臺灣博碩士論文加值系統

現代化的社會，生活習慣使得人們容易罹患慢性疾病，尤其是那些一天當中需要長期處於相同動作並且沒有規律運動習慣的人。為了避免這種情況更加的惡化，在即將到來的物聯網時代，智慧家庭成為了一個重要的議題。其中，照護服務，尤其是針對老人慢性病，更成為了一個重要的應用程式。許多文獻指出，適度的運動是能有效減緩慢性病的惡化，因此，在本篇論文中，我們提出一個新穎的活動監測和強度評估系統，他能夠產生卡路里地圖，這地圖的資訊將會包含患者的所在位置、持續性的活動和活動所造成的卡路里消耗量而形成一個監測服務。透過這個地圖的資訊，照護人員便可得知患者的狀態並且視狀況鼓勵患者活動以便改善他的生活習慣。這套系統利用無線訊號去判斷使用者位置和動作；而在身體活動所造成的卡路里消耗這方面，除了參考無線訊號外也多參考能量代謝當量去推測，過程中會需要感測元件少量時間的幫助。在環境中，將會有指路明燈佈建於各個房間，廁所、客廳、寢室、會議室，這些指路明燈將會發射藍芽訊號和超聲波訊號。病患將會在胸前被佩戴著智慧胸針，胸針會接收環境中的無線訊號進而去判斷使用者的位置、動作和卡路里消耗量。我們的系統比現存的系統有了三種好處。第一，無線訊號在許多應用程式只被拿來當作位置的指示符，但是在我們系統中，我們更將他視為一種能反映出活動的指示符；第二，我們的系統是一個半訓練的系統，即系統會有訓練時期，但是不需要人為介入，而是透過感測元件的幫助進行自動化的訓練，在離開訓練期之後，感測元件即可關閉。系統的訓練期將只占整體運作的一小部分，也此因感測元件所節省的電量會是可觀的；最後，本系統所提出的動作辨識的方法，他是非常的直覺性，不需要太過於複雜的想法及運作即可辨識出一些人類的基本動作。我們的系統已經成功被實現在智慧型手機和個人電腦上，並且整套系統是很容易被架設並使用的。

In the modern era, lifestyle make people get the chronic diseases easily, especially for the person who need to spend almost whole day staying in the same activity state and does not do exercise regularly. To avoid this situation become worse and worse, smart home has become an important issue in the coming new era of IoT field. Among the smart home, healthcare service, especially for the elder with chronic diseases, has become one of the most important applications. Many studies reported that the progress of chronic disease can be slow down effectively by moderate ctivities. In this paper, we proposed a novel activity monitoring and intensity estimation system which will produce the calorie map to support continuous motion and physical activity calorie burned monitoring service so that the caregivers can know the patients condition and encourage them to move and hence improving the life style. The system uses wireless signals and metabolic equivalent (MET) to estimate calorie burned by the physical activity with little assistance of motion sensors during the training phase. In the proposed system, Bluetooth Low Energy(BLE) beacons equipped with ultrasonic transducer were deployed in the living space , such as living room, bedroom, etc. The patients wore a smart brooch are continuously monitored for the location, activity and calorie burned by receiving wireless signals. The proposed system has three-fold advantages compared to the existed systems: Firstly, in addition to utilizing the wireless signal as a location indicator, the proposed system also uses the wireless signals as an activity indicator. Secondly, the proposed system is semi-training free, the system does not need the intervention of trained technician. Also, it only needs relatively short training time during the whole operations. Hence, The power consumption caused by the motion sensors can be greatly reduced. Finally, we provide an activity recognition without too much complicate though and operation. A prototype system has successfully implemented on HTC M8 smartphone and PC, and it is easily to set up.

Chinese Abstract i
English Abstract ii
Chinese Acknowledgement iii
Contents iv
1 Introduction 1
2 Related Work 6
2.1 Reports on Chronic Diseases 6
2.2 Indoor Localization Techniques 6
2.3 Activity Recognition 8
2.4 Walking Activity Tracking Techniques 8
3 Calorie Map Construction System 10
3.1 System Architecture 10
3.1.1 Wearable Devices 11
3.1.2 Environment Beacons 11
3.1.3 Cloud Server 11
3.1.4 Caregivers Assistant App 12
3.2 Prototype System Tools 12
3.2.1 Hardware 12
3.2.2 Software 14
3.3 Processing flow 15
3.3.1 Online Training Mode 15
3.3.2 Inference Mode 16
3.3.3 Mode Transition 16
4 Room-level Positioning 18
4.1 Positioning Expeimental Analysis 19
4.1.1 Testbed Setting 19
4.1.2 Experimental Results 20
5 Activity Monitoring 21
5.1 Walking Detection 21
5.2 Rule-Based Activity Recognition 22
5.2.1 Extracting Doppler shifts 31
5.2.2 Perform the rule-based activity recognition and self-correction 31
5.2.3 Activity Recognition Expeimental Analysis 31
6 RF-based Step Counts Estimation 33
6.1 RF-Fingerprint Segmentation 33
6.2 Cluster-Based Mapping Method 34
6.3 Source-Destination Mapping Method 35
6.4 Trail-Based Mapping Method 36
6.5 Step Estimation Expeimental Analysis 36
6.5.1 Testbed Setting 36
6.5.2 Experimental Results 37
7 Calorie Map Construction 40
7.1 Calorie Calculation 40
7.2 Calorie Map 40
8 Conclusions 42
Bibliography 43

