TY - GEN
T1 - Generalized decision aggregation in distributed sensing systems
AU - Su, Lu
AU - Li, Qi
AU - Hu, Shaohan
AU - Wang, Shiguang
AU - Gao, Jing
AU - Liu, Hengchang
AU - Abdelzaher, Tarek F.
AU - Han, Jiawei
AU - Liu, Xue
AU - Gao, Yan
AU - Kaplan, Lance
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2015/1/14
Y1 - 2015/1/14
N2 - In this paper, we present GDA, a generalized decision aggregation framework that integrates information from distributed sensor nodes for decision making in a resource efficient manner. Traditional approaches that target similar problems only take as input the discrete label information from individual sensors that observe the same events. Different from them, our proposed GDA framework is able to take advantage of the confidence information of each sensor about its decision, and thus achieves higher decision accuracy. Targeting generalized problem domains, our framework can naturally handle the scenarios where different sensor nodes observe different sets of events whose numbers of possible classes may also be different. GDA also makes no assumption about the availability level of ground truth label information, while being able to take advantage of any if present. For these reasons, our approach can be applied to a much broader spectrum of sensing scenarios. The advantages of our proposed framework are demonstrated through both theoretic analysis and extensive experiments.
AB - In this paper, we present GDA, a generalized decision aggregation framework that integrates information from distributed sensor nodes for decision making in a resource efficient manner. Traditional approaches that target similar problems only take as input the discrete label information from individual sensors that observe the same events. Different from them, our proposed GDA framework is able to take advantage of the confidence information of each sensor about its decision, and thus achieves higher decision accuracy. Targeting generalized problem domains, our framework can naturally handle the scenarios where different sensor nodes observe different sets of events whose numbers of possible classes may also be different. GDA also makes no assumption about the availability level of ground truth label information, while being able to take advantage of any if present. For these reasons, our approach can be applied to a much broader spectrum of sensing scenarios. The advantages of our proposed framework are demonstrated through both theoretic analysis and extensive experiments.
KW - Crowd Sensing
KW - Decision Aggregation
KW - Distributed Sensing System
KW - Participatory Sensing
KW - Social Sensing
UR - http://www.scopus.com/inward/record.url?scp=84936948171&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84936948171&partnerID=8YFLogxK
U2 - 10.1109/RTSS.2014.40
DO - 10.1109/RTSS.2014.40
M3 - Conference contribution
AN - SCOPUS:84936948171
T3 - Proceedings - Real-Time Systems Symposium
SP - 1
EP - 10
BT - Proceedings - IEEE 35th Real-Time Systems Symposium, RTSS 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 35th IEEE Real-Time Systems Symposium, RTSS 2014
Y2 - 2 December 2014 through 5 December 2014
ER -