@inbook {956, title = {Expectation{\textendash}maximisation based distributed estimation in sensor networks}, booktitle = {Data Fusion in Wireless Sensor Networks: A statistical signal processing perspective}, year = {2019}, pages = {201-230}, publisher = {The Institution of Engineering and Technology (IET)}, organization = {The Institution of Engineering and Technology (IET)}, chapter = {9}, address = {London, UK}, abstract = {
Estimating the unknown parameters of a statistical model based on the observations collected by a sensor network is an important problem with application in multiple fields. In this setting, distributed processing, by which computations are carried out within the network in order to avoid raw data transmission to a fusion centre, is a desirable feature resulting in improved robustness and energy savings. In the presence of incomplete data, the expectation-maximisation (EM) algorithm is a popular means to iteratively compute the maximum likelihood (ML) estimate. It has found application in diverse fields such as computational biology, anomaly detection, speech segmentation, reinforcement learning, and motion estimation, among others. In this chapter we will review the formulation of the centralised EM estimation algorithm as a starting point and then discuss distributed versions well suited for implementation in sensor networks. The first class of these distributed versions requires specialised routing through the network in terms of a linear or circular path visiting all nodes, whereas the second class does away with this requirement by using the concept of network consensus to diffuse information through the network. Our focus will be on a relevant sensor network application, in which the parameter of a linear model is to be estimated in the presence of an unknown number of randomly malfunctioning sensors.
}, keywords = {winter, wsn}, isbn = {978-1-78561-584-9}, author = {R. L{\'o}pez-Valcarce and Alba Pag{\`e}s-Zamora} } @conference {960, title = {Low-rank data matrix recovery with missing values and faulty sensors}, booktitle = {European Signal Processing Conference (EUSIPCO)}, year = {2019}, month = {09/2019}, address = {A Coru{\~n}a, Spain}, abstract = {In practice, data gathered by wireless sensor networks often belongs in a low-dimensional subspace, but it can present missing as well as corrupted values due to sensor malfunctioning and/or malicious attacks. We study the problem of Maximum Likelihood estimation of the low-rank factors of the underlying structure in such situation, and develop an Expectation-Maximization algorithm to this purpose, together with an effective initialization scheme. The proposed method outperforms previous schemes based on an initial faulty sensor identification stage, and is competitive in terms of complexity and performance with convex optimization-based matrix completion approaches.
}, keywords = {winter, wsn}, author = {R. L{\'o}pez-Valcarce and Josep Sala} } @article {913, title = {Parameter estimation in wireless sensor networks with faulty transducers: A distributed EM approach}, journal = {Signal Processing}, volume = {144}, year = {2018}, month = {03/2018}, pages = {226-237}, abstract = {We address the problem of distributed estimation of a vector-valued parameter performed by a wireless sensor network in the presence of noisy observations which may be unreliable due to faulty transducers. The proposed distributed estimator is based on the Expectation-Maximization (EM) algorithm and combines consensus and diffusion techniques: a term for information diffusion is gradually turned off, while a term for updated information averaging is turned on so that all nodes in the network approach the same value of the estimate. The proposed method requires only local exchanges of information among network nodes and, in contrast with previous approaches, it does not assume knowledge of the a priori probability of transducer failures or the noise variance. A convergence analysis is provided, showing that the convergent points of the centralized EM iteration are locally asymptotically convergent points of the proposed distributed scheme. Numerical examples show that the distributed algorithm asymptotically attains the performance of the centralized EM method.
}, keywords = {winter, wsn}, doi = {10.1016/j.sigpro.2017.10.012}, url = {https://authors.elsevier.com/a/1W90XbZX4rsob}, author = {Silvana Silva Pereira and R. L{\'o}pez-Valcarce and Alba Pag{\`e}s-Zamora} } @article {871, title = {CDMA-based Acoustic Local Positioning System for Portable Devices with Multipath Cancellation}, journal = {Digital Signal Processing}, volume = {62}, year = {2017}, month = {03/2017}, pages = {38-51}, abstract = {Crowdsourcing approaches rely on the collection of multiple individuals to solve problems that require analysis of large data sets in a timely accurate manner. The inexperience of participants or annotators motivates well robust techniques. Focusing on clustering setups, the data provided by all annotators is suitably modeled here as a mixture of Gaussian components plus a uniformly distributed random variable to capture outliers. The proposed algorithm is based on the expectation-maximization algorithm and allows for soft assignments of data to clusters, to rate annotators according to their performance, and to estimate the number of Gaussian components in the non-Gaussian/Gaussian mixture model, in a jointly manner.
