People are increasingly recognizing how their health affects their quality of life, and health is most easily tracked through the use of wearable devices. The goal of this study is to detect and monitor human motion via gait analysis to provide information that will help people enhance their health. After reviewing a range of wearable health-tracking devices, the shoe has been chosen as one of the best device for observing human motion. / Most measurement systems currently used for motion and gait detection are disadvantaged in that they monitor and analyze motion in limited environments and not in real time. Hence, they cannot be used for long-term monitoring and detection. The design of a new, inexpensive, compact and lightweight shoe-integrated platform is elaborated in this thesis. The intelligent shoe system comprises a suite of sensors, a microprocessor board and a wireless communication module. This ideal platform requires no specialized equipment or lab setup, meaning data can be collected not only in the narrow confines of a research lab, but essentially anywhere, whether indoors or outdoors. / Our everyday lives are shaped by a wide variety of motions, some of which can cause injury. Injuries suffered due to falls account for a significant portion of accidents and immediate help should be provided. The intelligent shoe system offers an approach of detecting the user’s motion, especially the movement and direction of a fall. This study used principle component analysis (PCA) to decrease the number of sensors in the prototype (eight pairs) by half (four pairs), so as to reduce computational cost and enhance real-time performance. The resultant system can learn the patterns necessary to detect fall directions from abundant tilted-standing data instead of actual fall data. / Fatigue can result in an abnormal gait, making injury more probable. Hence, detecting fatigue is very important. Experiments have been conducted to determine the relationship between fatigue and gait, and the resultant data are used to analyze the relationship between force information and foot attitude. These findings can help a user detect fatigue and avoid injury. / People carry various kinds of loads in their daily lives, and long-term load-bearing activities can result in motion deformation. Another objective of this study is to determine a load-carrying approach that will decrease such deformation to a great extent. Resampling is used to partition the related data cycle by cycle. A support vector machine (SVM) is adopted to model a user’s normal walking gait and abnormal gaits without loads, which allows for the determination of whether a gait is normal when a load is carried. / To enhance overall health, exercise is commonly adopted, but many forms of exercise are dull. The proposed system’s shoe-computer interface not only helps people obtain detailed lower-body feedback, but can also be used to promote everyday exercise. People are analyzed while sitting for long periods in the workplace, and two interfaces are designed as a result: the shoe-keyboard, in which the feet are used to type words into a computer, and the shoe-write system, in which the foot is used like a hand to write on the ground, with the words displayed on the computer screen. Both of these applications use back-propagation (BP) networks to classify the motions involved. The shoe-keyboard is based on logical coding to map the motion-to-word relationship, and the shoe-write system incorporates an optical tracker to translate motion into information. / 人們現在越來越重視自己的生活質量，而健康方面是最為重要的。穿戴式設備是最好容易使用的檢測健康的設備。本文的目標是通過智能鞋，來檢測步態，對其進行分析和預測，已達到檢測和提高人們的健康水平的要求。 / 現在絕大多數的步態運動檢測系統都不是實時的且長時間工作的。在研究中，基於鞋子的智能系統被提出并得以實現，其具有便宜，緊湊，輕便等的優點。該系統包括壓力和加速度傳感器，處理芯片和無線傳輸模塊。這種設計將滿足日常步態信息的採集，并且把環境影響的因素放置最小，以達到室內室外都可長時間連續實時監測的要求。 / 在本論文中，對一系列日常生活的行為進行檢測和分類，尤其是最為危險的摔倒。本系統通過採用主成分分析，對已有的壓力傳感器進行的了分析，在保證了預測的準確性的前提下，將壓力傳感器由8對減少至4對，大大的降低了運算的次數，使得該系統實時性更好。同時本系統通過傾斜站立獲得的數據并應用于跌倒方向的檢測，並且有著良好的結果。 / 在本文中，對疲勞步態進行的分析，通過設計實驗，來區分不同疲勞程度下人們的步態。壓力信號較為明顯，同時加速度反映出每一步的劇烈程度。最終結果表明，壓力和加速度相輔相成，與疲勞程度的關係也很明顯，基於這種關係，本系統對疲勞程度進行了預測，通過壓力傳感器的信號，預測疲勞的程度，實驗結果也較為理想。 / 長時間的負責對身體的負擔很大，在本文中，著重的分析了在不同負重方式下，步態的變化，並且通過對比正常步態，採用支持向量機進行分類。在分類的過程中，通過重新採樣，將採集的數據轉變為一步為一組的數據，進行分類，最終得到的結果表明，平衡狀態下的負重是最好的。 / 對於健康而言，除了檢查受傷和疲勞，提升自身的身體素質也尤為重要。在本文中，介紹了兩種基於智能鞋的應用，在鍛煉下肢靈活度的同時，也避免了鍛煉的無聊。智能鞋鍵盤是通過腳踝的運動，基於一定的編碼方式，已達到在電腦上輸入文字的方式。智能鞋寫字系統是通過對下腳點的定位結合光電傳感器記錄位移，最終獲得文字輸入。應用BP神經網絡，對腳下點進行了分類，結合壓力傳感器和腿部建模，可以準確的區分30個的基本點的位置，從而獲得每筆的起點。最終完成寫字輸入。 / Tao, Yanbo. / Thesis Ph.D. Chinese University of Hong Kong 2014. / Includes bibliographical references (leaves 134-141). / Abstracts also in Chinese. / Title from PDF title page (viewed on 12, October, 2016). / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only.
| Identifer | oai:union.ndltd.org:cuhk.edu.hk/oai:cuhk-dr:cuhk_1291520 |
| Date | January 2014 |
| Contributors | Tao, Yanbo (author.), Xu, Yangsheng , 1958- (thesis advisor.), Chinese University of Hong Kong Graduate School. Division of Mechanical and Automation Engineering. (degree granting institution.) |
| Source Sets | The Chinese University of Hong Kong |
| Language | English, Chinese |
| Detected Language | English |
| Type | Text, bibliography, text |
| Format | electronic resource, electronic resource, remote, 1 online resource (xvii, 141 leaves) : illustrations (some color), computer, online resource |
| Rights | Use of this resource is governed by the terms and conditions of the Creative Commons "Attribution-NonCommercial-NoDerivatives 4.0 International" License (http://creativecommons.org/licenses/by-nc-nd/4.0/) |
Page generated in 0.0019 seconds