本論文提出兩個具有新穎應用的照護及提昇幸福感體驗之嵌入式裝置系統。
在針對嵌入式照護系統中,本篇論文提出了一個基於將 GPS 定位模組嵌入於念珠之完善系統架構,其應用於追蹤患有早期失智症之年長者足跡,而此慢性疾病會造成年長者之記憶、思維、行為與能力逐漸惡化,使患者在日常生活中經常性健忘以及在過往熟悉的環境仍會迷失方向。該雛型主要由兩個模組區塊所構成,包括: 電源供應區塊和計算與通信區塊,電源供應區塊為具有供應能量之穩壓器元件組成,
其提供給計算與通信區塊:微控制器,GSM / GPRS 模組和 GPS 模組。
系統末端伺服器收集由念珠定位裝置發送出之即時定位資訊,因此照護者可透過個人行動裝置或是個人電腦從伺服器獲取被追蹤者的定位資訊。實驗結果顯示,透過結構化的管理方式可便於記錄和檢測年長者的足跡,然而,一些障礙如樹木,建築,高架橋等會造成系統過程中有機會失去連接而影響定位精度,這將是本篇論文在今後要克服的工作。
在提昇幸福感體驗與提供溫馨關懷之嵌入式裝置系統中,相對於一般設計的嵌入式裝置透過聲音與影像等管道進行遠距離溝通,本篇論文試圖透過人們日常生活中使用之杯具,來傳遞人們的行為與情緒。例如,一方在喝水時,身在遠端的另一方亦可感受到對方在喝水,藉此提昇日常生活之幸福感。本篇提出的嵌入式裝置系統在運作上分兩步驟,第一步驟,由後端伺服器事先將雙方 Android 手機根據 ID 進行配對。第二步驟,幸福杯將甲方之握杯動作資訊傳送至甲方 Android 手機端應用程式進行辨識,並將辨識結果傳送至後端伺服器,最後傳遞握杯資訊辨識結果於乙方 Android 手機端並以燈光色彩變化顯示於乙方幸福杯。相較於其他相關研究,本篇僅使用了一個三軸加速度感測器來獲取握杯資訊,並用於 Android 手機端中的兩種握杯動作辨識 (Holding-Cup Motion Recognition) 方法:基於動態時間校正 (DynamicTime Warping, DTW) 和支持向量機 (Support Vector Machine, SVM)。透過該方法能夠辨識出喝水、乾杯、水平搖杯子、垂直搖杯子、晃動等 5 種握杯動作。其辨識率在基於 DTW 的方法中能達到 71%,而在基於 SVM 的方法中則能達到 92.4%。

In this study, two embedded devices and systems are proposed to improve happiness
and care in our daily life.
In the first system, a prototyping of a prayer beads embedded with a GPS device is proposed, which is applied for tracking the trajectory of elderly to possibly detect the early stage of Dementia, of which the chronic diseases for elderly will lead to the deterioration in memory, thinking, behavior and ability, thus caused to the forgetfulness, losing track or losing familiar places gradually in their daily life.
The prototyping mainly consists of two blocks, including, the power supply block and the computation & communication block, in which three modules, i.e. microcontroller, GSM/GPRS module and GPS module are functional and enabled by the power supply block. To timely transmit the GPS trajectory from the prototyping wore on elderly to the caregiver on their smart device or laptop anytime and anywhere, a server is implemented to coordinate the GPS information processed among the proposed GPS-based prayer beads, the server, and the caregiver’s mobile device.
Eventually, the simulation result is shown that the trajectory of elderly can be detected and recorded through the proposed framework at a convenience manner, however, some obstacles e.g. trees, building, viaduct etc. during the tracking will tentatively lose connection and influence the positioning accuracy, that will be overcome in the future work.
In the second system, a Happiness Cups system is designed and implemented.
This work is trying to let people in different places are able to get in touch each other remotely by drinking, toasting with a cup, which adds more emotional channels to the traditional communication, such as audio, video or text and improves the quality of interconnections by drinking with care or love one in different places.
The reason that cups is chosen as a medium because cups are common and daily objects that people are familiar.
The system is composed of hardware and firmware design of the Happiness Cup, a server for pairing distant two Happiness Cups, and an Android application that not only acts as a medium between cup and server but executes holding-cup motion recognition method.
In this work, two holding-cup motion recognition methods which based on dynamic time warping (DTW) and support vector machine (SVM) are proposed.
