隨著醫療知識與研究的迅速成長，在婦產學科(OBS/GYN)中有許多的臨床技術不斷被提出與發表，特別是致力於預期分娩日期(預產期)的實用分類相關規則，預產期是一種用於預測孕婦分娩時間的醫學概念。但是，綜觀過去的文獻及研究，仍然缺乏如何根據預期的分娩日期為孕婦設計足夠準確的懷孕時間表之相關研究，以減輕孕婦在懷孕期間的壓力與焦慮。根據文獻，我們可以發現，過去大多數的研究人員僅針對正常產的婦女(預期在胎齡36-41週之間分娩)進行單一閥值的二元分類(Binary classification)，而沒有對於預期的分娩日期做出足夠準確的規則，這樣有可能造成分娩時間的誤判，加深孕婦的心理焦慮，並擾亂人們在懷胎十月期間的日程安排。
因此，本研究的目的是對分娩時間進行以週為單位的分類，以便於幫助孕婦及其家人去克服行程安排上的困難，例如訂定產檢假與安胎假的時間、或任何對於即將到來的嬰兒的準備，並減輕其心理壓力。
在研究方法方面，我們提出了一個將DNN架構、EMG(Electromyography)技術、和數個預處理步驟結合的方法，以結合出以週為單位的分類結果。總共129筆資料中，有122筆來自冰島的資料庫，有7筆來自我們的醫院資料，這些資料用於訓練模型和測試模型結果。經過對EMG訊號在頻域中的觀察及對數個模型的參數進行調整後，我們達到了出色的精準度，這是本論文的第一個重要貢獻。
在EMG資料中，有些孕婦將在一週內分娩，在其TOCO資料中卻看不出子宮收縮的跡象。而經過我們在頻域上的分析觀察，發現不同類別(代表不同的分娩時間)的資料在MNF(平均頻率)、MDF(中值頻率)、PF(峰值頻率)等特徵上具有不同的值。此外，我們的比較分析中表明，儘管在時域中沒有子宮收縮，但是EMG訊號在頻域中的各個類別上的特徵值仍然不相同，這樣的結果可以為臨床醫生提供有關子宮收縮的新觀點，這是本論文的第二個貢獻。
我們得出結果，這些發現對婦產學科的未來醫學從業者以及研究人員具有意義，能探索更多相關領域並推廣研究成果使更多有需要的婦女受益。希望這些結果可以提供新的研究方向，並為促進將來的研究提供預期的基礎。

With the rapid growth of medical knowledge, several clinical technological advances have been made in obstetrics and gynecology (OBS/GYN), particularly dedicated to obtaining a practical classification rule of the expected date of delivery (childbirth), a medical concept used to predict the delivery time of a pregnant woman. However, there remains a paucity of literature examining how we can devise a sufficiently accurate pregnancy schedule for a woman that is based on the expected date of delivery to alleviate her stress during pregnancy. Through the literature, we can find that most of the previous researchers obtain a single-threshold binary classification only for women having normal birth (expectant between 36 and 41 weeks), not achieving an accurate enough rule of the expected date of childbirth. Such abnormal birth would potentially deepen the psychological anxiety and disrupt people’s schedules during pregnancy.
The purpose of the present study, therefore, is to develop a week-level classification of the delivery time so that we can help pregnant women and their families overcome scheduling difficulties—such as making plans for maternity or tocolysis leaves and any preparation of a baby—and cope with the psychological stress.
In terms of research methods, a DNN architecture, EMG (Electromyography) technology, and several pre-processing steps were combined to produce the week-level classification. A total of 129 recordings, 122 from the Iceland database and 7 from our NCKU hospital, were used to validate the training model and the testing results. Several model parameters were tuned with the observations from the EMG signal in the frequency domain to achieve an outstanding accuracy, the first significant contribution of our thesis.
