Single-channel source separation for radio-frequency (RF) systems is a challenging problem relevant to key applications, including wireless communications, radar, and spectrum monitoring. This thesis addresses the challenge by focusing on data-driven approaches for source separation, leveraging datasets of sample realizations when source models are not explicitly provided. To this end, deep learning techniques are employed as function approximations for source separation, with models trained using available data. Two problem abstractions are studied as benchmarks for our proposed deep-learning approaches. Through a simplified problem involving Orthogonal Frequency Division Multiplexing (OFDM), we reveal the limitations of existing deep learning solutions and suggest modifications that account for the signal modality for improved performance. Further, we study the impact of time shifts on the formulation of an optimal estimator for cyclostationary Gaussian time series, serving as a performance lower bound for evaluating data-driven methods. ...

Future wireless networks will evolve to integrate communication, localization, and sensing capabilities. This evolution is driven by emerging application platforms such as digital twins, on the one hand, and advancements in wireless technologies, on the other, characterized by increased bandwidths, more antennas, and enhanced computational power. Crucial to this development is the application of artificial intelligence (AI), which is set to harness the vast amounts of available data in the sixth-generation (6G) of mobile networks and beyond. Integrating AI and machine learning (ML) algorithms, in particular, with wireless localization offers substantial opportunities to refine communication systems, improve the ability of wireless networks to locate the users precisely, enable context-aware transmission, and utilize processing and energy resources more efficiently. In this dissertation, advanced ML algorithms for enhanced wireless localization are proposed. Motivated by the capabilities of deep neural networks (DNNs) and ...

This dissertation explores advancements in future navigation satellite systems, proposing and analyzing solutions at system, signals, and user level. The objective of this work has been to seek for performance improvements, acting at various levels of the Global Navigation Satellite System (GNSS) value chain, yet fulfilling possible upcoming needs and constraints. In this context, this work focuses on improving the use of resources, both upstream, to enhance signals and services, and downstream, by leveraging such signals for a better user performance. Specific research questions were addressed for this purpose: how can inter-satellite links (ISLs) be assigned while optimizing data and navigation performance? Can multiple signals transmission be more efficient? How can we leverage signal multiplicity and receiver technologies to improve accuracy and robustness of the final position, velocity, and time (PVT) estimation? The first part focuses on space segment evolution, ...

Reverberation occurs in most of our environments and often degrades the intelligibility and quality of human speech, with an aggravated effect on hearing-impaired listeners. Meanwhile, the evolution of technologies for multimedia entertainment, communications and medical applications has led to a greater demand for improved sound quality. Therefore, many embedded devices now include a dereverberation algorithm, which aims to recover the anechoic component of speech. Dereverberation is an arduous task and an ill-posed inverse problem: even perfectly knowing the room acoustics does not guarantee to obtain a perfectly dereverberated signal. Furthermore, in most real-life cases, such knowledge is not available and therefore most dereverberation algorithms are blind, i.e. they must extract information from the reverberant speech signal only. Traditional dereverberation algorithms derive anechoic speech estimators exploiting statistical properties of speech signals, distributional assumptions and even knowledge of room acoustics when available. ...

Modeling dynamical systems is a fundamental task in various scientific and engineering domains, requiring accurate predictions, robustness to varying conditions, and interpretability of the underlying mechanisms. Traditional data-driven approaches often struggle with long-term prediction accuracy, generalization to out-of-distribution (OOD) scenarios, and providing insights into the system's behavior. This thesis explores the integration of supervised disentanglement into deep learning models as a means to address these challenges. We begin by advancing the state-of-the-art in modeling wave propagation governed by the Saint-Venant equations. Utilizing U-Net architectures and purposefully designed training strategies, we develop deep learning models that significantly improve prediction accuracy. Through OOD analysis, we highlight the limitations of standard deep learning models in capturing complex spatiotemporal dynamics, demonstrating how integrating domain knowledge through architectural design and training practices can enhance model performance. We further extend our supervised disentanglement approach to high-dimensional ...

Most cognitive processes in the brain are reflected through several aspects simultaneously, allowing us to observe the same process from different biological phenomena. The diverse nature of these biological processes suggests that a better understanding of cerebral activity may be achieved through multimodal measurements. One of the possible multimodal brain recording settings is the combination of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI), which is one of the main topics of this thesis. Two groups of EEG-fMRI integration approaches are possible. The first group, commonly called model-based techniques, are very popular due to the fact that the results from such analyses confirm or disprove a specific hypothesis. However, such hypotheses are not always available, requiring a more explorative approach to analyze the data. This exploration is possible with the second group of approaches, the so-called data-driven methods. The data-driven ...

In this doctoral thesis several scale-free texture segmentation procedures based on two fractal attributes, the Hölder exponent, measuring the local regularity of a texture, and local variance, are proposed.A piecewise homogeneous fractal texture model is built, along with a synthesis procedure, providing images composed of the aggregation of fractal texture patches with known attributes and segmentation. This synthesis procedure is used to evaluate the proposed methods performance.A first method, based on the Total Variation regularization of a noisy estimate of local regularity, is illustrated and refined thanks to a post-processing step consisting in an iterative thresholding and resulting in a segmentation.After evidencing the limitations of this first approach, deux segmentation methods, with either "free" or "co-located" contours, are built, taking in account jointly the local regularity and the local variance.These two procedures are formulated as convex nonsmooth functional minimization problems.We ...

