1. | Valera, Isabel; Ruiz, Francisco J R; Perez-Cruz, Fernando: Infinite Factorial Unbounded-State Hidden Markov Model. In: IEEE transactions on pattern analysis and machine intelligence, 38 (9), pp. 1816 – 1828, 2016, ISSN: 1939-3539. (Type: Journal Article | Abstract | Links | BibTeX) @article{Valera2016b, 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&amp;arnumber=7322279}, doi = {10.1109/TPAMI.2015.2498931}, issn = {1939-3539}, year = {2016}, date = {2016-09-01}, journal = {IEEE transactions on pattern analysis and machine intelligence}, volume = {38}, number = {9}, pages = {1816 -- 1828}, 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 = {}, pubstate = {published}, tppubtype = {article} } 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. |

2. | Valera, Isabel; Ruiz, Francisco J R; Perez-Cruz, Fernando: Infinite Factorial Unbounded-State Hidden Markov Model. In: IEEE transactions on pattern analysis and machine intelligence, To appear (99), pp. 1, 2016, ISSN: 1939-3539. (Type: Journal Article | Abstract | Links | BibTeX) @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&amp;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 = {}, pubstate = {published}, tppubtype = {article} } 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. |

3. | Martino, Luca; Elvira, Victor; Luengo, David; Artés-Rodríguez, Antonio; Corander, Jukka: Smelly Parallel MCMC Chains. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4070–4074, IEEE, Brisbane, 2015, ISBN: 978-1-4673-6997-8. (Type: Inproceedings | Abstract | Links | BibTeX) @inproceedings{Martino2015a, title = {Smelly Parallel MCMC Chains}, author = {Luca Martino and Victor Elvira and David Luengo and Antonio Artés-Rodríguez and Jukka Corander}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7178736 http://www.tsc.uc3m.es/~velvira/papers/ICASSP2015_martino.pdf}, doi = {10.1109/ICASSP.2015.7178736}, isbn = {978-1-4673-6997-8}, year = {2015}, date = {2015-04-01}, booktitle = {2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {4070--4074}, publisher = {IEEE}, address = {Brisbane}, abstract = {Monte Carlo (MC) methods are useful tools for Bayesian inference and stochastic optimization that have been widely applied in signal processing and machine learning. A well-known class of MC methods are Markov Chain Monte Carlo (MCMC) algorithms. In this work, we introduce a novel parallel interacting MCMC scheme, where the parallel chains share information, thus yielding a faster exploration of the state space. The interaction is carried out generating a dynamic repulsion among the “smelly” parallel chains that takes into account the entire population of current states. The ergodicity of the scheme and its relationship with other sampling methods are discussed. Numerical results show the advantages of the proposed approach in terms of mean square error, robustness w.r.t. to initial values and parameter choice.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Monte Carlo (MC) methods are useful tools for Bayesian inference and stochastic optimization that have been widely applied in signal processing and machine learning. A well-known class of MC methods are Markov Chain Monte Carlo (MCMC) algorithms. In this work, we introduce a novel parallel interacting MCMC scheme, where the parallel chains share information, thus yielding a faster exploration of the state space. The interaction is carried out generating a dynamic repulsion among the “smelly” parallel chains that takes into account the entire population of current states. The ergodicity of the scheme and its relationship with other sampling methods are discussed. Numerical results show the advantages of the proposed approach in terms of mean square error, robustness w.r.t. to initial values and parameter choice. |

