請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51257完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 闕志達(Tzi-Dar Chiueh) | |
| dc.contributor.author | Bo-Chen Huang | en |
| dc.contributor.author | 黃柏琛 | zh_TW |
| dc.date.accessioned | 2021-06-15T13:28:44Z | - |
| dc.date.available | 2019-03-08 | |
| dc.date.copyright | 2016-03-08 | |
| dc.date.issued | 2016 | |
| dc.date.submitted | 2016-02-05 | |
| dc.identifier.citation | [1] 「中華民國人口推計」（2014至2061年）-國發會
Available: https://www.ndc.gov.tw/Content_List.aspx?n=84223C65B6F94D72 [2] More than 78 Million Consumers Will Utilize Home Health Technologies by 2020 [3] N. Pannurat, S. Thiemjarus, E. Nantajeewarawat, “Automatic Fall Monitoring: A Review”. Sensors (Basel, Switzerland). 2014 [4] X. Yu, 'Approaches and principles of fall detection for elderly and patient,' in e-health Networking, Applications and Services, 2008. [5] M. Kangas; A. Konttila; I. Winblad; T. Jamsa, 'Determination of simple thresholds for accelerometry-based parameters for fall detection,' in Engineering in Medicine and Biology Society, 2007. [6] Medical Guardian. Available: https://www.medicalguardian.com/ [7] Alert1. Available: https://www.alert-1.com/ [8] Philips Lifeline. Available: https://www.lifeline.philips.com/ [9] Medical Alert Systems with Fall Detection - Best review. Available: https://medical-alert-systems.bestreviews.net/fall-detection/ [10] Z. Farid, R. Nordin, and M. Ismail, “Recent Advances in Wireless Indoor Localization Techniques and System,” Journal of Computer Networks and Communications, vol. 2013. [11] H. Liu, H. Darabi, P. Banerjee, and J. Liu, “Survey of Wireless Indoor Positioning Techniques and Systems,” Proceedings of IEEE on Systems, Man, and Cybernetics, Part C: Applications and Reviews, Nov. 2007. [12] Motion Sensors | Android Developers [Online] [13] 3D Cartesian Coordinate Rotation (Euler) - National Instruments [14] Euler angles - Wikipedia, 2015, December 14. [15] Quaternion - Wikipedia, 2016, January 6. [16] Understanding Quaternions | CH Robotics Available: http://www.chrobotics.com/library/understanding-quaternions [17] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, H. Ian, “The WEKA Data Mining Software: An Update”; SIGKDD Explorations, Witten (2009); [18] C. F. Chien, “Analysis of decision tree”, Data mining& Big Data Analysis [19] I. Guyon, J. Weston, S. Barnhill, V. Vapnik, “Gene Selection for Cancer Classification using Support Vector Machines”, Kluwer Academic Publishers. Netherlands 2002 [20] Artificial neural network - Wikipedia Available: http://en.wikipedia.org/wiki/Artificial_neural_network [21] R. Salakhutdinov, G. Hinton, “An Efficient Learning Procedure for Deep Boltzmann Machines,” Neural Computation, Vol. 24, pp. 1967-2006, August 2012. [22] Geoffrey Hinton, “A Practical Guide to Training Restricted Boltzmann Machines,” Lecture Notes in Computer Science, Vol. 7700, pp. 599-619, August 2010. [23] B.N. Gustav, “Cross-platform Development for Wearable Devices”, Final thesis, Linköpings university. [24] Apple Watch vs Android Wear. Time to Drive Tesla Further [25] Data Layer DataMap Objects — Android Wear Docs [Online] [26] K. Liu, “A Review of Existing Web Frameworks”, Master Thesis, National Central University, Jun. 2014. [27] Sensitivity and Specificity – Wikipedia [28] T. Degen, H. Jaeckel, M. Rufer, S. Wyss, “SPEEDY: a fall detector in a wrist watch”, Proceedings of IEEE Wearable Computers, 2003. [29] C.-B. Chen, C.-T. Chen, “The Development of Wrist-Watch Fall Detection System”, Master Thesis, National Yang Ming University, Nov. 2011. [30] S.-L. Hsieh, C.-C. Chen, S.-H. Wu, T.