Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0823112-163650 Statistics This thesis had been viewed 2176 times. Download 836 times. Author Ming-Hsiung Su Author's Email Address No Public. Department Computer Science and Enginerring Year 2011 Semester 2 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 53 Title A Fall Detection Mechanism for Smart Phones Based on Finite State Machine Keyword fall detection finite-state machine smartphones smartphones finite-state machine fall detection Abstract With the approaching of an aging society, healthcare for the elderly has gradually gained its importance. Early and accurate detection of the older people’s accidental falls can significantly shorten the time to receive instant and proper treatment. This can also lessen the avoidable harm resulting from the delay of sending the patients to the hospital, and thus improve the quality of healthcare. The study proposes a fall detection mechanism which can quickly and accurately detect falls of any kind. By utilizing the built-in 3 axis-accelerometers in Android-based smartphones, a finite-state machine was constructed from the triaxial variations of pre-falls and post-falls. Such mechanism was later realized by an Android application. When the smartphone running the application is placed in 3 positions, namely pockets of the shirts, and front and back pockets of the pants, the mechanism can effectively detect real falls, including forward, backward, rightward, and leftward falls. On the other hand, non-fall activities such as walking, sitting down, squatting, and going upstairs or downstairs will not be mistakenly recognized as real falls. The average sensitivity of the presented detection mechanism is 97%, and the average specificity is 100%. These results prove the effectiveness of the presented mechanism. Advisor Committee Shang-Lin Hsieh - advisor
Files Date of Defense 2012-07-20 Date of Submission 2012-08-23