4. | Valera, Isabel; Ruiz, Francisco J R; Perez-Cruz, Fernando: Infinite Factorial Unbounded Hidden Markov Model for Blind Multiuser Channel Estimation. In: 2014 4th International Workshop on Cognitive Information Processing (CIP), pp. 1–6, IEEE, Copenhagen, 2014, ISBN: 978-1-4799-3696-0. (Type: Inproceedings | Abstract | Links | BibTeX) @inproceedings{Valera2014a, title = {Infinite Factorial Unbounded Hidden Markov Model for Blind Multiuser Channel Estimation}, author = {Isabel Valera and Francisco J R Ruiz and Fernando Perez-Cruz}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6844506}, isbn = {978-1-4799-3696-0}, year = {2014}, date = {2014-01-01}, booktitle = {2014 4th International Workshop on Cognitive Information Processing (CIP)}, pages = {1--6}, publisher = {IEEE}, address = {Copenhagen}, abstract = {Bayesian nonparametric models allow solving estimation and detection problems with an unbounded number of degrees of freedom. In multiuser multiple-input multiple-output (MIMO) communication systems we might not know the number of active users and the channel they face, and assuming maximal scenarios (maximum number of transmitters and maximum channel length) might degrade the receiver performance. In this paper, we propose a Bayesian nonparametric prior and its associated inference algorithm, which is able to detect an unbounded number of users with an unbounded channel length. This generative model provides the dispersive channel model for each user and a probabilistic estimate for each transmitted symbol in a fully blind manner, i.e., without the need of pilot (training) symbols.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Bayesian nonparametric models allow solving estimation and detection problems with an unbounded number of degrees of freedom. In multiuser multiple-input multiple-output (MIMO) communication systems we might not know the number of active users and the channel they face, and assuming maximal scenarios (maximum number of transmitters and maximum channel length) might degrade the receiver performance. In this paper, we propose a Bayesian nonparametric prior and its associated inference algorithm, which is able to detect an unbounded number of users with an unbounded channel length. This generative model provides the dispersive channel model for each user and a probabilistic estimate for each transmitted symbol in a fully blind manner, i.e., without the need of pilot (training) symbols. |

5. | Balasingam, Balakumar; Bolic, Miodrag; Djuric, Petar M; Miguez, Joaquin: Efficient Distributed Resampling for Particle Filters. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3772–3775, IEEE, Prague, 2011, ISSN: 1520-6149. (Type: Inproceedings | Abstract | Links | BibTeX) @inproceedings{Balasingam2011, title = {Efficient Distributed Resampling for Particle Filters}, author = {Balakumar Balasingam and Miodrag Bolic and Petar M Djuric and Joaquin Miguez}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5947172}, issn = {1520-6149}, year = {2011}, date = {2011-01-01}, booktitle = {2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {3772--3775}, publisher = {IEEE}, address = {Prague}, abstract = {In particle filtering, resampling is the only step that cannot be fully parallelized. Recently, we have proposed algorithms for distributed resampling implemented on architectures with concurrent processing elements (PEs). The objective of distributed resampling is to reduce the communication among the PEs while not compromising the performance of the particle filter. An additional objective for implementation is to reduce the communication among the PEs. In this paper, we report an improved version of the distributed resampling algorithm that optimally selects the particles for communication between the PEs of the distributed scheme. Computer simulations are provided that demonstrate the improved performance of the proposed algorithm.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In particle filtering, resampling is the only step that cannot be fully parallelized. Recently, we have proposed algorithms for distributed resampling implemented on architectures with concurrent processing elements (PEs). The objective of distributed resampling is to reduce the communication among the PEs while not compromising the performance of the particle filter. An additional objective for implementation is to reduce the communication among the PEs. In this paper, we report an improved version of the distributed resampling algorithm that optimally selects the particles for communication between the PEs of the distributed scheme. Computer simulations are provided that demonstrate the improved performance of the proposed algorithm. |

