International Journal of Advanced Networking and Applications

Open Access Open Access  Restricted Access Subscription Access

A Distributed Diffusion Kalman Filter in Multi-TaskNetworks.


Affiliations
1 School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
2 School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731., China
3 School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731., China
 

The Distributed Diffusion Kalman Filter (DDKF) algorithm has earned great attention lately and shows an elaborate way to address the issue of distributed optimization over networks. Estimation and tracking of a single state vector collectively by nodes have been the point of focus. However, there are several multi-task-oriented issues where the optimal state vector for each node may not be the same. Thiswork considers sensor networks for distributed multi-task tracking in which individual nodes communicate with their immediate nodes. A diffusion-based distributed multi-task tracking algorithm is developed. This is done by implementing an unsupervised adaptive clustering process, which aids nodes in forming clusters and collaborating on tasks. This gave rise to an effective level of cooperation for improving state vector estimation accuracy, especially in cases where a cluster's background experience is unknown. To demonstrate the efficiency of our algorithm, computer simulations were conducted. Comparison has been carried out for the Diffusion Kalman Filtermulti-task with respect to the Adapt-Then-Combine (ATC) diffusion schemes utilizing both static and adaptive combination weights. Results showed that the ATC diffusion schemes algorithm has great performance with the adaptive combiners as compared to static combiners.

Keywords

Adaptive clustering, Diffusion scheme, Distributed Kalman filtering, Multi-task sensornetworks.
User
Notifications
Font Size

  • D. Ding, Q. L. Han, Z. Wang, and X. Ge, “A Survey on Model-Based Distributed Control and Filtering for Industrial Cyber-Physical Systems,” IEEE Trans. Ind. Informatics, vol. 15, no. 5, pp. 2883–2499, 2019, doi: 10.1109/TII.2019.2905295.

  • S. Aeron, V. Saligrama, and D. A. Castanon, “Efficient sensor management policies for distributed target tracking in multihop sensor networks,” IEEE Trans. Signal Process., vol. 56, no. 6, pp. 2562–2574, 2008, doi: 10.1109/TSP.2007.912891.

  • D. Blatt, A. O. Hero, and H. Gauchman, “A convergent incremental gradient method with a constant step size,” SIAM J. Optim., vol. 18, no. 1, pp. 29–51, 2007.

  • C. G. Lopes and A. H. Sayed, “Incremental adaptive strategies over distributed networks,” IEEE Trans. Signal Process., vol. 55, no. 8, pp. 4064–4067, 2007, doi: 10.1109/TSP.2007.896034.

  • P. Braca, S. Marano, V. Matta, and P. Willett, “Asymptotic optimality of running consensus in testing binary hypotheses,” IEEE Trans. Signal Process., vol. 58, no. 2, pp. 814–825, 2009.

  • A. G. Dimakis, S. Kar, J. M. F. Moura, M. G. Rabbat, and A. Scaglione, “Gossip algorithms for distributed signal processing,” Proc. IEEE, vol. 98, no. 11, pp. 1847–1864, 2010.

  • K. Srivastava and A. Nedic, “Distributed asynchronous constrained stochastic optimization,” IEEEJ. Sel. Top. Signal Process., vol. 5, no. 4, pp. 772–790, 2011.

  • A. H. Sayed, “Diffusion Adaptation Over Networks,”in Academic Press Library in Signal Processing, 2014, pp. 323–453. doi: 10.1016/b978-0-12-411597-2.00009-6.

  • X. Ge, Q.-L. Han, X.-M. Zhang, L. Ding, and F. Yang, “Distributed event-triggered estimation over sensor networks: A survey,” IEEE Trans. Cybern., vol. 50, no. 3, pp. 1306–1320, 2019.

  • F. S. Cattivelli and A. H. Sayed, “Diffusion strategies for distributed Kalman filtering and smoothing,” IEEE Trans. Automat. Contr., vol. 55, no. 9, pp. 2069–2084, 2010.

  • W. Li and Y. Jia, “Distributed Estimation for Markov Jump Systems via Diffusion Strategies,” IEEE Trans. Aerosp. Electron. Syst., vol. 53, no. 1, pp. 448–460, 2017, doi: 10.1109/TAES.2017.2650801.

  • K. Dedecius and P. M. Djurić, “Sequential estimation and diffusion of information over networks: A Bayesian approach with exponential family of distributions,” IEEE Trans. Signal Process., vol. 65, no. 7, pp. 1795–1809, 2016.

  • F. Pang, K. Doğançay, and Q. Zhang, “Distributed detection of Gauss–Markov signals using diffusion Kalman filtering,” Signal Processing, vol. 153, no. 368–378, 2018, doi: 10.1016/j.sigpro.2018.07.020.

  • S. Xie and L. Guo, “Analysis of Distributed Adaptive Filters Based on Diffusion Strategies over Sensor Networks,” IEEE Trans. Automat. Contr., vol. 63, no. 11, p. 3643 3658, 2018, doi: 10.1109/TAC.2018.2799567.

