Automatic Detection of Sleep Stages based on Accelerometer Signals from a Wristband

Abstract

Abstract:In this paper, we suggest an automated sleep scoring method using machine learning algorithms on accelerometer data from a wristband device. For an experiment, 36 subjects slept for about eight hours while polysomnography (PSG) data and accelerometer data were simultaneously recorded. After the experiments, the recorded signals from the subjects were preprocessed, and significant features for sleep stages were extracted. The extracted features were classified into each sleep stage using five machine learning algorithms. For validation of our approach, the obtained results were compared with PSG scoring results evaluated by sleep clinicians. Both accuracy and specificity yielded over 90 percent, and sensitivity was between 50 and 80 percent. In order to investigate the relevance between features and PSG scoring results, information gains were calculated. As a result, the features that had the lowest and highest information gain were skewness and band energy, respectively. In conclusion, the sleep stages were classified using the top 10 significant features with high information gain.

Computational Sleep Behavior Analysis: A Survey

“…Data are gathered from sensors such as 3-axis accelerometers, thermostats or photoplethysmography (PPG). Knowledge is generally obtained by applying data mining techniques for sleep position detection [15], [23], [46], sleep stage classification [4], [9], [11], [47], heart rate [29] and respiration rate [46] analysis, and body temperature monitoring [29], [48].…”

“…Sleep position detection is usually investigated using either accelerometers [15], [46] or wearable wireless devices [23] on the chest or ankles. In general, sleep stage classification uses either only 3-axis accelerometers [9], [11], [47] or in combination with, e.g., chest strap on wrist and ankle [4]; alternatively, such classification can use PPG [8], [49]. Other sensors include thermometers that measure body temperature to extract sleep and wakefulness [48].…”

“…Specifically, the CNN was able to separate wake and REM stages, whereas RNN could separate deep and light sleep [68]. Instead, accelerometer data were collected in [47] from the nondominant hand for 36 individuals. They analyzed different classifiers and performed feature selection, concluding that RC performs the best.…”

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

“…Polysomnography (PSG), which has been used for adaptive segmentation to classify sleep stages [6] and for the detection of sleep disorders using multi-modal bio-signals and movement information from video polysomnography [7,8], is one of these sleep monitoring methods. Because PSG is complex, expensive, and uncomfortable for subjects, another simple method, actigraphy, which scores sleep stages based on movement detection from a wristband device, has also been utilized [9]. This method enables subjects to perform the experiments in their familiar and comfortable home environments [10].…”

“…Moeynoi and Kitjaidure conducted sleep stage scoring using statistical features of EEG signals via simple statistical techniques and canonical correlation analysis to obtain the correlations among the feature vectors of the dataset [19]. For sleep scoring application, five machine learning methods, which include the kstar classifier, bagging, random committee, random subspace, and random forest, were applied by Yeo et al [9] in a study where features of accelerometer data from a wristband sensor were trained and classified into wake, rapid eye movement (REM), and light and deep stages. The naive Bayes algorithm, which has been utilized to predict sleep apnea severity and sleepiness [20], was trained based on demographics and polysomnogram and electrocardiogram EEG signals.…”