In this paper, a novel mobile agent-based distributed evidential expectation maximization (MADEEM) algorithm is presented for sensor networks. The proposed algorithm is used for probability density function estimation and data clustering in the presence of uncertainties in sensor measurements. It is assumed that the sensor measurements are statistically modeled by a common Gaussian mixture model. The proposed algorithm maximizes a new generalized likelihood criterion in an iterative and distributed manner. For this purpose, mobile agents compute some local sufficient statistics by using local measurements of each sensor node. After the local computations, the global sufficient statistics are updated. At the end of iterations, the parameters of the probability density function are updated by using the global sufficient statistics. The mentioned process will be continued until the convergence criterion is satisfied. Convergence analysis of the proposed algorithm is also presented in this paper. After the convergence analysis, the simulation results show the promising performance of the proposed algorithm. Finally, the last part of the paper is devoted to the concluding remarks.
AggarwalCC (2007) On density based transforms for uncertain data mining. In:IEEE 23rd International Conference on Data Engineering, Istanbul, Turkey, 15–20 April 2007, ICDE 2007. IEEE.
2.
AggarwalCC (2015) Outlier Analysis. Data Mining. Springer, Cham: Springer.
3.
AkyildizIF, et al. (2002) A survey on sensor networks. IEEE Communications Magazine40(8): 102–114.
4.
BiswasPK, et al. (2008) Mobile-agent-based collaborative sensor fusion. Information Fusion9(3): 399–411.
5.
CattivelliFSSayedAH (2010) Diffusion LMS strategies for distributed estimation. IEEE Transactions on Signal Processing58(3): 1035–1048.
6.
ChebbahM, et al. (2015) Combining partially independent belief functions. Decision Support Systems73: 37–46.
7.
ChengG, et al. (2019) Estimation of passenger route choices for urban rail transit system based on automatic fare collection mined data. Transactions of the Institute of Measurement and Control41(11): 3092–3102.
8.
ConstantinopoulosCLikasA (2007) Unsupervised learning of Gaussian mixtures based on variational component splitting. IEEE Transactions on Neural Networks18(3): 745–755.
9.
DedeciusK.SeckárováV (2016) Diffusion estimation of mixture models with local and global parameters. In: IEEE/SP 19th Workshop on Statistical Signal Processing, Palma de Mallorca, 26–29 June 2016. IEEE.
10.
DenoeuxT (2013) Maximum likelihood estimation from uncertain data in the belief function framework. IEEE Transactions on Knowledge and Data Engineering25(1): 119–130.
11.
DimitrakopoulosG, et al. (2013) Proactive, knowledge-based intelligent transportation system based on vehicular sensor networks. IET Intelligent Transport Systems7(4): 454–463.
12.
DuR, et al. (2015) Effective urban traffic monitoring by vehicular sensor networks. IEEE Transactions on Vehicular Technology64(1): 273–286.
13.
FagnaniF, et al. (2014) A distributed classification/estimation algorithm for sensor networks. SIAM Journal on Control and Optimization52(1): 189–218.
14.
FengS, et al. (2019) Three-dimensional robot localization using cameras in wireless multimedia sensor networks. Journal of Network and Computer Applications: 102425.
15.
ForeroPA, et al. (2011) Distributed clustering using wireless sensor networks. IEEE Journal of Selected Topics in Signal Processing5(4): 707–724.
16.
FraysseARodetT (2014) A measure-theoretic variational Bayesian algorithm for large dimensional problems. SIAM Journal on Imaging Sciences7(4): 2591–2622.
17.
FreschiV, et al. (2017) Fast distributed consensus through path averaging on random walks. Wireless Personal Communications96(4): 5865–5879.
18.
GholamiB, et al. (2016) Decentralized approximate Bayesian inference for distributed sensor network. In:Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence and the Twenty-Eighth Innovative Applications of Artificial Intelligence Conference. DOI:10.7282/T7283CN7275TJ.
19.
GomesRD, et al. (2019) Adaptive and beacon-based multi-channel protocol for industrial wireless sensor networks. Journal of Network and Computer Applications132: 22–39.
20.
GrassoR, et al. (2015) Environmental field estimation by consensus based dynamic sensor networks and underwater gliders. In:23rd European Signal Processing Conference (EUSIPCO). IEEE.
21.
GuD (2008) Distributed EM algorithm for Gaussian mixtures in sensor networks. IEEE Transactions on Neural Networks19(7): 1154–1166.
22.
GuessoumZ (2004) Adaptive agents and multiagent systems. IEEE Distributed Systems Online5(7): 1–4.
23.
HaoY-S, et al. (2017) Constrained fuzzy evidential multivariate model identified by EM algorithm: A soft sensor to monitoring imprecise and uncertain process parameters. Soft Computing21(6): 1619–1642.
24.
HeL, et al. (2018) Development and evaluation of a brine mining equipment monitoring and control system using wireless sensor network and fuzzy logic. Transactions of the Institute of Measurement and Control40(6): 2062–2081.
25.
HuaJLiC (2016) Distributed variational bayesian algorithms over sensor networks. IEEE Transactions on Signal Processing64(3): 783–798.
26.
