臺灣博碩士論文加值系統

睡眠不足日益被認為是健康的重要預後參數，並可能導致白天嗜睡。如果人們睡眠不足，可能會在運輸和工廠廠房中造成一些事故，並可能造成生命或財產損失。為避免這種情況，需要不斷警告人們“需要休息”。由於穿戴繁瑣的設備可能會影響人們的日常生活，因此許多人不願意將其戴在身上。本文提出了一種基於時間序列的睡眠檢測方法，該方法具有價格低，重量輕，舒適度高的可穿戴設備Garmin Vivosmart3。儘管低重量設備使人更舒適，但是它具有一個關鍵問題，即其接收生理信號的準確性較低。接收生理信號的準確性較低，可能會導致大量缺失值。本文提出的演算法可以通過減少資料量的方法來解決這個問題。而且由於睡眠是一種不能中斷的連續行為，因此本文中收集的數據被視為典型的時間序列數據集。針對時間序列數據集的特點，提出了一種基於連續序列發現的睡眠檢測方法。通過進行的幾次實際實驗，在所有受試者中報告的準確性，敏感性和特異性分別為94.79％，97.13％和93.86％。

Insufficient sleep is increasingly being recognized as an important prognostic parameter of health and could result in daytime sleepiness. If people do not have enough sleep, they may cause some accidents in transportation and factory plants and would loss their lives or properties. To avoid this circumstance, a constant warning about the people’s “need for rest” is required. Since wearing cumbersome equipments may affect people’s dayily lives, many peoples are not willing to put them on their bodies. This thesis proposes a time series based sleep detecting method with a low price, low weight and high comfort wearable device called Garmin Vivosmart3.
Although the low weight device is more comfortable for people, it has a critical problem which is its low accuracy of receiving physiological signals. Low accuracy of receiving physiological signals may cause large amount of missing values. In this thesis, the proposed algorithm could solve this problem with the aid of a data volume reduction method. And since sleep is a continuous behavior that cannot be interrupted, the collected data in this thesis is considered as a typical time series data set. Due to the characteristic of time series data set, a sleep detection method based on finding continuous sequences is proposed. With several real world experiments conducted, an accuracy, sensitivity, and specificity of 94.79%, 97.13%, and 93.86% is reported over all subjects.

摘要 iii
ABSTRACT v
CONTENTS vii
LIST OF FIGURES ix
LIST OF TABLES xi
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Problem Formulation 2
1.3 Contributions 3
1.4 Organization of the Thesis 4
Chapter 2 Background and Literature Survey 5
Chapter 3 Related Algorithms 9
3.1 Time series 9
3.2 Piecewise Aggregate Approximation 12
3.3 Symbolic Aggregate Approximation 13
Chapter 4 Sleep – Wake Discrimination 17
4.1 Data Acquisition 17
4.1.1 Data Recording 20
4.1.2 Ground Truth Setting 21
4.2 Pre-processing 24
4.2.1 Feature Selection 24
4.2.2 Missing value processing 27
4.3 Input Feature Volume Reduction 28
4.3.1 Normalization Without Missing Value Effect 29
4.3.2 Volume Reduction 31
4.4 Sleep Length Detection 36
4.4.1 Sleep and Missing Episode Selection 40
4.4.2 Missing Episode Length Detection 42
4.4.3 Sleep Episode Revision 44
4.4.4 Continuous Sequence Detection 45
4.4.5 Sleep Length Calculation 47
4.5 Training and Testing data selection 49
4.5.1 Missing Values Imputation 49
4.5.2 Missing Values Preserved 50
4.6 Performance Assessment 52
Chapter 5 Experimental Results and Analysis 54
5.1 Software Platforms 54
5.2 Input Feature Volume Reduction 55
5.2.1 Missing Values Imputation 56
5.2.2 Missing Values Preserved 59
5.2.3 Summary 62
5.3 Sleep Length Detection 64
5.3.1 Sleep Episode and Missing Episode Detection 64
5.3.2 Missing Episode Length Detection 69
5.3.3 Sleep Episode Revision 72
5.3.4 Sleep Length Calculation 80
5.3.5 Performances with Missing Values Imputation 81
5.3.6 Performances with Missing Values Preserved 92
5.4 Summary 119
5.4.1 Missing Values Imputation 119
5.4.2 Missing Values Preserved 120
Chapter 6 Conclusions and Future Works 125
6.1 Conclusions 125
6.2 Future Works 126
References 128

[1: Walsh et al. 2017]
Lorcan Walsh, Seán McLoone, Joseph Ronda, Jeanne F. Duffy, and Charles A. Czeisler, “Noncontact Pressure-Based Sleep Wake Discrimination,” IEEE Transactions on Biomedical Engineering, Vol. 64, No. 8, pp. 1750-1760, Aug. 2017.