In our EMG data, some women expectant in a week had no sign of contraction in their TOCO’s readings. Our analysis on the frequency domain revealed that signals in different classes (representing different delivery times) had different values on features such as MNF (mean frequency), MDF (median frequency), and PF (peak frequency). Moreover, our comparative analysis showed that, although there could be no uterine contraction in the time domain, the EMG signal still scored differently across classes in the frequency domain. Such results can provide doctors and clinicians with new perspectives on uterine contractions, the second contribution in our thesis.
We conclude with some implications of these findings for future medical practitioners in OBS/GYN and researchers who are dedicated to exploring more related areas and generalizing the results to benefit more women in need. It is hoped that these results may provide new research directions and serve as a basis to facilitate future studies in the prediction of the expected date of delivery.

References
[1] J.Sikorski, J.Wilson, S.Clement, S.Das, andN.Smeeton, “A randomised controlled trial comparing two schedules of antenatal visits: The antenatal care project,” Br. Med. J., vol. 312, no. 7030, pp. 546–553, 1996, doi: 10.1136/bmj.312.7030.546.
[2] P.Vandenbussche, E.Wollast, andP.Buekens, “Some characteristics of antenatal care in 13 European countries,” BJOG An Int. J. Obstet. Gynaecol., vol. 92, no. 12, pp. 1297–1297, 1985, doi: 10.1111/j.1471-0528.1985.tb04879.x.
[3] D. S.Walker, L.McCully, andV.Vest, “Evidence-based prenatal care visits: When less is more,” J. Midwifery Women’s Heal., vol. 46, no. 3, pp. 146–151, 2001, doi: 10.1016/S1526-9523(01)00120-9.
[4] R.Ahner, H.Kiss, C.Egarter, R.Zeillinger, W.Eppel, H.Karas, andP.Husslein, “Fetal fibronectin as a marker to predict the onset of term labor and delivery,” Am. J. Obstet. Gynecol., vol. 172, no. 1 PART 1, pp. 134–137, 1995, doi: 10.1016/0002-9378(95)90101-9.
[5] D.VonSchoning, T.Fischer, E.VonTucher, T.Slowinski, A.Weichert, W.Henrich, andA.Thomas, “Cervical sonoelastography for improving prediction of preterm birth compared with cervical length measurement and fetal fibronectin test,” J. Perinat. Med., vol. 43, no. 5, pp. 531–536, 2015, doi: 10.1515/jpm-2014-0356.
[6] T.Nikolova, O.Bayev, N.Nikolova, andG. C.DiRenzo, “Evaluation of a novel placental alpha microglobulin-1 (PAMG-1) test to predict spontaneous preterm delivery,” J. Perinat. Med., vol. 42, no. 4, pp. 473–477, 2014, doi: 10.1515/jpm-2013-0234.
[7] B. M.Mercer, R. L.Goldenberg, A.Das, A. H.Moawad, J. D.Iams, P. J.Meis, R. L.Copper, F.Johnson, E.Thom, D.McNellis, M.Miodovnik, M. K.Menard, S. N.Caritis, G. R.Thurnau, S. F.Bottoms, andJ.Roberts, “The preterm prediction study: A clinical risk assessment system,” Am. J. Obstet. Gynecol., vol. 174, no. 6, pp. 1885–1895, 1996, doi: 10.1016/S0002-9378(96)70225-9.
[8] M.Lucovnik, W. L.Maner, L. R.Chambliss, R.Blumrick, J.Balducci, Z.Novak-Antolic, andR. E.Garfield, “Noninvasive uterine electromyography for prediction of preterm delivery,” Am. J. Obstet. Gynecol., vol. 204, no. 3, pp. 228.e1-228.e10, 2011, doi: 10.1016/j.ajog.2010.09.024.
[9] J.You, Y.Kim, W.Seok, S.Lee, D.Sim, K. S.Park, andC.Park, “Multivariate Time–Frequency Analysis of Electrohysterogram for Classification of Term and Preterm Labor,” J. Electr. Eng. Technol., vol. 14, no. 2, pp. 897–916, 2019, doi: 10.1007/s42835-019-00118-9.