JaakkolaTS (2001) Tutorial on variational approximation methods. Advanced Mean Field Methods: Theory and Practice: 129–159.
27.
KadirSN, et al. (2014) High-dimensional cluster analysis with the masked EM algorithm. Neural Computation26(11): 2379–2394.
28.
KrishnanTMcLachlanG (1997) The EM algorithm and extensions. 2nd. edition. John Wiley & Sons, Inc. Publication, 58–60.
29.
KubjasK, et al. (2015) Fixed points of the EM algorithm and nonnegative rank boundaries. The Annals of Statistics43(1): 422–461.
30.
LeeH, et al. (2017) Gaussian-Based SMOTE Algorithm for Solving Skewed Class Distributions. International Journal of Fuzzy Logic and Intelligent Systems17(4): 229–234.
31.
LiuZ, et al. (2014) Distributed sparse recursive least-squares over networks. IEEE Transactions on Signal Processing62(6): 1386–1395.
32.
MateosG.GiannakisGB (2012) Distributed recursive least-squares: Stability and performance analysis. IEEE Transactions on Signal Processing60(7): 3740–3754.
33.
Mohammad-DjafariA (2015) Variational Bayesian approximation method for classification and clustering with a mixture of student-t model. In: Geometric Science of Information. Volume 9389. Springer International Publishing, pp. 723–731.
34.
MostafaeiHMenthM (2018) Software-defined wireless sensor networks: A survey. Journal of Network and Computer Applications119: 42–56.
35.
NealRMHintonGE (1998) A view of the EM algorithm that justifies incremental, sparse, and other variants. In: Learning in Graphical Models. Volume 89. Dordrecht: Springer, 355–368.
36.
NelloreKHanckeGP (2016) A survey on urban traffic management system using wireless sensor networks. Sensors16(2): 1–25.
37.
NowakRD (2003) Distributed EM algorithms for density estimation and clustering in sensor networks. IEEE Transactions on Signal Processing51(8): 2245–2253.
38.
OracevicA, et al. (2014) Secure target detection and tracking in mission critical wireless sensor networks. In: 2014 International Conference on Anti-counterfeiting, Security, and Identification (ASID), Macao, China, 2014, pp. 1–5. IEEE.
39.
OrdonezCOmiecinskiE (2005) Accelerating EM clustering to find high-quality solutions. Knowledge and Information Systems7(2): 135–157.
40.
QuostBDenoeuxT (2016) Clustering and classification of fuzzy data using the fuzzy EM algorithm. Fuzzy Sets and Systems286(1): 134–156.
41.
SafarinejadianBEstahbanatiME (2016) A novel distributed variational approximation method for density estimation in sensor networks. Measurement89: 78–86.
42.
SafarinejadianBEstahbanatiME (2017) Consensus filter-based distributed variational Bayesian algorithm for flow and speed density prediction with distributed traffic sensors. IEEE Systems Journal11(4): 2939–2948.
43.
SafarinejadianBHasanpourK (2014) Distributed data clustering using mobile agents and EM algorithm. IEEE Systems Journal10(1): 281–289.
44.
SafarinejadianBMozaffariM (2016) Mobile agent based distributed em algorithm for data clustering in sensor networks. Intelligent Automation & Soft Computing22(1): 45–60.
45.
SaihiM, et al. (2018) Hidden Gaussian Markov model for distributed fault detection in wireless sensor networks. Transactions of the Institute of Measurement and Control40(6): 1788–1798.
46.
SrbinovskaM, et al. (2015) Environmental parameters monitoring in precision agriculture using wireless sensor networks. Journal of Cleaner Production88: 297–307.
47.
ThemelisKE, et al. (2014) A variational Bayes framework for sparse adaptive estimation. IEEE Transactions on Signal Processing62(18): 4723–4736.
48.
TitsiasMLázaro-GredillaM (2014) Doubly stochastic variational Bayes for non-conjugate inference. In: Proceedings of the 31st International Conference on Machine Learning, Beijing, China, 2014, volume 32, pp. 1–9.
49.
WangBTitteringtonD (2006) Convergence properties of a general algorithm for calculating variational Bayesian estimates for a normal mixture model. Bayesian Analysis1(3): 625–650.
50.
WangS, et al. (2018) Event-triggered based distributed H∞ consensus filtering for discrete-time delayed systems over lossy sensor network. Transactions of the Institute of Measurement and Control40(9): 2740–2747.
51.
WuXLiF (2013) A method for application reconfiguration in wireless sensor networks. Transactions of the Institute of Measurement and Control35(3): 301–309.
52.
XuY, et al. (2017) A novel twin support-vector machine with pinball loss. IEEE Transactions on Neural Networks and Learning Systems28(2): 359–370.
53.
ZhuP, et al. (2019) Research on early fault warning system of coal mills based on the combination of thermodynamics and data mining. Transactions of the Institute of Measurement and Control42(1): 55–68.
54.
ZhuS, et al. (2015) Averaging based distributed estimation algorithm for sensor networks with quantized and directed communication. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, QLD, Australia, 19–24 April 2015. IEEE.
55.
ZuhraFT, et al. (2017) Routing protocols in wireless body sensor networks: A comprehensive survey. Journal of Network and Computer Applications99: 73–97.
