本篇論文希望可以研究出一套可以適用於商業化發展之血壓運算系統，其中包括血管訊號擷取、棘波分析、血壓運算。利用兩個壓電式感應器測量血液流經血管產生之脈波後，抓出兩組訊號之棘波位置並進行相位差的計算，最後使用GRNN(Generalized Regression Neural Networks)計算血壓。
目前市面上，有一家公司利用光學進行血壓的測量，由於需要不停地投射光致血管內，藉由反射出來的光來計算其血壓值，而導致耗電量不小，且可能因測量者的膚色不同而有所誤差，有時甚至會受測量地點的亮度影響；另外在現有的研究中，部分研究使用微波感測器測量血流速度，並利用線性迴歸分析血流速度及血壓值的關係，確實可以測量出一個人的血壓值，然而微波感測器容易受外界影響，使得採樣出之訊號不穩定，導致血壓值不隼，即使採集出來的訊號非常好，結果卻仍會因人而異，若測量不同人，則必須去重調線性迴歸參數，才可以達到準確的結果。
本論文所使用的壓電式感測器，是採集血液流經血管後所產生出來的脈動產生出來的訊號，可以解決易受光、外界干擾的缺點；利用GRNN計算血壓值，可以解決線性回歸測量時的誤差，並且根據個人體質分類，並定期校正數次後，可以準確地做出血壓運算。
關鍵字：壓電式感測器、廣義迴歸類神經網路、相位差、脈波傳播連率、血壓運算。

[1] H. D. Lin, Y. S. Lee and B. N. Chuang, “Using Dual-Antenna Nanosecond Pulse Near-field Sensing Technology for Non-contact and Continuous Blood Pressure Measurement,” in Proc. IEEE Int. Conf. Engineering in Medicine and Biology Society, pp. 219-222, 28 Aug.-1 Sept. 2012.

[2] S. Nomura, Y. Hanasaka, M. Hasegawa-Ohira and T. Ishiguro, “Identification of Human Pulse Waveform by Silicon Microphone Chip,” in Proc. IEEE Int. Conf. Man, and Cybernetics, pp. 1145-1150, 21 Nov 2011.

[3] J. Chen, S. Zhao and Z. Huang, ”Acoustic velocity measurement in seawater based on phase difference of signal,” in Proc. Int. Conf. Electronic Measurement & Instruments, pp. 181-184, 16-19 Aug. 2011.

[4] D. F. Specht. “A General Regression Neural Network,” IEEE Transactions on Neural Networks, vol. 2, no 6, pp. 568-576, Nov. 1991.

[5] Y. C. Tung, W. J. Hwang and C. H. Ho, “A Novel QoS Mapping Algorithm for Heterogeneous Home Networks Using General Regression Neural Networks,” in Proc. IEEE Int. Conf. Computational Science and Engineering, pp. 519-526, 19-21 Dec. 2014.

[6] D. Guan, J. H. Wu, J. Wu, J. Li and W. Zhao, ”Acoustic performance of aluminum foams with semiopen cells,” Appl. Acoustics, vol.87, pp.103- 108, Jan. 2015.

[7] W. Kazimierski, G. Zaniewicz, ”Analysis of the possibility of using radar tracking method based on GRNN for processing sonar spatial data,” vol. 8537, ser. Lecture Notes in Artificial Intelligence. Zurich, Switzerland: Springer-Verlag, 2014, pp. 319-326.

[8] M. A. Hossain, A. A. M. Madkour, K. P. Dahal and L. Zhang, ”A real-time dynamic optimal guidance scheme using a general regression neural network,” Eng. Appl. Artif. Intell., vol. 26, pp. 1230-1236, Apr. 2013.

[9] C. Lopez-Martin, C. Isaza and A. Chavoya, ”Software development effort prediction of industrial projects applying a general regression neural network,” Empir. Software Eng., vol. 17, pp. 738-756, Dec. 2012.

[10] N. F. Kenji, D. P. L. Anna and R. M. Carlos, ”Short-term multinodal load forecasting using a modified general regression neural network,” IEEE Trans. Power Deliv., vol. 26, pp. 2862-2869, Oct. 2011.

[11] W. J. Hwang, Y. C. Tung, Y. L. Chen, P. Y. Lai, and C. H. Ho, ”A novel user-oriented quality of service algorithm for home networks,” IEEE Syst. J., Accepted for Publication (Available online 14 October 2015, DOI: 10.1109/JSYST.2015.2480869).

[12] Ajara term website, http://www.ne.jp/asahi/ajara/kojara/index.htm (last access: 2017/6/20)

[13]血壓計測量原理, https://read01.com/naaALM.html (last access: 2017/5/1)