透過您的圖書館登入
IP:3.141.199.243
  • 學位論文

高準確跌倒偵測之智慧型手機演算法

Smartphone-based high accuracy algorithm for fall detection

指導教授 : 趙福杉

摘要


隨著人口老化而進入高齡化社會後,年長者的長照是十分重要的議題,其中跌倒之自動偵測在居家照護中是重要的環節,在年長者跌倒後可即時的偵測並通報以減少跌倒長躺後造成之影響,本論文利用智慧型手機內建感測器-加速規來實現跌倒之自動化偵測。 本論文共包含兩個系統,第一個為三特徵值跌倒偵測系統,擷取三個富含物理意義之特徵值送入支持向量機(SVM)作辨識,並使用二種正規化方法,使演算法能適用於不同廠牌之手機。另一個系統為多特徵值跌倒自動偵測系統,希望能更進一步提升第一種方法之準確度,透過計算重力方向上之加速度來獲取更適合辨識跌倒之特徵值,同時設計更符合跌倒模式之trigger key來減少進入運算之次數以節省手機之運算量。 本論文建立了高準確度之跌倒自動偵測系統,亦解決智慧型手機日常使用中沒有固定的配戴位置和方向之問題,並克服手機廠牌間之sensor差異,同時也考量了對智慧型手機合適之運算量和傳輸量。

並列摘要


參考文獻


[2] M. Tolkiehn, L. Atallah, B. Lo and G. Z. Yang, "Direction sensitive fall detection using a triaxial accelerometer and a barometric pressure sensor," Proceedings of 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Boston, MA, 2011, pp. 369-372.
[3] F. Bagalà., C. Becker, A. Cappello, L. Chiari, K. Aminian, J. M. Hausdorff, et al, "Evaluation of accelerometer-based fall detection algorithm in realworld falls", PLoS ONE, vol. 7, no. 5, pp.1-9, May 2012.
[6] J. Dai, X. Bai, Z. Yang, Z. Shen, and D. Xuan, "Mobile phone-based pervasive fall detection," Personal Ubiquitous Computing, vol. 14, issue 7, pp. 633-643, October 2010.
[9] B.T. Nukala, N. Shibuya, A.I. Rodriguez, J. Tsay, T.Q. Nguyen, S. Zupancic, and D.Y.C. Lie, “A real-time robust fall detection system using a wireless gait analysis sensor and an artificial neural network,” Proceedings of Healthcare Innovation Conference (HIC), Seattle, Washington, USA, 2014, pp. 219-222.
[11] O. Aziz, M. Musngi, E. J. Park, G. Mori, S. N. Robinovitch, “A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials,” Medical & biological engineering & computing, pp. 1-11, 2016.

延伸閱讀