6. | Achutegui, Katrin; Miguez, Joaquin: A Parallel Resampling Scheme and its Application to Distributed Particle Filtering in Wireless Networks. In: 2011 4th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), pp. 81–84, IEEE, San Juan, 2011, ISBN: 978-1-4577-2105-2. (Type: Inproceedings | Abstract | Links | BibTeX) @inproceedings{Achutegui2011, title = {A Parallel Resampling Scheme and its Application to Distributed Particle Filtering in Wireless Networks}, author = {Katrin Achutegui and Joaquin Miguez}, url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=6136051}, isbn = {978-1-4577-2105-2}, year = {2011}, date = {2011-01-01}, booktitle = {2011 4th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)}, pages = {81--84}, publisher = {IEEE}, address = {San Juan}, abstract = {We address the design of a particle filter (PF) that can be implemented in a distributed manner over a network of wireless sensor nodes, each of them collecting their own local data. This is a problem that has received considerable attention lately and several methods based on consensus, the transmission of likelihood information, the truncation and/or the quantization of data have been proposed. However, all existing schemes suffer from limitations related either to the amount of required communications among the nodes or the accuracy of the filter outputs. In this work we propose a novel distributed PF that is built around the distributed resampling with non-proportional allocation (DRNA) algorithm. This scheme guarantees the properness of the particle approximations produced by the filter and has been shown to be both efficient and accurate when compared with centralized PFs. The standard DRNA technique, however, places stringent demands on the communications among nodes that turn out impractical for a typical wireless sensor network (WSN). In this paper we investigate how to reduce this communication load by using (i) a random model for the spread of data over the WSN and (ii) methods that enable the out-of-sequence processing of sensor observations. A simple numerical illustration of the performance of the new algorithm compared with a centralized PF is provided.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We address the design of a particle filter (PF) that can be implemented in a distributed manner over a network of wireless sensor nodes, each of them collecting their own local data. This is a problem that has received considerable attention lately and several methods based on consensus, the transmission of likelihood information, the truncation and/or the quantization of data have been proposed. However, all existing schemes suffer from limitations related either to the amount of required communications among the nodes or the accuracy of the filter outputs. In this work we propose a novel distributed PF that is built around the distributed resampling with non-proportional allocation (DRNA) algorithm. This scheme guarantees the properness of the particle approximations produced by the filter and has been shown to be both efficient and accurate when compared with centralized PFs. The standard DRNA technique, however, places stringent demands on the communications among nodes that turn out impractical for a typical wireless sensor network (WSN). In this paper we investigate how to reduce this communication load by using (i) a random model for the spread of data over the WSN and (ii) methods that enable the out-of-sequence processing of sensor observations. A simple numerical illustration of the performance of the new algorithm compared with a centralized PF is provided. |

7. | Salamanca, Luis; Murillo-Fuentes, Juan Jose; Perez-Cruz, Fernando: Bayesian BCJR for Channel Equalization and Decoding. In: 2010 IEEE International Workshop on Machine Learning for Signal Processing, pp. 53–58, IEEE, Kittila, 2010, ISSN: 1551-2541. (Type: Inproceedings | Abstract | Links | BibTeX) @inproceedings{Salamanca2010, title = {Bayesian BCJR for Channel Equalization and Decoding}, author = {Luis Salamanca and Juan Jose Murillo-Fuentes and Fernando Perez-Cruz}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5589201}, issn = {1551-2541}, year = {2010}, date = {2010-01-01}, booktitle = {2010 IEEE International Workshop on Machine Learning for Signal Processing}, pages = {53--58}, publisher = {IEEE}, address = {Kittila}, abstract = {In this paper we focus on the probabilistic channel equalization in digital communications. We face the single input single output (SISO) model to show how the statistical information about the multipath channel can be exploited to further improve our estimation of the a posteriori probabilities (APP) during the equalization process. We consider not only the uncertainty due to the noise in the channel, but also in the estimate of the channel estate information (CSI). Thus, we resort to a Bayesian approach for the computation of the APP. This novel algorithm has the same complexity as the BCJR, exhibiting lower bit error rate at the output of the channel decoder than the standard BCJR that considers maximum likelihood (ML) to estimate the CSI.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In this paper we focus on the probabilistic channel equalization in digital communications. We face the single input single output (SISO) model to show how the statistical information about the multipath channel can be exploited to further improve our estimation of the a posteriori probabilities (APP) during the equalization process. We consider not only the uncertainty due to the noise in the channel, but also in the estimate of the channel estate information (CSI). Thus, we resort to a Bayesian approach for the computation of the APP. This novel algorithm has the same complexity as the BCJR, exhibiting lower bit error rate at the output of the channel decoder than the standard BCJR that considers maximum likelihood (ML) to estimate the CSI. |

