A Real-World Event Search System in Sensor Network Environments

2006 ◽  
Author(s):  
T. Okadome ◽  
T. Hattori ◽  
K. Hiramatsu ◽  
Y. Yanagisawa
Keyword(s):  
Sensor Network ◽  
Real World ◽  
Search System ◽  
Network Environments

Real-World Sensor Network for Long-Term Volcano Monitoring: Design and Findings

2012 ◽  
Vol 23 (2) ◽  
pp. 321-329 ◽  
Author(s):  
Renjie Huang ◽  
Wen-Zhan Song ◽  
Mingsen Xu ◽  
Nina Peterson ◽  
Behrooz Shirazi ◽  
...  
Keyword(s):  
Sensor Network ◽  
Real World ◽  
Volcano Monitoring ◽  
Monitoring Design

scholarly journals Wireless Sensor Network Operating System Design Rules Based on Real-World Deployment Survey

2013 ◽  
Vol 2 (3) ◽  
pp. 509-556 ◽  
Author(s):  
Girts Strazdins ◽  
Atis Elsts ◽  
Krisjanis Nesenbergs ◽  
Leo Selavo
Keyword(s):  
Operating System ◽  
Wireless Sensor Network ◽  
System Design ◽  
Sensor Network ◽  
Real World ◽  
Wireless Sensor ◽  
Design Rules ◽  
Operating System Design

scholarly journals Mobile sensor network noise reduction and re-calibration using Bayesian network

2015 ◽  
Vol 8 (8) ◽  
pp. 8971-9008 ◽  
Author(s):  
Y. Xiang ◽  
Y. Tang ◽  
W. Zhu
Keyword(s):  
Bayesian Network ◽  
Sensor Network ◽  
Real World ◽  
Bayesian Belief Network ◽  
Sensor Calibration ◽  
Mobile Sensor ◽  
Real World Data ◽  
Mobile Sensor Network ◽  
Belief Network ◽  
The Real

Abstract. People are becoming increasingly interested in mobile air quality sensor network applications. By eliminating the inaccuracies caused by spatial and temporal heterogeneity of pollutant distributions, this method shows great potentials in atmosphere researches. However, such system usually suffers from the problem of sensor noises and drift. For the sensing systems to operate stably and reliably in the real-world applications, those problems must be addressed. In this work, we exploit the correlation of different types of sensors caused by cross sensitivity to help identify and correct the outlier readings. By employing a Bayesian network based system, we are able to recover the erroneous readings and re-calibrate the drifted sensors simultaneously. Specifically, we have (1) designed a Bayesian belief network based system to detect and recover the abnormal readings; (2) developed methods to update the sensor calibration functions in-field without requirement of ground truth; and (3) deployed a real-world mobile sensor network using the custom-built M-Pods to verify our assumptions and technique. Compared with the existing Bayesian belief network technique, the experiment results on the real-world data demonstrate that our system can reduce error by 34.1 % and recover 4 times more data on average.

scholarly journals Mobile sensor network noise reduction and recalibration using a Bayesian network

2016 ◽  
Vol 9 (2) ◽  
pp. 347-357 ◽  
Author(s):  
Y. Xiang ◽  
Y. Tang ◽  
W. Zhu
Keyword(s):  
Air Quality ◽  
Bayesian Network ◽  
Sensor Network ◽  
Real World ◽  
Low Cost ◽  
Ground Truth ◽  
Bayesian Belief Network ◽  
Sensor Calibration ◽  
Belief Network ◽  
Network Applications

Abstract. People are becoming increasingly interested in mobile air quality sensor network applications. By eliminating the inaccuracies caused by spatial and temporal heterogeneity of pollutant distributions, this method shows great potential for atmospheric research. However, systems based on low-cost air quality sensors often suffer from sensor noise and drift. For the sensing systems to operate stably and reliably in real-world applications, those problems must be addressed. In this work, we exploit the correlation of different types of sensors caused by cross sensitivity to help identify and correct the outlier readings. By employing a Bayesian network based system, we are able to recover the erroneous readings and recalibrate the drifted sensors simultaneously. Our method improves upon the state-of-art Bayesian belief network techniques by incorporating the virtual evidence and adjusting the sensor calibration functions recursively.Specifically, we have (1) designed a system based on the Bayesian belief network to detect and recover the abnormal readings, (2) developed methods to update the sensor calibration functions infield without requirement of ground truth, and (3) extended the Bayesian network with virtual evidence for infield sensor recalibration. To validate our technique, we have tested our technique with metal oxide sensors measuring NO2, CO, and O3 in a real-world deployment. Compared with the existing Bayesian belief network techniques, results based on our experiment setup demonstrate that our system can reduce error by 34.1 % and recover 4 times more data on average.

Sign in / Sign up

Export Citation Format

Share Document