Technology advancements profoundly impact numerous aspects of life, including how we communicate and interact. For instance, hearing aids enable hearing-impaired or elderly people to participate comfortably in daily conversations; telecommunications equipment lifts distance constraints, enabling people to communicate remotely; smart machines are developed to interact with humans by understanding and responding to their instructions. These applications involve speech-based interaction not only between humans but also between humans and machines. However, the microphones mounted on these technical devices can capture both target speech and interfering sounds, posing challenges to the reliability of speech communication in noisy environments. For example, distorted speech signals may reduce communication fluency among participants during teleconferencing. Additionally, noise interference can negatively affect the speech recognition and understanding modules of a voice-controlled machine. This calls for speech enhancement algorithms to extract clean speech and suppress undesired interfering signals, ...

Distributed signal or information processing using Internet of Things (IoT), facilitates real-time monitoring of signals, for example, environmental pollutants, health indicators, and electric energy consumption in a smart city. Despite the promising capabilities of IoTs, these distributed deployments often face the challenge of data privacy and communication rate constraints. In traditional machine learning, training data is moved to a data center, which requires massive data movement from distributed IoT devices to a third-party location, thus raising concerns over privacy and inefficient use of communication resources. Moreover, the growing network size, model size, and data volume combined lead to unusual complexity in the design of optimization algorithms beyond the compute capability of a single device. This necessitates novel system architectures to ensure stable and secure operations of such networks. Federated learning (FL) architecture, a novel distributed learning paradigm introduced by McMahan ...

This dissertation explores the intersection of data fusion, federated learning, and Bayesian methods, with a focus on their applications in indoor localization, GNSS, and image processing. Data fusion involves integrating data and knowledge from multiple sources. It becomes essential when data is only available in a distributed fashion or when different sensors are used to infer a quantity of interest. Data fusion typically includes raw data fusion, feature fusion, and decision fusion. In this thesis, we will concentrate on feature fusion. Distributed data fusion involves merging sensor data from different sources to estimate an unknown process. Bayesian framework is often used because it can provide an optimal and explainable feature by preserving the full distribution of the unknown given the data, called posterior, over the estimated process at each agent. This allows for easy and recursive merging of sensor data ...

For a large class of non-delay-critical applications (e.g., buffered video streaming or data transfer from cloud services to local devices), end-to-end throughput becomes the most crucial key performance indicator (KPI). In cellular networks, the achievable end-user throughput (the maximum throughput a user will get when attempting to download as much data as possible) is a spatiotemporal function, and its estimation poses a challenging and as-yet unsolved problem. The ability to accurately predict achievable throughput in a given location and time interval would, for example, allow mobile operators to further optimize their networks and design more personalized offers for the customers, or allow end-users with mobile broadband modems to make more informed decisions when selecting a provider. This work investigates the impact of individual parameters on the end-user achievable throughput in cellular networks and analyzes the feasibility and limitations of constructing ...

Machine learning and deep learning techniques have emerged as powerful tools for addressing complex challenges across diverse domains. These methodologies are powerful because they extract patterns and insights from large and complex datasets, automate decision-making processes, and continuously improve over time. They enable us to observe and quantify patterns in data that a normal human would not be able to capture, leading to deeper insights and more accurate predictions. This dissertation presents two research papers that leverage these methodologies to tackle distinct yet interconnected problems in neuroimaging and computer vision for the quantification of human health. The first investigation, "Age prediction using resting-state functional MRI," addresses the challenge of understanding brain aging. By employing the Least Absolute Shrinkage and Selection Operator (LASSO) on resting-state functional MRI (rsfMRI) data, we identify the most predictive correlations related to brain age. Our study, ...

In the era of artificial intelligence, there has been a growing consensus that solutions to complex science and engineering problems require novel methodologies that can integrate interpretable physics-based modeling approaches with machine learning techniques, from stochastic optimization to deep neural networks. This thesis aims to develop new methodological and applied frameworks for combining the advantages of physics-based modeling and machine learning, with special attention to two important signal processing tasks: solving inverse problems in hyperspectral imaging and detecting changepoints in time series. The first part of the thesis addresses learning priors in model-based optimization for solving inverse problems in hyperspectral imaging systems. First, we introduce a tuning-free Plug-and-Play algorithm for hyperspectral image deconvolution (HID). Specifically, we decompose the optimization problem into two iterative sub-problems, learn deep priors to solve the blind denoising sub-problem with neural networks, and estimate hyperparameters with ...

Global Navigation Satellite Systems (GNSS) is the de facto technology for Position, Navigation, and Timing (PNT) applications when it is available. GNSS relies on one or more satellite constellations that transmit ranging signals, which a receiver can use to self-localize. Signal acquisition is a crucial step in GNSS receivers, which is typically solved by maximizing the so-called Cross Ambiguity Function (CAF) resulting from a hypothesis testing problem. The CAF is a two-dimensional function that is related to the correlation between the received signal and a local code replica for every possible delay/Doppler pair, which is then maximized for signal detection and coarse synchronization. The outcome of this statistical process decides whether the signal from a particular satellite is present or absent in the received signal, as well as provides a rough estimate of its associated code delay and Doppler frequency, ...

Despite a lot of progress in speech separation, enhancement, and automatic speech recognition realistic meeting recognition is still fairly unsolved. Most research on speech separation either focuses on spectral cues to address single-channel recordings or spatial cues to separate multi-channel recordings and exclusively either rely on neural networks or probabilistic graphical models. Integrating a spatial clustering approach and a deep learning approach using spectral cues in a single framework can significantly improve automatic speech recognition performance and improve generalizability given that a neural network profits from a vast amount of training data while the probabilistic counterpart adapts to the current scene. This thesis at hand, therefore, concentrates on the integration of two fairly disjoint research streams, namely single-channel deep learning-based source separation and multi-channel probabilistic model-based source separation. It provides a general framework to integrate spatial and spectral cues in ...