}, keywords = {winter, wsn}, doi = {10.1109/ICASSP.2017.7952910}, author = {Alba Pag{\`e}s-Zamora and Georgios Giannakis and R. L{\'o}pez-Valcarce and Pere Gimenez-Febrer} } @conference {846, title = {Design of data-injection adversarial attacks against spatial field detectors}, booktitle = {IEEE Workshop on Statistical Signal Processing (SSP)}, year = {2016}, month = {06/2016}, address = {Palma de Mallorca, Spain}, abstract = {Data-injection attacks on spatial field detection corrupt a subset of measurements to cause erroneous decisions. We consider a centralized decision scheme exploiting spatial field smoothness to overcome lack of knowledge on system parameters such as noise variance. We obtain closed-form expressions for system performance and investigate strategies for an intruder injecting false data in a fraction of the sensors in order to reduce the probability of detection. The problem of determining the most vulnerable subset of sensors is also analyzed.
}, keywords = {adversarial signal processing, compass, wsn}, author = {R. L{\'o}pez-Valcarce and Daniel Romero} } @conference {845, title = {Distributed multivariate regression with unknown noise covariance in the presence of outliers: a minimum description length approach}, booktitle = {IEEE Workshop on Statistical Signal Processing (SSP)}, year = {2016}, address = {Palma de Mallorca, Spain}, abstract = {We present techniques to improve convergence speed of distributed average consensus algorithms in wireless sensor networks by means of topology design. A broadcast network is assumed, so that only the transmit power of each node can be independently controlled, rather than each individual link. Starting with a maximally connected configuration in which all nodes transmit at full power, the proposed methods successively reduce the transmit power of a chosen node in order to remove one and only one link; nodes are greedily selected either in order to yield fastest convergence at each step, or if they have the largest degree in the network. These greedy schemes provide a good complexity-performance tradeoff with respect to full-blown global search methods. As a side benefit, improving the convergence speed also results in savings in energy consumption with respect to the maximally connected setting.
}, keywords = {compass, wsn}, doi = {10.1016/j.ipl.2014.11.009}, author = {Massimo Vecchio and R. L{\'o}pez-Valcarce} } @article {756, title = {Improving Area Coverage of Wireless Sensor Networks Via Controllable Mobile Nodes: a Greedy Approach}, journal = {Journal of Network and Computer Applications}, volume = {48}, year = {2015}, month = {02/2015}, pages = {1-13}, abstract = {This work proposes a novel method to estimate the Line-of-Sight Time-of-Flights (LOS-TOFs) in a broadband acoustic local positioning system (ALPS) with strong multipath interference. The proposed method is based on the Matching Pursuit channel estimation algorithm that provides a low complexity approximation to the Maximum Likelihood solution for sparse channels. A multichannel version of this algorithm has been implemented to estimate a minimum of three coefficients in the channel responses of a particular ALPS, composed of four beacons that perform the simultaneous emission of BPSK modulated 255-bit Kasami codes. A statistical analysis of performance has been carried out by using a set of test signals synthetically generated to simulate different positions and reflection coefficients of the environment. The results of this analysis show the enhanced capability of the proposed method to estimate the LOS-TOFs under strong multipath interference, with respect to that of a classical system based on correlation + thresholding.
