“In this paper, we propose a probabilistic approach to model user’s gesture patterns using continuous n-gram language model. We built a functional prototype SenSec, which keeps track of sensory reading from accelerometer, gyroscope and magnetometer on device, builds the context of user’s gesture patterns and use them to perform user classification or to identify whether it is the owner. The results showed that SenSec system achieves 75% accuracy in user classification tasks and 71.3% accuracy in user authentication tasks with only 13.1% false alarms and 4.
96 detection delay””In this paper we have attempted to present the theory of hidden Markov models from the simplest concepts (discrete Markov chains) to the most sophisticated models (variable duration, continuous density models). It has been our purpose to focus on physical explanations of the basic mathematics; hence we have avoided long, drawn out proofs and/or derivations of the key results, and concentrated primarily on trying to interpret the meaning of the math, and how it could be implemented in practice in real world systems. We have also attempted to illustrate some applications of the theory of HMMs to simple problems in speech recognition, and pointed out how the techniques could be (and have been) applied to more advanced speech recognition problems”
