用於年長者居家跌倒偵測系統設計

Abstract

對於獨居老人來說跌倒是一項嚴重的傷害，本研究的目的即在使用可穿戴式的加速度感測器及固定式的壓力感測器偵測老年人於行動時發生跌倒情況來進行研究。本研究結合地板壓力感測、加速度感測以及小波轉換可精確的偵測老年人跌倒。 小波轉換為近年來相當熱門的研究題目之一，小波定理提供了統一的架構給許多不同的訊號處理應用領域。目前小波轉換已廣泛地應用在通信系統，信號處理，影像和音訊處理等不同的研究領域。 本研究參考訊號相關之論文，並提出的以小波轉換搭配積函數的演算法為基礎作跌倒判斷，積函數是由信號經由小波轉換後產生的一低頻訊號和高頻訊號取絕對值相乘所得，此積函數能將一般運動的訊號衰減並突顯跌倒瞬間之能量，再加上新的訊號分割點判斷演算法並結合專家系統綜合推理，與傳統方法相較之下，本論文所提的判斷分割點的演算法可提昇判斷跌倒的準確度。

Unintentional falls are a common cause of severe injury in the elderly population. This research presents a wearable micro-sensing device worn on the waist and a network of fixed motes in the home environment for detecting human body falls because of stroke or elder movement. It combines micro-sensors and digital data processing technologies and wavelet transform. We can detect the occurrence of a fall.

The wavelet transform is one of the most exciting developments of the last decade. Wavelet theory provides a unified framework for a number of techniques that had been developed independently for various signal-processing applications.

This thesis makes use of wavelet transform and energy profile to indicate the segmentation point of signal and is no need to set any predetermined threshold. The product function is generated from the appropriate wavelet and scaling coefficients of input signal, and it can be applied to indicate the segmentation point. With this product function, expert system and the additional verification of energy profile, the segmentation point can be accurately to detect falls with a low computation complexity.