-W. Yue, “A wrist-worn fall detection system using accelerometers and gyroscopes”, Proceedings of IEEE Networking, Sensing and Control (ICNSC), 7-9 April 2014. [31] C.-C. Zhou, C.-L. Tu, Y. Gao, F.-X. Wang, H.-W. Gong, P. L., C. He, X.-S. Ye, 'A low-power, wireless, wrist-worn device for long time heart rate monitoring and fall detection,' Proceedings of IEEE Orange Technologies (ICOT), vol., pp.33-36, Sept. 2014 [32] M. Ghazal, Y. A. Khalil, F. J. Dehbozorgi, M.T. Alhalabi, 'An integrated caregiver-focused mHealth framework for elderly care,', Proceedings of IEEE Wireless and Mobile Computing, Networking and Communications (WiMob), vol., pp.238-245, Oct. 2015 [33] M.-Y. Tsai, “Design and Implementation of an Indoor Positioning System on SDR Platform” Master Thesis, National Taiwan University, Oct. 2014. [34] K. Borre, D. Akos, N. Bertelsen, P. Rinder and S. Jensen, “A Software-Defined GPS and Galileo Receiver - A Single Frequency Approach”, Birkhauser, 2007. [35] J.-Y. Yang, Design of a Software-Based Receiver for Global Positioning System, Master Thesis, National Taiwan University, Jul. 2009. [36] X. Chen, F. Dovis, S. Peng, Y. Morton, “Comparative Studies of GPS Multipath Mitigation Methods Performance,” IEEE Trans. on Aerospace and Electronic Systems, vol. 49, pp. 1555-1568, Jul. 2013. [37] J. Tsui, “Fundamentals of Global Positioning System Receivers - A Software Approach” 2nd, John Wiley & Sons, Inc., Nov. 2004. [38] G. Shen, R. Zetik, and R. Thoma, “Performance Comparison of TOA and TDOA Based Location Estimation Algorithms in LOS environment,” Positioning, Navigation, and Communication, Mar. 2008, pp. 71-78. [39] X. Tu, H. Zhang, X. Cui, and T. A. Gulliver, “3-D TDOA/AOA Location Based on Extended Kalman Filter”, International Symposium on Antennas Propagation and EM Theory, Nov. 2010, pp. 473-476. [40] C.-Y. Chu. “Design and Implementation of a Baseband Receiver for 3GPP Long Term Evolution System”, M.S. thesis, National Taiwan University, Taipei, Taiwan, July 2013. [41] J. A. Starzyk, Z. Zhu, “Averaging correlation for C/A code acquisition and tracking in frequency domain”, Proceedings of IEEE Midwest Symp. on Circuits and Systems, Vol. 2. MWSCAS 2001. [42] National Instruments, “NI USRP RIO Datasheet”, [Online] Available: http://www.ni.com/datasheet/pdf/en/ds-538 [43] Y.-F. Cheng, “Design and Implementation of Baseband Transceiver with Adaptive MIMO-OFDM Technology”, National Taiwan University, Nov. 2014. [44] National Instruments, “How DMA Transfers Work (FPGA Module)” [Online] | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51257 | - |
| dc.description.abstract | 由於老年人口比例穩定成長，使台灣邁向成為人口老化社會。然而這波社會結構改變，使銀髮族群問題逐漸受到重視。因此銀髮族群的居家照護時常被拿來討論。在居家照護議題中，跌倒是年長人在家最常遇到的危險意外，其會造成傷者龐大的身心靈創傷。也阻礙銀髮族獨自居住。
在本論文中，我們提出一完整的居家照護系統(Home Care System)。使用者穿戴一般智慧型手錶，即時偵測手腕資料。資料會傳輸至伺服器端，進行即時運算判斷。當伺服器偵測到跌倒意外時，會即時發出警訊，通知照護人員協助處理。此時照護系統中室內定位功能會通知照護人員跌倒傷者在的屋內精確位置，使其把握黃金搶救時間。 為驗證系統可行性，我們會將跌倒偵測以及室內定位功能個別實作成即時系統。跌倒偵測部分，以安卓穿戴系統之智慧型手錶蒐集動態資料，透過手機Wi-Fi傳輸到以Django架設之網頁伺服器，電腦再將這些收集到的資料交由MATALB運算，判斷是否跌倒。而室內定位部分，使用現有的室內定位驗算法，但其有計算量過大的問題。故我們除了軟體定義無線電之外，額外再使用FPGA進行硬體加速，使定位結果能即時呈現於螢幕上。 | zh_TW |
| dc.description.abstract | The elderly population in many developed countries are steadily growing, Taiwan has also entered the aging society. The change of population structure has made us gradually conscious of the aging problems. Therefore, there is no doubt that we need to pay more attention to the home-care for the elderly. As far as home-care issue is concerned, falling is one of the major accidents at home for the elder people. It not only causes lots of physiological and psychological injuries, but it is also the main obstacle for elder people to live alone.
