Open Access Open Access  Restricted Access Subscription Access
Stations’ location map

Estimation method based on deep neural network for consecutively missing sensor data

Feng Liu, Huilin Li, Zhong Yang


The phenomenon of missing sensor data is very common in wireless sensor networks (WSN). It has a dramatic effect on the usability, stability and efficiency of the WSN-based applications. There exist many methods for the missing sensor data estimation. However, the accurate and efficient consequent estimation of missing sensor data remains a challenging problem. To solve this problem, we propose a new method named consecutive sensor data deep neural network (CSDNN). In this method, firstly, we analyze the correlation coefficients among different types of sensor data and choose a certain number of nearest neighbors of the target sensor nodes. Secondly, to estimate a certain type of sensor data from a target sensor node, we utilize the different types of sensor data that are from the same target sensor node and have strong correlation with the missing ones, and the same type of sensor data from the aforementioned nearest neighbors. We treat these data as the input of the deep neural networks (DNN). Thirdly, we construct the DNN model, discuss the optimized DNN structure for the missing data problem, and test the accuracy of CSDNN for different types of environmental sensor data. The results show that the CSDNN method allows to accurately estimate the consecutively missing sensor data.


wireless sensor network; missing sensor data; missing data estimation; deep neural network

Full Text:



BELAKBIR, A.; AMGHAR, M.; SBITI, N. “Sensor data fusion for an indoor and outdoor localization,” Radioelectron. Commun. Syst., v.57, n.4, p.149-158, 2014. DOI:

KAUR, J.; RANDHAWA, S.; JAIN, S. “A novel energy efficient cluster head selection method for wireless sensor networks,” Int. J. Wireless Microwave Technol., v.8, n.2, p.37-51, 2018. DOI:

CHEN, J.; YATSKIV, V.V.; SACHENKO, A.A.; SU, J. “Wireless sensor networks based on modular arithmetic,” Radioelectron. Commun. Syst., v.60, n.5, p.215-224, 2017. DOI:

QUSHTOM, H.; RABAYA, K. “Enhancing the QoS of IoT networks with lightweight security protocol using Contiki OS,” Int. J. Computer Network Inf. Security, v.9, n.11, p.27-35, 2017. DOI:

TOVKACH, I.O.; ZHUK, S.Y. “Adaptive filtration of radio source movement parameters with complex use of sensor network data based on TDOA and RSS methods,” Radioelectron. Commun. Syst., v.60, n.12, p.528-537, 2017. DOI:

MISHRA, N.; SONI, H.K.; SHARMA, S.; UPADHYAY, A.K. “Development and analysis of artificial neural network models for rainfall prediction by using time-series data,” Int. J. Intelligent Systems Appl., v.1, p.16-23, 2018. DOI:

ZHANG, Hongguo; YANG, Liang. “An improved algorithm for missing data in wireless sensor networks,” Proc. of Int. Conf. on Software Intelligence Technologies and Applications & International Conf. on Frontiers of Internet of Things 2014, 4-6 Dec. 2014, Hsinchu, Taiwan. IEEE, 2014, p.346-350. DOI:

PAN, L.; GAO, Huijun; LI, J.; GAO, Hong; GUO, Xintong. “CIAM: An adaptive 2-in-1 missing data estimation algorithm in wireless sensor networks,” Proc. of 2013 19th IEEE Int. Conf. on Networks, ICON, 10-13 Dec. 2013, Singapore. IEEE, 2013, p.1-6. DOI:

ALIPPI, C.; NTALAMPIRAS, S.; ROVERI, M. “Model ensemble for an effective on-line reconstruction of missing data in sensor networks,” Proc. of 2013 Int. Joint Conf. on Neural Networks, IJCNN, 4-9 Aug. 2013, Dallas, TX, USA. IEEE, 2013, p.1-6. DOI:

SATTER, A.; IBTEHAZ, N. “A regression based sensor data prediction technique to analyze data trustworthiness in cyber-physical system,” Int. J. Inf. Eng. Electron. Business, v.3, p.15-22, 2018. DOI:

GRUENWALD, L.; YANG, H.; SADIK, M.S.; SHUKLA, R. “Using data mining to handle missing data in multi-hop sensor network applications,” Proc. of Ninth ACM Int. Workshop on Data Engineering for Wireless and Mobile Access, 6 Jun. 2010, Indianapolis, Indiana. ACM, 2010. DOI:

NIU, K.; ZHAO, F.; QIAO, X. “A missing data imputation algorithm in wireless sensor network based on minimized similarity distortion,” Proc. of 2013 Sixth Int. Symp. on Computational Intelligence and Design, 28-29 Oct. 2013, Hangzhou, China. IEEE, 2013, p.235-238. DOI:

GUO, D.; QU, X.; HUANG, L.; YAO, Y.; LIU, Z.; SUN, M.-T. “Sparsity-based online missing sensor data recovery,” Proc. of 2012 IEEE Int. Symp. on Circuits and Systems, 20-23 May 2012, Seoul, South Korea. IEEE, 2012, p.918-921. DOI:

FEKADE, B.; MAKSYMYUK, T.; KYRYK, M.; JO, M. “Probabilistic recovery of incomplete sensed data in IoT,” IEEE IoT J., v.PP, n.99, p.1, 2017. DOI:

XIE, K.; NING, X.; WANG, X.; XIE, D.; CAO, J.; XIE, G.; WEN, J. “Recover corrupted data in sensor networks: A matrix completion solution,” IEEE Trans. Mobile Computing, v.16, n.5, p.1434-1448, 2017. DOI:

ANAGNOSTOPOULOS, C.; TRIANTAFILLOU, P. “Scaling out big data missing value imputations: pythia vs. godzilla,” Proc. of 20th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 24-27 Aug. 2014, New York, USA. ACM, 2014. DOI:

SCHMIDHUBER, J. “Deep learning in neural networks: An overview,” Neural Networks, v.61, p.85-117, Jan. 2015. DOI:

© Radioelectronics and Communications Systems, 2004–2019
When you copy an active link to the material is required
ISSN 1934-8061 (Online), ISSN 0735-2727 (Print)
tel./fax +38044 204-82-31, 204-90-41