[10] D.Despotovic, A.Zec, K.Mladenovic, N.Radin, andT. L.Turukalo, “A Machine Learning Approach for an Early Prediction of Preterm Delivery,” SISY 2018 - IEEE 16th Int. Symp. Intell. Syst. Informatics, Proc., pp. 265–270, 2018, doi: 10.1109/SISY.2018.8524818.
[11] M.Lucovnik, R. J.Kuon, L. R.Chambliss, W. L.Maner, S. Q.Shi, L.Shi, J.Balducci, andR. E.Garfield, “Use of uterine electromyography to diagnose term and preterm labor,” Acta Obstet. Gynecol. Scand., vol. 90, no. 2, pp. 150–157, 2011, doi: 10.1111/j.1600-0412.2010.01031.x.
[12] M.Shahrdad andM. C.Amirani, “Detection of preterm labor by partitioning and clustering the EHG signal,” Biomed. Signal Process. Control, vol. 45, pp. 109–116, 2018, doi: 10.1016/j.bspc.2018.05.044.
[13] P.Ren, S.Yao, J.Li, P. A.Valdes-Sosa, andK. M.Kendrick, “Improved prediction of preterm delivery using empirical mode decomposition analysis of uterine electromyography signals,” PLoS One, vol. 10, no. 7, pp. 1–16, 2015, doi: 10.1371/journal.pone.0132116.
[14] S.Jain, A. F.Saad, andS. S.Basraon, “Comparing Uterine Electromyography & Tocodynamometer to Intrauterine Pressure Catheter For Monitoring Labor,” J. Woman’s Reprod. Heal., vol. 1, no. 3, pp. 22–30, 2016, [Online]. Available: 10.14302/issn.2381-826X.jwrh-15-771.
[15] M. P. G. C.Vinken, C.Rabotti, M.Mischi, J. O. E. H.vanLaar, andS. G.Oei, “Nifedipine-Induced Changes in the Electrohysterogram of Preterm Contractions: Feasibility in Clinical Practice,” Obstet. Gynecol. Int., vol. 2010, pp. 1–8, 2010, doi: 10.1155/2010/325635.
[16] B.Vasak, E. M.Graatsma, E.Hekman-Drost, M. J.Eijkemans, J. H.Schagen Van Leeuwen, G. H.Visser, andB. C.Jacod, “Uterine electromyography for identification of first-stage labor arrest in term nulliparous women with spontaneous onset of labor,” Am. J. Obstet. Gynecol., vol. 209, no. 3, pp. 232.e1-232.e8, 2013, doi: 10.1016/j.ajog.2013.05.056.
[17] W. L.Maner, R. E.Garfield, H.Maul, G.Olson, andG.Saade, “Predicting term and preterm delivery with transabdominal uterine electromyography,” Obstet. Gynecol., vol. 101, no. 6, pp. 1254–1260, 2003, doi: 10.1016/S0029-7844(03)00341-7.
[18] P.Fergus, P.Cheung, A.Hussain, D.Al-Jumeily, C.Dobbins, andS.Iram, “Prediction of Preterm Deliveries from EHG Signals Using Machine Learning,” PLoS One, vol. 8, no. 10, 2013, doi: 10.1371/journal.pone.0077154.
[19] B.Moslem, M. O.Diab, M.Khalil, andC.Marque, “DETRENDED FLUCTUATION ANALYSIS OF UTERINE ELECTROMYOGRAPHY,” pp. 450–453, 2011.
[20] R. E.Garfield, W. L.Maner, L. B.MacKay, D.Schlembach, andG. R.Saade, “Comparing uterine electromyography activity of antepartum patients versus term labor patients,” Am. J. Obstet. Gynecol., vol. 193, no. 1, pp. 23–29, 2005, doi: 10.1016/j.ajog.2005.01.050.
[21] G.Fele-Žorž, G.Kavšek, Ž.Novak-Antolič, andF.Jager, “A comparison of various linear and non-linear signal processing techniques to separate uterine EMG records of term and pre-term delivery groups,” Med. Biol. Eng. Comput., vol. 46, no. 9, pp. 911–922, 2008, doi: 10.1007/s11517-008-0350-y.