The holding-cup motion such as drinking, shaking, swaying, and toasting with only an accelerometer are able to be recognized.
Finally, experimental results demonstrate that recognition accuracy reaches 71% and 92.4% based on DTW and SVM, respectively.

[1] J. F. Wang, B. W. Chen, Y. Y. Chen, and Y. C. Chen. Orange computing: Challenges and opportunities for affective signal processing. In Signal Processing, Communications and Computing (ICSPCC), 2011 IEEE International Conference on, pages 1–4, Sept 2011.
[2] WHO. Dementia, fact sheet N°362. factsheets/fs362/en/, 2015. http://www.who.int/mediacentre/
[3] Hyemin Chung, Chia-Hsun Jackie Lee, and Ted Selker. Lover’s cups: drinking interfaces as new communication channels. In CHI’06 extended abstracts on Human factors in computing systems, pages 375–380. ACM, 2006.
[4] B. Xiao, M. Z. Asghar, T. Jämsä, and P. Pulii. Canderoid: A mobile system to remotely monitor travelling status of the elderly with dementia. In Awareness Science and Technology and Ubi-Media Computing (iCAST-UMEDIA), 2013 International Joint Con-
ference on, pages 648–654, Nov 2013.
[5] Q. Lin, D. Zhang, H. Ni, X. Zhou, and Z. Yu. An integrated service platform for pervasive elderly care. In Services Computing Conference (APSCC), 2012 IEEE Asia-Pacific, pages 165–172, Dec 2012.
[6] J. Geddes and K. Warwick. Cloud based global positioning system as a safety monitor for dementia patients. In Cybernetic Intelligent Systems (CIS), 2010 IEEE 9th International Conference on, pages 1–6, Sept 2010.
[7] R. K. Moloo and V. K. Digumber. Low-cost mobile gps tracking solution. In 2011 International Conference on Business Computing and Global Informatization, pages 516–519, July 2011.
[8] N. Chadil, A. Russameesawang, and P. Keeratiwintakorn. Real-time tracking management system using gps, gprs and google earth. In Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, 2008. ECTI-CON 2008.
5th International Conference on, volume 1, pages 393–396, May 2008.
[9] C. C. Lin, M. J. Chiu, C. C. Hsiao, R. G. Lee, and Y. S. Tsai. Wireless health care service system for elderly with dementia. IEEE Transactions on Information Technology in Biomedicine, 10(4):696–704, Oct 2006.
[10] A. Schwarzmeier, J. Besser, R. Weigel, G. Fischer, and D. Kissinger. A compact back-plaster sensor node for dementia and alzheimer patient care. In Sensors Applications Symposium (SAS), 2014 IEEE, pages 75–78, Feb 2014.
[11] Y. L. Hsu, C. L. Chu, Y. J. Tsai, and J. S. Wang. An inertial pen with dynamic time warping recognizer for handwriting and gesture recognition. IEEE Sensors Journal, 15(1):154–163, Jan 2015.
[12] Christoph Amma, Marcus Georgi, and Tanja Schultz. Airwriting: a wearable handwriting recognition system. Personal and Ubiquitous Computing, 18(1):191–203, 2013.
[13] R. Xie, X. Sun, X. Xia, and J. Cao. Similarity matching-based extensible hand gesture recognition. IEEE Sensors Journal, 15(6):3475–3483, June 2015.
[14] A. Akl, C. Feng, and S. Valaee. A novel accelerometer-based gesture recognition system. IEEE Transactions on Signal Processing, 59(12):6197–6205, Dec 2011.
[15] Chih-Chung Chang and Chih-Jen Lin. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1–27:27, 2011. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[16] Stan Salvador and Philip Chan. Toward accurate dynamic time warping in linear time and space. Intelligent Data Analysis, 11(5):561–580, 2007.
[17] P. Gupta and T. Dallas. Feature selection and activity recognition system using a single triaxial accelerometer. IEEE Transactions on Biomedical Engineering, 61(6):1780–1786, June 2014.
[18] PJayChen. PIC32 Firmware of Happiness Cups. https://github.com/PJayChen/Connecting-Cups-PIC32-firmware.
[19] PJayChen. Android Application of Happiness Cups. https://github.com/PJayChen/Connecting-Cups-Android-App.
[20] PJayChen.Server of Happiness Cups. https://github.com/PJayChen/Connecting-Cups-MalteseAnnCup.
[21] FreeRTOS. http://www.freertos.org/.