analyzed using Deep-ACTINet and conventional approaches, and the suggested end-to-end deep learning model gained the highest accuracy of 89.65%, recall of 92.99%, and precision of 92.09% on average. These values were approximately 4.74% and 4.05% higher than those for the traditional model based and feature based machine learning algorithms, respectively. In addition, the neuron outputs of Deep-ACTINet contained the most significant information for separating the asleep and awake states, which was demonstrated by their high correlations with conventional significant features. Deep-ACTINet was designed to be a general model and thus has the potential to replace current actigraphy algorithms equipped in wristband wearable devices. View Full-Text
Keywords: sleep scoring; actigraphy; machine learning; CNN; LSTM; accuracy; recall; precision; deep learning sleep scoring; actigraphy; machine learning; CNN; LSTM; accuracy; recall; precision; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Cho, T.; Sunarya, U.; Yeo, M.; Hwang, B.; Koo, Y.S.; Park, C. Deep-ACTINet: End-to-End Deep Learning Architecture for Automatic Sleep-Wake Detection Using Wrist Actigraphy. Electronics 2019, 8, 1461.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop