本篇論文結合注入鎖定與被動式雷達技術，發展一套能偵測手勢的都卜勒雷達。自身無須產生發射訊號，並使用外部的Wi-Fi訊號，作為感測所需之雷達訊號源。因此雷達接收機的電路架構是本篇的重點，其中電路架構主要又分為注入鎖定振盪器與正交解調器。
首先介紹注入鎖定振盪器，本論文使用環形振盪器的架構來實現擁有較高注入鎖定範圍與寬頻調整範圍的振盪器，且採用TSMC 0.18μm的製程來實作電路。至於正交解調器則以混合式元件搭配印刷電路板的技術來實作。之後再將注入鎖定振盪器與正交解調器結合起來，並與先前本實驗室所使用的接收機電路相互比較效能。比較後，可得到本論文的接收機電路其手勢訊號訊雜比優秀於先前接收機電路的結果。
而為了可以辨識手勢並提高其正確率，本篇論文會介紹深度學習的方法，並使用深度學習去訓練手勢訊號的辨識。得到訊號不同的特徵值再經過神經網路的訓練，判斷出手勢種類，接著透過使用不同的神經網路架構而得到更好的辨識正確率。

This thesis presents a passive radar which is able to detect hand gesture by Doppler effect. The Wi-Fi signals are utilized as the signal sources in this radar for detecting a moving target. Since this is a passive radar, the architecture of the radar receiver is the main focus of the work. The radar receiver architecture is divided into two parts, an injection-locked oscillator (ILO) and a quadrature demodulator.
Firstly, this thesis introduces the ILO design method. To fulfill the ILO with a high locking range and wide frequency tuning range, a ring oscillator based ILO was used and implemented using TSMC 0.18μm process. Next, the quadrature demodulator is implemented with hybrid components on a printed circuit board. Then this work combine the ILO and the quadrature demodulator to form the radar receiver, and compares the performance with the radar receiver used in the previous work. It is concluded that the presented radar receiver outperforms the previous one.
To recognize the gesture signals collected from the receiver and to raise the accuracy of recognition, this work uses the deep learning algorithm to train the gesture recognition process. The training procedure outputs different characteristic parameters of the signals, which is useful to recognize the gesture using the neural network. Moreover, different neural network structures were used to improve the accuracy of the gesture recognition.

目錄

論文審定書 i
論文公開授權書 ii
誌謝 iii
摘要 iv
Abstract v
目錄 vi
圖次 viii
表次 xii
第一章 序論 1
1.1 研究背景與動機 1
1.2 都卜勒雷達簡介 4
1.3 章節規劃 7
第二章 具有寬頻調整範圍之CMOS注入鎖定振盪器 8
2.1 晶片電路設計 8
2.1.1 電路架構的考量與選擇 8
2.1.2 電路設計流程 10
2.1.3 電路設計方法 11
2.1.4 Body-biased架構原理 13
2.2 晶片電路模擬與量測 15
2.2.1 模擬與量測儀器設置 15
2.2.2 模擬與量測結果 17
第三章 手勢感測系統正交解調電路 24
3.1 手勢感測雷達架構簡介 24
3.1.1 直接降頻正交接收機 24
3.1.2 手勢感測雷達 25
3.2 解調電路設計與整合 27
3.2.1 架構考量選擇 27
3.2.2 電路元件選擇 29
3.3 規格測試之性能比較 36
3.4 解調電路應用於手勢雷達之比較 39
第四章 深度學習與應用 50
4.1 深度學習介紹 50
4.1.1 歷史背景 50
4.1.2 深度學習簡介 50
4.1.3 神經網路的基本架構 51
4.2 訓練方法 56
4.2.1 收集數據和訓練流程 56
4.2.2 隱藏層架構介紹:CNN 57
4.2.3 隱藏層架構介紹:RNN 57
4.3 訓練結果 59
第五章 結論 65
參考文獻 66
附錄A 振盪器與注入鎖定理論 71
A.1 注入鎖定振盪器原理 71
A.1.1 振盪條件 71
A.1.2 注入鎖定現象 73
參考文獻 77

[1] V. I. Pavlovic, R. Sharma and T. S. Huang, "Visual interpretation of hand gestures for human-computer interaction: a review," IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 7, pp. 677-695, Jul 1997.
[2] K. Oka, Y. Sato and H. Koike, "Real-time fingertip tracking and gesture recognition," IEEE Comput. Graph. Appl. Mag., vol. 22, no. 6, pp. 64-71, Nov/Dec 2002.
