本碩士論文最主要是利用頻率為 24GHz 的 Doppler radar，透過 Doppler radar 所提供的 Continuous­Wave (CW) 雷達和 Frequency­Modulated Continuous Wave (FMCW)雷達，前者是發射一個固定頻率的信號，因此最主要是偵測動作的速度以及頻率的變化率；後者則是利用時間上改變發射信號的頻率，並測量接收信號相對於發射信號的頻率方來測定目標距離，其發射頻率和接收頻率的相對關係不但可測量目標距離還可測量出目標的徑向速度，利用這兩種方法即可達成利用非接觸式的方式收集人類常見的動作特徵，並搭配 Machine Learning 中的支援向量機 (Support Vector Machine)，針對人運動所常見的七種動作像是跌倒、原地跳、跑步、坐下、彎腰、蹲下以及拄拐杖走路這幾種動作進行辨識，之後將數據進行訓練，調整相關的參數，確立最後所使用的模型，並進行人體動作辨識的實驗以及分析，透過實驗的結果及分析，本篇論文可以針對七種人體動作辨識的準確率平均可以達 96%，說明本文利用混合式雷達系統來進行人體動作辨識具有不錯的辨識能力。

This thesis focuses on devising a 24GHZ hybrid radar system for human motion recognition based on the Continuous Wave radar and the Frequency Modulated Continuous Wave
radar. The distance and velocity of targets can be estimated by the relationship between
the transmitted frequency and the received frequency of the 24GHZ hybrid radar model.
The hybrid radar system first collects the characteristics of everyday human activities in
a non­contact manner, and inputs to our algorithm based on Support Vector Machine to
identify seven popular human movements of daily life, including falling, jumping in place,
running, sitting, bending, squatting, and walking on crutches. Through analysis and evaluation of the experimental results, the accuracy of this system can reach an average of 96%
for seven kinds of human motion recognition, indicating that this article uses a hybrid
radar system that has good recognition ability for practical applications.

[1] O. D. Lara and M. A. Labrador, “A survey on human activity recognition using wearable sensors,” IEEE communications surveys & tutorials, vol. 15, no. 3, pp. 1192–
1209, 2012.
[2] E. Cippitelli, F. Fioranelli, E. Gambi, and S. Spinsante, “Radar and rgb­depth sensors
for fall detection: A review,” IEEE Sensors Journal, vol. 17, no. 12, pp. 3585–3604,
2017.
[3] C. Ding, H. Hong, Y. Zou, H. Chu, X. Zhu, F. Fioranelli, J. Le Kernec, and C. Li,
“Continuous human motion recognition with a dynamic range­doppler trajectory
method based on fmcw radar,” IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 9, pp. 6821–6831, 2019.
[4] Z.­Y. He and L.­W. Jin, “Activity recognition from acceleration data using ar model
representation and svm,” in 2008 international conference on machine learning and
cybernetics, vol. 4, pp. 2245–2250, IEEE, 2008.
[5] O. D. Lara, A. J. Pérez, M. A. Labrador, and J. D. Posada, “Centinela: A human
activity recognition system based on acceleration and vital sign data,” Pervasive and
mobile computing, vol. 8, no. 5, pp. 717–729, 2012.
[6] K. Wang, J. He, and L. Zhang, “Attention­based convolutional neural network for
weakly labeled human activities’recognition with wearable sensors,” IEEE Sensors
Journal, vol. 19, no. 17, pp. 7598–7604, 2019.
[7] H. Peng, F. Long, and C. Ding, “Feature selection based on mutual information criteria of max­dependency, max­relevance, and min­redundancy,” IEEE Transactions
on pattern analysis and machine intelligence, vol. 27, no. 8, pp. 1226–1238, 2005.
[8] L. C. Jatoba, U. Grossmann, C. Kunze, J. Ottenbacher, and W. Stork, “Context­aware
mobile health monitoring: Evaluation of different pattern recognition methods for
classification of physical activity,” in 2008 30th annual international conference of
the ieee engineering in medicine and biology society, pp. 5250–5253, IEEE, 2008.
45
[9] C. Randell and H. Muller, “Context awareness by analysing accelerometer data,”
in Digest of Papers. Fourth International Symposium on Wearable Computers,
pp. 175–176, IEEE, 2000.
[10] T.­P. Kao, C.­W. Lin, and J.­S. Wang, “Development of a portable activity detector
for daily activity recognition,” in 2009 ieee international symposium on industrial
electronics, pp. 115–120, IEEE, 2009.
[11] I. A. Lawal and S. Bano, “Deep human activity recognition using wearable sensors,”
in Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments, pp. 45–48, 2019.
[12] W. Jiang and Z. Yin, “Human activity recognition using wearable sensors by deep
convolutional neural networks,” in Proceedings of the 23rd ACM international conference on Multimedia, pp. 1307–1310, 2015.
[13] I. A. Lawal and S. Bano, “Deep human activity recognition with localisation of wearable sensors,” IEEE Access, vol. 8, pp. 155060–155070, 2020.
[14] J. Zhao, J. Katupitiya, and J. Ward, “Global correlation based ground plane estimation using v­disparity image,” in Proceedings 2007 IEEE international conference
on robotics and automation, pp. 529–534, IEEE, 2007.
[15] P. Bilski, P. Mazurek, and J. Wagner, “Application of k nearest neighbors approach
to the fall detection of elderly people using depth­based sensors,” in 2015 IEEE 8th
International Conference on Intelligent Data Acquisition and Advanced Computing
Systems: Technology and Applications (IDAACS), vol. 2, pp. 733–739, IEEE, 2015.