In this thesis, we provide an ICT solution to home-care of elderly people. The user will wear a smart watch which can detect the wrist motion instantaneously. The sensor data are delivered to the server, which is able to detect the motion in real-time. If a falling accident is detected, the system will send a short message to the caregiver. Then indoor positioning function provides the location of the user to the caregiver so that they can assist the elder user immediately. In order to validate our system, we implemented two functions separately in different platforms. In the part of fall detection, we took advantage of Android wear smart watch to collect motion data, which will be sent to the Django web server. Then, the laptop could compute and determine the detection result by means of MATLAB simulation. In the part of indoor positioning, we built a real-time system. Besides using the National Instrument software-defined radio platform to receive the RF signal, we also implemented hardware acceleration with FPGA. In this way, we can track motion of the elderly people on the monitor screen in real time. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T13:28:44Z (GMT). No. of bitstreams: 1 ntu-105-R02943052-1.pdf: 7084402 bytes, checksum: e4e19f449bf150ea10954fe2bb534a45 (MD5) Previous issue date: 2016 | en |
| dc.description.tableofcontents | 誌謝 i
摘要 iii Abstract i 目錄 iii 圖目錄 ix 表目錄 xiii 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機 2 1.3 論文簡介 3 1.4 論文組織 4 第二章 居家照護系統介紹 5 2.1 跌倒偵測系統分類 6 2.1.1 穿戴式偵測(Wearable Device Detection) 6 2.1.1.1門檻型穿戴式偵測(Thresholding) 6 2.1.1.2 機器學習型穿戴式偵測(Machine Learning) 7 2.1.2 影像式偵測(Camera-based Detection) 8 2.1.2.1身形變化(Shape Change) 8 2.1.2.2靜態偵測(Inactivity Detection) 8 2.1.2.3頭像偵測(Head motion) 9 2.1.3 環境式偵測(Ambience Device Detection) 9 2.1.3.1壓力感測(Pressure Detection) 9 2.1.3.2 地板震動 10 2.1.3.3 紅外線偵測(Infrared Sensing) 10 2.2 系統效能指標[3] 11 2.2.1 系統設計重點 11 2.2.1.1 非侵略性(Non-invasive) 11 2.2.1.2 非封閉性(Non-occlusive) 11 2.2.1.3 多人使用(Multi-user Access) 11 2.2.1.4 年齡(Aging) 12 2.2.1.5 隱私(Privacy) 12 2.2.1.6 計算成本(Computational