@article{Vazquez-Vilar2016,

title = {Bayesian M-Ary Hypothesis Testing: The Meta-Converse and Verd\'{u}-Han Bounds Are Tight},

author = {Gonzalo Vazquez-Vilar and Adria Tauste Campo and Albert Guillen i Fabregas and Alfonso Martinez},

url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7434042},

doi = {10.1109/TIT.2016.2542080},

issn = {0018-9448},

year  = {2016},

date = {2016-05-01},

journal = {IEEE Transactions on Information Theory},

volume = {62},

number = {5},

pages = {2324--2333},

abstract = {Two alternative exact characterizations of the minimum error probability of Bayesian M-ary hypothesis testing are derived. The first expression corresponds to the error probability of an induced binary hypothesis test and implies the tightness of the meta-converse bound by Polyanskiy et al.; the second expression is a function of an information-spectrum measure and implies the tightness of a generalized Verd\'{u}-Han lower bound. The formulas characterize the minimum error probability of several problems in information theory and help to identify the steps where existing converse bounds are loose.},

keywords = {Bayes methods, Channel Coding, Electronic mail, error probability, Journal, Random variables, Testing},

pubstate = {published},

tppubtype = {article}

}

@article{Miguez2016,

title = {A Proof of Uniform Convergence Over Time for a Distributed Particle Filter},

author = {Joaqu\'{i}n M\'{i}guez and Manuel A V\'{a}zquez},

url = {http://www.sciencedirect.com/science/article/pii/S0165168415004077},

doi = {10.1016/j.sigpro.2015.11.015},

issn = {01651684},

year  = {2016},

date = {2016-05-01},

journal = {Signal Processing},

volume = {122},

pages = {152--163},

abstract = {Distributed signal processing algorithms have become a hot topic during the past years. One class of algorithms that have received special attention are particles filters (PFs). However, most distributed PFs involve various heuristic or simplifying approximations and, as a consequence, classical convergence theorems for standard PFs do not hold for their distributed counterparts. In this paper, we analyze a distributed PF based on the non-proportional weight-allocation scheme of Bolic et al (2005) and prove rigorously that, under certain stability assumptions, its asymptotic convergence is guaranteed uniformly over time, in such a way that approximation errors can be kept bounded with a fixed computational budget. To illustrate the theoretical findings, we carry out computer simulations for a target tracking problem. The numerical results show that the distributed PF has a negligible performance loss (compared to a centralized filter) for this problem and enable us to empirically validate the key assumptions of the analysis.},

keywords = {Convergence analysis, Distributed algorithms, Journal, Parallelization, Particle filtering, Wireless Sensor Networks},

pubstate = {published},

tppubtype = {article}

}

@article{Koblents2016,

title = {A Nonlinear Population Monte Carlo Scheme for the Bayesian Estimation of Parameters of α-stable Distributions},

author = {Eugenia Koblents and Joaqu\'{i}n M\'{i}guez and Marco A Rodr\'{i}guez and Alexandra M Schmidt},

url = {http://www.sciencedirect.com/science/article/pii/S0167947315002340},

doi = {10.1016/j.csda.2015.09.007},

issn = {01679473},

year  = {2016},

date = {2016-03-01},

journal = {Computational Statistics \& Data Analysis},

volume = {95},

pages = {57--74},

abstract = {The class of $alpha$-stable distributions enjoys multiple practical applications in signal processing, finance, biology and other areas because it allows to describe interesting and complex data patterns, such as asymmetry or heavy tails, in contrast with the simpler and widely used Gaussian distribution. The density associated with a general $alpha$-stable distribution cannot be obtained in closed form, which hinders the process of estimating its parameters. A nonlinear population Monte Carlo (NPMC) scheme is applied in order to approximate the posterior probability distribution of the parameters of an $alpha$-stable random variable given a set of random realizations of the latter. The approximate posterior distribution is computed by way of an iterative algorithm and it consists of a collection of samples in the parameter space with associated nonlinearly-transformed importance weights. A numerical comparison of the main existing methods to estimate the $alpha$-stable parameters is provided, including the traditional frequentist techniques as well as a Markov chain Monte Carlo (MCMC) and a likelihood-free Bayesian approach. It is shown by means of computer simulations that the NPMC method outperforms the existing techniques in terms of parameter estimation error and failure rate for the whole range of values of $alpha$, including the smaller values for which most existing methods fail to work properly. Furthermore, it is shown that accurate parameter estimates can often be computed based on a low number of observations. Additionally, numerical results based on a set of real fish displacement data are provided.},

keywords = {Animal movement, Bayesian inference, Importance sampling, L{\'{e}}vy process, α-stable distributions},

pubstate = {published},

tppubtype = {article}

}

@article{Martin-Fernandez2015b,

title = {A Bayesian Method for Model Selection in Environmental Noise Prediction},

