Stadius Center for Dynamical Systems

Leuven, Belgium

Stadius Center for Dynamical Systems

Leuven, Belgium
SEARCH FILTERS
Time filter
Source Type

Plata-Chaves J.,Stadius Center for Dynamical Systems | Bertrand A.,Stadius Center for Dynamical Systems | Moonen M.,Stadius Center for Dynamical Systems | Theodoridis S.,National and Kapodistrian University of Athens | Zoubir A.M.,TU Darmstadt
IEEE Journal on Selected Topics in Signal Processing | Year: 2017

Unlike traditional homogeneous single-task wireless sensor networks (WSNs), heterogeneous and multitask WSNs allow the cooperation among multiple heterogeneous devices dedicated to solving different signal processing tasks. Despite their heterogenous nature and the fact that each device may solve a different task, the devices could still benefit from a collaboration between them to achieve a superior performance. However, the design of such heterogeneous WSNs is very challenging and requires the design of scalable algorithms that maximize the performance of the devices without transmitting their raw sensor signals in an uncontrolled fashion. Towards this goal, novel techniques are needed both on the signal processing level and on the network-communication level. In this paper, we give an overview of applications in the field of heterogeneous and multitask WSNs with special focus on the signal processing aspects. Moreover, we provide a general overview of the existing algorithms for distributed node-specific estimation. Finally, we discuss the main challenges that have to be tackled for the design of heterogeneous multitask WSNs. © 2017 IEEE.


Biesmans W.,Stadius Center for Dynamical Systems | Das N.,Stadius Center for Dynamical Systems | Das N.,Catholic University of Leuven | Francart T.,Catholic University of Leuven | Bertrand A.,Stadius Center for Dynamical Systems
IEEE Transactions on Neural Systems and Rehabilitation Engineering | Year: 2017

This paper considers the auditory attention detection (AAD) paradigm, where the goal is to determine which of two simultaneous speakers a person is attending to. The paradigm relies on recordings of the listener's brain activity, e.g., from electroencephalography (EEG). To perform AAD, decoded EEG signals are typically correlated with the temporal envelopes of the speech signals of the separate speakers. In this paper, we study how the inclusion of various degrees of auditory modelling in this speech envelope extraction process affects the AAD performance, where the best performance is found for an auditory inspired linear filter bank followed by power law compression. These two modelling stages are computationally cheap, which is important for implementation in wearable devices, such as future neuro-steered auditory prostheses. We also introduce a more natural way to combine recordings (over trials and subjects) to train the decoder, which reduces the dependence of the algorithm on regularization parameters. Finally, we investigate the simultaneous design of the EEG decoder and the audio sub band envelope recombination weights vector using either a norm-constrained least squares or a canonical correlation analysis, but conclude that this increases computational complexity without improving AAD performance. © 2016 IEEE.


Bertrand A.,Stadius Center for Dynamical Systems
IEEE Transactions on Signal Processing | Year: 2017

In a previous paper, Liu et al. have presented a distributed method to rank the nodes of a network according to their importance for maintaining a fast average consensus within the network. Their method essentially estimates the decrease in algebraic connectivity for each possible node removal, based on a distributed estimation of the Fiedler vector. In this comment correspondence, we argue that their approach is limited to certain parameter ranges in the average consensus algorithm, and we briefly comment on how the framework can be extended accordingly. We also point out that their proposed algorithm for distributed Fiedler vector computation is essentially a special case of an earlier proposed algorithm, and in fact a numerically unstable version thereof. Finally, we correct some statements in their paper. © 2016 IEEE.


Timmerman D.,Catholic University of Leuven | Timmerman D.,University Hospitals Leuven | Van Calster B.,Catholic University of Leuven | Testa A.,Catholic University of the Sacred Heart | And 24 more authors.
American Journal of Obstetrics and Gynecology | Year: 2016

