基於區間第二型模糊理論之異常行走步態分析

帕金森氏症、中風及癡呆症並列為老年人三大疾病，帕金森氏症主要症狀有四肢無力、站立困難、動作困難、步伐短促，晚期患者更可能出現四肢癱瘓的情形。中風主要症狀為手腳或臉部突然發麻或無力，尤其是身體的單側，突然舉步困難、覺得昏眩、失去平衡或協調。本系統欲針對這些疾病在步伐上異常之症狀來做檢測，判別受測者在行走時身體之平衡與協調能力是否為正常，使用這些較具代表性之特徵來做步態是否異常之判別。先前的許多研究都是針對使用者之日常活動進行判別，且需要配戴許多感測器，但是較缺乏便利性，因此本研究使用智慧型手機內建之三軸加速度計，設計一個結合計步器與異常步態判別之第二型模糊推論系統，針對使用者整個行走期間之身體平均傾斜角度以及身體平均傾斜角度變化來進行步態之分析與判別，並使用第二型模糊理論來做推論，以考慮各種不明確性的影響來得到較可靠之結果。本系統之判斷結果分為正常、異常，這些結果會儲存在資料庫中讓醫療人員可以做後續的觀察與分析。本研究針對正常行走和身體傾斜狀態之行走進行各種模擬與測試，並觀察將裝置配戴於腰間之不同側對結果之影響，實驗結果顯示，正常行走判別之準確率為95%，而異常行走判別之準確率為85%，驗證本研究所提出之步態異常判別系統的可行性。

關鍵字

第二型模糊理論；步態判別；智慧型手機；三軸加速度計

並列摘要

The three most commonly diseases of elderly include Parkinson's disease, Stroke and Dementia. The main symptoms of Parkinson’s disease are weakness of the limbs, difficult to stand or move and fast-short pace. In advanced stage, it may even become quadriplegia. The main symptoms of Stroke are limbs, face sudden numb or weakness, which always happened on one side of the body, sudden trouble walking, feeling dizziness, and loss of balance or coordination. Our system is devised to detect the symptoms of abnormal pace, identify whether the subject's body balance and coordination while walking are normal. Many previous studies are aimed at daily activity identification. However, it is inconvenient as they require some sensors to be attached on the body. Therefore, our study chose to use the triaxial accelerometer built-in smart phone to design a system that combined the pedometer with abnormal gait analysis systems based on interval type-2 fuzzy theory. Using two parameters, average body tilt angle and average difference of body tilt angle, to analyze and identify user’s gait. The type-2 fuzzy theory considers the impact of a variety of ambiguity to get more reliable results than type-1 fuzzy theory, and this is the reason why we design our system based on the type-2 fuzzy theory. The determination result of this system is divided into normal and abnormal. The results will be stored in the database so that medical professionals can do the follow-up observation and analysis. In this study, users wear the mobile device on the waist, and simulate the situation of normal walking and tilt the body during walking. We also observe the effect of wearing device on the opposite side of waist. The experimental results show that the accuracy of normal walking identification is about 95%, and the accuracy of abnormal walking identification is about 85%. The results verify that the proposed abnormal gait analysis systems are effective.

並列關鍵字

interval type-2 fuzzy theory ； gait analysis ； smart phone ； triaxial accelerometer

參考文獻

[2] J.M. Mendel, R.I. John and F. Liu, “Interval type-2 fuzzy logic systems made simple,” IEEE Trans. on Fuzzy Systems, vol. 14, no. 6, pp.808-821, Dec. 2006.

[3] A. Khosravi, S. Nahavandi, D. Creighton and D. Srinivasan, “Interval type-2 fuzzy logic systems for load forecasting: a comparative study,” IEEE Trans. on Power Systems, vol. 27, no. 3, pp.1274-1282, Aug. 2012.

[4] S.M. Zhou, J.M. Garibaldi, R.I. John and F. Chiclana, “On constructing parsimonious type-2 fuzzy logic systems via influential rule selection,” IEEE Trans. on Fuzzy Systems, vol. 17, no. 3, pp.654-667, June 2009.

[5] N.N. Karnik and J.M. Mendel, “Centroid of a type-2 fuzzy set,” Information Sciences, vol. 132, no. 1-4, pp.195-220, Feb. 2001.

[6] Introduction to interval type-2 fuzzy logic controllers - towards better uncertainty handling in real world applications,

國際替代計量

基於區間第二型模糊理論之異常行走步態分析

全文下載

主題瀏覽