Cost) 12 2.2.1.7 功率消耗(Energy Consumption) 12 2.2.1.8 資料傳輸 12 2.2.1.9 感測器數目 13 2.2.1.10 取樣率與精準度 13 2.2.2 現有跌倒偵測系統介紹 13 2.2.2.1 Medical Guardian Fall Alert [6] 13 2.2.2.2 Alert1 [7] 14 2.2.2.3 飛利浦生命線(Philips Lifeline)[8] 14 2.2.2.4 跌倒偵測系統比較表 15 2.3 定位技術介紹 15 2.3.1 鄰近偵測(Proximity Detection) 16 2.3.2 場景分析(Scene Analysis) 17 2.3.3 三角測量(Triangulation) 17 2.3.3.1 Angle Based Method 18 2.3.3.2 Time Based Methods 18 2.3.3.2.1 抵達時間(Time of Arrival) 18 2.3.3.2.2 抵達時間差(Time Difference of Arrival) 19 2.3.3.2.3 往返飛行時間(Round-trip Time of Flight) 20 2.3.3.3 Signal Property Based Methods 21 2.3.4 航位推測法(Dead Reckoning) 21 2.3.5 定位技術比較 22 2.4 無線室內定位系統 22 2.4.1 效能指標(Performance Metrics) 23 2.4.1.1 準確度(Accuracy) 23 2.4.1.2 精確度(Precision) 24 2.4.1.3 覆蓋率(Coverage) 24 2.4.1.4 複雜度(Complexity) 24 2.4.1.5 穩健性(Robustness) 25 2.4.1.6 可擴展性(Scalability) 25 2.4.1.7 成本(Cost) 25 2.4.2 基於紅外線之系統(Infrared Based System) 25 2.4.3 基於射頻之系統(Radio Frequency Based System) 26 2.4.3.1 Wi-Fi 26 2.4.3.2 RFID 26 2.4.3.3 Bluetooth 26 2.4.3.4 ZigBee 27 2.4.3.5 UWB 27 2.4.3.6 FM 27 2.4.3.7 Hybrid 27 2.4.4 基於超音波之系統(Ultrasound Based System) 28 2.4.5 室內定位系統比較 28 2.5 設計之室內定位系統藍圖 29 第三章 手錶型跌倒偵測系統設計 31 3.1 感測器資料與前處理 31 3.1.1 資料蒐集 31 3.1.2 訊號前處理 32 3.1.2.1 降噪 32 3.1.2.2 角度轉換 33 3.1.2.2.1 尤拉角(Euler angles) 33 3.1.2.2.2 四元數(Quaternions)[15] 34 3.1.2.2.3 四元數至尤拉角轉換[16] 36 3.1.2.3 標示跌倒徵兆時間點 36 3.1.2.4 分割並擷取波形 37 3.2 特徵擷取 37 3.2.1 懷卡托智能分析環境(Weka)[17] 38 3.2.2 特徵篩選演算法 38 3.2.2.1 資訊增益評估(Information Gain Evaluation)[18] 38 3.2.2.2 支持向量機之屬性評估[19] 39 3.2.3 選用之感測器特徵值 40 3.3 類神經網路 41 3.3.1 倒傳遞類神經網路 41 3.3.2 深層學習類神經網路 45 3.3.2.1 架構及演算法 45 3.3.2.2 延伸型限制性波茲曼機演算法 46 第四章 跌倒偵測系統架構與結果分析 49 4.1 跌倒偵測系統平台 49 4.1.1 安卓穿戴(Android wear) 50 4.1.2 安卓穿戴系統架構 51 4.1.2.1 Node API 51 4.1.2.2 Data API 51 4.1.2.3 Messages API 52 4.1.3 感測資料伺服器架設 52 4.1.4 Django 54 4.1.4.1 Django架構優點 55 4.1.4.2 Django架構缺點 55 4.2 跌倒偵測實驗結果 55 4.2.1 實驗設置與測試動作 55 4.2.2 實驗結果之數值指標 56 4.2.3受試者工作特徵曲線 57 4.2.4 實驗結果 58 4.2.5 文獻成果比較 60 第五章 室內定位系統基頻軟體發射&接收機 61 5.1 展頻通訊系統簡介 61 5.1.1 展頻通訊技術介紹 62 5.1.2 展頻通訊系統特性 63 5.1.2.1 抗干擾能力(Interference Suppression) 63 5.1.2.2 多重存取(Multiple