8. | Fresia, Maria; Perez-Cruz, Fernando; Poor, Vincent H; Verdu, Sergio: Joint Source and Channel Coding. In: IEEE Signal Processing Magazine, 27 (6), pp. 104–113, 2010, ISSN: 1053-5888. (Type: Journal Article | Abstract | Links | BibTeX) @article{Fresia2010, title = {Joint Source and Channel Coding}, author = {Maria Fresia and Fernando Perez-Cruz and Vincent H Poor and Sergio Verdu}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5563107}, issn = {1053-5888}, year = {2010}, date = {2010-01-01}, journal = {IEEE Signal Processing Magazine}, volume = {27}, number = {6}, pages = {104--113}, abstract = {The objectives of this article are two-fold: First, to present the problem of joint source and channel (JSC) coding from a graphical model perspective and second, to propose a structure that uses a new graphical model for jointly encoding and decoding a redundant source. In the first part of the article, relevant contributions to JSC coding, ranging from the Slepian-Wolf problem to joint decoding of variable length codes with state-of-the-art source codes, are reviewed and summarized. In the second part, a double low-density parity-check (LDPC) code for JSC coding is proposed. The double LDPC code can be decoded as a single bipartite graph using standard belief propagation (BP) and its limiting performance is analyzed by using extrinsic information transfer (EXIT) chart approximations.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The objectives of this article are two-fold: First, to present the problem of joint source and channel (JSC) coding from a graphical model perspective and second, to propose a structure that uses a new graphical model for jointly encoding and decoding a redundant source. In the first part of the article, relevant contributions to JSC coding, ranging from the Slepian-Wolf problem to joint decoding of variable length codes with state-of-the-art source codes, are reviewed and summarized. In the second part, a double low-density parity-check (LDPC) code for JSC coding is proposed. The double LDPC code can be decoded as a single bipartite graph using standard belief propagation (BP) and its limiting performance is analyzed by using extrinsic information transfer (EXIT) chart approximations. |

## 2016 |

## Journal Articles |

Valera, Isabel; Ruiz, Francisco J R; Perez-Cruz, Fernando Infinite Factorial Unbounded-State Hidden Markov Model Journal Article IEEE transactions on pattern analysis and machine intelligence, 38 (9), pp. 1816 – 1828, 2016, ISSN: 1939-3539. Abstract | Links | BibTeX | Tags: Bayes methods, Bayesian nonparametrics, CASI CAM CM, Computational modeling, GAMMA-L+ UC3M, Gibbs sampling, Hidden Markov models, Inference algorithms, Journal, Markov processes, Probability distribution, reversible jump Markov chain Monte Carlo, slice sampling, Time series, variational inference, Yttrium @article{Valera2016b, 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&amp;arnumber=7322279}, doi = {10.1109/TPAMI.2015.2498931}, issn = {1939-3539}, year = {2016}, date = {2016-09-01}, journal = {IEEE transactions on pattern analysis and machine intelligence}, volume = {38}, number = {9}, pages = {1816 -- 1828}, 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, Journal, Markov processes, Probability distribution, reversible jump Markov chain Monte Carlo, slice sampling, Time series, variational inference, Yttrium}, pubstate = {published}, tppubtype = {article} } 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. |

Valera, Isabel; Ruiz, Francisco J R; Perez-Cruz, Fernando Infinite Factorial Unbounded-State Hidden Markov Model Journal Article IEEE transactions on pattern analysis and machine intelligence, To appear (99), pp. 1, 2016, ISSN: 1939-3539. Abstract | Links | BibTeX | Tags: 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 @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&amp;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} } |

