Fast Adaptation of Activity Sensing Policies in Mobile Devices

Mohammad Abu Alsheikh, Dusit Niyato, Shaowei Lin, Hwee Pink Tan, Dong In Kim

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

With the proliferation of sensors, such as accelerometers, in mobile devices, activity and motion tracking has become a viable technology to understand and create an engaging user experience. This paper proposes a fast adaptation and learning scheme of activity tracking policies when user statistics are unknown a priori, varying with time, and inconsistent for different users. In our stochastic optimization, user activities are required to be synchronized with a backend under a cellular data limit to avoid overcharges from cellular operators. The mobile device is charged intermittently using wireless or wired charging for receiving the required energy for transmission and sensing operations. First, we propose an activity tracking policy by formulating a stochastic optimization as a constrained Markov decision process (CMDP). Second, we prove that the optimal policy of the CMDP has a threshold structure using a Lagrangian relaxation approach and the submodularity concept. We accordingly present a fast Q-learning algorithm by considering the policy structure to improve the convergence speed over that of conventional Q-learning. Finally, simulation examples are presented to support the theoretical findings of this paper.

Original languageEnglish
Article number7744681
Pages (from-to)5995-6008
Number of pages14
JournalIEEE Transactions on Vehicular Technology
Volume66
Issue number7
DOIs
Publication statusPublished - 15 Nov 2017
Externally publishedYes

Fingerprint

Dive into the research topics of 'Fast Adaptation of Activity Sensing Policies in Mobile Devices'. Together they form a unique fingerprint.

Cite this