Background Accurate methods to preoperatively characterize adnexal tumors are pivotal for optimal patient management. A recent metaanalysis concluded that the International Ovarian Tumor Analysis algorithms such as the Simple Rules are the best approaches to preoperatively classify adnexal masses as benign or malignant. Objective We sought to develop and validate a model to predict the risk of malignancy in adnexal masses using the ultrasound features in the Simple Rules. Study Design This was an international cross-sectional cohort study involving 22 oncology centers, referral centers for ultrasonography, and general hospitals. We included consecutive patients with an adnexal tumor who underwent a standardized transvaginal ultrasound examination and were selected for surgery. Data on 5020 patients were recorded in 3 phases from 2002 through 2012. The 5 Simple Rules features indicative of a benign tumor (B-features) and the 5 features indicative of malignancy (M-features) are based on the presence of ascites, tumor morphology, and degree of vascularity at ultrasonography. Gold standard was the histopathologic diagnosis of the adnexal mass (pathologist blinded to ultrasound findings). Logistic regression analysis was used to estimate the risk of malignancy based on the 10 ultrasound features and type of center. The diagnostic performance was evaluated by area under the receiver operating characteristic curve, sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR-), positive predictive value (PPV), negative predictive value (NPV), and calibration curves. Results Data on 4848 patients were analyzed. The malignancy rate was 43% (1402/3263) in oncology centers and 17% (263/1585) in other centers. The area under the receiver operating characteristic curve on validation data was very similar in oncology centers (0.917; 95% confidence interval, 0.901-0.931) and other centers (0.916; 95% confidence interval, 0.873-0.945). Risk estimates showed good calibration. In all, 23% of patients in the validation data set had a very low estimated risk (<1%) and 48% had a high estimated risk (≥30%). For the 1% risk cutoff, sensitivity was 99.7%, specificity 33.7%, LR+ 1.5, LR- 0.010, PPV 44.8%, and NPV 98.9%. For the 30% risk cutoff, sensitivity was 89.0%, specificity 84.7%, LR+ 5.8, LR- 0.13, PPV 75.4%, and NPV 93.9%. Conclusion Quantification of the risk of malignancy based on the Simple Rules has good diagnostic performance both in oncology centers and other centers. A simple classification based on these risk estimates may form the basis of a clinical management system. Patients with a high risk may benefit from surgery by a gynecological oncologist, while patients with a lower risk may be managed locally. © 2016 Elsevier Inc. All rights reserved.


PubMed | University Hospitals Leuven, University of Udine, Stadius Center for Dynamical Systems, Italian National Cancer Institute and 12 more.
Type: Journal Article | Journal: American journal of obstetrics and gynecology | Year: 2016

Accurate methods to preoperatively characterize adnexal tumors are pivotal for optimal patient management. A recent metaanalysis concluded that the International Ovarian Tumor Analysis algorithms such as the Simple Rules are the best approaches to preoperatively classify adnexal masses as benign or malignant.We sought to develop and validate a model to predict the risk of malignancy in adnexal masses using the ultrasound features in the Simple Rules.This was an international cross-sectional cohort study involving 22 oncology centers, referral centers for ultrasonography, and general hospitals. We included consecutive patients with an adnexal tumor who underwent a standardized transvaginal ultrasound examination and were selected for surgery. Data on 5020 patients were recorded in 3 phases from 2002 through 2012. The 5 Simple Rules features indicative of a benign tumor (B-features) and the 5 features indicative of malignancy (M-features) are based on the presence of ascites, tumor morphology, and degree of vascularity at ultrasonography. Gold standard was the histopathologic diagnosis of the adnexal mass (pathologist blinded to ultrasound findings). Logistic regression analysis was used to estimate the risk of malignancy based on the 10 ultrasound features and type of center. The diagnostic performance was evaluated by area under the receiver operating characteristic curve, sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR-), positive predictive value (PPV), negative predictive value (NPV), and calibration curves.Data on 4848 patients were analyzed. The malignancy rate was 43% (1402/3263) in oncology centers and 17% (263/1585) in other centers. The area under the receiver operating characteristic curve on validation data was very similar in oncology centers (0.917; 95% confidence interval, 0.901-0.931) and other centers (0.916; 95% confidence interval, 0.873-0.945). Risk estimates showed good calibration. In all, 23% of patients in the validation data set had a very low estimated risk (<1%) and 48% had a high estimated risk (30%). For the 1% risk cutoff, sensitivity was99.7%, specificity 33.7%, LR+ 1.5, LR- 0.010, PPV 44.8%, and NPV 98.9%. For the 30% risk cutoff, sensitivity was 89.0%, specificity 84.7%, LR+ 5.8, LR- 0.13, PPV 75.4%, and NPV 93.9%.Quantification of the risk of malignancy based on the Simple Rules has good diagnostic performance both in oncology centers and other centers. A simple classification based on these risk estimates may form the basis of a clinical management system. Patients with a high risk may benefit from surgery by a gynecological oncologist, while patients with a lower risk may be managed locally.


Sampathirao A.K.,IMT Institute for Advanced Studies Lucca | Sopasakis P.,IMT Institute for Advanced Studies Lucca | Bemporad A.,IMT Institute for Advanced Studies Lucca | Patrinos P.,Stadius Center for Dynamical Systems
Proceedings of the IEEE Conference on Decision and Control | Year: 2016

Stochastic optimal control problems arise in many applications and are, in principle, large-scale involving up to millions of decision variables. Their applicability in control applications is often limited by the availability of algorithms that can solve them efficiently and within the sampling time of the controlled system. In this paper we propose a dual accelerated proximal gradient algorithm which is amenable to parallelization and demonstrate that its GPU implementation affords high speed-up values (with respect to a CPU implementation) and greatly outperforms well-established commercial optimizers such as Gurobi. © 2015 IEEE.