author = {L Mart\'{i}n-Fern\'{a}ndez and D P Ruiz and A J Torija and Joaquin Miguez},

url = {http://www.researchgate.net/publication/268213140_A_Bayesian_method_for_model_selection_in_environmental_noise_prediction},

issn = {1726-2135},

year  = {2016},

date = {2016-03-01},

journal = {Journal of Environmental Informatics},

volume = {27},

number = {1},

pages = {31--42},

abstract = {Environmental noise prediction and modeling are key factors for addressing a proper planning and management of urban sound environments. In this paper we propose a maximum a posteriori (MAP) method to compare nonlinear state-space models that describe the problem of predicting environmental sound levels. The numerical implementation of this method is based on particle filtering and we use a Markov chain Monte Carlo technique to improve the resampling step. In order to demonstrate the validity of the proposed approach for this particular problem, we have conducted a set of experiments where two prediction models are quantitatively compared using real noise measurement data collected in different urban areas.},

keywords = {Journal},

pubstate = {published},

tppubtype = {article}

}

@article{Martino2016a,

title = {Layered adaptive importance sampling},

author = {Luca Martino and Victor Elvira and David Luengo and Jukka Corander},

url = {http://link.springer.com/10.1007/s11222-016-9642-5},

doi = {10.1007/s11222-016-9642-5},

issn = {0960-3174},

year  = {2016},

date = {2016-03-01},

journal = {Statistics and Computing},

pages = {1--25},

publisher = {Springer US},

abstract = {Monte Carlo methods represent the de facto standard for approximating complicated integrals involving multidimensional target distributions. In order to generate random realizations from the target distribution, Monte Carlo techniques use simpler proposal probability densities to draw candidate samples. The performance of any such method is strictly related to the specification of the proposal distribution, such that unfortunate choices easily wreak havoc on the resulting estimators. In this work, we introduce a layered (i.e., hierarchical) procedure to generate samples employed within a Monte Carlo scheme. This approach ensures that an appropriate equivalent proposal density is always obtained automatically (thus eliminating the risk of a catastrophic performance), although at the expense of a moderate increase in the complexity. Furthermore, we provide a general unified importance sampling (IS) framework, where multiple proposal densities are employed and several IS schemes are introduced by applying the so-called deterministic mixture approach. Finally, given these schemes, we also propose a novel class of adaptive importance samplers using a population of proposals, where the adaptation is driven by independent parallel or interacting Markov chain Monte Carlo (MCMC) chains. The resulting algorithms efficiently combine the benefits of both IS and MCMC methods.},

keywords = {Bayesian inference Adaptive importance sampling Po, Journal},

pubstate = {published},

tppubtype = {article}

}

@article{Stinner2016,

title = {On the Waterfall Performance of Finite-Length SC-LDPC Codes Constructed From Protographs},

author = {Markus Stinner and Pablo M Olmos},

url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7339427},

doi = {10.1109/JSAC.2015.2504279},

issn = {0733-8716},

year  = {2016},

date = {2016-02-01},

journal = {IEEE Journal on Selected Areas in Communications},

volume = {34},

number = {2},

pages = {345--361},

abstract = {An analysis of spatially coupled low-density parity-check (SC-LDPC) codes constructed from protographs is proposed. Given the protograph used to generate the SC-LDPC code ensemble, a set of scaling parameters to characterize the average finite-length performance in the waterfall region is computed. The error performance of structured SC-LDPC code ensembles is shown to follow a scaling law similar to that of unstructured randomly constructed SC-LDPC codes. Under a finite-length perspective, some of the most relevant SC-LDPC protograph structures proposed to date are compared. The analysis reveals significant differences in their finite-length scaling behavior, which is corroborated by simulation. Spatially coupled repeat-accumulate codes present excellent finite-length performance, as they outperform in the waterfall region SC-LDPC codes of the same rate and better asymptotic thresholds.},

keywords = {Analytical models, capacity-achieving codes, Complexity theory, Couplings, Decoding, Encoding, finite-length analysis, Iterative decoding, Low-density parity-check (LDPC) codes, spatially coupled LDPC codes constructed from prot},

pubstate = {published},

tppubtype = {article}

}

@article{Valera2016ab,

title = {Infinite Continuous Feature Model for Psychiatric Comorbidity Analysis.},

author = {Isabel Valera and Francisco J R Ruiz and Pablo M Olmos and Carlos Blanco and Fernando Perez-Cruz},