Access) 63 5.2 室內定位系統基頻發射機技術與架構 64 5.2.1 訊號調變方式與設計規格 64 5.2.2 偽隨機碼產生器及其訊號特性 65 5.2.2.1 偽隨機碼產生器 65 5.2.2.2 偽隨機碼之自相關與互相關特性 67 5.2.3 室內定位訊號結構 68 5.3 室內定位系統基頻接收機之技術與架構 68 5.3.1 室內定位訊號擷取 69 5.3.1.1 整數載波頻率偏移估測 69 5.3.1.2 分數載波頻率偏移估測 70 5.3.1.3 偽隨機碼相位估測 70 5.3.2 室內定位訊號追蹤 71 5.3.2.1 載波頻率追蹤[34] 71 5.3.2.2 偽隨機碼追蹤 72 5.3.2.2.1 延遲鎖定迴路(Delay-Lock Loop) 72 5.3.2.2.2 多路徑效應(Multipath Effect) 72 5.3.2.2.3 高分辨率相關器[36] 73 5.3.2.2.4 有限頻寬(Bandwidth Limited) 74 5.4 室內定位訊號處理 75 5.4.1 抵達時間差估測 75 5.4.2 同相積分(Coherent Integration) 76 5.4.3 定位目標位置估測 76 5.4.4 擴展卡爾曼濾波器 78 第六章 室內定位接收機硬體設計 81 6.1 接收機硬體加速架構概述 81 6.2 載波頻率偏移與追蹤 82 6.2.1 整數載波頻率偏移估測(Integer CFO Estimation) 82 6.2.2 分數載波頻率飄移估測(Fractional CFO Estimation) 84 6.2.3 載波頻率飄移追蹤迴路(CFO Tracking) 86 6.3 平均式平行碼相位搜尋法 87 6.3.1 平均相關性平行碼相位搜尋法[41] 87 6.3.2 改良版平均相關性平行碼相位搜尋法 88 6.4 硬體加速之執行時間分析 90 第七章 室內定位實作平台介紹與實驗結果 91 7.1 室內定位系統之實作平台架構 91 7.1.1 軟體定義室內定位系統發射機 92 7.1.2 軟體定義室內定位系統接收機與同步設計 93 7.2 FPGA模擬驗證流程 94 7.2.1 LabVIEW電路驗證 95 7.2.2 電路合成與驗證 96 7.3 室內定位系統現場測試與驗證結果 97 7.3.1 電機二館504討論室(約5.7m x 8m) 98 7.3.2 電機二館142會議室(約9.1m x 15.6m) 101 7.3.3 Kalman filter不同參數下的追蹤情形 104 第八章 結論與未來展望 111 8.1 成果結論 111 8.1.1 跌倒偵測部分 111 8.1.2 室內定位部分 112 8.2 未來展望 112 8.2.1 系統整合 112 8.2.2 跌倒偵測部分 113 8.2.2.1 跌倒偵測系統之運行速度分析 113 8.2.3 室內定位部分 114 參考文獻 115 | |
| dc.language.iso | zh-TW | |
| dc.title | 結合穿戴式裝置之室內定位與跌倒偵測系統開發 | zh_TW |
| dc.title | Development of an Indoor Positioning & Fall Detection System Based on Wearable Devices | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 104-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 馬席彬(Hsi-Pin Ma),蔡佩芸(Pei-Yun Tsai) | |
| dc.subject.keyword | 居家照護,跌倒偵測,智慧手錶,安卓穿戴,室內定位,軟體定義無線電,基頻接收機設計,實時系統, | zh_TW |
| dc.subject.keyword | Home-care,Fall detection,Smart watch,Android wear,Indoor Positioning,Soft Defined Radio,Real-time System, | en |
| dc.relation.page | 118 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2016-02-06 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
| 顯示於系所單位： | 電子工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-105-1.pdf 目前未授權公開取用 | 6.92 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。