## 2015 |

## Inproceedings |

Martino, Luca; Elvira, Victor; Luengo, David; Artés-Rodríguez, Antonio; Corander, Jukka Smelly Parallel MCMC Chains Inproceedings 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4070–4074, IEEE, Brisbane, 2015, ISBN: 978-1-4673-6997-8. Abstract | Links | BibTeX | Tags: Bayesian inference, learning (artificial intelligence), Machine learning, Markov chain Monte Carlo, Markov chain Monte Carlo algorithms, Markov processes, MC methods, MCMC algorithms, MCMC scheme, mean square error, mean square error methods, Monte Carlo methods, optimisation, parallel and interacting chains, Probability density function, Proposals, robustness, Sampling methods, Signal processing, Signal processing algorithms, signal sampling, smelly parallel chains, smelly parallel MCMC chains, Stochastic optimization @inproceedings{Martino2015a, title = {Smelly Parallel MCMC Chains}, author = {Luca Martino and Victor Elvira and David Luengo and Antonio Artés-Rodríguez and Jukka Corander}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7178736 http://www.tsc.uc3m.es/~velvira/papers/ICASSP2015_martino.pdf}, doi = {10.1109/ICASSP.2015.7178736}, isbn = {978-1-4673-6997-8}, year = {2015}, date = {2015-04-01}, booktitle = {2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {4070--4074}, publisher = {IEEE}, address = {Brisbane}, abstract = {Monte Carlo (MC) methods are useful tools for Bayesian inference and stochastic optimization that have been widely applied in signal processing and machine learning. A well-known class of MC methods are Markov Chain Monte Carlo (MCMC) algorithms. In this work, we introduce a novel parallel interacting MCMC scheme, where the parallel chains share information, thus yielding a faster exploration of the state space. The interaction is carried out generating a dynamic repulsion among the “smelly” parallel chains that takes into account the entire population of current states. The ergodicity of the scheme and its relationship with other sampling methods are discussed. Numerical results show the advantages of the proposed approach in terms of mean square error, robustness w.r.t. to initial values and parameter choice.}, keywords = {Bayesian inference, learning (artificial intelligence), Machine learning, Markov chain Monte Carlo, Markov chain Monte Carlo algorithms, Markov processes, MC methods, MCMC algorithms, MCMC scheme, mean square error, mean square error methods, Monte Carlo methods, optimisation, parallel and interacting chains, Probability density function, Proposals, robustness, Sampling methods, Signal processing, Signal processing algorithms, signal sampling, smelly parallel chains, smelly parallel MCMC chains, Stochastic optimization}, pubstate = {published}, tppubtype = {inproceedings} } Monte Carlo (MC) methods are useful tools for Bayesian inference and stochastic optimization that have been widely applied in signal processing and machine learning. A well-known class of MC methods are Markov Chain Monte Carlo (MCMC) algorithms. In this work, we introduce a novel parallel interacting MCMC scheme, where the parallel chains share information, thus yielding a faster exploration of the state space. The interaction is carried out generating a dynamic repulsion among the “smelly” parallel chains that takes into account the entire population of current states. The ergodicity of the scheme and its relationship with other sampling methods are discussed. Numerical results show the advantages of the proposed approach in terms of mean square error, robustness w.r.t. to initial values and parameter choice. |

## 2014 |

## Inproceedings |

Valera, Isabel; Ruiz, Francisco J R; Perez-Cruz, Fernando Infinite Factorial Unbounded Hidden Markov Model for Blind Multiuser Channel Estimation Inproceedings 2014 4th International Workshop on Cognitive Information Processing (CIP), pp. 1–6, IEEE, Copenhagen, 2014, ISBN: 978-1-4799-3696-0. Abstract | Links | BibTeX | Tags: Bayes methods, Bayesian non parametrics, Bayesian nonparametric models, blind multiuser channel estimation, Channel estimation, degrees of freedom, detection problems, dispersive channel model, generative model, Hidden Markov models, HMM, inference algorithm, infinite factorial unbounded hidden Markov model, Markov chain Monte Carlo, Markov processes, MIMO, MIMO communication, MIMO communication systems, multiple-input multiple-output (MIMO), multiple-input multiple-output communication syste, receiver performance, Receivers, Signal to noise ratio, Transmitters, unbounded channel length, unbounded number, user detection @inproceedings{Valera2014a, title = {Infinite Factorial Unbounded Hidden Markov Model for Blind Multiuser Channel Estimation}, author = {Isabel Valera and Francisco J R Ruiz and Fernando Perez-Cruz}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6844506}, isbn = {978-1-4799-3696-0}, year = {2014}, date = {2014-01-01}, booktitle = {2014 4th International Workshop on Cognitive Information Processing (CIP)}, pages = {1--6}, publisher = {IEEE}, address = {Copenhagen}, abstract = {Bayesian nonparametric models allow solving estimation and detection problems with an unbounded number of degrees of freedom. In multiuser multiple-input multiple-output (MIMO) communication systems we might not know the number of active users and the channel they face, and assuming maximal scenarios (maximum number of transmitters and maximum channel length) might degrade the receiver performance. In this paper, we propose a Bayesian nonparametric prior and its associated inference algorithm, which is able to detect an unbounded number of users with an unbounded channel length. This generative model provides the dispersive channel model for each user and a probabilistic estimate for each transmitted symbol in a fully blind manner, i.e., without the need of pilot (training) symbols.}, keywords = {Bayes methods, Bayesian non parametrics, Bayesian nonparametric models, blind multiuser channel estimation, Channel estimation, degrees of freedom, detection problems, dispersive channel model, generative model, Hidden Markov models, HMM, inference algorithm, infinite factorial unbounded hidden Markov model, Markov chain Monte Carlo, Markov processes, MIMO, MIMO communication, MIMO communication systems, multiple-input multiple-output (MIMO), multiple-input multiple-output communication syste, receiver performance, Receivers, Signal to noise ratio, Transmitters, unbounded channel length, unbounded number, user detection}, pubstate = {published}, tppubtype = {inproceedings} } Bayesian nonparametric models allow solving estimation and detection problems with an unbounded number of degrees of freedom. In multiuser multiple-input multiple-output (MIMO) communication systems we might not know the number of active users and the channel they face, and assuming maximal scenarios (maximum number of transmitters and maximum channel length) might degrade the receiver performance. In this paper, we propose a Bayesian nonparametric prior and its associated inference algorithm, which is able to detect an unbounded number of users with an unbounded channel length. This generative model provides the dispersive channel model for each user and a probabilistic estimate for each transmitted symbol in a fully blind manner, i.e., without the need of pilot (training) symbols. |

