運動辨識是近年來十分廣泛受到運用的研究方向，目前許多智慧型手機、手表、行人導航系統內皆有內建慣性感測器，使用其訊號搭配GPS或計步器之類的感測裝置，配合運動辨識演算法去進行運動位移的估測，抑或是分析使用者當下的生理狀態，幫助使用者記錄運動過程的細節。
有鑑於大多的運動辨識演算法皆是利用運動慣性感測器測得的時域訊號進行分析，進而取得頻域特性加以利用，本論文試著使用小波轉換(Wavelet Transform)進行訊號轉換，直接找出走路、跑步、上下樓、電梯、游泳等運動模式的頻域特徵差異，最後嘗試著配合類神經網路(Neural Network)的訓練，得到小波轉換後特徵參數與實際運動距離的相對函數。

The research in motion identification is very popular recently. Inertial sensors are widely embedded in many consumer electronic devices, such as smart phone, watch, and pedestrian navigation system. In these applications, inertial sensors are integrated with GPS or the pedometer in the positioning algorithm, which can estimate the displacement of motion. After that we can do real-time analysis of user’s physical conditions and also can help to get the detail conditions from their exercise process.
There are a lot of research papers in motion identification, many of which were established first by analyzing the time domain signal then by taking advantage of frequency domain features. In this thesis the signal was converted by using Wavelet Transform, and different motion modes including walking, running and swimming were determined from the transformed signal features. Neural Network is then utilized to get the relationship between the characteristic parameters converted by Wavelet Transform and the distance of motion.

[1]林敬弦，個人運動模式辨識與建模，碩士論文，國立台灣科技大學機械工程研究所，台北，2011。
[2]S. H. Shin, C. G. Park, J. W. kim, H.S. Hong and J. M. Lee, ”Adaptive Step Length Estimation Alogrithm Using Low-Cost MEMS Inertial Sensors”, IEEE Sensors Applications Symposium San Diego, California USA, 6-8 February 2007.
[3]Yunqian Ma,”Gate Classification Using Wavelet Descriptors in Pedestrian Navigation”, ION GNSS-2011.
[4]走路與慢跑圖，http://flash.abang.com/od/cartoon/
[5]http://www.wcps.cyc.edu.tw/wcps/swimming/course1.htm
[6]http://www.swimst.net/freestyle/freeimp/freebreath.htm
[7]黃國維，使用FPGA實現離散小波轉換之硬體架構，碩士論文，國立台灣科技大學電子工程研究所，台北，2006。
[8]http://zh.wikipedia.org/wiki/%E9%9B%A2%E6%95%A3%E5%B0%8F%E6%B3%A2%E8%AE%8A%E6%8F%9B
[9]鄭美滿，實驗性比壓器局部放電圖譜之辨識，碩士論文，國立台灣科技大學電機工程研究所，台北，2005。
[10]http://ishare.iask.sina.com.cn/f/5484328.html
[11]http://mines.humanoriented.com/classes/2010/fall/csci568/portfolio_exports/jthomas/knn.html
[12]趙良嘉，倒傳遞類神經網路之學習控制系統，碩士論文，私立元智大學機械工程研究所，桃園，1994。
[13]羅華強，類神經網路-Matlab的應用，高立出版社，2011。
[14]陳慶坤，步伐偵測與GPS整合之個人運動定位系統，碩士論文，國立台灣科技大學機械工程研究所，台北，2011。