User Authentication Using Accelerometer Sensor in Wrist-Type Wearable Device


KIPS Transactions on Computer and Communication Systems, Vol. 6, No. 2, pp. 67-74, Feb. 2017
10.3745/KTCCS.2017.6.2.67,   PDF Download:
Keywords: Accelerometer, User Authentication, Machine Learning, Wearable Device, Biometric
Abstract

This paper proposes a method of user authentication through the patterns of arm movement with a wrist-type wearable device. Using the accelerometer sensor which is built in the device, the 3-axis accelerometer data are collected. Then, the collected data are integrated and the periodic cycle are extracted. In the cycle, the features of frequency are generated with the accelerometer. With the frequency features, 2D Gaussian mixture are modelled. For authenticating an user, the data(the accelerometer) of the user at some point are tested with confidence interval of the Gaussian distribution. The model showed a valuable results for the user authentication with an example, which is average 92% accuracy with 95% confidence interval.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. Y. Kwang and M. J. Sub, "User Authentication Using Accelerometer Sensor in Wrist-Type Wearable Device," KIPS Transactions on Computer and Communication Systems, vol. 6, no. 2, pp. 67-74, 2017. DOI: 10.3745/KTCCS.2017.6.2.67.

[ACM Style]
Kim Yong Kwang and Moon Jong Sub. 2017. User Authentication Using Accelerometer Sensor in Wrist-Type Wearable Device. KIPS Transactions on Computer and Communication Systems, 6, 2, (2017), 67-74. DOI: 10.3745/KTCCS.2017.6.2.67.