[3] G. Sharma, S. Jyoti and A. Dhall, "Hybrid Neural Networks Based Approach for Holoscopic Micro-Gesture Recognition in Images and Videos," 2018 13th IEEE Int. Conf. on Automatic Face & Gesture Recognition (FG 2018), Xi'an, 2018, pp. 808-814.
[4] D. J. Sturman and D. Zeltzer, "A survey of glove-based input," IEEE Comput. Graph. Appl. Mag., vol. 14, no. 1, pp. 30-39, Jan. 1994.
[5] L. Dipietro, A. M. Sabatini and P. Dario, "A Survey of Glove-Based Systems and Their Applications," IEEE Trans. Syst., Man, Cybern., Syst., vol. 38, no. 4, pp. 461-482, July 2008.
[6] 王國榮，基於資料手套的智慧型手勢辨識之廣泛研究，國立臺灣科技大學電機工程學系碩士論文，2001。
[7] S. Gupta, D. Morris, S. Patel, and D. Tan, "SoundWave: using the doppler effect to sense gestures,"in Proc. of the 2012 ACM Annu. Conf. on Human Factors in Computing Systems - CHI 12, 2012.
[8] K. Kalgaonkar and B. Raj, "One-handed gesture recognition using ultrasonic Doppler sonar," 2009 IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Taipei, 2009, pp. 1889-1892.
[9] Q. Pu, S. Jiang, and S. Gollakota, "Whole-home gesture recognition using wireless signals," in Proc. of the ACM SIGCOMM 2013 Conf. on SIGCOMM - SIGCOMM, pp. 27–38, 2013.
[10] V. C. Chen, F. Li, S. S. Ho and H. Wechsler, "Micro-Doppler effect in radar: phenomenon, model, and simulation study," IEEE Trans. Aerosp. Electron. Syst, vol. 42, no. 1, pp. 2-21, Jan. 2006.
[11] C. Howard, C. H. Hansen and A. C. Zander, "Review of current recommendations for airborne ultrasound exposure limits." Annu. Conf. of the Australian Acoustical Society 2005, Acoustics 2005: Acoustics in a Changing Environment, 2005, pp. 341-343.
[12] R. Watson-Watt, "Radar in War and in Peace," Nature, vol. 156, no. 3959, pp. 319–324, 1945.
[13] M. I. Skolnik, Introduction to radar systems. Boston: McGraw-Hill, 2007.
[14] L. Brown, A radar history of World War II: technical and military imperatives. Bristol: Institute of Physics Publishing, 2000.
[15] P. Molchanov, S. Gupta, K. Kim and K. Pulli, "Short-range FMCW monopulse radar for hand-gesture sensing," 2015 IEEE Radar Conf. (RadarCon), Arlington, VA, 2015, pp. 1491-1496.
[16] J. Lien, N. Gillian, M. E. Karagozler, P. Amihood, C. Schwesig, E. Olson, H. Raja, and I. Poupyrev, "Soli: ubiquitous gesture sensing with millimeter wave radar, " ACM Trans. Graphics , vol. 35, no. 4, article 142, Jul. 2016.
[17] Z. Peng, C. Li, J. M. Muñoz-Ferreras and R. Gómez-García, "An FMCW radar sensor for human gesture recognition in the presence of multiple targets," 2017 First IEEE MTT-S Int. Microwave Bio Conf., Gothenburg, 2017, pp. 1-3.
[18] F. Folster, H. Rohling and U. Lubbert, "An automotive radar network based on 77 GHz FMCW sensors," IEEE Int. Radar Conf., 2005, pp. 871-876.
[19] T. Mitomo, N. Ono, H. Hoshino, Y. Yoshihara, O. Watanabe and I. Seto, "A 77 GHz 90 nm CMOS Transceiver for FMCW Radar Applications," IEEE J. Solid-State Circuits, vol. 45, no. 4, pp. 928-937, April 2010.
[20] S. Zhang, G. Li, M. Ritchie, F. Fioranelli and H. Griffiths, "Dynamic hand gesture classification based on radar micro-Doppler signatures," 2016 CIE Int. Conf. on Radar, Guangzhou, 2016, pp. 1-4.
[21] J. Fink, H. Guissouma and F. Jondral, "Feature-based gesture classification by means of high resolution radar measurements," 2017 18th Int. Radar Symp., Prague, 2017, pp. 1-10.
