利用三軸加速度計設計與實現跌倒偵測

The Design and Implementation of Fall Detection based on Triaxial Accelerometer

陳重亦(Chung-Yi Chen)

指導教授 ： 朱元三

國立中正大學/工學院/電機工程學系/碩士(2013年)

摘要

台灣自1993年起邁入高齡化社會，65歲以上老年人口佔比例逐年攀升，老人面臨的問題和各項生活需求，會因人口結構的改變而不同。而隨著老年人老化身體功能逐漸退化，跌倒造成老人意外死亡，已成為一個不可忽視的問題。關於跌倒的預防與搶救，在近年來的研究上已成為一個注目的話題。本論文提出一套加速度跌倒偵測系統，具有跌倒偵測、計步與偵測步伐不穩等功能。

在此篇論文中我們在嵌入式系統使用來三軸加速度計實現跌倒偵測功能，並利用加速度實現計步功能與偵測步伐不穩的功能。在使用者發生跌倒時，可以立即偵測到並發出警訊，計步器可以自我監測，經由漸進式的目標設定，可以有效增加每天運動量，使得腿力增強，降低跌倒發生的可能性，而在使用者步伐不穩時，可以事先發出警訊發生跌倒的可能。本系統的特色是能迅速偵測使用者是否跌倒，並且能偵測使用者是否步伐不穩，跌倒偵測的敏感度(Sensitivity)可達約95%，步伐不穩偵測的敏感度可達約99%。

關鍵字

跌倒偵測 ； 嵌入式系統 ； 計步器

並列摘要

Since 1993, Taiwan has entered population-aging society. Elderly population aged over 65 has increased steadily proportion. Due to the population structure alteration, the elderly problems and life needs will change. With the elderly physical degradation, accidental deaths caused by falls has become an unavoidable issue. About falls prevention and rescue research in recent years has become a topic of attention. In this thesis, we proposed an acceleration fall detection system which has fall detection, pedometer and unsteady gait detection.

In this thesis, we implement fall detection on an embedded system and use accelerometer to implement pedometer and unsteady gait detection. It can immediately detect and send an alert when user falls. Pedometer can be used to self-monitoring and effectively increase the amount of exercise every day by the way of progressive goal setting. Therefore, it can reduce the probability of falls due to the leg strength enhancement. It also can send an alert in advance when detecting user's unsteady gait. The system characteristic are rapid fall detection and unsteady gait detection. The sensitivity of fall detection can achieve 95% and the sensitivity of unsteady gait detection can achieve 99%.

並列關鍵字

Fall Detection ； Embedded System ； Pedometer

參考文獻

[7] 劉建賢，「使用加速度計和陀螺儀之跌倒偵測系統」，大同大學資訊工程所碩士論文，Jan. 2012

[8] S.Y.Chang, H.C.Chao, Y.M.Huang, “Detection of Cognitive Injured Body Region Using Multiple Triaxial Accelerometers for Elderly Falling,” IEEE SENSORS JOURNAL, VOL. 11, NO. 3, pp. 763-770, March. 2011

[9] Bourke, A.K., et al. , “ Evaluation of Waist-Mounted Tri-axial Accelerometer Based Fall-Detection Algorithms During Scripted and Continuous Unscripted Activities,” Journal of Biomechanics, pp. 3051-3057,2010

[11] Yi-Mao Hsiao, Wan-Ting Liu, Yuan-Sun Chu,” Design and implementation of a healthcare system with fall detection, “International Symposium on Bioelectronics and Bioinformatics (ISBB), Nov. 2011,pp.131-134.

[12] S. H. Fang, Y. C. Liang, and K. M. Chiu, “Developing a mobile phone-based fall detection system on an Android platform,” Computing Communications and Applications Conference, Jan. 2012 , pp. 143-146.