生命徵象檢測的準確度與OHCA(out-of-cardiac arrest)患者的存活率有著密不可分的關係。若是能盡早實施CPR(cardiopulmonary resuscitation)，可有效地提高OHCA患者的存活率。然而，目前國際上仍是倚賴手指觸摸頸動脈的方式來辨識突發性昏迷者是否存在生命徵象。但是，即便是專業的醫護人員，也無法在短時間內有自信地說出判斷的結果。在本篇論文中，我們利用活體人類才擁有的脈搏週期訊號特性與人體全身心脈變化一致性的概念，提出一套新穎的非接觸式脈搏量測之活體皮膚辨識演算法。藉由擷取人體臉部兩塊不同區域的rPPG(remote Photoplethysmography)訊號，除了可用於計算脈搏率之外，也結合本論文提出的PCD(pulse-correlation-deviation)演算法，有效地分辨活體/非活體訊號。經過多個實驗證實，所有受測者的瞬時脈搏率在統計學之95%信賴區間中平均誤差為+2.2 ~ -2.02 bpm(beat per minute)，而在本論文提出的活體皮膚檢測實驗中，靜態實驗與動態實驗可個別獲得95%與90%的準確度。最後，本論文將此技術實現於智慧型手機中，不僅提供一般民眾一個便利的生理訊號監測平台，亦是可隨身攜帶、即時使用的生命偵測器，用以協助辨識突發性心脈停止並盡早實施CPR與體外電擊提升患者的存活率，並與救護隊聯絡時可明確地說明患者的情況，增加高階救護隊派遣的正確率。

The poor recognition of out-of-hospital cardiac arrest (OHCA) with checking carotid pulse is less than 50% correct by the public. Thus, to assist public for more effective recognition of cardiac arrest and to facilitate patients receiving early resuscitation, we propose a pulse-correlation-deviation (PCD) method to differentiate the living/non-living skin tissue by analyzing the contactless pulse signal. We firstly constructed the identification method on the smartphone, which is ubiquitous and eligible to accord realistic emergency demands. The image sensor on the smartphone was utilized to capture the remote PPG (rPPG) physiological signal and a cross-correlation operation was used to enhance the characteristics of cardiac condition of a living subject. The results show that the proposed PCD method outperforms the existed method (FDR) by providing faster and higher detection rates (95% and 90% for the fixed-holding and hand-holding smartphone experiment, respectively). In the future, the proposed innovation can facilitate the bystander to recognize OHCA in short time (within 8 seconds), and to execute earlier CPR, earlier PAD, and to provide more information for emergency calls to improve the survival rate of OHCA patients.

[1] M.-L. Weisfeldt et al., "Ventricular tachyarrhythmias after cardiac arrest in public versus at home," NEJM, pp. 313-321, 2011.
[2] J. Bahr et al., "Skills of lay people in checking the carotid pulse," Resuscitation, vol. 35, pp. 23-26, 8 1997.
[3] B. J. Bobrow et al., "Chest Compression–Only CPR by Lay Rescuers and Survival From Out-of-Hospital Cardiac Arrest," JAMA, vol. 304, pp. 1447-1454, 2010.
[4] L. White et al., "Dispatcher-Assisted Cardiopulmonary Resuscitation - Risks for Patients Not in Cardiac Arrest," Circulation, vol. 121, pp. 97-97, 2010.
[5] D. Chamberlain et al., "Trials of teaching methods in basic life support : comparison of simulated CPR performance after first training and at 6 months, with a note on the value of re-training," Resuscitation, vol. 53, pp. 179-187, 2002.
[6] F. Lapostolle et al., "Basic cardiac life support providers checking the carotid pulse: performance, degree of conviction, and influencing factors," Acad Emerg Med, vol. 11, pp. 878-880, 2004.
[7] W. Verkruysse et al., "Remote plethysmographic imaging using ambient," Opt. Exp., vol. 16, no. 23, p. 21434–21445, 2008.
