中高齡長者常患有慢性病，而藥物是慢性病常見的長期治療處方。因此，定期定時完成服藥，成為照護中高齡中不可或缺的事項。在此研究中，期望以簡單的嵌入式系統，以低成本設備來輔助照護人員，減少因為忘記服藥或是重複服藥造成的影響。
本研究針對服藥的一系列行為動作，選擇嵌入式系統，搭配攝影模組，透過演算法處理取得邊緣化圖像，並將其導入深度學習模型，利用訓練完成的模型，即時判斷用戶是否完成服藥。判定結果會同步以即時通訊軟體傳送給指定對象。
研究最終共收集到 3248 張圖片，隨機選擇 2270 張圖片進行訓練，另外選擇 489張圖片進行驗證。研究中的系統最終獲得的 97.3%的準確度。

Elderly people often suffer from chronic diseases, and long-term medication is a common treatment for chronic diseases. Therefore, taking medicines regularly has become an indispensable routine in the care of elderly people. In this study, a simple embedded system is expected to assist caregivers to reduce the impact of forgetting or duplicate medication.
This study implemented a system to accomplish the goal. It contains a small single-board computer, with a camera module that captured a series of behaviors of taking medicine. Edged images are derived through edge-detection algorithm processing, and imported to the deep learning model. The trained model in this system can instantly detect whether the user has finished taking the medicine. Lastly, the system will send an instant message to the caregivers.
At the final step of the experiment, 3248 images were collected. 2270 images were randomly selected for training, and 489 images were selected for verification. The result showed that the recognition accuracy reaches 97.3% .

[1] 衛生福利部國民健康署, "注意長輩8大功能，疫情期間也能保固健康". Available: https://www.hpa.gov.tw/Pages/Detail.aspx?nodeid=4306&pid=14610, last retrieve 10 June 2022
[2] A. Sav et al., "Burden of Treatment for Chronic Illness: A Concept Analysis and Review of the Literature", Health Expect, vol. 18, no. 3, pp. 312-24, Jun 2015, doi: 10.1111/hex.12046.
[3] P. E. Morrissey et al., "Medication Noncompliance and Its Implications in Transplant Recipients", Drugs, vol. 67, no. 10, pp. 1463-81, 2007, doi: 10.2165/00003495-200767100-00007.
[4] E. M. Vasquez et al., "Medication Noncompliance after Kidney Transplantation", American Journal of Health-System Pharmacy, vol. 60, no. 3, pp. 266-269, 2003, doi: 10.1093/ajhp/60.3.266.
[5] G. A. Roth et al., "High Total Serum Cholesterol, Medication Coverage and Therapeutic Control: An Analysis of National Health Examination Survey Data from Eight Countries", Bull World Health Organ, vol. 89, no. 2, pp. 92-101, 2011, doi: 10.2471/BLT.10.079947.
[6] B. Ayshwarya and R. Velmurugan, "Intelligent and Safe Medication Box in Health Iot Platform for Medication Monitoring System with Timely Remainders", in 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, 19-20 March 2021 2021, vol. 1, pp. 1828-1831, doi: 10.1109/ICACCS51430.2021.9442017
[7] D. S. Abdul Minaam and M. Abd-Elfattah, "Smart Drugs:Improving Healthcare Using Smart Pill Box for Medicine Reminder and Monitoring System", Future Computing and Informatics Journal, vol. 3, no. 2, pp. 443-456, 2018/12/01/ 2018, doi: https://doi.org/10.1016/j.fcij.2018.11.008.
[8] A. Salgia et al., "Smart Pill Box", Indian Journal of Science and Technology, vol. 8, 02/02 2015, doi: 10.17485/ijst/2015/v8iS2/58744.
[9] H. L. Tsai et al., "Bidirectional Smart Pill Box Monitored through Internet and Receiving Reminding Message from Remote Relatives", in 2017 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-TW), Taipei, Taiwan, 12-14 June 2017 2017, pp. 393-394, doi: 10.1109/ICCE-China.2017.7991161
[10] W. Chang et al., "A Deep Learning-Based Intelligent Medicine Recognition System for Chronic Patients", IEEE Access, vol. 7, pp. 44441-44458, 2019, doi: 10.1109/ACCESS.2019.2908843.
[11] S. Jaipriya et al., "An Intelligent Medical Box Remotely Controlled by Doctor", in 2019 International Conference on Intelligent Sustainable Systems (ICISS), Palladam, India, 21-22 Feb. 2019 2019, pp. 565-569, doi: 10.1109/ISS1.2019.8907996, Available: https://ieeexplore.ieee.org/stampPDF/getPDF.jsp?tp=&arnumber=8907996&ref=
[12] M. Srinivas et al., "Intelligent Medicine Box for Medication Management Using Iot", in 2018 2nd International Conference on Inventive Systems and Control (ICISC), Coimbatore, India, 19-20 Jan. 2018 2018, pp. 32-34, doi: 10.1109/ICISC.2018.8399097, Available: https://ieeexplore.ieee.org/document/8399097/
[13] P. Ranjana and E. Alexander, "Health Alert and Medicine Remainder Using Internet of Things", in 2018 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), Madurai, India, 13-15 Dec. 2018 2018, pp. 1-4, doi: 10.1109/ICCIC.2018.8782349
[14] L. Corporation, "Line," vol. windows, mac, android, ios, ed.