url = {http://www.ncbi.nlm.nih.gov/pubmed/26654208},

doi = {10.1162/NECO_a_00805},

issn = {1530-888X},

year  = {2016},

date = {2016-02-01},

journal = {Neural computation},

volume = {28},

number = {2},

pages = {354--381},

abstract = {We aim at finding the comorbidity patterns of substance abuse, mood and personality disorders using the diagnoses from the National Epidemiologic Survey on Alcohol and Related Conditions database. To this end, we propose a novel Bayesian nonparametric latent feature model for categorical observations, based on the Indian buffet process, in which the latent variables can take values between 0 and 1. The proposed model has several interesting features for modeling psychiatric disorders. First, the latent features might be off, which allows distinguishing between the subjects who suffer a condition and those who do not. Second, the active latent features take positive values, which allows modeling the extent to which the patient has that condition. We also develop a new Markov chain Monte Carlo inference algorithm for our model that makes use of a nested expectation propagation procedure.},

keywords = {Journal},

pubstate = {published},

tppubtype = {article}

}

@article{Durisi2016b,

title = {Short-Packet Communications Over Multiple-Antenna Rayleigh-Fading Channels},

author = {Giuseppe Durisi and Tobias Koch and Johan Ostman and Yury Polyanskiy and Wei Yang},

url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7362178},

doi = {10.1109/TCOMM.2015.2511087},

issn = {0090-6778},

year  = {2016},

date = {2016-02-01},

journal = {IEEE Transactions on Communications},

volume = {64},

number = {2},

pages = {618--629},

publisher = {IEEE},

abstract = {Motivated by the current interest in ultra-reliable, low-latency, machine-type communication systems, we investigate the tradeoff between reliability, throughput, and latency in the transmission of information over multiple-antenna Rayleigh block-fading channels. Specifically, we obtain finite-blocklength, finite-SNR upper and lower bounds on the maximum coding rate achievable over such channels for a given constraint on the packet error probability. Numerical evidence suggests that our bounds delimit tightly the maximum coding rate already for short blocklengths (packets of about 100 symbols). Furthermore, our bounds reveal the existence of a tradeoff between the rate gain obtainable by spreading each codeword over all available time-frequency-spatial degrees of freedom, and the rate loss caused by the need of estimating the fading coefficients over these degrees of freedom. In particular, our bounds allow us to determine the optimal number of transmit antennas and the optimal number of time-frequency diversity branches that maximize the rate. Finally, we show that infinite-blocklength performance metrics such as the ergodic capacity and the outage capacity yield inaccurate throughput estimates},

keywords = {diversity branches, Encoding, ergodic capacity, Fading, fading channels, finite-blocklength information theory, finiteblocklength information theory, infinite-blocklength performance metrics, Journal, machine-type communication systems, maximum coding rate, Mission critical systems, mission-critical machine-type communications, multiple antennas, multiple-antenna Rayleigh block-fading channels, Multiplexing, optimal number, outage capacity, rate gain, Rayleigh channels, Receivers, Reliability, short-packet communications, spatial multiplexing, Throughput, Time-frequency analysis, time-frequency-spatial degrees of freedom, transmit antennas, transmit diversity, Transmitting antennas, Ultra-reliable low-latency communications},

pubstate = {published},

tppubtype = {article}

}

@article{Valera2016c,

title = {Infinite Factorial Unbounded-State Hidden Markov Model},

author = {Isabel Valera and Francisco J R Ruiz and Fernando Perez-Cruz},

url = {http://www.ncbi.nlm.nih.gov/pubmed/26571511 http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true\&arnumber=7322279},

doi = {10.1109/TPAMI.2015.2498931},

issn = {1939-3539},

year  = {2016},

date = {2016-01-01},

journal = {IEEE transactions on pattern analysis and machine intelligence},

volume = {To appear},

number = {99},

pages = {1},

abstract = {There are many scenarios in artificial intelligence, signal processing or medicine, in which a temporal sequence consists of several unknown overlapping independent causes, and we are interested in accurately recovering those canonical causes. Factorial hidden Markov models (FHMMs) present the versatility to provide a good fit to these scenarios. However, in some scenarios, the number of causes or the number of states of the FHMM cannot be known or limited a priori. In this paper, we propose an infinite factorial unbounded-state hidden Markov model (IFUHMM), in which the number of parallel hidden Markov models (HMMs) and states in each HMM are potentially unbounded. We rely on a Bayesian nonparametric (BNP) prior over integer-valued matrices, in which the columns represent the Markov chains, the rows the time indexes, and the integers the state for each chain and time instant. First, we extend the existent infinite factorial binary-state HMM to allow for any number of states. Then, we modify this model to allow for an unbounded number of states and derive an MCMC-based inference algorithm that properly deals with the trade-off between the unbounded number of states and chains. We illustrate the performance of our proposed models in the power disaggregation problem.},