Parada P.P.,Nuance Communications | Sharma D.,Nuance Communications | Lainez J.,Nuance Communications | Barreda D.,Nuance Communications | And 3 more authors.
IEEE/ACM Transactions on Speech and Language Processing | Year: 2016

Several intrusive measures of reverberation can be computed from measured and simulated room impulse responses, over the full frequency band or for each individual mel-frequency subband. It is initially shown that full-band clarity index C50 is the most correlated measure on average with reverberant speech recognition performance. This corroborates previous findings but now for the dataset to be used in this study. We extend the previous findings to show that C50 also exhibits the highest mutual information on average. Motivated by these extended findings, a nonintrusive room acoustic (NIRA) estimation method is proposed to estimate C50 from only the reverberant speech signal. The NIRA method is a data-driven approach based on computing a number of features from the speech signal and it employs these features to train a model used to perform the estimation. The choice of features and learning techniques are explored in this work using an evaluation set which comprises approximately 100 000 different reverberant signals (around 93 h of speech) including reverberation from measured and simulated room impulse responses. The feature importance of each feature with respect to the estimation of the target C50 is analysed following two different approaches. In both cases, the newly chosen set of features shows high importance for the target. The best C50 estimator provides a root-mean-square deviation around 3 dB on average for all reverberant test environments. ©2016 IEEE.


Szurley J.,Stadius Center for Dynamical Systems | Bertrand A.,Stadius Center for Dynamical Systems | Moonen M.,Stadius Center for Dynamical Systems
Signal Processing | Year: 2015

A wireless sensor network (WSN) is considered where each node estimates a number of node-specific desired signals by means of the distributed adaptive node-specific signal estimation (DANSE) algorithm. It is assumed that the topology of the WSN is constructed based on one of the two approaches, either a top-down approach where the WSN is composed of heterogeneous nodes, or a bottom-up approach where the nodes are not necessarily heterogeneous. In the top-down approach, nodes with the largest energy budgets are designated as cluster heads and the remaining nodes form clusters around these nodes. In the bottom-up approach, an ad hoc WSN is partitioned into a set of smaller substructures consisting of non-overlapping cliques that are arranged in a tree topology. These two approaches are shown to be conceptually equivalent, in that the same building blocks constitute both envisaged topologies, and the functionality of the DANSE algorithm is extended to such topologies. In using the DANSE algorithm in such topologies, the WSN converges to the same solution as if all nodes had access to all of the sensor signal observations, and provides faster convergence when compared to DANSE in a single tree topology with only a slight increase in per-node energy usage. © 2015 Elsevier B.V. All rights reserved.


Bertrand A.,Stadius Center for Dynamical Systems | Moonen M.,Stadius Center for Dynamical Systems
IEEE Transactions on Signal Processing | Year: 2015

Canonical correlation analysis (CCA) is a widely used data analysis tool that allows to assess the correlation between two distinct sets of signals. It computes optimal linear combinations of the signals in both sets such that the resulting signals are maximally correlated. The weight vectors defining these optimal linear combinations are referred to as "principal CCA directions". In addition to this particular type of data analysis, CCA is also often used as a blind source separation (BSS) technique, i.e., under certain assumptions, the principal CCA directions have certain demixing properties. In this paper, we propose a distributed CCA (DCCA) algorithm that can operate in wireless sensor networks (WSNs) with a fully connected or a tree topology. The algorithm estimates the Q principal CCA directions from the sensor signal observations collected by the different nodes in the WSN and extracts the corresponding sources. These network-wide principal CCA directions are estimated in a time-recursive fashion without explicitly constructing the corresponding network-wide correlation matrices, i.e., without the need for data centralization. Instead, each node locally computes smaller CCA problems and only transmits compressed sensor signal observations (of dimension Q), which significantly reduces the bit rate over the wireless links of the WSN. We prove convergence and optimality of the DCCA algorithm, and we demonstrate its performance by means of numerical simulations in a blind source separation scenario. © 2015 IEEE.


Jukiac A.,University of Oldenburg | Van Waterschoot T.,Stadius Center for Dynamical Systems | Gerkmann T.,University of Oldenburg | Doclo S.,University of Oldenburg
IEEE Transactions on Audio, Speech and Language Processing | Year: 2015

The quality of speech signals recorded in an enclosure can be severely degraded by room reverberation. In this paper, we focus on a class of blind batch methods for speech dereverberation in a noiseless scenario with a single source, which are based on multi-channel linear prediction in the short-time Fourier transform domain. Dereverberation is performed by maximum-likelihood estimation of the model parameters that are subsequently used to recover the desired speech signal. Contrary to the conventional method, we propose to model the desired speech signal using a general sparse prior that can be represented in a convex form as a maximization over scaled complex Gaussian distributions. The proposed model can be interpreted as a generalization of the commonly used time-varying Gaussian model. Furthermore, we reformulate both the conventional and the proposed method as an optimization problem with an ℓp-norm cost function, emphasizing the role of sparsity in the considered speech dereverberation methods. Experimental evaluation in different acoustic scenarios show that the proposed approach results in an improved performance compared to the conventional approach in terms of instrumental measures for speech quality. © 2015 IEEE.

Loading Stadius Center for Dynamical Systems collaborators
Loading Stadius Center for Dynamical Systems collaborators