[22] G. T.Conger andJ. H.Randall, “Precipitate labor,” Am. J. Obstet. Gynecol., vol. 73, no. 6, pp. 1321–1325, 1957, doi: 10.1016/0002-9378(57)90276-4.
[23] A.Weber, G. L.Darmstadt, S.Gruber, M. E.Foeller, S. L.Carmichael, D. K.Stevenson, andG. M.Shaw, “Application of machine-learning to predict early spontaneous preterm birth among nulliparous non-Hispanic black and white women,” Ann. Epidemiol., vol. 28, no. 11, pp. 783-789.e1, 2018, doi: 10.1016/j.annepidem.2018.08.008.
[24] P.Zhu, H.Zhou, S.Cao, P.Yang, andS.Xue, “Control with gestures: A hand gesture recognition system using off-the-shelf smartwatch,” Proc. - 2018 4th Int. Conf. Big Data Comput. Commun. BIGCOM 2018, pp. 72–77, 2018, doi: 10.1109/BIGCOM.2018.00018.
[25] W.Geng, Y.Hu, Y.Wong, W.Wei, Y.Du, andM.Kankanhalli, “A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition,” PLoS One, vol. 13, no. 10, pp. 1–18, 2018, doi: 10.1371/journal.pone.0206049.
[26] K. H.Park andS. W.Lee, “Movement intention decoding based on deep learning for multiuser myoelectric interfaces,” 4th Int. Winter Conf. Brain-Computer Interface, BCI 2016, pp. 7–8, 2016, doi: 10.1109/IWW-BCI.2016.7457459.
[27] P.Xia, J.Hu, andY.Peng, “EMG-Based Estimation of Limb Movement Using Deep Learning With Recurrent Convolutional Neural Networks,” Artif. Organs, vol. 42, no. 5, pp. E67–E77, 2018, doi: 10.1111/aor.13004.
[28] R. E. X.Rxqj, R. R.Lp, K. D.Dqg, R. Q. J.Dq, G.Nqx, D. F.Nu, H. W.Iurp, W. K. H.Prwlrq, G.Lv, S.Dqg, V. V.Lv, G.Wr, L.Wkh, andS.Dojrulwkp, “A Real-Time Sleeping Position Recognition System Using IMU Sensor Motion Data,” pp. 6–7, 2018.
[29] M.Atzori, M.Cognolato, andH.Müller, “Deep learning with convolutional neural networks applied to electromyography data: A resource for the classification of movements for prosthetic hands,” Front. Neurorobot., vol. 10, no. SEP, pp. 1–10, 2016, doi: 10.3389/fnbot.2016.00009.
[30] C.Spampinato, S.Palazzo, I.Kavasidis, D.Giordano, N.Souly, andM.Shah, “Deep learning human mind for automated visual classification,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 4503–4511, 2017, doi: 10.1109/CVPR.2017.479.
[31] P.Kumar, V. K.Sehgal, andD. S.Chauhan, “TrueNorth-enabled Real-time Classification of EEG Data for Brain- Computer Interfacing,” vol. 2, no. 5, pp. 25–42, 2012.
[32] U. R.Acharya, S. L.Oh, Y.Hagiwara, J. H.Tan, andH.Adeli, “Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals,” Comput. Biol. Med., vol. 100, no. August 2017, pp. 270–278, 2018, doi: 10.1016/j.compbiomed.2017.09.017.
[33] G.Huve, K.Takahashi, andM.Hashimoto, “Brain activity recognition with a wearable fNIRS using neural networks,” 2017 IEEE Int. Conf. Mechatronics Autom. ICMA 2017, pp. 1573–1578, 2017, doi: 10.1109/ICMA.2017.8016051.
[34] E.Nurse, B. S.Mashford, A. J.Yepes, I.Kiral-Kornek, S.Harrer, andD. R.Freestone, “Decoding EEG and LFP signals using deep learning: Heading truenorth,” 2016 ACM Int. Conf. Comput. Front. - Proc., pp. 259–266, 2016, doi: 10.1145/2903150.2903159.