}, keywords = {compass, wsn}, doi = {10.1109/WISP.2015.7139174}, author = {Fernando J. Alvarez and R. L{\'o}pez-Valcarce} } @conference {762, title = {Cooperative compressive power spectrum estimation}, booktitle = {IEEE Sensor Array Multichannel Signal Process. Workshop (SAM)}, year = {2014}, keywords = {cognitive radio, wsn}, author = {Dyonisius D Ariananda and Daniel Romero and Geert Leus} } @conference {731, title = {Distributed Total Least Squares Estimation over Networks}, booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)}, year = {2014}, address = {Florence, Italy}, abstract = {We consider Total Least Squares (TLS) estimation in a network in which each node has access to a subset of equations of an overdetermined linear system. Previous distributed approaches require that the number of equations at each node be larger than the dimension L of the unknown parameter. We present novel distributed TLS estimators which can handle as few as a single equation per node. In the first scheme, the network computes an extended correlation matrix via standard iterative average consensus techniques, and the TLS estimate is extracted afterwards by means of an eigenvalue decomposition (EVD). The second scheme is EVD-free, but requires that a linear system of size L be solved at each iteration by each node. Replacing this step by a single Gauss-Seidel subiteration is shown to be an effective means to reduce computational cost without sacrificing performance.
}, keywords = {dynacs, wsn}, doi = {10.1109/ICASSP.2014.6855074}, author = {R. L{\'o}pez-Valcarce and Silvana Silva Pereira and Alba Pag{\`e}s-Zamora} } @conference {733, title = {How to Implement Doubly-Stochastic Matrices for Consensus-Based Distributed Algorithms}, booktitle = {IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM)}, year = {2014}, address = {A Coru{\~n}a, Spain}, abstract = {We address the problem of distributed estimation of a parameter from a set of noisy observations collected by a sensor network, assuming that some sensors may be subject to data failures and report only noise. In such scenario, simple schemes such as the Best Linear Unbiased Estimator result in an error floor in moderate and high signal-to-noise ratio (SNR), whereas previously proposed methods based on hard decisions on data failure events degrade as the SNR decreases. Aiming at optimal performance within the whole range of SNRs, we adopt a Maximum Likelihood framework based on the Expectation-Maximization (EM) algorithm. The statistical model and the iterative nature of the EM method allow for a diffusion-based distributed implementation, whereby the information propagation is embedded in the iterative update of the parameters. Numerical examples show that the proposed algorithm practically attains the Cramer{\textendash}Rao Lower Bound at all SNR values and compares favorably with other approaches.
}, keywords = {dynacs, wsn}, doi = {10.1109/LSP.2013.2260329}, author = {Silvana Silva Pereira and R. L{\'o}pez-Valcarce and Alba Pag{\`e}s-Zamora} } @article {677, title = {A novel heuristic approach for distance- and connectivity-based multihop node localization in wireless sensor networks}, journal = {Soft Computing}, volume = {17}, year = {2013}, month = {01/2013}, pages = {17-28}, chapter = {17}, keywords = {dynacs, wsn}, doi = {10.1007/s00500-012-0897-2}, author = {Diana Manjarres and Javier Del Ser and Sergio Gil-Lopez and Massimo Vecchio and Itziar Landa-Torres and R. L{\'o}pez-Valcarce} } @article {Vecchio2011, title = {A two-objective evolutionary approach based on topological constraints for node localization in wireless sensor networks}, journal = {Applied Soft Computing}, volume = {12}, year = {2011}, month = {07/2012}, pages = {1891-1901}, abstract = {To know the location of nodes plays an important role in many current and envisioned wireless sensor network applications. In this framework, we consider the problem of estimating the locations of all the nodes of a network, based on noisy distance measurements for those pairs of nodes in range of each other, and on a small fraction of anchor nodes whose actual positions are known a priori. The methods proposed so far in the literature for tackling this non-convex problem do not generally provide accurate estimates. The difficulty of the localization task is exacerbated by the fact that the network is not generally uniquely localizable when its connectivity is not sufficiently high. In order to alleviate this drawback, we propose a two-objective evolutionary algorithm which takes concurrently into account during the evolutionary process both the localization accuracy and certain topological constraints induced by connectivity considerations. The proposed method is tested with different network configurations and sensor setups, and compared in terms of normalized localization error with another metaheuristic approach, namely SAL, based on simulated annealing. The results show that, in all the experiments, our approach achieves considerable accuracies and significantly outperforms SAL, thus manifesting its effectiveness and stability.
}, keywords = {dynacs, Multiobjective evolutionary algorithms, Node localization, Range measurements, Stochastic optimization, wsn}, issn = {1568-4946}, doi = {10.1016/j.asoc.2011.03.012}, author = {Massimo Vecchio and R. L{\'o}pez-Valcarce and Francesco Marcelloni} }