## 2011 |

## Inproceedings |

Balasingam, Balakumar; Bolic, Miodrag; Djuric, Petar M; Miguez, Joaquin Efficient Distributed Resampling for Particle Filters Inproceedings 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3772–3775, IEEE, Prague, 2011, ISSN: 1520-6149. Abstract | Links | BibTeX | Tags: Approximation algorithms, Copper, Covariance matrix, distributed resampling, Markov processes, Probability density function, Sequential Monte-Carlo methods, Signal processing, Signal processing algorithms @inproceedings{Balasingam2011, title = {Efficient Distributed Resampling for Particle Filters}, author = {Balakumar Balasingam and Miodrag Bolic and Petar M Djuric and Joaquin Miguez}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5947172}, issn = {1520-6149}, year = {2011}, date = {2011-01-01}, booktitle = {2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {3772--3775}, publisher = {IEEE}, address = {Prague}, abstract = {In particle filtering, resampling is the only step that cannot be fully parallelized. Recently, we have proposed algorithms for distributed resampling implemented on architectures with concurrent processing elements (PEs). The objective of distributed resampling is to reduce the communication among the PEs while not compromising the performance of the particle filter. An additional objective for implementation is to reduce the communication among the PEs. In this paper, we report an improved version of the distributed resampling algorithm that optimally selects the particles for communication between the PEs of the distributed scheme. Computer simulations are provided that demonstrate the improved performance of the proposed algorithm.}, keywords = {Approximation algorithms, Copper, Covariance matrix, distributed resampling, Markov processes, Probability density function, Sequential Monte-Carlo methods, Signal processing, Signal processing algorithms}, pubstate = {published}, tppubtype = {inproceedings} } In particle filtering, resampling is the only step that cannot be fully parallelized. Recently, we have proposed algorithms for distributed resampling implemented on architectures with concurrent processing elements (PEs). The objective of distributed resampling is to reduce the communication among the PEs while not compromising the performance of the particle filter. An additional objective for implementation is to reduce the communication among the PEs. In this paper, we report an improved version of the distributed resampling algorithm that optimally selects the particles for communication between the PEs of the distributed scheme. Computer simulations are provided that demonstrate the improved performance of the proposed algorithm. |