[35] H.Piroska andS.János, “Specific movement detection in EEG signal using time-frequency analysis,” Proc. - 2008 1st Int. Conf. Complex. Intell. Artif. Nat. Complex Syst. Med. Appl. Complex Syst. Biomed. Comput. CANS 2008, pp. 209–215, 2008, doi: 10.1109/CANS.2008.32.
[36] B.Pourbabaee, M. J.Roshtkhari, andK.Khorasani, “Deep Convolutional Neural Networks and Learning ECG Features for Screening Paroxysmal Atrial Fibrillation Patients,” IEEE Trans. Syst. Man, Cybern. Syst., vol. 48, no. 12, pp. 2095–2104, 2018, doi: 10.1109/TSMC.2017.2705582.
[37] J. H.Tan, Y.Hagiwara, W.Pang, I.Lim, S. L.Oh, M.Adam, R. S.Tan, M.Chen, andU. R.Acharya, “Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals,” Comput. Biol. Med., vol. 94, no. December 2017, pp. 19–26, 2018, doi: 10.1016/j.compbiomed.2017.12.023.
[38] U. R.Acharya, S. L.Oh, Y.Hagiwara, J. H.Tan, M.Adam, A.Gertych, andR. S.Tan, “A deep convolutional neural network model to classify heartbeats,” Comput. Biol. Med., vol. 89, no. August, pp. 389–396, 2017, doi: 10.1016/j.compbiomed.2017.08.022.
[39] J.Zhang, S.Li, andR.Wang, “Pattern recognition of momentary mental workload based on multi-channel electrophysiological data and ensemble convolutional neural networks,” Front. Neurosci., vol. 11, no. MAY, pp. 1–16, 2017, doi: 10.3389/fnins.2017.00310.
[40] X.Zhu, W. L.Zheng, B. L.Lu, X.Chen, S.Chen, andC.Wang, “EOG-based drowsiness detection using convolutional neural networks,” Proc. Int. Jt. Conf. Neural Networks, pp. 128–134, 2014, doi: 10.1109/IJCNN.2014.6889642.
[41] F.Attal, S.Mohammed, M.Dedabrishvili, F.Chamroukhi, L.Oukhellou, andY.Amirat, “Physical human activity recognition using wearable sensors,” Sensors (Switzerland), vol. 15, no. 12, pp. 31314–31338, 2015, doi: 10.3390/s151229858.
[42] S. Z.Deng, B. T.Wang, C. G.Yang, andG. R.Wang, “Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors,” Ruan Jian Xue Bao/Journal Softw., vol. 30, no. 3, pp. 718–737, 2019, doi: 10.13328/j.cnki.jos.005685.
[43] “Efficient dense labelling of human activity sequences from wearables using fully convolutional networks.” .
[44] F.Li, K.Shirahama, M. A.Nisar, L.Köping, andM.Grzegorzek, “Comparison of feature learning methods for human activity recognition using wearable sensors,” Sensors (Switzerland), vol. 18, no. 2, pp. 1–22, 2018, doi: 10.3390/s18020679.
[45] Y.Zhang, Y.Zhang, Z.Zhang, J.Bao, andY.Song, “Human activity recognition based on time series analysis using U-Net,” 2018, [Online]. Available: http://arxiv.org/abs/1809.08113.
[46] F. J.Ordóñez andD.Roggen, “Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition,” Sensors (Switzerland), vol. 16, no. 1, 2016, doi: 10.3390/s16010115.
[47] O.Dehzangi andV.Sahu, “IMU-Based Robust Human Activity Recognition using Feature Analysis, Extraction, and Reduction,” Proc. - Int. Conf. Pattern Recognit., vol. 2018-Augus, pp. 1402–1407, 2018, doi: 10.1109/ICPR.2018.8546311.
[48] Q.Wen, L.Sun, X.Song, J.Gao, X.Wang, andH.Xu, “Time Series Data Augmentation for Deep Learning: A Survey,” 2020, [Online]. Available: http://arxiv.org/abs/2002.12478.