[8] M. N. K. Boulos et al., "How smartphones are changing the face of mobile and participatory healthcare: an overview, with example from eCAALYX," Biomed Eng Online, vol. 10, 2011.
[9] Y. Sun and N. Thakor, "Photoplethysmography revisited: From contact to noncontact, from point to imaging," IEEE Transactions on Biomedical Engineering, vol. 63, pp. 463-477, 2016.
[10] A. B. Hertzman, “The blood supply of various skin areas as estimated by the photoelectric plethysmograph,” Am. J. Physiol, pp. 328-340, 1938.
[11] M. Z. Poh et al., "Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam," IEEE. Trans. Biomed. Eng, vol. 58, no. 1, pp. 7-11, 2011.
[12] S. Kwon et al., "Validation of heart rate extraction using video imaging on a built-in camera system of a smartphone," Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE, 2012.
[13] G. Balakrishnan et al., "Detecting Pulse from Head Motions in Video," IEEE Conference on Computer Vision and Pattern Recognition, pp. 3430-3437, 2013.
[14] D. McDuff et al., "Improvements in Remote Cardiopulmonary Measurement Using a Five Band Digital Camera," IEEE Transactions on Biomedical Engineering, vol. 61, pp. 2593-2601, 2014.
[15] F. Bousefsaf et al., "Continuous wavelet filtering on webcam photoplethysmographic signals to remotely assess the instantaneous heart rate," Biomedical Signal Processing and Control, pp. 568-574, 2013.
[16] G. de Haan, V. Jeanne, "Robust Pulse Rate From Chrominance-Based rPPG," IEEE Transactions on Biomedical Engineering, vol. 60, pp. 2878-2886, 2013.
[17] L. Feng et al., "Motion-resistant remote imaging photoplethysmography based on the optical properties of skin," IEEE trans. on Circuits and System for Video Technology, vol. 25, no. 5, pp. 879-891, 2015.
[18] P. Viola, M. Jones, "Rapid object detection using a boosted cascade of simple features," Proc. IEEE Comput. Vis. Pattern Recog, vol. 1, pp. I-511—I-518, 2001.
[19] G. Gibert et al., "Face detection method based on photoplethysmography," Proc. IEEE 10th Int. Conf. Adv. Video Signal Based Surveillance, pp. 449-453, 2013.
[20] A. Hyvarinen, "Fast and robust fixed-point algorithms for independent component analysis," IEEE Transactions on Neural Networks, vol. 10, pp. 626-634, 1999.
[21] W. Wang et al., "Unsupervised Subject Detection via Remote PPG," IEEE Transactions on Biomedical Engineering, vol. 62, pp. 2629-2637, 2015.
[22] S. Bobbia et al., "Remote Photoplethysmography Based on Implicit Living Skin Tissue Segmentation," IEEE International Conference on Pattern Recognition (ICPR 2016), 2016.
[23] J. Chang et al., "A Video Representation Using Temporal Superpixels," Proc. IEEE Conference on Computer Vision and Pattern Recognition (2013), pp. 2051-2058, 2013.
[24] WHF, 2016. [Online]. Available: http://worldheartday.org/resources/.
[25] Y. C. Lin et al., "Development of a FPGA-based contactless pulse rate detection system," Intelligent Green Building and Smart Grid (IGBSG), 2016 2nd International Conference on, 2016.
[26] M. C. Li and Y. H. Lin, "A real-time non-contact pulse rate detector based on smartphone," Next-Generation Electronics (ISNE), 2015 International Symposium on, 2015.
[27] Y. Zhang et al, "Sparse PCA: Convex relaxations, algorithms and applications," Int. Ser. Oper. Res. Manage. Sci, vol. 166, pp. 915-940, 2012.
[28] D. F. Swinehart, "The Beer-Lambert Law," J. Chem. Educ., vol. 39, no. 7, pp. 333-335, 1962.