Achutegui, Katrin; Miguez, Joaquin A Parallel Resampling Scheme and its Application to Distributed Particle Filtering in Wireless Networks Inproceedings 2011 4th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), pp. 81–84, IEEE, San Juan, 2011, ISBN: 978-1-4577-2105-2. Abstract | Links | BibTeX | Tags: Approximation algorithms, Approximation methods, Artificial neural networks, distributed resampling, DRNA technique, Markov processes, nonproportional allocation algorithm, parallel resampling scheme, PF, quantization, Signal processing, Vectors, Wireless sensor network, Wireless Sensor Networks, WSN @inproceedings{Achutegui2011, title = {A Parallel Resampling Scheme and its Application to Distributed Particle Filtering in Wireless Networks}, author = {Katrin Achutegui and Joaquin Miguez}, url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=6136051}, isbn = {978-1-4577-2105-2}, year = {2011}, date = {2011-01-01}, booktitle = {2011 4th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)}, pages = {81--84}, publisher = {IEEE}, address = {San Juan}, abstract = {We address the design of a particle filter (PF) that can be implemented in a distributed manner over a network of wireless sensor nodes, each of them collecting their own local data. This is a problem that has received considerable attention lately and several methods based on consensus, the transmission of likelihood information, the truncation and/or the quantization of data have been proposed. However, all existing schemes suffer from limitations related either to the amount of required communications among the nodes or the accuracy of the filter outputs. In this work we propose a novel distributed PF that is built around the distributed resampling with non-proportional allocation (DRNA) algorithm. This scheme guarantees the properness of the particle approximations produced by the filter and has been shown to be both efficient and accurate when compared with centralized PFs. The standard DRNA technique, however, places stringent demands on the communications among nodes that turn out impractical for a typical wireless sensor network (WSN). In this paper we investigate how to reduce this communication load by using (i) a random model for the spread of data over the WSN and (ii) methods that enable the out-of-sequence processing of sensor observations. A simple numerical illustration of the performance of the new algorithm compared with a centralized PF is provided.}, keywords = {Approximation algorithms, Approximation methods, Artificial neural networks, distributed resampling, DRNA technique, Markov processes, nonproportional allocation algorithm, parallel resampling scheme, PF, quantization, Signal processing, Vectors, Wireless sensor network, Wireless Sensor Networks, WSN}, pubstate = {published}, tppubtype = {inproceedings} } We address the design of a particle filter (PF) that can be implemented in a distributed manner over a network of wireless sensor nodes, each of them collecting their own local data. This is a problem that has received considerable attention lately and several methods based on consensus, the transmission of likelihood information, the truncation and/or the quantization of data have been proposed. However, all existing schemes suffer from limitations related either to the amount of required communications among the nodes or the accuracy of the filter outputs. In this work we propose a novel distributed PF that is built around the distributed resampling with non-proportional allocation (DRNA) algorithm. This scheme guarantees the properness of the particle approximations produced by the filter and has been shown to be both efficient and accurate when compared with centralized PFs. The standard DRNA technique, however, places stringent demands on the communications among nodes that turn out impractical for a typical wireless sensor network (WSN). In this paper we investigate how to reduce this communication load by using (i) a random model for the spread of data over the WSN and (ii) methods that enable the out-of-sequence processing of sensor observations. A simple numerical illustration of the performance of the new algorithm compared with a centralized PF is provided. |

