Hierarchical modular Bayesian networks for low-power context-aware smartphone

Abstract Nowadays, smartphone has a tremendous number of applications using sensors and devices for several applications such as healthcare and game. However, serious consideration to increase the duration of battery use of phone is required because of the limited battery capacity. In this paper, we propose a hybrid system to increase the longevity of phone with hierarchical modular Bayesian networks that recognize the user's contexts, and device management rules that infer the unnecessary devices in smartphone. Inferring the user's contexts with sensor data and considering the device status, the context inferred and user's tendency, we determine the superfluous devices that are consuming the battery as dispensable. The experiments with the real log data collected from 28 people for 6 months verify that the proposed system performs the accuracy of 85.68% and the reduction of battery consumption of about 6%.

[1]  Johannes Peltola,et al.  Activity classification using realistic data from wearable sensors , 2006, IEEE Transactions on Information Technology in Biomedicine.

[2]  P. Costa,et al.  Age differences in personality structure: a cluster analytic approach. , 1976, Journal of gerontology.

[3]  Sushil Jajodia,et al.  Anonymity in Location-Based Services: Towards a General Framework , 2007, 2007 International Conference on Mobile Data Management.

[4]  Kent Larson,et al.  Real-Time Recognition of Physical Activities and Their Intensities Using Wireless Accelerometers and a Heart Rate Monitor , 2007, 2007 11th IEEE International Symposium on Wearable Computers.

[5]  Sung-Bae Cho,et al.  Landmark detection from mobile life log using a modular Bayesian network model , 2009, Expert Syst. Appl..

[6]  Vijay Srinivasan,et al.  Boe: Context-Aware Global Power Management for Mobile Devices Balancing Battery Outage and User Experience , 2014, 2014 IEEE 11th International Conference on Mobile Ad Hoc and Sensor Systems.

[7]  Tajana Rosing,et al.  Context Aware Power Management of Mobile Systems for Sensing Applications , 2012 .

[8]  Xia Zhao,et al.  A system context-aware approach for battery lifetime prediction in smart phones , 2011, SAC '11.

[9]  Gary M. Weiss,et al.  Identifying user traits by mining smart phone accelerometer data , 2011, SensorKDD '11.

[10]  Jatinder Pal Singh,et al.  Improving energy efficiency of location sensing on smartphones , 2010, MobiSys '10.

[11]  Balaram Das,et al.  Generating Conditional Probabilities for Bayesian Networks: Easing the Knowledge Acquisition Problem , 2004, ArXiv.

[12]  Sung-Bae Cho,et al.  Integrated modular Bayesian networks with selective inference for context-aware decision making , 2015, Neurocomputing.

[13]  Kazuhisa Ishizaka,et al.  Power Saving in Mobile Devices Using Context-Aware Resource Control , 2010, 2010 First International Conference on Networking and Computing.

[14]  R. McCrae,et al.  An introduction to the five-factor model and its applications. , 1992, Journal of personality.

[15]  Liviu Iftode,et al.  Context-aware Battery Management for Mobile Phones , 2008, 2008 Sixth Annual IEEE International Conference on Pervasive Computing and Communications (PerCom).

[16]  Valérie Renaudin,et al.  Motion Mode Recognition and Step Detection Algorithms for Mobile Phone Users , 2013, Sensors.

[17]  K. Sakamura,et al.  A framework for context-aware power management on embedded devices , 2012, The 1st IEEE Global Conference on Consumer Electronics 2012.

[18]  Tajana Simunic,et al.  Context-Aware Mobile Power Management Using Fuzzy Inference as a Service , 2012, MobiCASE.

[19]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.