TY - GEN
T1 - CCS-TA
T2 - 3rd ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2015
AU - Wang, Leye
AU - Zhang, Daqing
AU - Pathak, Animesh
AU - Chen, Chao
AU - Xiong, Haoyi
AU - Yang, Dingqi
AU - Wang, Yasha
N1 - Publisher Copyright:
Copyright © 2015 ACM.
PY - 2015/9/7
Y1 - 2015/9/7
N2 - Data quality and budget are two primary concerns in urban-scale mobile crowdsensing applications. In this paper, we leverage the spatial and temporal correlation among the data sensed in different sub-Areas to significantly reduce the re-quired number of sensing tasks allocated (corresponding to budget), yet ensuring the data quality. Specifically, we propose a novel framework called CCS-TA, combining the state-of-The-Art compressive sensing, Bayesian inference, and active learning techniques, to dynamically select a mini-mum number of sub-Areas for sensing task allocation in each sensing cycle, while deducing the missing data of un-allocated sub-Areas under a probabilistic data accuracy guar-antee. Evaluations on real-life temperature and air qual-ity monitoring datasets show the effectiveness of CCS-TA. In the case of temperature monitoring, CCS-TA allocates 18.0-26.5% fewer tasks than baseline approaches, allocating tasks to only 15.5% of the sub-Areas on average while keeping overall sensing error below 0.25°C in 95% of the cycles.
AB - Data quality and budget are two primary concerns in urban-scale mobile crowdsensing applications. In this paper, we leverage the spatial and temporal correlation among the data sensed in different sub-Areas to significantly reduce the re-quired number of sensing tasks allocated (corresponding to budget), yet ensuring the data quality. Specifically, we propose a novel framework called CCS-TA, combining the state-of-The-Art compressive sensing, Bayesian inference, and active learning techniques, to dynamically select a mini-mum number of sub-Areas for sensing task allocation in each sensing cycle, while deducing the missing data of un-allocated sub-Areas under a probabilistic data accuracy guar-antee. Evaluations on real-life temperature and air qual-ity monitoring datasets show the effectiveness of CCS-TA. In the case of temperature monitoring, CCS-TA allocates 18.0-26.5% fewer tasks than baseline approaches, allocating tasks to only 15.5% of the sub-Areas on average while keeping overall sensing error below 0.25°C in 95% of the cycles.
KW - Crowdsensing
KW - Data Quali
KW - Task Allocation
UR - https://www.scopus.com/pages/publications/84960857721
U2 - 10.1145/2750858.2807513
DO - 10.1145/2750858.2807513
M3 - Conference contribution
AN - SCOPUS:84960857721
T3 - UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing
SP - 683
EP - 694
BT - UbiComp 2015 - Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing
PB - Association for Computing Machinery, Inc
Y2 - 7 September 2015 through 11 September 2015
ER -