## 2010 |

## Journal Articles |

Fresia, Maria; Perez-Cruz, Fernando; Poor, Vincent H; Verdu, Sergio Joint Source and Channel Coding Journal Article IEEE Signal Processing Magazine, 27 (6), pp. 104–113, 2010, ISSN: 1053-5888. Abstract | Links | BibTeX | Tags: belief propagation, Channel Coding, combined source-channel coding, Decoding, Encoding, graphical model, Hidden Markov models, Iterative decoding, joint source channel coding, JSC coding, LDPC code, low density parity check code, Markov processes, parity check codes, Slepian-Wolf problem, variable length codes @article{Fresia2010, title = {Joint Source and Channel Coding}, author = {Maria Fresia and Fernando Perez-Cruz and Vincent H Poor and Sergio Verdu}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5563107}, issn = {1053-5888}, year = {2010}, date = {2010-01-01}, journal = {IEEE Signal Processing Magazine}, volume = {27}, number = {6}, pages = {104--113}, abstract = {The objectives of this article are two-fold: First, to present the problem of joint source and channel (JSC) coding from a graphical model perspective and second, to propose a structure that uses a new graphical model for jointly encoding and decoding a redundant source. In the first part of the article, relevant contributions to JSC coding, ranging from the Slepian-Wolf problem to joint decoding of variable length codes with state-of-the-art source codes, are reviewed and summarized. In the second part, a double low-density parity-check (LDPC) code for JSC coding is proposed. The double LDPC code can be decoded as a single bipartite graph using standard belief propagation (BP) and its limiting performance is analyzed by using extrinsic information transfer (EXIT) chart approximations.}, keywords = {belief propagation, Channel Coding, combined source-channel coding, Decoding, Encoding, graphical model, Hidden Markov models, Iterative decoding, joint source channel coding, JSC coding, LDPC code, low density parity check code, Markov processes, parity check codes, Slepian-Wolf problem, variable length codes}, pubstate = {published}, tppubtype = {article} } The objectives of this article are two-fold: First, to present the problem of joint source and channel (JSC) coding from a graphical model perspective and second, to propose a structure that uses a new graphical model for jointly encoding and decoding a redundant source. In the first part of the article, relevant contributions to JSC coding, ranging from the Slepian-Wolf problem to joint decoding of variable length codes with state-of-the-art source codes, are reviewed and summarized. In the second part, a double low-density parity-check (LDPC) code for JSC coding is proposed. The double LDPC code can be decoded as a single bipartite graph using standard belief propagation (BP) and its limiting performance is analyzed by using extrinsic information transfer (EXIT) chart approximations. |

## Inproceedings |

Salamanca, Luis; Murillo-Fuentes, Juan Jose; Perez-Cruz, Fernando Bayesian BCJR for Channel Equalization and Decoding Inproceedings 2010 IEEE International Workshop on Machine Learning for Signal Processing, pp. 53–58, IEEE, Kittila, 2010, ISSN: 1551-2541. Abstract | Links | BibTeX | Tags: a posteriori probability, Bayes methods, Bayesian BCJR, Bayesian methods, Bit error rate, channel decoding, channel estate information, Channel estimation, Decoding, digital communication, digital communications, equalisers, Equalizers, error statistics, Markov processes, Maximum likelihood decoding, maximum likelihood estimation, multipath channel, probabilistic channel equalization, Probability, single input single output model, SISO model, statistical information, Training @inproceedings{Salamanca2010, title = {Bayesian BCJR for Channel Equalization and Decoding}, author = {Luis Salamanca and Juan Jose Murillo-Fuentes and Fernando Perez-Cruz}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5589201}, issn = {1551-2541}, year = {2010}, date = {2010-01-01}, booktitle = {2010 IEEE International Workshop on Machine Learning for Signal Processing}, pages = {53--58}, publisher = {IEEE}, address = {Kittila}, abstract = {In this paper we focus on the probabilistic channel equalization in digital communications. We face the single input single output (SISO) model to show how the statistical information about the multipath channel can be exploited to further improve our estimation of the a posteriori probabilities (APP) during the equalization process. We consider not only the uncertainty due to the noise in the channel, but also in the estimate of the channel estate information (CSI). Thus, we resort to a Bayesian approach for the computation of the APP. This novel algorithm has the same complexity as the BCJR, exhibiting lower bit error rate at the output of the channel decoder than the standard BCJR that considers maximum likelihood (ML) to estimate the CSI.}, keywords = {a posteriori probability, Bayes methods, Bayesian BCJR, Bayesian methods, Bit error rate, channel decoding, channel estate information, Channel estimation, Decoding, digital communication, digital communications, equalisers, Equalizers, error statistics, Markov processes, Maximum likelihood decoding, maximum likelihood estimation, multipath channel, probabilistic channel equalization, Probability, single input single output model, SISO model, statistical information, Training}, pubstate = {published}, tppubtype = {inproceedings} } In this paper we focus on the probabilistic channel equalization in digital communications. We face the single input single output (SISO) model to show how the statistical information about the multipath channel can be exploited to further improve our estimation of the a posteriori probabilities (APP) during the equalization process. We consider not only the uncertainty due to the noise in the channel, but also in the estimate of the channel estate information (CSI). Thus, we resort to a Bayesian approach for the computation of the APP. This novel algorithm has the same complexity as the BCJR, exhibiting lower bit error rate at the output of the channel decoder than the standard BCJR that considers maximum likelihood (ML) to estimate the CSI. |