[15] V. Sanchez et al., "Scanalert: Electronic Medication Monitor and Reminder to Improve Medical Adherence", in 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 7-9 Jan. 2019 2019, pp. 0537-0543, doi: 10.1109/CCWC.2019.8666581
[16] Z. Pang et al., "Intelligent Packaging and Intelligent Medicine Box for Medication Management Towards the Internet-of-Things", in 16th International Conference on Advanced Communication Technology, Pyeongchang, Korea (South), 16-19 Feb. 2014 2014, pp. 352-360, doi: 10.1109/ICACT.2014.6779193
[17] 林志穎, 增進居家用藥安全與提醒之裝置, 碩士論文, 工程科學系, 國立成功大學, 台南市, 2010. Available: https://hdl.handle.net/11296/7k3fu2
[18] 芮杰, 服藥偵測器的設計與實作, 碩士論文, 工程科學系, 國立成功大學, 台南市, 2015. Available: https://hdl.handle.net/11296/v339y8
[19] J. Ma et al., "Medhere: A Smartwatch-Based Medication Adherence Monitoring System Using Machine Learning and Distributed Computing", in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA, 18-21 July 2018 2018, pp. 4945-4948, doi: 10.1109/EMBC.2018.8513169
[20] S. Yamanaka and V. Moshnyaga, "New Method for Medical Intake Detection by Kinect", in 2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS), Windsor, ON, Canada, 5-8 Aug. 2018 2018, pp. 218-221, doi: 10.1109/MWSCAS.2018.8624053
[21] H. Lee and S. Youm, "Development of a Wearable Camera and Ai Algorithm for Medication Behavior Recognition", Sensors, vol. 21, no. 11, 2021, doi: 10.3390/s21113594.
[22] Q. Ni et al., "The Elderly’s Independent Living in Smart Homes: A Characterization of Activities and Sensing Infrastructure Survey to Facilitate Services Development", Sensors, vol. 15, pp. 11312-11362, 05/01 2015, doi: 10.3390/s150511312.
[23] K. He et al., "Deep Residual Learning for Image Recognition", in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778,
[24] T. Y. Lin et al., "Feature Pyramid Networks for Object Detection", in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21-26 July 2017 2017, pp. 936-944, doi: 10.1109/CVPR.2017.106
[25] H. Law and J. Deng, "Cornernet: Detecting Objects as Paired Keypoints", in Proceedings of the European conference on computer vision (ECCV), Munich, Germany, 2018, pp. 734-750,
[26] A. Newell et al., "Stacked Hourglass Networks for Human Pose Estimation", in European conference on computer vision, Amsterdam, The Netherlands, 2016: Springer, pp. 483-499,
[27] K. Duan et al., "Centernet: Keypoint Triplets for Object Detection", in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 27 Oct.-2 Nov. 2019 2019, pp. 6568-6577, doi: 10.1109/ICCV.2019.00667
[28] Raspberry Pi Foundation, "Raspberry Pi 3 Model B+". Available: https://www.raspberrypi.com/products/raspberry-pi-3-model-b-plus/, last retrieve 28 May 2022
[29] D.Jones, "Version 1.13 Picamera ". Available: https://github.com/waveform80/picamera., last retrieve 24 April 2022
[30] Google, "Tensorflow 2 Object Detection Api ". Available: https://github.com/tensorflow/models/tree/master/research/object_detection, last retrieve 25 April 2022
[31] COCO Consortium, "Coco". Available: https://cocodataset.org/, last retrieve 23 April 2022
[32] LINE Corporation, "Line Developers Console". Available: https://developers.line.biz/console/, last retrieve 20 April 2022
[33] Google, "Tensorflow 2 Detection Model Zoo". Available: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md, last retrieve 27 April 2022
[34] J. Huang et al., "Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors", in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 21-26 July 2017 2017, pp. 3296-3297, doi: 10.1109/CVPR.2017.351
[35] Dorhea, "B07fm6ll3v". Available: https://www.amazon.com/Infrared-Illuminator-Adjustable-Resistor-Raspberry/dp/B07FM6LL3V?th=1), last retrieve 28 April 2022
[36] 林旻賢, 使用低解析度熱感測器與深度學習進行跌倒偵測, 碩士論文, 工程科學系, 國立成功大學, 台南市, 2021. Available: https://hdl.handle.net/11296/gpsrhs