睡眠問題在現今對人類來說是個重要的問題。睡眠的品質會影響一個人段時間的活力，並且長時間的糟糕睡眠品質會造成人的心理疾病。傳統上區分人的睡眠品質會採用PSG 的測試並由專家進行判別。由於採用PSG 會因為接在身上的感測器造成睡眠品質的影響進而對實驗結果產生不好的影響。使用ECG 的資料是一個可能的替代方案。ECG 資料只需要採用三個電極在身上，但這依舊是個影響。然後目光轉向了PPG，由血管的管徑變化來反推心率。這個技術已經被廣泛的使用在穿戴式裝置上，並且成本比前述的方法都低。由於一般的PSG 檢查並不包含PPG 的資料，因此多數的相關研究都使用ECG 為主。這個研究使用了一個同時有ECG 與PPG 的資料庫來判別睡眠階段。這研究在84 個個體資料判別四分類的睡眠階段問題中達到87%的準確率。我們也比較了不同種類的輸入方式對於模型的影響，讓未來在尋找新的特徵時會能找到與睡眠階段關聯性更高的特徵。
Keywords: 類神經網路，睡眠分期，心電圖

Sleep problems nowadays have become a big issue to human beings. Sleep quality will affect one’s energy the next in short time, and may cause mental disease while suffering from bad sleep for a long time. The traditional way to judge sleep quality is to take PSG data and determine it by experts. While taking PSG needs to connect to lots of sensors and may disrupt the quality of sleeping and that makes the result not as accurate as we thought. An alternative way is to use ECG data to determine it. This way you do not have to wear any sensor on head but still need some electrical patches paste on body. Then the idea comes to PPG data, which takes data from the change of blood vessels to indirectly get the heart rate. This technique has been used on many kinds of wearable devices and costs less. Somehow the research before used ECG data as main target because that the PPG data is not a standard while taking PSG data, most of the database can only use ECG. This work we found a database with both channels to make the sleep stage
classification. The experiment used 84 subjects and made a 78% accuracy determination of the four sleep stages. We also compared different kinds of input to find out which would make the best performance to the model, which may help future research to find out a better feature to find out the relationships between heart rate variability and sleep stages.
Keywords: neural network, sleep stage, PPG, ECG, inception

Kales, Anthony, and Allan Rechtschaffen. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. US Department of Health, Education and Welfare, Public Health Service, National Institutes of Health, National Institute of Neurological Diseases and Blindness, Neurological Information Network, 1968.

Berry, Richard B., et al. "The AASM manual for the scoring of sleep and associated events." Rules, Terminology and Technical Specifications, Darien, Illinois, American Academy of Sleep Medicine 176 (2012): 2012.

Stein, Phyllis K., and Yachuan Pu. "Heart rate variability, sleep and sleep disorders." Sleep medicine reviews 16.1 (2012): 47-66.

Pinheiro, Nuno, et al. "Can PPG be used for HRV analysis?." 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2016.

Schäfer, Axel, and Jan Vagedes. "How accurate is pulse rate variability as an estimate of heart rate variability?: A review on studies comparing photoplethysmographic technology with an electrocardiogram." International journal of cardiology 166.1 (2013): 15-29.

Fonseca, Pedro, et al. "Validation of photoplethysmography-based sleep staging compared with polysomnography in healthy middle-aged adults." Sleep 40.7 (2017): zsx097.

Fonseca, Pedro, et al. "A comparison of probabilistic classifiers for sleep stage classification." Physiological measurement 39.5 (2018): 055001.

Radha, Mustafa, et al. "Sleep stage classification from heart-rate variability using long short-term memory neural networks." Scientific reports 9.1 (2019): 1-11.

Li, Qiao, et al. "Deep learning in the cross-time frequency domain for sleep staging from a single-lead electrocardiogram." Physiological measurement 39.12 (2018): 124005.

Werth, Jan, et al. "Deep learning approach for ECG-based automatic sleep state classification in preterm infants." Biomedical Signal Processing and Control 56 (2020): 101663.

Sharan, Roneel V., et al. "ECG-Derived Heart Rate Variability Interpolation and 1-D Convolutional Neural Networks for Detecting Sleep Apnea." 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 2020.

Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.

Goldberger, A., et al. "PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220." (2000).

Ioffe, Sergey, and Christian Szegedy. "Batch normalization: Accelerating deep network training by reducing internal covariate shift." International conference on machine learning. PMLR, 2015.

Chen, Guangyong, et al. "Rethinking the usage of batch normalization and dropout in the training of deep neural networks." arXiv preprint arXiv:1905.05928 (2019).

Zhou, Bolei, et al. "Learning deep features for discriminative localization." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.

Yoon, Heenam, et al. "REM sleep estimation based on autonomic dynamics using R–R intervals." Physiological measurement 38.4 (2017): 631.

Yücelbaş, Şule, et al. "Automatic sleep staging based on SVD, VMD, HHT and morphological features of single-lead ECG signal." Expert Systems with Applications 102 (2018): 193-206.

Mitsukura, Yasue, et al. "Sleep stage detection using only heart rate." Health informatics journal 26.1 (2020): 376-387.

Zhang, Junming, and Yan Wu. "Competition convolutional neural network for sleep stage classification." Biomedical Signal Processing and Control 64 (2021): 102318.

Adnane, Mourad, Zhongwei Jiang, and Zhonghong Yan. "Sleep–wake stages classification and sleep efficiency estimation using single-lead electrocardiogram." Expert Systems with Applications 39.1 (2012): 1401-1413.

Bsoul, Majdi, Hlaing Minn, and Lakshman Tamil. "Apnea MedAssist: real-time sleep apnea monitor using single-lead ECG." IEEE transactions on information technology in biomedicine 15.3 (2010): 416-427.

Zhu, Tianqi, Wei Luo, and Feng Yu. "Convolution-and attention-based neural network for automated sleep stage classification." International Journal of Environmental Research and Public Health 17.11 (2020): 4152.

Zhang, Linda, et al. "Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks." Sleep 42.11 (2019): zsz159.

Faust, Oliver, et al. "A review of automated sleep stage scoring based on physiological signals for the new millennia." Computer methods and programs in biomedicine 176 (2019): 81-91.

Malafeev, Alexander, et al. "Automatic human sleep stage scoring using deep neural networks." Frontiers in neuroscience 12 (2018): 781.

Malik, John, Yu-Lun Lo, and Hau-tieng Wu. "Sleep-wake classification via quantifying heart rate variability by convolutional neural network." Physiological measurement 39.8 (2018): 085004.

Sridhar, Niranjan, et al. "Deep learning for automated sleep staging using instantaneous heart rate." NPJ digital medicine 3.1 (2020): 1-10.

Sun, Haoqi, et al. "Sleep staging from electrocardiography and respiration with deep learning." Sleep 43.7 (2020): zsz306.

Saleem, Shemaila, et al. "Gender differences of heart rate variability in healthy volunteers." JPMA-Journal of the Pakistan Medical Association 62.5 (2012): 422.

Choi, Jong-Bae, et al. "Age and ethnicity differences in short-term heart-rate variability." Psychosomatic medicine 68.3 (2006): 421-426.

Kleiger, Robert E., et al. "Stability over time of variables measuring heart rate variability in normal subjects." The American journal of cardiology 68.6 (1991): 626-630.

Acharya, Rajendra, et al. "Heart rate analysis in normal subjects of various age groups." Biomedical engineering online 3.1 (2004): 1-8.