[16] R. Planinc and M. Kampel, “Introducing the use of depth data for fall detection,”
Personal and ubiquitous computing, vol. 17, no. 6, pp. 1063–1072, 2013.
[17] C. K. Lee and V. Y. Lee, “Fall detection system based on kinect sensor using novel
detection and posture recognition algorithm,” in International Conference on Smart
Homes and Health Telematics, pp. 238–244, Springer, 2013.
[18] C. Kawatsu, J. Li, and C.­J. Chung, “Development of a fall detection system with
microsoft kinect,” in Robot Intelligence Technology and Applications 2012, pp. 623–
630, Springer, 2013.
46
[19] S.­W. Yang and S.­K. Lin, “Fall detection for multiple pedestrians using depth image
processing technique,” Computer methods and programs in biomedicine, vol. 114,
no. 2, pp. 172–182, 2014.
[20] Z.­P. Bian, J. Hou, L.­P. Chau, and N. Magnenat­Thalmann, “Fall detection based
on body part tracking using a depth camera,” IEEE journal of biomedical and health
informatics, vol. 19, no. 2, pp. 430–439, 2014.
[21] N. Noury, A. Fleury, P. Rumeau, A. K. Bourke, G. Laighin, V. Rialle, and J. Lundy,
“Fall detection­principles and methods,” in 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1663–1666,
IEEE, 2007.
[22] A. Amini, K. Banitsas, and J. Cosmas, “A comparison between heuristic and machine
learning techniques in fall detection using kinect v2,” in 2016 IEEE International
Symposium on Medical Measurements and Applications (MeMeA), pp. 1–6, IEEE,
2016.
[23] M. Kepski and B. Kwolek, “Unobtrusive fall detection at home using kinect sensor,”
in International Conference on Computer Analysis of Images and Patterns, pp. 457–
464, Springer, 2013.
[24] A. Dubois and F. Charpillet, “Human activities recognition with rgb­depth camera
using hmm,” in 2013 35th Annual International Conference of the IEEE Engineering
in Medicine and Biology Society (EMBC), pp. 4666–4669, IEEE, 2013.
[25] B. Jokanovic, M. G. Amin, and F. Ahmad, “Effect of data representations on deep
learning in fall detection,” in 2016 IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM), pp. 1–5, IEEE, 2016.
[26] B. Erol, M. Amin, F. Ahmad, and B. Boashash, “Radar fall detectors: A comparison,” in Radar Sensor Technology XX, vol. 9829, p. 982918, International Society
for Optics and Photonics, 2016.
[27] B. Erol, M. Amin, Z. Zhou, and J. Zhang, “Range information for reducing fall false
alarms in assisted living,” in 2016 IEEE Radar Conference (RadarConf), pp. 1–6,
IEEE, 2016.
47
[28] M. Mercuri, P. J. Soh, G. Pandey, P. Karsmakers, G. A. Vandenbosch, P. Leroux, and
D. Schreurs, “Analysis of an indoor biomedical radar­based system for health monitoring,” IEEE Transactions on Microwave Theory and Techniques, vol. 61, no. 5,
pp. 2061–2068, 2013.
[29] C. Garripoli, M. Mercuri, P. Karsmakers, P. J. Soh, G. Crupi, G. A. Vandenbosch,
C. Pace, P. Leroux, and D. Schreurs, “Embedded dsp­based telehealth radar system
for remote in­door fall detection,” IEEE journal of biomedical and health informatics, vol. 19, no. 1, pp. 92–101, 2014.
[30] X. Ma, H. Wang, B. Xue, M. Zhou, B. Ji, and Y. Li, “Depth­based human fall detection via shape features and improved extreme learning machine,” IEEE journal
of biomedical and health informatics, vol. 18, no. 6, pp. 1915–1922, 2014.
[31] M. Aslan, A. Sengur, Y. Xiao, H. Wang, M. C. Ince, and X. Ma, “Shape feature
encoding via fisher vector for efficient fall detection in depth­videos,” Applied Soft
Computing, vol. 37, pp. 1023–1028, 2015.
[32] E. Akagündüz, M. Aslan, A. Şengür, H. Wang, and M. C. Ince, “Silhouette orientation volumes for efficient fall detection in depth videos,” IEEE journal of biomedical
and health informatics, vol. 21, no. 3, pp. 756–763, 2016.
[33] A.­K. Seifert, M. G. Amin, and A. M. Zoubir, “Toward unobtrusive in­home gait
analysis based on radar micro­doppler signatures,” IEEE Transactions on Biomedical Engineering, vol. 66, no. 9, pp. 2629–2640, 2019.
[34] M. G. Amin, Y. D. Zhang, F. Ahmad, and K. D. Ho, “Radar signal processing for
elderly fall detection: The future for in­home monitoring,” IEEE Signal Processing
Magazine, vol. 33, no. 2, pp. 71–80, 2016.
[35] E. E. Stone and M. Skubic, “Fall detection in homes of older adults using the microsoft kinect,” IEEE journal of biomedical and health informatics, vol. 19, no. 1,
pp. 290–301, 2014.
[36] C.­C. Chang and C.­J. Lin, “Libsvm: a library for support vector machines,” ACM
transactions on intelligent systems and technology (TIST), vol. 2, no. 3, pp. 1–27,
2011.
48
[37] C. Ding, L. Zhang, C. Gu, L. Bai, Z. Liao, H. Hong, Y. Li, and X. Zhu, “Non­contact
human motion recognition based on uwb radar,” IEEE Journal on Emerging and
Selected Topics in Circuits and Systems, vol. 8, no. 2, pp. 306–315, 2018.