[29] T. Tamura et al., "Wearable Photoplethysmographic Sensors—Past and Present," Electronics (2014), pp. 282-302, 2014.
[30] H. Y. Wu et al., "Eulerian Video Magnification for Revealing Subtle Changes in the World," ACM Trans. Graph. Proceedings SIGGRAPH, 2012.
[31] M. Z. Poh et al., "Non-contact, automated cardiac pulse measurements using video imaging and blind source separation," Optics Express, vol. 18, pp. 10762-10774, 2010.
[32] K. Y. Lin et al., "Face-Based Heart Rate Signal Decomposition and Evaluation Using Multiple Linear Regression," IEEE Sensors Journal, vol. 16, no. 5, pp. 1351-1360, 2016.
[33] "Fujitsu Laboratories Develops Real-Time Pulse Monitor Using Facial Imaging," 2013. [Online]. Available: http://www.fujitsu.com/global/about/resources/news/press-releases/2013/0318-01.html.
[34] OpenCV. [Online]. Available: http://docs.opencv.org/2.4/modules/objdetect/doc/cascade_classification.html.
[35] B. D. Lucas and T. Kanade, "An iterative image registration technique with an application to stereo vision," Proceedings of Imaging Understanding Workshop, pp. 121-130, 1981.
[36] B. K. P. Horn and B. G. Schunck, "Determining optical flow," Artificial Intelligence, vol. 17, pp. 185-203, 1981.
[37] G. Bradski and A. Kaehler, Learning OpenCV: Computer Vision with the OpenCV Library, O'Reilly Media, Inc, 2008.
[38] J. Y. Bouguet, "Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the algorithm," Intel Corporation Microprocessor Research Labs, pp. 1-10, 2001.
[39] E. R. Nye, "the effect of blood pressure alteration on the pulse wave velocity," British Heart Journal, vol. 26, pp. 261-265, 1964.
[40] L. Terminelli et al., "Photoplethysmography and electrocardiography for real time evaluation of pulse transit time A diagnostic marker of peripheral vascular diseases," Photonics Technologies, 2014 Fotonica AEIT Italian Conference on, 2014.
[41] "Sony mobile," [Online]. Available: http://support.sonymobile.com/tw/xperiazultra/supportDocumentation/.
[42] G. Lempe et al., "ROI Selection for Remote Photoplethysmography," Bildverarbeitung für die Medizin 2013, pp. 99-103, 2013.
[43] S. Kwon et al., "ROI analysis for remote photoplethysmography on facial video," 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 4938-4941, 2015.
[44] B. Chwyl et al., "Time-Frequency Domain Analysis via Pulselets for Non-contact Heart Rate Estimation from Remotely Acquired Photoplethysmograms," 2016 13th Conference on Computer and Robot Vision (CRV), pp. 201-207, 2016.
[45] J. A. Crowe and D. Damianou, "The wavelength dependence of the photoplethysmogram and its implication to pulse oximetry," 1992 14th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 6, pp. 2423-2424, 1992.
[46] R. E. Kalman, "A New Approach to Linear Filtering and Prediction Problems," Transactions of the ASME - Journal of Basic Engineering, vol. 82, pp. 35-45, 1960.
[47] S. H. Liu et al., "Using a Kalman Filter to Compensate for Photoplethysmogram Artifacts when Monitoring CT Examinations," 2009 2nd International Conference on Biomedical Engineering and Informatics, pp. 1-5, 2009.
[48] A. Treesirichod et al., "Digital Photographic RGB Scores used for the Evaluation of Skin Color," Indian Journal of Clinical and Experimental Dermatology, vol. 1, pp. 17-20, 2015.
[49] G. de Haan and A. van Leest, "Improved motion robustness of remote-PPG by using the blood volume pulse signature," Physiol. Meas., vol. 3, no. 2, pp. 1913-1926, 2014.