[49] B.Zhao, H.Lu, S.Chen, J.Liu, andD.Wu, “Multi-Scale Convolutional neural networks for time series classification,” J. Syst. Eng. Electron., vol. 28, no. 1, pp. 162–169, 2017, doi: 10.21629/JSEE.2017.01.18.
[50] T.Wen andR.Keyes, “Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer Learning,” 2019, [Online]. Available: http://arxiv.org/abs/1905.13628.
[51] E.Doi andM. S.Lewicki, “A theory of retinal population coding,” Adv. Neural Inf. Process. Syst., pp. 353–360, 2007.
[52] C. E.Kuo, Y. C.Liu, D. W.Chang, C. P.Young, F. Z.Shaw, andS. F.Liang, “Development and Evaluation of a Wearable Device for Sleep Quality Assessment,” IEEE Trans. Biomed. Eng., vol. 64, no. 7, pp. 1547–1557, 2017, doi: 10.1109/TBME.2016.2612938.
[53] “Monitoring the onset and progress of labor with electromyography in pregnant women.” .
[54] D.Devedeux, C.Marque, S.Mansour, G.Germain, andJ.Duchêne, “Uterine electromyography: A critical review,” Am. J. Obstet. Gynecol., vol. 169, no. 6, pp. 1636–1653, 1993, doi: 10.1016/0002-9378(93)90456-S.
[55] E.Garfield andR. E.Garfield, “Changes in Transcripts Encoding Calcium Channel Subunits of Rat Myometrium During Pregnancy,” 2019.
[56] A. R.Fuchs, F.Fuchs, P.Husslein, andM. S.Soloff, “Oxytocin receptors in the human uterus during pregnancy and parturition,” Am. J. Obstet. Gynecol., vol. 150, no. 6, pp. 734–741, 1984, doi: 10.1016/0002-9378(84)90677-X.
[57] H.Leitich, M.Brunbauer, A.Kaider, C.Egarter, andP.Husslein, “Cervical length and dilatation of the internal cervical os detected by vaginal ultrasonography as markers for preterm delivery: A systematic review,” Am. J. Obstet. Gynecol., vol. 181, no. 6, pp. 1465–1472, 1999, doi: 10.1016/S0002-9378(99)70407-2.
[58] H.Honest, L. M.Bachmann, J. K.Gupta, J.Kleijnen, andK. S.Khan, “Accuracy of cervicovaginal fetal fibronectin test in predicting risk of spontaneous preterm birth: systematic review,” BMJ, vol. 325, no. 7359, p. 301, 2002, doi: 10.1136/bmj.325.7359.301.
[59] C.Sousa, “Electrohysterogram Signal Component Cataloging with Spectral and Time-Frequency Methods,” no. October, p. 149, 2015, [Online]. Available: http://hdl.handle.net/10362/16081.
[60] M. B. I.Reaz, M. S.Hussain, andF.Mohd-Yasin, “Techniques of EMG signal analysis: Detection, processing, classification and applications,” Biol. Proced. Online, vol. 8, no. 1, pp. 11–35, 2006, doi: 10.1251/bpo115.
[61] R. H.Chowdhury, M. B. I.Reaz, M. A.BinMohd Ali, A. A. A.Bakar, K.Chellappan, andT. G.Chang, “Surface electromyography signal processing and classification techniques,” Sensors (Switzerland), vol. 13, no. 9, pp. 12431–12466, 2013, doi: 10.3390/s130912431.
[62] K. G.Oweiss andD. J.Anderson, “Noise reduction in multichannel neural recordings using a new array wavelet denoising algorithm,” vol. 40, pp. 1687–1693, 2001.
[63] O. P.Neto andE. A.Christou, “Rectification of the EMG signal impairs the identification of oscillatory input to the muscle,” J. Neurophysiol., vol. 103, no. 2, pp. 1093–1103, 2010, doi: 10.1152/jn.00792.2009.