[2: Sano et al. 2019]
Akane Sano, Weixuan Chen, Daniel Lopez-Martinez, Sara Taylor, and Rosalind W. Picard, “Multimodal Ambulatory Sleep Detection Using LSTM Recurrent Neural Networks,” IEEE Journal of Biomedical and Health Informatics, Vol. 23, No. 4, pp. 1607-1617, July 2019.
[3: Hwang et al. 2017]
Su Hwan Hwang, Sangwon Seo, Hee Nam Yoon, Da Woon Jung, Hyun Jae Baek, Jaegeol Cho, Jae Won Choi, Yu Jin Lee, Do-Un Jeong, and Kwang Suk Par, “Sleep Period Time Estimation Based on Electrodermal Activity,” IEEE Journal of Biomedical and Health Informatics, Vol. 21, No. 1, pp. 115-12, Jan. 2017.
[4: Hu et al. 2015]
Bin Hu, Hong Peng, Qinglin Zhao, Bo Hu, Dennis Majoe, Fang Zheng, and Philip Moore, “Signal Quality Assessment Model for Wearable EEG Sensor on Prediction of Mental Stress,” IEEE Transactions on NanoBioscience, Vol. 14, No. 5, pp. 553-561, July 2015.
[5: Karlen et al. 2009]
Walter Karlen, Claudio Mattiussi, and Dario Floreano, “Sleep and Wake Classification With ECG and Respiratory Effort Signals,” IEEE Transactions on Biomedical Circuits and Systems, Vol. 3, No. 2, pp. 71-78, April 2009.
[6: Hayano et al. 2017]
Junichiro Hayano, Emi Yuda, and Yutaka Yoshida, “Sleep stage classification by combination of actigraphic and heart rate signals,” in Proceedings of 2017 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-TW), Taipei, Taiwan, pp. 387-388, June 12-14, 2017.
[7: Dehkordi et al. 2016]
Parastoo Dehkordi, Ainara Garde, Guy A. Dumont, and J. Mark Ansermino, “Sleep wake classification using cardiorespiratory features extracted from photoplethysmogram,” in Proceedings of 2016 Computing in Cardiology Conference (CinC), Vancouver, BC, Canada, pp. 1021-1024, Sept. 11-14, 2016.
[8: Long et al. 2017]
Xi Long, Pedro Fonseca, Reinder Haakma, and Ronald M. Aarts, “Actigraphy-based sleep wake detection for insomniacs,” in Proceedings of 2017 IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks (BSN), Eindhoven, Netherlands, pp. 1-4, May 9-12, 2017.
[9: Long et al. 2014]
Xi Long, Pedro Fonseca, Jérôme Foussier, Reinder Haakma, and Ronald M. Aarts, “Sleep and Wake Classification With Actigraphy and Respiratory Effort Using Dynamic Warping,” IEEE Journal of Biomedical and Health Informatics, Vol. 18, No. 4, pp. 1272-1284, July 2014.
[10: El-Manzalawy et al. 2017]
Yasser El-Manzalawy, Orfeu Buxton, and Vasant Honavar, “Sleep wake state prediction and sleep parameter estimation using unsupervised classification via clustering,” in Proceedings of 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Kansas City, MO, USA, pp. 718-723, Nov. 13-16, 2017.
[11: Khademi et al. 2018]
Aria Khademi, Yasser El-Manzalawy, Orfeu M. Buxton, and Vasant Honavar, “Toward personalized sleep-wake prediction from actigraphy,” in Proceedings of 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Las Vegas, NV, USA, pp. 414-417, March 4-7, 2018.
[12: Chen et al. 2019]
Zhenghua Chen, Min Wu, Jiyan Wu, Jie Ding, Zeng Zeng, Karl Surmacz, and Xiaoli Li, “A Deep Learning Approach for Sleep-Wake Detection from HRV and Accelerometer Data,” in Proceedings of 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Chicago, IL, USA., May 19-22, 2019.