[22] M. Ritchie, A. Jones, J. Brown and H. D. Griffiths, "Hand gesture classification using 24 GHz FMCW dual polarised radar," Int. Conf. on Radar Systems, Belfast, 2017, pp. 1-6.
[23] G. Malysa, D. Wang, L. Netsch and M. Ali, "Hidden Markov model-based gesture recognition with FMCW radar," 2016 IEEE Global Conf. on Signal and Information Processing, Washington, DC, 2016, pp. 1017-1021.
[24] J. Zhang and Z. Shi, "Deformable deep convolutional generative adversarial network in microwave based hand gesture recognition system," 2017 9th Int. Conf. on Wireless Communications and Signal Processing, Nanjing, 2017, pp. 1-6.
[25] M. S. Seyfioğlu, S. Z. Gürbüz, A. M. Özbayoğlu and M. Yüksel, "Deep learning of micro-Doppler features for aided and unaided gait recognition," 2017 IEEE Radar Conf., Seattle, WA, 2017, pp. 1125-1130.
[26] B. Dekker, S. Jacobs, A. S. Kossen, M. C. Kruithof, A. G. Huizing and M. Geurts, "Gesture recognition with a low power FMCW radar and a deep convolutional neural network," 2017 European Radar Conf., Nuremberg, 2017, pp. 163-166.
[27] Mu-Cyun Tang, F. K. Wang and T. S. Horng, "Human gesture sensor using ambient wireless signals based on passive radar technology," 2015 IEEE MTT-S Int. Microwave Symp., Phoenix, AZ, 2015, pp. 1-4.
[28] F. K. Wang, M. C. Tang, Y. C. Chiu and T. S. Horng, "Gesture Sensing Using Retransmitted Wireless Communication Signals Based on Doppler Radar Technology," IEEE Trans. Microw. Theory Techn., vol. 63, no. 12, pp. 4592-4602, Dec. 2015.
[29] M. C. Tang, C. L. Chen, M. H. Lin, F. K. Wang, C. H. Yeh and T. S. Horng, "A hybrid computer vision and Wi-Fi Doppler radar system for capturing the 3-D hand gesture trajectory with a smartphone," 2017 IEEE MTT-S Int. Microwave Symp., Honololu, HI, 2017, pp. 1251-1254.
[30] B. Razavi, RF Microelectronics, 2nd ed. Prentice-Hall, Upper Saddle River, 2011.
[31] M. K. Mandal and B. C. Sarkar, "Ring oscillators: characteristics and applications, " Indian J. Pure and Applied Physics, vol. 48, pp. 136-145, Feb. 2010.
[32] A. Hajimiri, S. Limotyrakis and T. H. Lee, "Jitter and phase noise in ring oscillators," IEEE J. Solid-State Circuits, vol. 34, no. 6, pp. 790-804, Jun 1999.
[33] K. Yamamoto and M. Fujishima, "A 44-μW 4.3-GHz injection-locked frequency divider with 2.3-GHz locking range," IEEE J. Solid-State Circuits, vol. 40, no. 3, pp. 671-677, March 2005.
[34] 葉榮富，含積體化被動元件之寬頻與低功率金氧半導體射頻積體電路設計，國立中山大學電機工程學系博士論文，2013。
[35] P. Andreani and S. Mattisson, "On the use of MOS varactors in RF VCOs," IEEE J. Solid-State Circuits, vol. 35, no. 6, pp. 905-910, June 2000.
[36] 盧貫中，針對射頻系統之低相位雜訊與高調變頻寬CMOS壓控振盪器設計，國立高雄大學電機工程學系碩士論文，2006。
[37] Y. J. Moon, Y. S. Roh, C. Y. Jeong and C. Yoo, "A 4.39–5.26 GHz LC-Tank CMOS Voltage-Controlled Oscillator With Small VCO-Gain Variation," IEEE Microw. Compon. Lett, vol. 19, no. 8, pp. 524-526, Aug. 2009.
[38] Y. J. Moon, Y. S. Roh, C. Y. Jeong and C. Yoo, "A 4.39–5.26 GHz LC-Tank CMOS Voltage-Controlled Oscillator With Small VCO-Gain Variation," IEEE Microw. Compon. Lett, vol. 19, no. 8, pp. 524-526, Aug. 2009.
