Self-Optimizing IoT Wireless Video Sensor Node With In-Situ Data Analytics and Context-Driven Energy-Aware Real-Time Adaptation

It is well understood that data-acquisition by distributed sensors and subsequent transmission of all the acquired data to the cloud will produce a "data deluge" in next-generation wireless networks leading to immense network congestion, and data back-logs on the server which will prevent...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems. I, Regular papers Regular papers, 2017-09, Vol.64 (9), p.2470-2480
Main Authors: Ningyuan Cao, Bin Nasir, Saad, Shreyas Sen, Raychowdhury, Arijit
Format: Article
Language:English
Subjects:
adaptive radio
Algorithm design and analysis
Ambient intelligence
Amplification
Analytics
Cameras
Cloud computing
Congestion
Data acquisition
Data analysis
Design optimization
Energy consumption
Energy management
Feature extraction
Gain
Hardware
IoT
Microprocessors
Real time
Sensors
Servers
Software radio
video surveillance
Wireless communication
Wireless communications
Wireless networks
Wireless sensor networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is well understood that data-acquisition by distributed sensors and subsequent transmission of all the acquired data to the cloud will produce a "data deluge" in next-generation wireless networks leading to immense network congestion, and data back-logs on the server which will prevent real-time processing and control. This motivates in situ data analytics in energy-constrained wireless sensor nodes that can perform context-aware acquisition and processing of data; and transmit data only when required. This paper presents a camerabased wireless sensor node with a self-optimizing end-to-end computation and communication design, targeted for surveillance applications. We demonstrate support for multiple featureextraction and classification algorithms, tunable processing depth and power amplifier gain. Depending on the amount of information content, accuracy targets and condition of the wireless channel, the system choses the minimum-energy operating-point by dynamically optimizing the amount of processing done on the sensor itself. We demonstrate a complete system with ADI ADSP-BF707 image processor, OV7670 camera sensor, and USRP B200 software defined radio; and achieve 4.3× reduction in energy consumption compared with a baseline design.
ISSN:1549-8328
1558-0806
DOI:10.1109/TCSI.2017.2716358