[13: Chen et al. 2017]
Weixuan Chen, Akane Sano, Daniel Lopez Martinez, Sara Taylor, Andrew W. McHill, Andrew J. K. Phillips, Laura Barger, Elizabeth B. Klerman, and Rosalind W. Picard, “Multimodal ambulatory sleep detection,” in Proceedings of 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Orlando, FL, USA., pp. 465-468, Feb. 16-19, 2017.
[14: Dissanayaka et al. 2015]
Chamila Dissanayaka, Dean Cvetkovic, Chanakya Reddy Patti, Sobhan Salari Shahrbabaki, Beena Ahmed, Claudia Schilling, and Michael Schredl, “Sleep onset detection with multiple EEG alpha-band features Comparison between healthy, insomniac and schizophrenic patients,” in Proceedings of 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS), Atlanta, GA, USA., Oct. 22-24, 2015.
[15: Karlen & Floreano 2011]
Walter Karlen, and Dario Floreano, “Adaptive Sleep–Wake Discrimination for Wearable Devices,” IEEE Transactions on Biomedical Engineering, Vol. 58, No. 4, pp. 920-926, April 2011.
[16: Nakamura et al. 2017]
Takashi Nakamura, Valentin Goverdovsky, Mary J. Morrell, and Danilo P. Mandic, “Automatic Sleep Monitoring Using Ear-EEG,” IEEE Journal of Translational Engineering in Health and Medicine, Vol. 5, June 2017.
[17: Nakamura et al. 2019]
Takashi Nakamura, Yousef D. Alqurashi, Mary J. Morrell, and Danilo Mandic, “Hearables: Automatic overnight sleep monitoring with standardised in-ear EEG sensor,” IEEE Transactions on Biomedical Engineering ( Early Access ), pp. 1-8, April 2019.
[18: Ye et al. 2016]
Yanqing Ye, Kewei Yang, Jiang Jiang, and Bingfeng Ge, “Automatic sleep and wake classifier with heart rate and pulse oximetry Derived dynamic time warping features and logistic model,” in Proceedings of 2016 Annual IEEE Systems Conference (SysCon), Orlando, FL, USA., April 18-21, 2016.
[20: Keogh et al. 2001]
Eamonn Keogh, Kaushik Chakrabarti, Michael Pazzani, and Sharad Mehrotra, “Dimensionality reduction for fast similarity search in large time series databases,” J. Knowl. Inf. Syst, Vol. 3, pp. 263-286, Aug. 2001.
[21: Lin et al. 2003]
Jessica Lin, Eamonn Keogh, Stefano Lonardi, and Bill Chiu, “A symbolic representation of time series, with implications for streaming algorithms,” in Proceedings of 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery, San Diego, U.S., pp. 2-11, June 13-13, 2003.
[22: Penzel et al. 2003]
Thomas Penzel, Jan W Kantelhardt, Chung-Chang Lo, Karlheinz Voigt and Claus Vogelmeier , “Dynamics of Heart Rate and Sleep Stages in Normals and Patients with Sleep Apnea,” Neuropsychopharmacology, Vol.28, pp. 48-53, June 2003.
[23: Mensen et al. 2016]
Armand Mensen, Zhongxing Zhang, Ming Qi and Ramin Khatami, “The occurrence of individual slow waves in sleep is predicted by heart rate,” Sci Rep, Vol.6, pp. 29671, July 2016.
[24: Radha et al. 2019]
Mustafa Radha, Pedro Fonseca, Arnaud Moreau, Marco Ross, Andreas Cerny, Peter Anderer, Xi Long and Ronald M. Aarts , “Sleep stage classification from heart-rate variability using long short-term memory neural networks,” Sci Rep, Vol.9, pp. 14149, Oct. 2019.
[25: Pratama et al. 2016]
Irfan Pratama, Adhistya Erna Permanasari, Igi Ardiyanto, and Rini Indrayani, “A Review of Missing Values Handling Methods on Time-Series Data ,” in Proceedings of 2016 International Conference on Information Technology Systems and Innovation (ICITSI), Bandung, Indonesia, Oct. 24-27, 2016.
Book:
[19: Brockwell & Davis 2016]
PJ Brockwell, and RA Davis, “Introduction to time series and forecasting,”, 3rd Birmingham, UK, 2016.
Website:
[26: Normalization]
Normalization. (2020, Jan. 07). In Wikipedia. Retrieved Jan. 07, 2020, form
https://en.wikipedia.org/wiki/Normalization_(statistics)