ZigBee無線感測網路之跌倒偵測系統

Fall Detection be ZigBee Wireless Sensor Network

林昆遠(Kun-Yuan Lin)

指導教授 ： 蔡章仁

國立中央大學/資訊電機學院/電機工程學系/碩士(2008年)

摘要

跌倒是高齡者和學步的孩童在居家生活中常見的意外。本系統是一套能偵測人體跌倒的無線感測網路(Wireless Sensor Network, WSN)，主要目的在於有效地偵測跌倒以將其所造成的傷害減到最低。希望能在人體跌倒發生的最短時間內，發出警報給緊急聯絡人。偵測跌倒的方法是在地板上面佈置一個陣列的反射光感應器做為人體感測器，各感測器之間隔著固定距離，當人體壓在感測器上的時候，便會觸發被遮擋的感測器，藉由搭載群蜂(ZigBee)協定之節點以無線傳輸的方式，傳送訊號給網路協調器(Coordinator)及後端伺服器。伺服器分析這些感測器的位置及個數等等，來判斷是否為跌倒的發生。

關鍵字

ZigBee ； 無線感測網路 ； 跌倒

並列摘要

Fall often happens to aged people and toddlers. It is a common accident during their daily lives. The purpose of our system was to effectively decrease the damage by detecting fall incidents and issuing an alerting message. Our system was based on wireless sensor network (WSN) conforming to the ZigBee protocol. We hoped that the system would inform someone as soon as possible when a fall happens. The detecting part consisted of reflective optical sensors deployed as an array on the ground. When a human body lay over the sensor array, the covered sensors would be triggered. The information would be transmitted to a coordinator of the WSN by ZigBee end devices connected to the covered sensors. The server of the WSN then received the information from the coordinator and analyzed the spatial pattern of the covered sensors to determine if a fall happened. Aimed to be used in bathrooms, we implemented the WSN fall detection system on an acrylic slab about the size of a bathroom floor area. Simulations were conducted to analyze the covered sensors’ pattern when a human body fell on the floor with different poses. Based on these data, a fall detection algorithm was developed.

並列關鍵字

ZigBee ； Fall ； WSN ； Wireless Sensor Network

參考文獻

[1] Centers for Disease Control and Prevention. Web-based Injury Statistics Query and Reporting System (WISQARS). National Center for Injury Prevention and Control, Centers for Disease Control and Prevention (producer). Available at http://www.cdc.gov/ncipc/wisqars (accessed July 2008).

[2] J. A. Stevens, P. S. Corso, E. A. Finkelstein, T. R. Miller, The costs of fatal and nonfatal falls among older adults, Injury Prevention, VOL. 12, (2006), 290-295.

[3] C.-F. Juang, C.-M. Chang, Human Body Posture Classification by a Neural Fuzzy Network and Home Care System Application, IEEE Transactions On Systems, Man, and Cybernetics – Part A: Systems and Humans, VOL. 37, NO. 6, (November 2007), 984-994

[5] H. Nait-Charif, S. J. McKenna, Activity Summarisation and Fall Detection in a Supportive Home Environment, Proceedings of the 17th International Conference on Pattern Recognition, 2004.

[6] C.-W. Lin, Z.-H. Ling, Yeng-Cheng Chang, Compressed-domain Fall Incident Detection for Intelligent Homecare, Journal of VLSI Signal Processing, VOL. 49, (2007), 393–408