keywords = {Bayes methods, Bayesian nonparametrics, CASI CAM CM, Computational modeling, GAMMA-L+ UC3M, Gibbs sampling, Hidden Markov models, Inference algorithms, Markov processes, Probability distribution, reversible jump Markov chain Monte Carlo, slice sampling, Time series, variational inference, Yttrium},

pubstate = {published},

tppubtype = {article}

}

@article{Nazabal2016bb,

title = {Human Activity Recognition by Combining a Small Number of Classifiers},

author = {Alfredo Nazabal and Pablo Garcia-Moreno and Antonio Artes-Rodriguez and Zoubin Ghahramani},

url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=7161292},

doi = {10.1109/JBHI.2015.2458274},

issn = {2168-2208},

year  = {2016},

date = {2016-01-01},

journal = {IEEE journal of biomedical and health informatics},

volume = {To appear},

publisher = {IEEE},

abstract = {We consider the problem of daily Human Activity Recognition (HAR) using multiple wireless inertial sensors and, specifically, HAR systems with a very low number of sensors, each one providing an estimation of the performed activities. We propose new Bayesian models to combine the output of the sensors. The models are based on a soft outputs combination of individual classifiers to deal with the small number of sensors. We also incorporate the dynamic nature of human activities as a first order homogeneous Markov chain. We develop both inductive and transductive inference methods for each model to be employed in supervised and semi-supervised situations, respectively. Using different real HAR databases, we compare our classifiers combination models against a single classifier that employs all the signals from the sensors. Our models exhibit consistently a reduction of the error rate and an increase of robustness against sensor failures. Our models also outperform other classifiers combination models that do not consider soft outputs and a Markovian structure of the human activities.},

keywords = {Bayes methods, Bayesian inference, Biological system modeling, Classifier combination, Databases, Estimation, Hidden Markov models, Sensor systems},

pubstate = {published},

tppubtype = {article}

}

@article{Borchani2016,

title = {Mining multi-dimensional concept-drifting data streams using Bayesian network classifiers},

author = {Hanen Borchani and Pedro Larra\~{n}aga and J Gama and Concha Bielza},

url = {http://cig.fi.upm.es/node/879},

year  = {2016},

date = {2016-01-01},

journal = {Intelligent Data Analysis},

volume = {20},

keywords = {CASI CAM CM, CIG UPM, Journal},

pubstate = {published},

tppubtype = {article}

}

@article{Asheghan2016,

title = {Stability Analysis and Robust Control of Heart Beat Rate During Treadmill Exercise},

author = {Mohammad Mostafa Asheghan and Joaqu\'{i}n M\'{i}guez},

doi = {10.1016/j.automatica.2015.10.027},

issn = {00051098},

year  = {2016},

date = {2016-01-01},

journal = {Automatica},

volume = {63},

pages = {311--320},

abstract = {We investigate a nonlinear dynamical model of a human's heart beat rate (HBR) during a treadmill exercise. We begin with a rigorous analysis of the stability of the model that extends significantly the results available in the literature. In particular, we first identify a simple set of necessary and sufficient conditions for both input-state stability and Lyapunov stability of the system, and then prove that the same conditions also hold when the model parameters are subject to unknown but bounded perturbations. The second part of the paper is devoted to the design and analysis of a control structure for this model, where the treadmill speed plays the role of the control input and the output is the subject's HBR, which is intended to follow a prescribed pattern. We propose a simple control scheme, suitable for a practical implementation, and then analyze its performance. Specifically, we prove (i) that the same conditions that guarantee the stability of the system also ensure that the controller attains a desired level of performance (quantified in terms of the admissible deviation of the HBR from the prescribed profile) and (ii) that the controller is robust to bounded perturbations both in the system parameters and the control input. Numerical simulations are also presented in order to illustrate some of the theoretical results.},

keywords = {Cardiovascular system, Journal, Nonlinear systems, Robust control},

pubstate = {published},

tppubtype = {article}

}

@article{F.Pradier2016,

title = {Prior Design for Dependent Dirichlet Processes: An Application to Marathon Modeling},

author = {Melanie F. Pradier and Francisco J R Ruiz and Fernando Perez-Cruz},

editor = {Guy Brock},

url = {http://dx.plos.org/10.1371/journal.pone.0147402},

doi = {10.1371/journal.pone.0147402},

issn = {1932-6203},

year  = {2016},

date = {2016-01-01},

journal = {PLOS ONE},

volume = {11},

number = {1},

pages = {e0147402},

publisher = {Public Library of Science},

abstract = {This paper presents a novel application of Bayesian nonparametrics (BNP) for marathon data modeling. We make use of two well-known BNP priors, the single-p dependent Dirichlet process and the hierarchical Dirichlet process, in order to address two different problems. First, we study the impact of age, gender and environment on the runners' performance. We derive a fair grading method that allows direct comparison of runners regardless of their age and gender. Unlike current grading systems, our approach is based not only on top world records, but on the performances of all runners. The presented methodology for comparison of densities can be adopted in many other applications straightforwardly, providing an interesting perspective to build dependent Dirichlet processes. Second, we analyze the running patterns of the marathoners in time, obtaining information that can be valuable for training purposes. We also show that these running patterns can be used to predict finishing time given intermediate interval measurements. We apply our models to New York City, Boston and London marathons.},

