Data Estimation in Sensor Networks

Data imputation

In wireless sensor networks, sensors typically transmit their data to servers at predefined time intervals. In this environment, data packets are very susceptible to losses, delays, or corruption due to various reasons, such as power outage at the sensor’s node, a higher bit error rate of the wireless radio transmissions compared to the wire communication alternative, an inefficient routing algorithm implemented in the network, or random occurrences of local interferences (e.g., mobile radio devices, microwaves, or broken line-of-sight path). To process queries that need to access the missing data, if repeated requests are sent to sensors asking them to resend the missing information, this would incur power-costly communications as those sensors must be constantly in the listening mode. In addition, it is not guaranteed that those sensors would resend their missing data or would resend them in a timely manner. Alternatively, one might choose to...

Authors and Affiliations

1. School of Computer Science, University of Oklahoma, Norman, OK, USA

   Le Gruenwald

Corresponding author

Correspondence to Le Gruenwald .

Editors and Affiliations

1. Georgia Institute of Technology College of Computing, Atlanta, GA, USA

   Ling Liu

2. University of Waterloo School of Computer Science, Waterloo, ON, Canada

   M. Tamer Özsu

1. School of Computer Science, Univ. of Oklahoma, Norman, OK, USA

   Le Gruenwald

Reprints and permissions

© 2018 Springer Science+Business Media, LLC, part of Springer Nature

Policies and ethics