[64] I.Halim, Rawaida, S. R.Kamat, A.Rohana, A.Saptari, andM.Shahrizan, “Analysis of muscle activity using surface electromyography for muscle performance in manual lifting task,” Appl. Mech. Mater., vol. 564, pp. 644–649, 2014, doi: 10.4028/www.scientific.net/AMM.564.644.
[65] A. R.Abdullah, E. F.Shair, andM.Saleh, “EMG Signal Analysis of Fatigue Muscle Activity in Manual Lifting,” pp. 1–7, 2015.
[66] L.Wang, A.Lu, S.Zhang, W.Niu, F.Zheng, andM.Gong, “Fatigue-related electromyographic coherence and phase synchronization analysis between antagonistic elbow muscles,” Exp. Brain Res., vol. 233, no. 3, pp. 971–982, 2014, doi: 10.1007/s00221-014-4172-x.
[67] H.Niu, R.Li, G.Liu, F.Pu, D.Li, andY.Fan, “Using EMG to evaluate muscular fatigue induced during video display terminal keyboard use task,” IFMBE Proc., vol. 19 IFMBE, pp. 329–332, 2008, doi: 10.1007/978-3-540-79039-6-83.
[68] F. S.Castro, E. M.Scheeren, A. M.Pressi, C. T.Candotti, andJ. F.Loss, “Comparative study of the EMG signal of human vastus lateralis and soleus muscles during fatigue and recovery,” no. Mvc, pp. 1–4, 1993.
[69] X.Qian, P.Li, S. Q.Shi, R. E.Garfield, andH.Liu, “Simultaneous Recording and Analysis of Uterine and Abdominal Muscle Electromyographic Activity in Nulliparous Women during Labor,” Reprod. Sci., vol. 24, no. 3, pp. 471–477, 2017, doi: 10.1177/1933719116658704.
[70] E.High-, B. B. D.Amplifier, L.Detection, T.Signals, B.Oscillator, F.Power-down, andS.Mode, “ADS1299-x Low-Noise, 4-, 6-, 8-Channel, 24-Bit, Analog-to-Digital Converter for EEG and Biopotential Measurements,” 2017.
[71] A.Alexandersson, T.Steingrimsdottir, J.Terrien, C.Marque, andB.Karlsson, “The Icelandic 16-electrode electrohysterogram database,” Sci. Data, vol. 2, pp. 1–9, 2015, doi: 10.1038/sdata.2015.17.
[72] S.Bach, A.Binder, G.Montavon, F.Klauschen, K. R.Müller, andW.Samek, “On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation,” PLoS One, vol. 10, no. 7, pp. 1–46, 2015, doi: 10.1371/journal.pone.0130140.
[73] R.Caldeyro-barcia andH.Alvarez, “Montevideo units - Wikipedia,” pp. 2–3, 2020.
[74] T. N.Sainath, O.Vinyals, A.Senior, andH.Sak, “Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks,” ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., vol. 2015-Augus, pp. 4580–4584, 2015, doi: 10.1109/ICASSP.2015.7178838.
[75] J.Grezmak, J.Zhang, P.Wang, K. A.Loparo, andR. X.Gao, “Interpretable Convolutional Neural Network through Layer-wise Relevance Propagation for Machine Fault Diagnosis,” IEEE Sens. J., vol. 20, no. 6, pp. 3172–3181, 2020, doi: 10.1109/JSEN.2019.2958787.
[76] V.R., “EMG Signal Noise Removal Using Neural Netwoks,” Adv. Appl. Electromyogr., 2011, doi: 10.5772/23780.
[77] S. N.Kale andS.V.Dudul, “Intelligent Noise Removal from EMG Signal Using Focused Time-Lagged Recurrent Neural Network,” Appl. Comput. Intell. Soft Comput., vol. 2009, pp. 1–12, 2009, doi: 10.1155/2009/129761.
[78] D.Ban andS.Kwon, “Movement noise cancellation in PPG signals,” 2016 IEEE Int. Conf. Consum. Electron. ICCE 2016, no. 1, pp. 47–48, 2016, doi: 10.1109/ICCE.2016.7430517.