keywords = {Journal},

pubstate = {published},

tppubtype = {article}

}

@article{Guzman2015,

title = {Cooperative Optical Wireless Transmission for Improving Performance in Indoor Scenarios for Visible Light Communications},

author = {Borja Genoves Guzman and Alejandro Lancho Serrano and V\'{i}ctor Gil P Jimenez},

url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=7389772},

doi = {10.1109/TCE.2015.7389772},

issn = {0098-3063},

year  = {2015},

date = {2015-11-01},

journal = {IEEE Transactions on Consumer Electronics},

volume = {61},

number = {4},

pages = {393--401},

publisher = {IEEE},

abstract = {In this paper, a novel cooperative transmission and reception scheme in Visible Light Communications (VLC) is proposed and evaluated. This new scheme provides improvements and reliability in large indoor scenarios, such as corridors, laboratories, shops or conference rooms, where the coverage needs to be obtained by using different access points when VLC is used. The main idea behind the proposal is a simple cooperative transmission scheme where the receiver terminal will obtain the signal from different access points at the same time. This proposal outperforms traditional VLC schemes, especially in Non-Line-of-Sight reception where around 3 dB of gain, with respect to traditional schemes, can be obtained for unoptimized parameters, and larger than 3 dB could easily be achieved. The cooperation is studied in terms of the percentage of light coming from the main access point and a parameter called sidelobes??? amplitude level. The performance is evaluated according to the location within the atto-cell.},

keywords = {CoMP, Cooperative transmission andreception, Interference, Journal, Nonlinear optics, Optical receivers, Proposals, Pulse Position Division Multiplexing, Radio frequency, VLC, Wireless communication},

pubstate = {published},

tppubtype = {article}

}

@article{Ramirez2015,

title = {Detection of Multivariate Cyclostationarity},

author = {David Ram\'{i}rez and Peter J Schreier and Javier Via and Ignacio Santamaria and L L Scharf},

url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=7134806},

doi = {10.1109/TSP.2015.2450201},

issn = {1053-587X},

year  = {2015},

date = {2015-10-01},

journal = {IEEE Transactions on Signal Processing},

volume = {63},

number = {20},

pages = {5395--5408},

publisher = {IEEE},

abstract = {This paper derives an asymptotic generalized likelihood ratio test (GLRT) and an asymptotic locally most powerful invariant test (LMPIT) for two hypothesis testing problems: 1) Is a vector-valued random process cyclostationary (CS) or is it wide-sense stationary (WSS)? 2) Is a vector-valued random process CS or is it nonstationary? Our approach uses the relationship between a scalar-valued CS time series and a vector-valued WSS time series for which the knowledge of the cycle period is required. This relationship allows us to formulate the problem as a test for the covariance structure of the observations. The covariance matrix of the observations has a block-Toeplitz structure for CS and WSS processes. By considering the asymptotic case where the covariance matrix becomes block-circulant we are able to derive its maximum likelihood (ML) estimate and thus an asymptotic GLRT. Moreover, using Wijsman's theorem, we also obtain an asymptotic LMPIT. These detectors may be expressed in terms of the Loève spectrum, the cyclic spectrum, and the power spectral density, establishing how to fuse the information in these spectra for an asymptotic GLRT and LMPIT. This goes beyond the state-of-the-art, where it is common practice to build detectors of cyclostationarity from ad-hoc functions of these spectra.},

keywords = {ad hoc function, asymptotic GLRT, asymptotic LMPIT, block circulant, block-Toeplitz structure, Correlation, covariance matrices, Covariance matrix, covariance structure, cycle period, cyclic spectrum, Cyclostationarity, Detectors, Frequency-domain analysis, generalized likelihood ratio test, generalized likelihood ratio test (GLRT), hypothesis testing problem, locally most powerful invariant test, locally most powerful invariant test (LMPIT), Loe{\&}{#}x0300, maximum likelihood estimation, multivariate cyclostationarity detection, power spectral density, random processes, s theorem, scalar valued CS time series, signal detection, spectral analysis, statistical testing, Testing, Time series, Time series analysis, Toeplitz matrices, Toeplitz matrix, ve spectrum, vector valued random process cyclostationary, vector valued WSS time series, wide sense stationary, Wijsman theorem, Wijsman{\&}{#}x2019},

