由於醫療技術的進步以及生育率的下降，而使得高齡人口的比例逐漸上升，根據國家發展委員會的預估，在2050年時台灣地區的高齡人口將會佔有總人口的36.6%，在2070更有可能達到41.6%。而隨著高齡人口的增加，老人獨居的案例也隨之增加，在此情況下高齡人口的照顧者將不能隨時在他們身邊給予照顧，由於長者的健康狀況退化造成行動不便，進而使得意外更加容易發生。一旦有意外事件發生，僅能夠透過照顧者來訪時發現並且處理。然而當長者發生意外後若未能即時發現，將會導致通報以及急救的延遲，產生更為嚴重的危害。因此，開發一套能夠自動監測長者安全的智慧監測照護系統將能夠提高他們在獨居空間內生活的安全性。
在本研究中提出了一種將長者居住房屋分為數個空間，藉由長者在一個空間中的停留時間是否符合其生活習慣以判斷是否發生意外，當停留時間過久時能夠自動向照顧者通報意外發生的系統。本系統的組成包含用於判斷長者是否進出不同空間的進出感測裝置、用於傳輸進出數據的無線通訊系統以及向照顧者發出通知和設置的使用者界面。進出感測裝置會被安裝於不同空間中的出入口，其運用兩個雷射距離測量儀以感測進出的方向。當自進出感測裝置前方經過時會經過兩個雷射距離測量儀的波束範圍，其會分別測量到前方距離的改變，而裝置中的演算法便能夠依兩個雷射距離測量儀先後狀態的變換得知長者是進入或離開一空間。
 
為了使系統中的感測器能夠傳遞長者進出的數據，因此在系統中建立了一個基於LoRa技術的廣域低功耗網路，並且能夠經由電腦中的應用程式或手機簡訊對系統進行設定或接收警告。在此網路當中最基本的部分為各感測器組成的節點，節點會將感測器收集到的數據訊號送出。在使用電腦作為操作方式時，在每個節點的通訊範圍內需有一個用於接收和轉送訊號的gateway，gateway會將由節點廣播出的訊號進行識別，並通過網際網路傳送至電腦中。最終，當架設於網際網路上的電腦完成設定後，便可以通過TCP/IP協議接收來自gateway的資訊。位於電腦上的的使用者介面能夠根據接收到的資訊顯示長者的進出狀態，並且設定警示時間。在使用簡訊作為操作方式時，則在每個節點的通訊範圍內需有一個用於接訊號與控制簡訊的簡訊控制單元，照顧者便能夠經由向其發送簡訊以設定警示時間長度和通知電話號碼。
當長者進入一空間且超過設定時間未離開時，系統將會通過電腦或簡訊通知照顧者，照顧者在收到通知後便能夠及時因應。期望藉由本研究中所提出的系統架構，能夠提高長者獨居時的安全性。

Due to the advancement of medical technology and the decline in fertility, the proportion of the elderly population has gradually increased. According to estimates by the National Development Council, Taiwan, the elder in Taiwan will account for 36.6% of the total population in 2050, and it may reach 41.6% in 2070. With the increase of the elderly population, the number of cases of the elderly living alone also increases. When the elderly live alone, the caregivers of the elderly will not be able to take care of them at any time. The deteriorating health of the elderly will bring inconvenience to their walking and make accidents more likely to happen. Once an accident occurs, it can only be discovered and dealt with when the caregiver visits. However, if the elderly is not found immediately after an accident, the first aid will be delayed, and result in more serious harm. Therefore, the development of a smart monitoring and care system that can automatically monitor the actions of the elderly will be able to improve the safety of their lives in the solitary space.
In this research, a system is developed that divides the residential house for an elder into several spaces, determines the occurrence of accidents by whether the elder’s staying time in a space is in line with their living habits. If staying for too long, the system will automatically notify the caregivers of the accident. The composition of the system includes passing detection devices for judging whether the elder enters and exits a space, a wireless communication system for data transmission, and a user interface for alarms and settings to caregivers. The passing detection devices will be installed at entrances and exits of spaces, which use two laser rangefinders to sense the direction of the elder’s passing. The elder will pass through the beam of two rangefinders when walking through the device, and rangefinders will measure the change of front distance separately. The algorithm in the device can detect the elder enter or exit a space according to the change of the state of the two laser rangefinders.
In order to transmit the entrance or exit data from devices, a low-power wide-area network based on LoRa technology is set up in the system, and the system can be configured via an application in a computer or SMS. The basic part of the network are nodes composed of devices that send out the data collected by the sensors. When a computer is used as the operating method, there is at least one gateway within the communication area of each node for receiving and forwarding signals. The gateway identifies the signals broadcast by the nodes and sends them to the computer over the Internet. Ultimately, once the computer on the Internet is set up, it can receive signals from the gateway via TCP/IP protocol. The user interface on the computer can display the current location of the elder based on the data received and set up the alarm time. When using SMS as the operating method, there is at least one SMS control unit within the communication range of each node for receiving and controlling SMS, and the caregivers can set the alarm time and phone number by sending SMS to them.
When the elder enters a space and does not leave within the set time, the system will notify the caregivers through computer or SMS, and the caregivers can respond in time after receiving the alarm. It is hoped that the system architecture proposed in this study can improve the safety of the elderly when they live alone.

