A novel data fusion scheme using grey model and extreme learning machine in wireless sensor networks

详细信息    查看全文

• 作者：Xiong Luo ; Xiaohui Chang
• 关键词：Data fusion ; extreme learning machine ; grey model ; wireless sensor networks
• 刊名：International Journal of Control, Automation and Systems
• 出版年：2015
• 出版时间：June 2015
• 年：2015
• 卷：13
• 期：3
• 页码：539-546
• 全文大小：835 KB
• 参考文献：[1]R. Tan, G. Xing, B. Liu, J. Wang, and X. Jia, 鈥淓xploiting data fusion to improve the coverage of wireless sensor networks,鈥?IEEE/ACM Trans. on Networking, vol. 20, no. 2, pp. 450鈥?62, April 2012.View Article
  [2]P. Ji, C. Wu, Y. Zhang, and F. Chen, 鈥淎 lowenergy adaptive clustering routing protocol of wireless sensor networks,鈥?Proc. of the 7th Conf. Wireless Communications, Networking and Mobile Computing, pp. 1鈥?, 2011.
  [3]M. Li, Z. Li, and A. V. Vasilakos, 鈥淎 survey on topology control in wireless sensor networks: taxonomy, comparative study, and open issues,鈥?Proceedings of the IEEE, vol. 101, no. 12, pp. 2538鈥?557, December 2013.View Article
  [4]W. Zhou, C. Ji, J. Mou, D. Tong, and Y. Gao, 鈥淎daptive target synchronization for wireless sensor networks with Markov delays and noise perturbation,鈥?International Journal of Control, Automation, and Systems, vol. 11, no. 5, pp. 919鈥?25, October 2013.View Article
  [5]C. H. Yu and J. W. Choi, 鈥淚nteracting multiple model filter-based distributed target tracking algorithm in underwater wireless sensor networks,鈥?International Journal of Control, Automation, and Systems, vol.12, no. 3, pp. 618鈥?27, June 2014.View Article
  [6]G. Anastasi, M. Conti, M. Di Francesco, and A. Passarella, 鈥淓nergy conservation in wireless sensor networks: a survey,鈥?Ad Hoc Networks, vol. 7, no. 3, pp. 537鈥?68, May 2009.View Article
  [7]E. F. Nakamura, A. A. F. Loureiro, and A. C. Frery, 鈥淚nformation fusion for wireless sensor networks: Methods, models, and classifications,鈥?ACM Computing Surveys, vol. 39, no. 3, Article 9, September 2007.
  [8]D. Chu, A. Deshpande, J. M. Hellerstein, and W. Hong, 鈥淎pproximate data collection in sensor networks using probabilistic models,鈥?Proc. of the 22nd International Conf. on Data Engineering, pp. 48鈥?0, 2006.
  [9]A. Hui and L. Cui, 鈥淔orecast-based temporal data aggregation in wireless sensor networks,鈥?Computer Engineering and Applications, vol. 43, no. 21, pp.121鈥?25, July 2007.
  [10]G. Wei, Y. Ling, B. Guo, B Xiao, and A. V. Vasilakos, 鈥淧rediction-based data aggregation in wireless sensor networks: combining grey model and Kalman Filter,鈥?Computer Communications, vol. 34, no. 6, p- p. 793鈥?02, May 2011.View Article
  [11]R. Wang, J. Tang, D. Wu, and Q. Sun, 鈥淕MLSSVM based data aggregation in WSN,鈥?Computer Engineering and Design, vol. 33, no. 9, pp. 3371鈥?375, September 2012.
  [12]S. Zheng, W. Z. Shi, J. Liu, and J. Tian, 鈥淩emote sensing image fusion using multiscale mapped LSSVM,鈥?IEEE Trans. on Geoscience and Remote Sensing, vol. 46, no. 5, pp. 1313鈥?322, May 2008.View Article
  [13]Y. Miche, A. Sorjamaa, P. Bas, O. Simula, C. Jutten, and A. Lendasse, 鈥淥P-ELM: optimally pruned extreme learning machine,鈥?IEEE Trans. on Neural Networks, vol. 21, no. 1, pp. 158鈥?62, January 2010.View Article
  [14]F. M. Tseng, H. C. Yu, and G. H. Tzeng, 鈥淎pplied hybrid grey model to forecast seasonal time series,鈥?Technological Forecasting and Social Change, vol. 67, no. 2, pp. 291鈥?02, June/July 2001.View Article
  [15]E. Kayacan, B. Ulutas, and O. Kaynak, 鈥淕rey system theory-based models in time series prediction,鈥?Expert Systems with Applications, vol. 37, no. 2, pp. 1784鈥?789, March 2010.View Article
  [16]Z. Zhao, J. Wang, J. Zhao, and Z. Su, 鈥淯sing a grey model optimized by differential evolution algorithm to forecast the per capita annual net income of rural households in China,鈥?Omega, vol. 40, no. 5, pp.525鈥?32, October 2012.View Article
  [17]Y. S. Lee and L. I. Tong, 鈥淔orecasting nonlinear time series of energy consumption using a hybrid dynamic model,鈥?Applied Energy, vol. 94, pp. 251鈥?56, June 2012.View Article
  [18]P. Horata, S. Chiewchanwattana, and K. Sunat, 鈥淩obust extreme learning machine,鈥?Neurocomputing, vol. 102, pp. 31鈥?4, February 2013.View Article
  [19]G. B. Huang, D. H. Wang, and Y. Lan, 鈥淓xtreme learning machines: a survey,鈥?International Journal of Machine Learning and Cybernetics, vol. 2, no. 2, pp. 107鈥?22, June 2011.View Article
  [20]H. Chen, J. Peng, Y. Zhou, L. Li, and Z. Pan, 鈥淓xtreme learning machine for ranking: generalization analysis and applications,鈥?Neural Networks, vol. 53, pp. 119鈥?26, May 2014.View Article MATH
  [21]X. Luo, X. H. Chang, and H. Liu, 鈥淎 Taylor based localization algorithm for wireless sensor network using extreme learning machine,鈥?IEICE Trans. on Information and Systems, vol. E97D, no. 10, pp. 2652鈥?659, October 2014.View Article
  [22]A. Grigorievskiy, Y. Miche, A. M. Ventel盲, E. S茅verin, and A. Lendasse, 鈥淟ong-term time series prediction using OP-ELM,鈥?Neural Networks, vol.51, pp. 50鈥?6, March 2014.View Article MATH
  [23]LS-SVMlab Toolbox [Online]. Available: http://鈥媤ww.鈥媏sat.鈥媖uleuven.鈥媌e/鈥媠ista/鈥媗ssvmlab/鈥?/span> .
  [24]S. Madden, Intel Berkeley research lab data. Intel Corporation, 2004 [Online]. Available: http://鈥媎b.鈥媍sail.鈥媘it.鈥媏du/鈥媗abdata/鈥媗abdata.鈥媓tml .
  
