基於區間第二型模糊理論之跌倒偵測系統設計

The Design of Fall Detection System Based on Interval Type-2 Fuzzy Theory

劉韋亨(Wei-Heng Liu)

指導教授 ： 黃有評

國立臺北科技大學/電資學院/電機工程系所/碩士(2013年)

https://doi.org/10.6841/NTUT.2013.00104

摘要

近年來隨著醫學的進步，使得國人平均壽命逐年提升，老年人口大幅增加，根據內政部統計「跌倒」是六十五歲以上老人事故傷害死亡的主要原因。而獨居老人的生活照顧是一項被關注的焦點，根據內政部於2009年所進行的老人狀況調查報告中，指出臺灣地區六十五歲以上人口，實際獨居或僅與配偶同居比例為27.9%。世界衛生組織曾將獨居老人定為高危險群，原因在於當有緊急事故發生時無法即時的得到幫助。因此，本研究利用智慧型手機設計一套適用於居家環境之跌倒偵測系統，透過智慧型手機內建的重力加速度感測器擷取使用者行走與跌倒的加速度訊號，根據加速度變化值設計對應的模糊規則庫，並透過學習演算法調整模糊歸屬函數，之後藉由模糊推論判別使用者是否發生跌倒意外，若發生跌倒，系統會發出警報聲並透過簡訊傳送訊息，讓使用者的家屬及醫護人員能即時提供支援。最後本研究比較第一型模糊邏輯系統、第二型模糊邏輯系統及已學習之第二型模糊邏輯系統的偵測效果，實驗結果顯示使用者若發生跌倒，系統的辨識準確率均可達到100%；而在行走的情況下，第一型模糊邏輯系統、第二型模糊邏輯系統及已學習之第二型模糊邏輯系統的辨識準確率依序為85.8%、92.3%及94.8%，由實驗結果可得知，基於第二型模糊理論所設計之跌倒偵測系統可更有效的判斷跌倒或行走狀況。

關鍵字

區間第二型模糊理論 ； 跌倒偵測 ； 智慧型手機 ； 重力加速度感測器

並列摘要

In recent years, with national’s average life increases year by year, the elderly population increase substantially. According to the Ministry of the Interior’s statistics, falling is the main reason that causes death to elderly with age over sixty five. The home care of solitary elderly is the focus issue, according to the Ministry of the Interior’s investigation which reports about the elderly condition in 2009 pointing out that the percentage of person age over sixty five in Taiwan live alone or with mate is 27.9%. Solitary elderly has been considered as the high risky group by WHO because if they were injured in an accident, they could not get help immediately. In this study, we base on smart phones to design fall detection systems that are suitable for home environment. By analyzing the accelerometer sensors from smart phones during a user’s walking, we can design fuzzy inference models to determine if the user has fallen over. If the user has fallen over, the system will alarm and send short message to user’s family members and medical doctors to find immediate cure. Finally, we compare experimental results from type-1, type-2 and adjusted type-2 fuzzy logic systems. The results show that if the user has fallen over, all of the systems can have 100% accuracy in detecting the walking patterns. Under the walking condition, the accuracies are 85.8%, 92.3% and 94.8% respectively. Experiment results show that the designed system based on interval type-2 fuzzy theory can effectively detect the fall over and walking patterns.

並列關鍵字

interval type-2 fuzzy theory ； fall detection ； smart phones ； accelerometer ； fall detection

參考文獻

[2]財團法人門諾社會福利慈善事業基金會 – 用愛關懷，溫暖到宅~~102年度東部獨居老人照顧計畫，http://www.mf.org.tw/item06/10201.pdf。

[3]A. M. Khan, Y. K. Lee, S. Y. Lee and T. S. Kim, “A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer,” IEEE Trans. on Information Technology in Biomedicine, vol. 14, no. 5, pp.1166-1172, Sep. 2010.

[4]F. Bianchi, S. J. Redmond, M. R. Narayanan, S. Cerutti and N. H. Lovell, “Barometric pressure and triaxial accelerometry-based falls event detection,” IEEE Trans. on Neural Systems and Rehabilitation Engineering, vol. 18, no. 6, pp.619-627, Dec. 2010.

[5]D. Curone, A. Tognetti, E. L. Secco, G. Anania, N. Carbonaro, D. D. Rossi and G. Magenes, “Heart rate and accelerometer data fusion for activity assessment of rescuers during emergency interventions,” IEEE Trans. on Information Technology in Biomedicine, vol. 14, no. 3, pp.702-710, May 2010.

[6]Y. Li, K. C. Ho and M. Popescu, “A microphone array system for automatic fall detection,” IEEE Trans. on Biomedical Engineering, vol. 59, no. 5, pp.1291-1301, May 2012.