pubstate = {published},

tppubtype = {article}

}

@article{Elvira2015bb,

title = {Efficient Multiple Importance Sampling Estimators},

author = {Victor Elvira and Luca Martino and David Luengo and Monica F Bugallo},

url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=7105865},

doi = {10.1109/LSP.2015.2432078},

issn = {1070-9908},

year  = {2015},

date = {2015-10-01},

journal = {IEEE Signal Processing Letters},

volume = {22},

number = {10},

pages = {1757--1761},

publisher = {IEEE},

abstract = {Multiple importance sampling (MIS) methods use a set of proposal distributions from which samples are drawn. Each sample is then assigned an importance weight that can be obtained according to different strategies. This work is motivated by the trade-off between variance reduction and computational complexity of the different approaches (classical vs. deterministic mixture) available for the weight calculation. A new method that achieves an efficient compromise between both factors is introduced in this letter. It is based on forming a partition of the set of proposal distributions and computing the weights accordingly. Computer simulations show the excellent performance of the associated partial deterministic mixture MIS estimator.},

keywords = {Adaptive importance sampling, classical mixture approach, computational complexity, Computational efficiency, Computer Simulation, deterministic mixture, estimation theory, Journal, Monte Carlo methods, multiple importance sampling, multiple importance sampling estimator, partial deterministic mixture MIS estimator, Proposals, signal sampling, Sociology, Standards, variance reduction, weight calculation},

pubstate = {published},

tppubtype = {article}

}

@article{Mihaljevic2015,

title = {Classifying GABAergic interneurons with semi-supervised projected model-based clustering.},

author = {Bojan Mihaljevi\'{c} and Ruth Benavides-Piccione and Luis Guerra and Javier DeFelipe and Pedro Larra\~{n}aga and Concha Bielza},

url = {http://www.aiimjournal.com/article/S0933365714001481/fulltext http://cig.fi.upm.es/articles/2015/Mihaljevic-2015-AIIM.pdf},

doi = {10.1016/j.artmed.2014.12.010},

issn = {1873-2860},

year  = {2015},

date = {2015-09-01},

journal = {Artificial intelligence in medicine},

volume = {65},

number = {1},

pages = {49--59},

publisher = {Elsevier},

abstract = {OBJECTIVES: A recently introduced pragmatic scheme promises to be a useful catalog of interneuron names. We sought to automatically classify digitally reconstructed interneuronal morphologies according to this scheme. Simultaneously, we sought to discover possible subtypes of these types that might emerge during automatic classification (clustering). We also investigated which morphometric properties were most relevant for this classification. MATERIALS AND METHODS: A set of 118 digitally reconstructed interneuronal morphologies classified into the common basket (CB), horse-tail (HT), large basket (LB), and Martinotti (MA) interneuron types by 42 of the world's leading neuroscientists, quantified by five simple morphometric properties of the axon and four of the dendrites. We labeled each neuron with the type most commonly assigned to it by the experts. We then removed this class information for each type separately, and applied semi-supervised clustering to those cells (keeping the others' cluster membership fixed), to assess separation from other types and look for the formation of new groups (subtypes). We performed this same experiment unlabeling the cells of two types at a time, and of half the cells of a single type at a time. The clustering model is a finite mixture of Gaussians which we adapted for the estimation of local (per-cluster) feature relevance. We performed the described experiments on three different subsets of the data, formed according to how many experts agreed on type membership: at least 18 experts (the full data set), at least 21 (73 neurons), and at least 26 (47 neurons). RESULTS: Interneurons with more reliable type labels were classified more accurately. We classified HT cells with 100% accuracy, MA cells with 73% accuracy, and CB and LB cells with 56% and 58% accuracy, respectively. We identified three subtypes of the MA type, one subtype of CB and LB types each, and no subtypes of HT (it was a single, homogeneous type). We got maximum (adapted) Silhouette width and ARI values of 1, 0.83, 0.79, and 0.42, when unlabeling the HT, CB, LB, and MA types, respectively, confirming the quality of the formed cluster solutions. The subtypes identified when unlabeling a single type also emerged when unlabeling two types at a time, confirming their validity. Axonal morphometric properties were more relevant that dendritic ones, with the axonal polar histogram length in the [$pi$, 2$pi$) angle interval being particularly useful. CONCLUSIONS: The applied semi-supervised clustering method can accurately discriminate among CB, HT, LB, and MA interneuron types while discovering potential subtypes, and is therefore useful for neuronal classification. The discovery of potential subtypes suggests that some of these types are more heterogeneous that previously thought. Finally, axonal variables seem to be more relevant than dendritic ones for distinguishing among the CB, HT, LB, and MA interneuron types.},

keywords = {Automatic neuron classification, CASI CAM CM, Cerebral cortex, CIG UPM, Gaussian mixture models, Journal, Semi-supervised projected clustering},