• 作者单位：Xiong Luo (1) (2)
  Xiaohui Chang (1) (2)
  
  1. School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB), Beijing, 100083, China
  2. Beijing Key Laboratory of Knowledge Engineering for Materials Science, Beijing, 100083, China
  
• 刊物类别：Engineering
• 刊物主题：Control Engineering
  
• 出版者：The Institute of Control, Robotics and Systems Engineers and The Korean Institute of Electrical Engi
• ISSN：2005-4092

文摘

With the increasing presence and adoption of wireless sensor networks (WSNs), the demand of data acquisition and data fusion are becoming stronger and stronger. In WSN, sensor nodes periodically sense data and send them to the sink node. Since the network consists of plenty of low-cost sensor nodes with limited battery power and the sensed data usually are of high temporal redundancy, prediction- based data fusion has been put forward as an important issue to reduce the number of transmissions and save the energy of the sensor nodes. Considering the fact that the sensor node usually has limited capabilities of data processing and storage, a novel prediction-based data fusion scheme using grey model (GM) and optimally pruned extreme learning machine (OP-ELM) is proposed. The proposed data fusion scheme called GM-OP-ELM uses a dual prediction mechanism to keep the prediction data series at the sink node and sensor node synchronous. During the data fusion process, GM is introduced to initially predict the data of next period with a small number of data items, and an OPELM- based single-hidden layer feedforward network (SLFN) is used to make the initial predicted value approximate its true value with extremely fast speed. As a robust and fast neural network learning algorithm, OP-ELM can adaptively adjust the structure of the SLFN. Then, GM-OP-ELM can provide high prediction accuracy, low communication overhead, and good scalability. We evaluate the performance of GM-OP-ELM on three actual data sets that collected from 54 sensors deployed in the Intel Berkeley Research lab. Simulation results have shown that the proposed data fusion scheme can significantly reduce redundant transmissions and extend the lifetime of the whole network with low computational cost.