  • Y. Zhang, C. Wang, N. Li, and J. Chambers, “Diffusion Kalman filter based on local estimate exchanges,” Int. Conf. Digit. Signal Process. DSP, vol. 2015-Septe, pp. 828–832, 2015, doi: 10.1109/ICDSP.2015.7251992.

  • Z. Wu, M. Fu, Y. Xu, and R. Lu, “A distributed Kalman filtering algorithm with fast finite-time convergence for sensor networks,” Automatica, vol. 95, pp. 63–72, 2018, doi: 10.1016/j.automatica.2018.05.012.

  • F. Cattivelli and A. H. Sayed, “Diffusion distributed Kalman filtering with adaptive weights,”in Conference Record - Asilomar Conference on Signals, Systems and Computers, 2009, pp. 908– 912. doi: 10.1109/ACSSC.2009.5470006.

  • S. P. Talebi, S. Kanna, Y. Xia, and D. P. Mandic, “Cost-effective diffusion Kalman filtering with implicit measurement exchanges,”in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2017, pp. 4411–4415. doi: 10.1109/ICASSP.2017.7952990.

  • O. Hlinka, O. Sluciak, F. Hlawatsch, and M. Rupp, “Distributed data fusion using iterative covariance intersection,”in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2014, pp. 1861–1865. doi: 10.1109/ICASSP.2014.6853921.

  • G. Wang, N. Li, and Y. Zhang, “Diffusion distributed Kalman filter over sensor networks without exchanging raw measurements,” Signal Processing, vol. 132, pp. 1–7, 2017, doi: 10.1016/j.sigpro.2016.07.033.

  • X. Zhang and Y. Shen, “Distributed kalman filtering based on the non-repeated diffusion strategy,” Sensors (Switzerland), vol. 20, p. 6923, 2020, doi: 10.3390/s20236923.

  • M. Uney, D. E. Clark, and S. J. Julier, “Distributed fusion of PHD filters via exponential mixture densities,” IEEE J. Sel. Top. Signal Process., vol. 7, no. 3, pp. 521–531, 2013, doi: 10.1109/JSTSP.2013.2257162.

  • G. Battistelli, L. Chisci, C. Fantacci, A. Farina, and A. Graziano, “Consensus CPHD filter for distributed multitarget tracking,” IEEE J. Sel. Top. Signal Process., vol. 7, no. 3, pp. 505–520, 2013,doi: 10.1109/JSTSP.2013.2250911.

  • M. R. Leonard and A. M. Zoubir, “Multi-Target tracking in distributed sensor networks using particle PHD filters,” Signal Processing, vol. 159, pp. 130–146, 2019, doi: 10.1016/j.sigpro.2019.01.020.

  • C. Wang, W. P. Tay, Y. Wang, and Y. Wei, “A Privacy-preserving Diffusion Strategy over Multi-task Networks,”in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2019, pp. 7600–7604. doi: 10.1109/ICASSP.2019.8682425.

  • J. Ni, Y. Zhu, and J. Chen, “Multi-task diffusion affine projection sign algorithm and its sparse variant for distributed estimation,” Signal Processing, vol. 172, p. 107561, 2020, doi: 10.1016/j.sigpro.2020.107561.

  • Chen, C. Richard, S. K. Ting, and A. H. Sayed, “Multi-task Learning Over Adaptive Networks With Grouping Strategies,”in Cooperative and Graph Signal Processing: Principles and Applications, Academic Press, 2018, pp. 109–129. doi: 10.1016/B978-0-12-813677-5.00003-1.

  • X. Cao and K. J. R. Liu, “Decentralized Sparse Multi-task RLS Over Networks,” IEEE Trans. Signal Process., vol. 65, no. 23, pp. 6217–6232, 2017, doi: 10.1109/TSP.2017.2750110.

  • J. Liu, M. Chu, and J. E. Reich, “Multitarget tracking in distributed sensor networks,” IEEE Signal Process. Mag., vol. 24, no. 3, pp. 36–46, 2007, doi: 10.1109/MSP.2007.361600.

  • A. H. Sayed, S. Y. Tu, J. Chen, X. Zhao, and Z. Towfic, “Diffusion strategies for adaptation and learning over networks: An examination of distributed strategies and network behavior,” IEEE Signal Process. Mag., vol. 30, no. 3, pp. 155–171, 2013, doi: 10.1109/MSP.2012.2231991.

  • J. Chen, C. Richard, and A. H. Sayed, “Adaptive clustering for multi-task diffusion networks,”in 2015 23rd European Signal Processing Conference, EUSIPCO 2015, 2015, pp. 200–204. doi: 10.1109/EUSIPCO.2015.7362373.

  • J. Chen, C. Richard, and A. H. Sayed, “Multi-task diffusion adaptation over networks,” IEEE Trans. Signal Process., vol. 62, no. 16, pp. 4129–4144, 2014, doi: 10.1109/TSP.2014.2333560.

  • R. Nassif, S. Vlaski, C. Richard, J. Chen, and A. H. Sayed, “Multi-task learning over graphs: An approach for distributed, streaming machine learning,” IEEE Signal Process. Mag., vol. 37, no. 3, pp. 14–25, 2020.