pubstate = {published},

tppubtype = {article}

}

@article{Borchani2015,

title = {A survey on multi-output regression},

author = {Hanen Borchani and Gherardo Varando and Concha Bielza and Pedro Larra\~{n}aga},

url = {http://doi.wiley.com/10.1002/widm.1157 http://cig.fi.upm.es/articles/2015/Borchani-2015-WDMKD.pdf},

doi = {10.1002/widm.1157},

issn = {19424787},

year  = {2015},

date = {2015-09-01},

journal = {Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery},

volume = {5},

number = {5},

pages = {216--233},

abstract = {In recent years, a plethora of approaches have been proposed to deal with the increasingly challenging task of multi-output regression. This study provides a survey on state-of-the-art multi-output regression methods, that are categorized as problem transformation and algorithm adaptation methods. In addition, we present the mostly used performance evaluation measures, publicly available data sets for multi-output regression real-world problems, as well as open-source software frameworks.},

keywords = {algorithm adaptation methods, CASI CAM CM, CIG UPM, Journal, Multi-output regression, multi-target regression, performance evaluation measure, problem transformation methods},

pubstate = {published},

tppubtype = {article}

}

@article{Moreno2015b,

title = {Bayesian Nonparametric Crowdsourcing},

author = {Pablo Garcia-Moreno and Yee Whye Teh and Fernando Perez-Cruz and Antonio Art\'{e}s-Rodr\'{i}guez},

url = {http://www.jmlr.org/papers/volume16/moreno15a/moreno15a.pdf},

year  = {2015},

date = {2015-08-01},

journal = {Journal of Machine Learning Research},

volume = {16},

number = {August},

pages = {1607--1627},

abstract = {Crowdsourcing has been proven to be an effective and efficient tool to annotate large datasets. User annotations are often noisy, so methods to combine the annotations to produce reliable estimates of the ground truth are necessary. We claim that considering the existence of clusters of users in this combination step can improve the performance. This is especially important in early stages of crowdsourcing implementations, where the number of annotations is low. At this stage there is not enough information to accurately estimate the bias introduced by each annotator separately, so we have to resort to models that consider the statistical links among them. In addition, finding these clusters is interesting in itself as knowing the behavior of the pool of annotators allows implementing efficient active learning strategies. Based on this, we propose in this paper two new fully unsupervised models based on a Chinese Restaurant Process (CRP) prior and a hierarchical structure that allows inferring these groups jointly with the ground truth and the properties of the users. Efficient inference algorithms based on Gibbs sampling with auxiliary variables are proposed. Finally, we perform experiments, both on synthetic and real databases, to show the advantages of our models over state-of-the-art algorithms.},

keywords = {Bayesian nonparametrics, Dirichlet process, Gibbs sampling, Hierarchical clustering, Journal, Multiple annotators},

pubstate = {published},

tppubtype = {article}

}

@article{Martino2015bbb,

title = {An Adaptive Population Importance Sampler: Learning From Uncertainty},

author = {Luca Martino and Victor Elvira and David Luengo and Jukka Corander},

url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=7117437},

doi = {10.1109/TSP.2015.2440215},

issn = {1053-587X},

year  = {2015},

date = {2015-08-01},

journal = {IEEE Transactions on Signal Processing},

volume = {63},

number = {16},

pages = {4422--4437},

publisher = {IEEE},

abstract = {Monte Carlo (MC) methods are well-known computational techniques, widely used in different fields such as signal processing, communications and machine learning. An important class of MC methods is composed of importance sampling (IS) and its adaptive extensions, such as population Monte Carlo (PMC) and adaptive multiple IS (AMIS). In this paper, we introduce a novel adaptive and iterated importance sampler using a population of proposal densities. The proposed algorithm, named adaptive population importance sampling (APIS), provides a global estimation of the variables of interest iteratively, making use of all the samples previously generated. APIS combines a sophisticated scheme to build the IS estimators (based on the deterministic mixture approach) with a simple temporal adaptation (based on epochs). In this way, APIS is able to keep all the advantages of both AMIS and PMC, while minimizing their drawbacks. Furthermore, APIS is easily parallelizable. The cloud of proposals is adapted in such a way that local features of the target density can be better taken into account compared to single global adaptation procedures. The result is a fast, simple, robust, and high-performance algorithm applicable to a wide range of problems. Numerical results show the advantages of the proposed sampling scheme in four synthetic examples and a localization problem in a wireless sensor network.},

keywords = {Adaptive importance sampling, adaptive multiple IS, adaptive population importance sampler, AMIS, APIS, Estimation, Importance sampling, IS estimators, iterative estimation, iterative methods, Journal, MC methods, Monte Carlo (MC) methods, Monte Carlo methods, population Monte Carlo, Proposals, Signal processing algorithms, simple temporal adaptation, Sociology, Standards, Wireless sensor network, Wireless Sensor Networks},

