Dynamic Field Monitoring Based on Multitask Learning in Sensor Networks

被引:2
作者
Wang, Di [1 ]
Zhang, Xi [1 ]
机构
[1] Peking Univ, Dept Ind Engn & Management, Beijing 100871, Peoples R China
关键词
multitask learning; field monitoring; missing data; cumulative sum (CUSUM) control chart; FRAMEWORK; DISEASE;
D O I
10.3390/s19071533
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Field monitoring serves as an important supervision tool in a variety of engineering domains. An efficient monitoring would trigger an alarm timely once it detects an out-of-control event by learning the state change from the collected sensor data. However, in practice, multiple sensor data may not be gathered appropriately into a database for some unexpected reasons, such as sensor aging, wireless communication failures, and data reading errors, which leads to a large number of missing data as well as inaccurate or delayed detection, and poses a great challenge for field monitoring in sensor networks. This fact motivates us to develop a multitask-learning based field monitoring method in order to achieve an efficient detection when considerable missing data exist during data acquisition. Specifically, we adopt a log likelihood ratio (LR)-based multivariate cumulative sum (MCUSUM) control chart given spatial correlation among neighboring regions within the monitored field. To deal with the missing data problem, we integrate a multitask learning model into the LR-based MCUSUM control chart in the sensor network. Both simulation and real case studies are conducted to validate our proposed approach and the results show that our approach can achieve an accurate and timely detection for an out-of-control state when a large number of missing data exist in the sensor database. Our model provides an effective field monitoring strategy for engineering applications to accurately and timely detect the products with abnormal quality during production and reduce product losses.
引用
收藏
页数:17
相关论文
共 38 条
[1]   Real-Time Estimation of Zero Crossings of Sampled Signals for Timing Using Cubic Spline Interpolation [J].
Aliaga, Ramon J. .
IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2017, 64 (08) :2414-2422
[2]  
[Anonymous], 2009, Introduction to Statistical Quality Control
[3]  
[Anonymous], 2008, P ASS ADV ART INT AA
[4]   Monitoring of fuel oil process of marine diesel engine [J].
Boullosa-Falces, David ;
Larrabe Barrena, Juan Luis ;
Lopez-Arraiza, Alberto ;
Menendez, Jaime ;
Gomez Solaetxe, Miguel Angel .
APPLIED THERMAL ENGINEERING, 2017, 127 :517-526
[5]   Multitask learning [J].
Caruana, R .
MACHINE LEARNING, 1997, 28 (01) :41-75
[6]   A Statistical Transfer Learning Perspective for Modeling Shape Deviations in Additive Manufacturing [J].
Cheng, Longwei ;
Tsung, Fugee ;
Wang, Andi .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2017, 2 (04) :1988-1993
[7]   Channel estimation by modulated Lagrange interpolation [J].
Cheng, Zheng ;
Mark, Jon W. .
SIGNAL PROCESSING, 2010, 90 (09) :2749-2759
[8]   MULTIVARIATE GENERALIZATIONS OF CUMULATIVE SUM QUALITY-CONTROL SCHEMES [J].
CROSIER, RB .
TECHNOMETRICS, 1988, 30 (03) :291-303
[9]   Comparing syndromic surveillance detection methods:: EARS' versus a CUSUM-based methodology [J].
Fricker, Ronald D., Jr. ;
Hegler, Benjamin L. ;
Dunfee, David A. .
STATISTICS IN MEDICINE, 2008, 27 (17) :3407-3429
[10]  
Gonçalves AR, 2017, AAAI CONF ARTIF INTE, P4509