  • D. Ramesh and G. S. Biradar, “Secured Dynamic Clustering using Light Weighted Key Authentication for Target Tracking in WSN,” Int. J. Adv. Netw. Appl., vol. 10, no. 2, pp. 3794– 3799, 2018

  • J. Chen, C. Richard, and A. H. Sayed, “Diffusion LMS over multi-task networks,” IEEE Trans. Signal Process., vol. 63, no. 11, pp. 2733–2748, 2015.

  • C. A. Ijeoma, M. A. Hossin, H. A. Bemnet, A. A. Tesfaye, A. H. Hailu, and C. N. Chiamaka, “Exploration of Diffusion LMS Over Static and Adaptive Combination Policy,”in 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), 2020, pp. 424–427 doi:10.1109/ICCWAMTIP51612.2020.9317326.

  • X. Zhao and A. H. Sayed, “Performance limits for distributed estimation over LMS adaptive networks,” IEEE Trans. Signal Process., vol. 60, no. 10, pp. 5107–5124, 2012, doi: 10.1109/TSP.2012.2204985.

  • V. D. Blondel, J. M. Hendrickx, A. Olshevsky, and J. N. Tsitsiklis, “Convergence in multiagent coordination, consensus, and flocking,”in Proceedings of the 44th IEEE Conference on Decision and Control, and the European Control Conference, CDC-ECC ’05, 2005, pp. 2996–3000. doi: 10.1109/CDC.2005.1582620.

  • S. Yang, T. Huang, J. Guan, Y. Xiong, and M. Wang, “Diffusion Strategies for Distributed Kalman Filter with Dynamic Topologies in Virtualized Sensor Networks,” Mob. Inf. Syst., vol. 2016, 2016, doi: 10.1155/2016/8695102.

  • F. S. Cattivelli, C. G. Lopes, and A. H. Sayed, “Diffusion recursive least-squares for distributed estimation over adaptive networks,” IEEE Trans. Signal Process., vol. 56, no. 5, pp. 1865–1877, 2008, doi: 10.1109/TSP.2007.913164.

  • F. S. Cattivelli and A. H. Sayed, “Diffusion LMS strategies for distributed estimation,” IEEE Trans. Signal Process., vol. 58, no. 3, pp. 1035–1048, 2009, doi: 10.1109/TSP.2009.2033729.

  • S. Y. Tu and A. H. Sayed, “Optimal combination rules for adaptation and learning over networks,”in 2011 4th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2011, 2011, pp. 317–320. doi: 10.1109/CAMSAP.2011.6136014.

  • K. T. Wagner and M. I. Doroslovački, “Combination coefficients for fastest convergence of distributed LMS estimation,”in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2014, pp. 7218– 7222. doi: 10.1109/ICASSP.2014.6855001.

  • J. Fernandez-Bes, J. Arenas-García, M. T. M. Silva, and L. A. Azpicueta-Ruiz, “Adaptive diffusion schemes for heterogeneous networks,” IEEE Trans. Signal Process., vol. 65, no. 21, pp. 5661–5674, 2017, doi: 10.1109/TSP.2017.2740199.

  • J. Wang, F. Dai, J. Yang, and G. Gui, “Efficient combination policies for diffusion adaptive networks,” Peer-to-Peer Netw. Appl., vol. 13, no. 1, pp. 123–126, 2020, doi: 10.1007/s12083-019-00726-2.


Abstract Views: 214

PDF Views: 0




  • A Distributed Diffusion Kalman Filter in Multi-TaskNetworks.

Abstract Views: 214  |  PDF Views: 0

Authors

Ijeoma Amuche Chikwendu
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
KulevomeDelanyoKwameBensah
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731., China
ChiagoziemChimaUkwuoma
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731., China
Chukwuebuka Joseph Ejiyi
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731., China

Abstract


The Distributed Diffusion Kalman Filter (DDKF) algorithm has earned great attention lately and shows an elaborate way to address the issue of distributed optimization over networks. Estimation and tracking of a single state vector collectively by nodes have been the point of focus. However, there are several multi-task-oriented issues where the optimal state vector for each node may not be the same. Thiswork considers sensor networks for distributed multi-task tracking in which individual nodes communicate with their immediate nodes. A diffusion-based distributed multi-task tracking algorithm is developed. This is done by implementing an unsupervised adaptive clustering process, which aids nodes in forming clusters and collaborating on tasks. This gave rise to an effective level of cooperation for improving state vector estimation accuracy, especially in cases where a cluster's background experience is unknown. To demonstrate the efficiency of our algorithm, computer simulations were conducted. Comparison has been carried out for the Diffusion Kalman Filtermulti-task with respect to the Adapt-Then-Combine (ATC) diffusion schemes utilizing both static and adaptive combination weights. Results showed that the ATC diffusion schemes algorithm has great performance with the adaptive combiners as compared to static combiners.

Keywords


Adaptive clustering, Diffusion scheme, Distributed Kalman filtering, Multi-task sensornetworks.

References