[39] B. Soltanian, H. Ainspan, W. Rhee, D. Friedman and P. R. Kinget, "An Ultra-Compact Differentially Tuned 6-GHz CMOS LC-VCO With Dynamic Common-Mode Feedback," IEEE J. Solid-State Circuits, vol. 42, no. 8, pp. 1635-1641, Aug. 2007.
[40] 張盛富、張嘉展，無線通訊射頻晶片模組設計－射頻系統篇，台北，全華圖書股份有限公司，2009年
[41] Skyworks Solutions, “400-3000 MHz Direct Quadrature Demodulator,” SKY73009 datasheet, Nov. 2006.
[42] Analog Devices, “400 MHz to 6 GHz Quadrature Demodulator,” ADL5380 datasheet, 2009.
[43] Mini Circuits - Global Leader of RF and Microwave Components. [Online]. Available: https://www.minicircuits.com/.
[44] 蘇聖超，應用於生命偵測儀之雙頻自我注入鎖定雷達，國立中山大學電機工程學系碩士論文，2017。
[45] W. S. Mcculloch and W. Pitts, “A logical calculus of the ideas immanent in nervous activity,” The Bulletin of Mathematical Biophysics, vol. 5, no. 4, pp. 115–133, 1943.
[46] 鄭澤宇、顧思宇、才雲科技Caicloud，實戰Google深度學習技術:使用TensorFlow，台北，松崗資產管理股份有限公司，2017年。
[47] 劉惠琳，應用深度學習於手機端天線選擇之研究，國立中山大學電機工程學系碩士論文，2017。
[48] “Neural Networks (Learning),” ritchieng.github.io. [Online]. Available: https://www.ritchieng.com/neural-networks-learning/.
[49] A. Bhande, “What is underfitting and overfitting in machine learning and how to deal with it.,” Medium, 11-Mar-2018. [Online]. Available: https://medium.com/greyatom/what-is-underfitting-and-overfitting-in-machine-learning-and-how-to-deal-with-it-6803a989c76.
[50] H.J.T., “Deep learning笔记2-CNN卷积神经网络,” H.J.T. Github, 01-Jan-2018. [Online]. Available: https://hjtso.github.io/2017/09/16/zh-Deep-learning笔记2-CNN卷积神经网络/zh/.
[51] Colah, “Understanding LSTM Networks,” Understanding LSTM Networks -- colah's blog. [Online]. Available: http://colah.github.io/posts/2015-08-Understanding-LSTMs/.

[A1] 張盛富、張嘉展，無線通訊射頻晶片模組設計－射頻晶片篇，台北，全華圖書股份有限公司，2008年。
[A2] N. M. Nguyen and R. G. Meyer, "Start-up and frequency stability in high-frequency oscillators," IEEE J. Solid-State Circuits, vol. 27, no. 5, pp. 810-820, May 1992.
[A3] D. M. Pozar, Microwave Engineering, 4th ed. Hoboken: John Willey & Sons, New Jersey, 2012.
[A4] R. Adler, “A study of locking phenomena in oscillators,” Proc. I.R.E. and Waves and Electrons, vol. 46, pp. 351-357, June 1946.
[A5] R. C. Mackey, "Injection locking of klystron oscillators, "I.R.E. Trans. Microwave Theory and Techniques, vol. 10, pp. 228-235, July 1962.
[A6] L. J. Paciorek, "Injection locking of oscillators, " Proc. IEEE, vol. 53, pp. 1723-1727, Nov. 1965.
[A7] K. Kurokawa, "Injection locking in microwave solid-state oscillators, " Proc. IEEE, vol. 61, pp. 1336-1410, Oct. 1973.
[A8] B. Razavi, "A study of injection locking and pulling in oscillators, " IEEE J. Solid-State Circuits, vol. 39, pp. 1415-1424, Sep. 2004.
[A9] 蕭介勛，本地振盪源的注入鎖定與牽引現象研究，國立中山大學電機工程學系碩士論文，2008。
[A10] 錢世樺，注入鎖定發射機研製與波束成型應用，國立中山大學電機工程學系碩士論文，2016。
[A11] H. L. Stover and R. C. Shaw, "Injection-locked oscillators as amplifiers for angle-modulation signals, " in IEEE MTT-S Int. Microw. Symp. Dig., 1966, pp. 60-66.
[A12] N. Lanka, S. Patnaik, and R. Harjani, "Understanding the transient behavior of injection locked LC oscillators, " Proc. IEEE custom Integr. Circuits Conf., San Jose, CA, 2007, pp.667-670.