使用手機重力感應器和類神經網路於姿態辨識

Posture Recognition with Mobile Phone G-Sensor and Artificial Neural Networks

蔡康俊(Kang-Chun Tsai)

指導教授 ： 許輝煌

淡江大學/工學院/資訊工程學系碩士班/碩士(2012年)

https://doi.org/10.6846/TKU.2012.01078

摘要

隨著智慧型手機的興起，目前在路上幾乎每個人都擁有一隻智慧型手機，而智慧型手機的問世改變了固有的手機模式，從原本單純的通話功能擴展至類似電腦的作用，此外行動網路的發展也是促長智慧型手機蓬勃發展的主因，智慧型手機搭配行動網路以及內建的一些硬體設備可以滿足更多使用者的需求。而在如今的社會，運動和健康一直是人們所關心的事情，因為運動量不足而肥胖引發的慢性疾病更是驚人。因此本論文中提出一個基於類神經網路辨識的手機應用程式，在此系統中我們會利用使用者口袋內建G-Sensor的手機抓取加速度值，放入經過訓練的類神經模型中辨識出四種狀態：坐、站、走、跑，每當使用者有狀態轉換時，系統便會把狀態和持續時間放進手機資料庫內。使用者隨時隨地可以在手機的介面上查詢到某一天內的四種狀態持續時間，並且可以藉由這四種不同的狀態和使用者的體重算出該天消耗的卡路里。此系統對於控制每天的運動量是一項很有幫助的軟體，並且希望能依靠此軟體幫助平常忙碌的人們更佳的健康。

關鍵字

重力感應器 ； 類神經網路 ； 智慧型手機 ； 姿態辨識

並列摘要

Mobile phone is a popular device in the world, every people almost have a mobile phone in their hand. The smart phone applications combine many hardware devices, like GPS and G-Sensor. The smart phone can do more than your computer, moreover, the smart phone has mobility, hardware device and mobile network which is inexistent in any computer. Many researches are based on mobile phone applications in recent years.
In this research, we propose a method that can recognize four human posture states, i.e., sit, stand, walk and run. When the user clicks the start button, the system will catch accelerometer data into the recognition module. In this module, data will be processed with moving average and enter artificial neural networks. When the state change, the system record posture state and duration into the database. In history module, the user can find each state duration and total calorie from user interface for a certain. We hope this system can be ease of use and really helps the user to achieve moderate exercise.

並列關鍵字

G-Sensor ； Artificial Neural Networks ； Smart Phone ； Posture Recognition

參考文獻

[5] J. Kela, P.Korpipaa, J. Mantyjarvi, S.Kallio, G.Savino, L.Jozzo and S. D. Marca, “Accelerometer-Based Gesture Control For A Design Environment”, Personal and Ubiquitous Computing, vol. 10, no. 5, 2006, pp. 285~299

[6] J. G. Lim, S. Y. Kim and D. S. Kwon, “Pattern Recognition-Based Real-Time End Point DetectionSpecialized For Accelerometer Signal”, in Proc. IEEE/ASME Int. Conf. Adv. Int. Mechatron., 2009, pp. 203–208.

[7] I. Constandache, R. R. Choudhury and I. Rhee, “Towards Mobile Phone LocalizationwithoutWar-Driving”, In Proc. of the 9th Int. Conf. on UbiquitousComputing,, 2010, pp. 1-9

[8] M.Youssef, M.A.Yosefand M.E.Derini, “GAC: Energy-Efficient HybridGPS-Accelerometer-Compass GSM Localization”, Global Telecommunications Conference, 2010, pp. 1-5

[9] A. Ofstad, E. Nicholas, R. Szcodronski, and R. R. Choudhury, “AAMPL: Accelerometer Augmented Mobile Phone Localization”,In Proc.of the14th Annual Int. Conf.on Mobile Computing and Networking, 2008, pp. 13–18.