臺灣博碩士論文加值系統

本論文選擇以Android智慧型手機為基礎，設計出一套物聯網居家照護系統。在伺服器端架設資料庫與應用程式介面(Application Program Interface, API)，資料庫蒐集感測器的資料並儲存，API則作為手機與資料庫之間的橋樑，可以避免私人資料洩漏的風險；而在手機端開發一款APP，其中有兩大功能，其一為即時監控功能，能夠觀看家中所有的感測器數值，當感測器數值異常時，立刻通知使用者，並且能夠利用APP控制感測器，隨時查看IP Camera的即時影像，確保居家安全；其二為跌倒偵測功能，利用內建的三軸加速度計、陀螺儀與方位感應器實現此系統。由於老年人與孩童常因跌倒時，無法及時獲得適當幫助而造成更嚴重的傷害，此系統能夠偵測跌倒事件，當跌倒時將此訊息傳出並透過GPS與Google Maps API提供位置訊息。走失時，也能透過定位功能協助搜尋。
實驗結果顯示，跌倒偵測的靈敏度為92.5%，特異度為97.6%，證明本系統能有效應用在居家照護上。

This paper proposed a smart home care system based on Android platform, which is built on the smart phone. The database and API(Application Program Interface) are set up on the server side. The database collects the information of the sensor and stores them; and that the API acts as a bridge between the mobile phone and the database. The API can avoid the risk on the leakage of private data. For the designed App on mobile phone, two functions need to be established. One is the instant monitor based on the sensor’s data in home. As the sensor data is abnormal, the controller in notified immediately. Also, the remote control can view the real-time image in IP camera at any time to guarantee the home safety. The other function is the fall detection, which is designed to detect the fall event using the built-in three-axis accelerometer, gyroscope, and orientation sensor. Owing to serious injure in elder people and children, the proposed App system can detect a fall event, send the help message out, and provide a location message by GPS and Google Maps API when he falls or loses.
Simulated results show that the sensitivity of fall detection is 92.5% and the specificity is 97.6%, which proves that the system can be effectively applied to home care.

摘 要 i
Abstract ii
致 謝 iv
目 錄 v
圖目錄 ix
第一章 緒論 1
1.1 研究動機與目的 1
1.2 研究方法 2
1.3 論文架構 2
第二章 通訊系統介紹 3
2.1 Android作業系統 3
2.1.1 系統架構 3
2.1.2 生命週期 6
2.2 網路協定簡介 10
2.2.1 實體層(Physical Layer) 12
2.2.2 資料鏈結層(Data Link Layer) 12
2.2.3 網路層(Network Layer) 13
2.2.4 傳輸層(Transport Layer) 16
2.2.5 會議層(Session Layer) 17
2.2.6 表達層(Presentation Layer) 17
2.2.7 應用層(Application Layer) 17
2.3 MQTT通訊協定 18
2.3.1 MQTT發展歷史 18
2.3.2 MQTT傳輸機制 19
2.4 跌倒偵測系統介紹 24
2.4.1 穿戴式偵測(Wearable Device Detection) 24
2.4.2 影像式偵測(Camera-based Detection) 26
2.4.3 環境式偵測(Ambience Device Detection) 27
第三章 App系統架構與設計 29
3.1 系統架構 29
3.2 App功能 31
3.2.1 居家監控 31
3.2.2 即時通訊 33
3.2.3 GPS定位 34
3.2.4 緊急求救 36
3.2.5 跌倒偵測 36
3.3 跌倒偵測功能實現 36
3.3.1 三軸加速度計(3-Axis Accelerometer) 37
3.3.2 陀螺儀(Gyroscope) 39
3.3.3 方位感應器(Orientation Sensor) 42
3.3.4 跌倒偵測流程 44
第四章 實驗結果 46
4.1 開發環境 46
4.2 實作展示 48
4.2.1 註冊與登入 48
4.2.2 功能操作 49
4.3 跌倒偵測實驗結果 58
第五章 結論與未來展望 61
5.1 結論 61
5.2 未來展望 61
參考文獻 62