pubstate = {published},

tppubtype = {article}

}

@article{Read2015b,

title = {Scalable Multi-Output Label Prediction: From Classifier Chains to Classifier Trellises},

author = {Jesse Read and Luca Martino and Pablo M Olmos and David Luengo},

url = {http://www.sciencedirect.com/science/article/pii/S0031320315000084},

year  = {2015},

date = {2015-06-01},

journal = {Pattern Recognition},

volume = {48},

number = {6},

pages = {2096--2106},

abstract = {Multi-output inference tasks, such as multi-label classification, have become increasingly important in recent years. A popular method for multi-label classification is classifier chains, in which the predictions of individual classifiers are cascaded along a chain, thus taking into account inter-label dependencies and improving the overall performance. Several varieties of classifier chain methods have been introduced, and many of them perform very competitively across a wide range of benchmark datasets. However, scalability limitations become apparent on larger datasets when modeling a fully cascaded chain. In particular, the methods' strategies for discovering and modeling a good chain structure constitutes a mayor computational bottleneck. In this paper, we present the classifier trellis (CT) method for scalable multi-label classification. We compare CT with several recently proposed classifier chain methods to show that it occupies an important niche: it is highly competitive on standard multi-label problems, yet it can also scale up to thousands or even tens of thousands of labels.},

keywords = {Bayesian networks, classifer chains, Journal, Multi-label classification, multi-output prediction, structured inference},

pubstate = {published},

tppubtype = {article}

}

@article{Varando2015a,

title = {Decision functions for chain classifiers based on Bayesian networks for multi-label classification},

author = {Gherardo Varando and Concha Bielza and Pedro Larra\~{n}aga},

url = {http://www.researchgate.net/publication/279069321_Decision_functions_for_chain_classifiers_based_on_Bayesian_networks_for_multi-label_classification http://cig.fi.upm.es/node/887},

doi = {10.1016/j.ijar.2015.06.006},

issn = {0888613X},

year  = {2015},

date = {2015-06-01},

journal = {International Journal of Approximate Reasoning},

abstract = {Multi-label classification problems require each instance to be assigned a subset of a defined set of labels. This problem is equivalent to finding a multi-valued decision function that predicts a vector of binary classes. In this paper we study the decision boundaries of two widely used approaches for building multi-label classifiers, when Bayesian network-augmented naive Bayes classifiers are used as base models: Binary relevance method and chain classifiers. In particular extending previous single-label results to multi-label chain classifiers, we find polynomial expressions for the multi-valued decision functions associated with these methods. We prove upper boundings on the expressive power of both methods and we prove that chain classifiers provide a more expressive model than the binary relevance method Decision functions for chain classifiers based on Bayesian networks for multi-label classification. Available from: http://www.researchgate.net/publication/279069321_Decision_functions_for_chain_classifiers_based_on_Bayesian_networks_for_multi-label_classification [accessed Nov 15, 2015].},

keywords = {CASI CAM CM, CIG UPM, Journal},

pubstate = {published},

tppubtype = {article}

}

@article{Olmos2015bb,

title = {A Scaling Law to Predict the Finite-Length Performance of Spatially-Coupled LDPC Codes},

author = {Pablo M Olmos and Rudiger Urbanke},

url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7086074},

doi = {10.1109/TIT.2015.2422816},

issn = {0018-9448},

year  = {2015},

date = {2015-06-01},

journal = {IEEE Transactions on Information Theory},

volume = {61},

number = {6},

pages = {3164--3184},

abstract = {Spatially-coupled low-density parity-check (SC-LDPC) codes are known to have excellent asymptotic properties. Much less is known regarding their finite-length performance. We propose a scaling law to predict the error probability of finite-length spatially coupled code ensembles when transmission takes place over the binary erasure channel. We discuss how the parameters of the scaling law are connected to fundamental quantities appearing in the asymptotic analysis of these ensembles and we verify that the predictions of the scaling law fit well to the data derived from simulations over a wide range of parameters. The ultimate goal of this line of research is to develop analytic tools for the design of SC-LDPC codes under practical constraints.},

keywords = {asymptotic analysis, asymptotic properties, binary erasure channel, Channel Coding, Codes on graphs, Couplings, Decoding, Differential equations, error probability, finite length performance, finite length spatially coupled code, finite-length code performance, finite-length performance, Iterative decoding, iterative decoding thresholds, Journal, parity check codes, Probability, SC-LDPC codes, scaling law, Sockets, spatially coupled LDPC codes, spatially-coupled LDPC codes},

pubstate = {published},

tppubtype = {article}

}