[1] 國家發展委員會, 2020, “中華民國人口推估（2020至2070年）”.
[2] United Nations, 2019, “World Population Prospects 2019”.
[3] Ministry of Health and Welfare (Taiwan), 2020, “The Service Conditions for Elders Living Alone”.
[4] Ministry of Health and Welfare (Taiwan), 2017, “Report of the Senior Citizen Condition Survey”.
[5] Clarke, L. H., & Korotchenko, A. (2011). Aging and the body: A review. Canadian Journal on Aging/La revue canadienne du vieillissement, 30(3), 495-510.
[6] Erkal, S. (2010). Home safety, safe behaviors of elderly people, and fall accidents at home. Educational Gerontology, 36(12), 1051-1064.
[7] Verghese, J., Holtzer, R., Lipton, R. B., & Wang, C. (2009). Quantitative gait markers and incident fall risk in older adults. The Journals of Gerontology: Series A, 64(8), 896-901.
[8] Mubashir, M., Shao, L., & Seed, L. (2013). A survey on fall detection: Principles and approaches. Neurocomputing, 100, 144-152.
[9] Nguyen, V. D., Le, M. T., Do, A. D., Duong, H. H., Thai, T. D., & Tran, D. H. (2014, June). An efficient camera-based surveillance for fall detection of elderly people. In 2014 9th IEEE Conference on Industrial Electronics and Applications (pp. 994-997). IEEE.
[10] Anderson, D., Luke, R. H., Keller, J. M., Skubic, M., Rantz, M., & Aud, M. (2009). Linguistic summarization of video for fall detection using voxel person and fuzzy logic. Computer vision and image understanding, 113(1), 80-89.
[11] Yang, L., Ren, Y., & Zhang, W. (2016). 3D depth image analysis for indoor fall detection of elderly people. Digital Communications and Networks, 2(1), 24-34.
[12] Pierleoni, P., Belli, A., Palma, L., Pellegrini, M., Pernini, L., & Valenti, S. (2015). A high reliability wearable device for elderly fall detection. IEEE Sensors Journal, 15(8), 4544-4553.
[13] Yin, J., Fang, M., Mokhtari, G., & Zhang, Q. (2016, May). Multi-resident location tracking in smart home through non-wearable unobtrusive sensors. In International Conference on Smart Homes and Health Telematics (pp. 3-13). Springer, Cham.
[14] Alwan, M., Rajendran, P. J., Kell, S., Mack, D., Dalal, S., Wolfe, M., & Felder, R. (2006, April). A smart and passive floor-vibration based fall detector for elderly. In 2006 2nd International Conference on Information & Communication Technologies (Vol. 1, pp. 1003-1007). IEEE.
[15] Pouliot, M., Joshi, V., Chauvin, J., Goubran, R., & Knoefel, F. (2012, May). Differentiating assisted and unassisted bed exits using ultrasonic sensor. In 2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings (pp. 1104-1108). IEEE.
[16] Suh, Y. S. (2019). Laser Sensors for Displacement, Distance and Position.
[17] Lee, J. H., Tsubouchi, T., Yamamoto, K., & Egawa, S. (2006, October). People tracking using a robot in motion with laser range finder. In 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 2936-2942). Ieee.
[18] Kirsch, C., & Röhrig, C. (2010, March). Position tracking using sensor fusion of a wireless network and a laser range finder. In 2010 7th Workshop on Positioning, Navigation and Communication (pp. 193-199). IEEE.
[19] Zhao, H., & Shibasaki, R. (2005). A novel system for tracking pedestrians using multiple single-row laser-range scanners. IEEE Transactions on systems, man, and cybernetics-Part A: systems and humans, 35(2), 283-291.
[20] Famolari, D. (2001, June). Link performance of an embedded Bluetooth personal area network. In ICC 2001. IEEE International Conference on Communications. Conference Record (Cat. No. 01CH37240) (Vol. 8, pp. 2573-2577). IEEE.
[21] Hüsig, S., Hipp, C., & Dowling, M. (2005). Analysing disruptive potential: the case of wireless local area network and mobile communications network companies. R&D Management, 35(1), 17-35.
[22] 38 Balakrishnan, H., Stemm, M., Seshan, S., & Katz, R. H. (1997, June). Analyzing stability in wide-area network performance. In Proceedings of the 1997 ACM SIGMETRICS international conference on Measurement and modeling of computer systems (pp. 2-12).
[23] Mekki, K., Bajic, E., Chaxel, F., & Meyer, F. (2019). A comparative study of LPWAN technologies for large-scale IoT deployment. ICT express, 5(1), 1-7.
[24] Chaudhari, B. S., Zennaro, M., & Borkar, S. (2020). LPWAN technologies: Emerging application characteristics, requirements, and design considerations. Future Internet, 12(3), 46.
[25] Ikpehai, A., Adebisi, B., Rabie, K. M., Anoh, K., Ande, R. E., Hammoudeh, M., ... & Mbanaso, U. M. (2018). Low-power wide area network technologies for Internet-of-Things: A comparative review. IEEE Internet of Things Journal, 6(2), 2225-2240.
[26] Vejlgaard, B., Lauridsen, M., Nguyen, H., Kovács, I. Z., Mogensen, P., & Sorensen, M. (2017, June). Coverage and capacity analysis of sigfox, lora, gprs, and nb-iot. In 2017 IEEE 85th vehicular technology conference (VTC Spring) (pp. 1-5). IEEE.