[1]衛生福利部，106年國人死因統計結果，https://www.mohw.gov.tw/cp-3795-41794-1.html。
[2]Wikipedia, “Android”, https://zh.wikipedia.org/wiki/Android。
[3]Wikipedia, “Open Handset Alliance”, https://en.wikipedia.org/wiki/Open_Handset_Alliance。
[4]Android Developers, “Platform Architecture”, https://developer.android.com/guide/platform。
[5]黃彬華，Android 7.x APP開發教戰手冊，臺北：碁峰，2017。
[6]Android Developers, “Activities”, https://developer.android.com/guide/components/activities.html?hl=zh-TW#Creating。
[7]邵喻美、潘育群譯，電腦網路第五版，臺北：東華，2012。
[8]OSI Layering, https://www.slideshare.net/PankajYadav49/osi-layering。
[9]施威銘研究室，最新網路概論 第15版，臺北：旗標，2017。
[10]MQTT V3.1 Protocol Specification, http://public.dhe.ibm.com/software/dw/webservices/ws-mqtt/mqtt-v3r1.html#publish。
[11]MQTT示意圖, https://thenewstack.io/mqtt-protocol-iot/。
[12]Cubie，認識MQTT， https://swf.com.tw。
[13]Lucy Zhang, “Building Facebook Messenger”, https://www.facebook.com/notes/facebook-engineering/building-facebook-messenger/10150259350998920。
[14]Y. Xinguo, “Approaches and principles of fall detection for elderly and patient,” HealthCom2008 - 10th International Conference on e-health Networking, Applications and Services, Singapore, 2008, pp.42-47.
[15]O. Almeida, M. Zhang, and L. C. Liu. “Dynamic fall detection and pace measurement in walking sticks,” 2007 Joint Workshop on High Confidence Medical Devices, Software, and Systems and Medical Device Plug-and-Play Interoperability, Boston, 2007, pp.204-206.
[16]J. Jacob, T. Nguyen, D. Y. C. Lie, S. Zupancic, J. Bishara, A. Dentino, and R. E. Banister, “A fall detection study on the sensors placement location and a rule-based multi-thresholds algorithm using both accelerometer and gyroscopes,” Proceedings of the 2011 IEEE International Conference on Fuzzy Systems, Taipei, 2011, pp.666-671.
[17]A. M. Sabatini, G. Ligorio, A. Mannini, V. Genovese, and L. Pinna, “Prior-to- and post-impact fall detection using inertial and barometric altimeter measurements,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2016, pp.774-783.
[18]H. Nart-Charif and S. j. McKenna, “Activity summarization and fall detection in a supportive home environment,” Proceedings of the 17th International Conference on Pattern Recognition, Cambridge, UK, 2004.
[19]D. Anderson, J. M. Keller, M. Skubic, X. Chen, and Z. He, “Recognizing falls from silhouettes,” 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, New York, 2006, pp.6388-6391.
[20]C. Rougier, J. Meunier, A. St-Arnaud, and J. Rousseau, “Monocular 3D Head Tracking to Detect Falls of Elderly People,” 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, New York, 2006, pp.6384-6387.
[21]M. Daher, A. Diab, M. E. B. E. Najjar, M. A. Khalil, and F. Charpillet, “Elder Tracking and Fall Detection System Using Smart Tiles,” IEEE Sensors Journal, 2016, pp. 469-479.
[22]陳智聖，基於Android行動平台之口袋行跌倒偵測系統設計與實現，碩士論文，國立臺北科技大學電腦與通訊研究所，臺北，2013。
[23]Lina Tong, Quanjun Song, Yunjian Ge, and Ming Liu, “HMM-Based Human Fall Detection and Prediction Method Using Tri-Axial Accelerometer,” IEEE Sensors Journal, 2013, pp. 1849-1856.
[24]W.C. Cheng and D.M. Jhan, “Triaxial accelerometer-based fall detection method using a self-constructing cascade-AdaBoost-SVM classifier,” IEEE Journal of Biomedical and Health Informatics, 2013, pp.411-419.
[25]Capturing Azimuth, Pitch, and Roll Example, https://www.mathworks.com/matlabcentral/mlc-downloads/downloads/submissions/40876/versions/8/previews/sensorgroup/Examples/html/CapturingAzimuthRollPitchExample.html。