[1] J. L. Durstine, B. Gordon, Z. Wang, and X. Luo, “Chronic disease and the link to physical
activity,” Journal of Sport and Health Science, vol. 2, no. 1, pp. 3–11, March 2013.
[2] P. R. Dexter, D. K. Miller, D. O. Clark, M. Weiner, L. E. Harris, L. Livin, I. Myers,
D. Shaw, L. A. Blue, MSN, J. Kunzer, and J. M. Overhage, “Preparing for an aging
population and improving chronic disease management,” in AMIA Annual Symposium
Proceedings, 13-17 November 2010, pp. 162–166.
[3] P. Bahl and V. N. Padmanabhan, “Radar: An in-building rf-based user location and tracking
system,” in Nineteenth Annual Joint Conference of the IEEE Computer and Communications
Societies. (INFOCOM 2000.), vol. 2, 26-30 March 2000, pp. 775–784.
[4] E. Foxlin, “Pedestrian tracking with shoe-mounted inertial sensors,” IEEE Computer
Graphics and Applications, vol. 25, no. 6, pp. 38–46, November/December 2005.
[5] C.-C. Lo, L.-Y. Hsu, and Y.-C. Tseng, “Adaptive radio maps for pattern-matching localization
via inter-beacon co-calibration,” Pervasive and Mobile Computing, vol. 8, no. 2,
pp. 282–291, April 2012.
[6] K. Chang and D. Han, “Crowdsourcing-based radio map update automation for wi-fi positioning
systems,” in GeoCrowd ’14: Proceedings of the 3rd ACM SIGSPATIAL International
Workshop on Crowdsourced and Volunteered Geographic Information, 4-7 November
2014, pp. 24–31.
[7] H. Shin, Y. Chon, Y. Kim, and H. Cha, “Mri: Model-based radio interpolation for indoor
war-walking,” IEEE Transactions on Mobile Computing, vol. 14, no. 6, pp. 1231–1244,
June 2015.
[8] D. Niculescu and B. Nath, “Ad hoc positioning system(aps) using aoa,” in Twenty-Second
Annual Joint Conference of the IEEE Computer and Communications Societies. (INFOCOM
2003.), vol. 3, 30 March-3 April 2003, pp. 1734–1743.
43
[9] X. Wang, Z. Wang, and B. O’Dea, “A toa-based location algorithm reducing the errors
due to non-line-ofsight(nlos) propagation,” IEEE Transactions on Vehicular Technology,
vol. 52, no. 1, pp. 112–116, January 2003.
[10] I. Martin-Escalona, M. Malpartida, and F. Barcelo-Arroyo, “Performance evaluation of
the passive tdoa algorithm in dark areas,” in Ubiquitous Positioning, Indoor Navigation,
and Location Based Service (UPINLBS), 2012, 3-4 October 2012, pp. 1–8.
[11] F. M. Ghannouchi, D. Wang, and S. Tiwari, “Accurate wireless indoor position estimation
by using hybrid tdoa/rss algorithm,” in 2012 IEEE International Conference on Vehicular
Electronics and Safety, 24-27 January 2012, pp. 437–441.
[12] S. Beauregard, Widyawan, and M. Klepal, “Indoor pdr performance enhancement using
minimal map information and particle filters,” in 2008 IEEE/ION Position, Location and
Navigation Symposium (PLANS)., 5-8 May 2008, pp. 141–147.
[13] A. Brajdic and R. Harle, “Walk detection and step counting on unconstrained smartphones,”
in UbiComp ’13: Proceedings of the 2013 ACM international joint conference on
Pervasive and ubiquitous computing, 8-12 September 2013, pp. 225–234.
[14] J. Seo, Y. Chiang, A. M. Khan, and T. H. Laine, “Step counting on smartphones using
advanced zero-crossing and linear regression,” in IMCOM ’15: Proceedings of the 9th
International Conference on Ubiquitous Information Management and Communication,
8-10 January 2015, pp. 1–7.
[15] J. Krumm, S. Harris, B. Meyers, B. Brumitt, M. Hale, and S. Shafer, “Multi-camera multiperson
tracking for easyliving,” in Proceedings of the Third IEEE International Workshop
on Visual Surveillance, 2000., 1 July 2000, pp. 3–10.
[16] K. Ozcan and S. Velipasalar, “Robust and reliable step counting by mobile phone cameras,”
in ICDSC ’15: Proceedings of the 9th International Conference on Distributed Smart
Cameras, 8-11 September 2015, pp. 164–169.
[17] “National health expenditure data,” Website, https://www.cms.gov/research-statisticsdata-and-systems/statistics-trends-and-reports/nationalhealthexpenddata/nhe-factsheet.html.
[18] “Chronic diseases: The leading causes of death and disability in the united states,” Website,
http://www.cdc.gov/chronicdisease/overview/.
44
[19] “Here Co., Ltd.” http://www.here-apps.com/.
[20] B. E. Ainsworth, , W. L. Haskell, S. D. Herrmanl, N. Meckes, D. R. B. JR., C. TudorLocke,
J. L. Greer, J. Vezina, M. C. Whitt-Clover, and A. S. Leon, “2011 compendium
of physical activities: A second update of codes and met values,” Medicine & Science in
Sports & Exercise, vol. 43, no. 8, pp. 1575–1581, August 2011.