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 ...

The unprecedented processing demand, posed by the explosion of big data, challenges researchers to design efficient and adaptive machine learning algorithms that do not require persistent retraining and avoid learning redundant information. Inspired from learning techniques of intelligent biological agents, identifying transferable knowledge across learning problems has been a significant research focus to improve machine learning algorithms. In this thesis, we address the challenges of knowledge transfer through embedding spaces that capture and store hierarchical knowledge. In the first part of the thesis, we focus on the problem of cross-domain knowledge transfer. We first address zero-shot image classification, where the goal is to identify images from unseen classes using semantic descriptions of these classes. We train two coupled dictionaries which align visual and semantic domains via an intermediate embedding space. We then extend this idea by training deep networks that ...

When listening to music, some humans can easily recognize which instruments play at what time or when a new musical segment starts, but cannot describe exactly how they do this. To automatically describe particular aspects of a music piece – be it for an academic interest in emulating human perception, or for practical applications –, we can thus not directly replicate the steps taken by a human. We can, however, exploit that humans can easily annotate examples, and optimize a generic function to reproduce these annotations. In this thesis, I explore solving different music perception tasks with deep learning, a recent branch of machine learning that optimizes functions of many stacked nonlinear operations – referred to as deep neural networks – and promises to obtain better results or require less domain knowledge than more traditional techniques. In particular, I employ ...

This Thesis is focused on the combination of multiple biometric traits for automatic person authentication, in what is called a multimodal biometric system. More generally, any type of biometric information can be combined in what is called a multibiometric system. The information sources in multibiometrics include not only multiple biometric traits but also multiple sensors, multiple biometric instances (e.g., different fingers in fingerprint verification), repeated instances, and multiple algorithms. Most of the approaches found in the literature for combining these various information sources are based on the combination of the matching scores provided by individual systems built on the different biometric evidences. The combination schemes following this architecture are typically based on combination rules or trained pattern classifiers, and most of them assume that the score level fusion function is fixed at verification time. This Thesis considers the problem of ...

Current Human-Machine Interfaces (HMI) lack of “emotional intelligence”, i.e. they are not able to identify human emotional states and take this information into account to decide on the proper actions to execute. The goal of affective computing is to fill this lack by detecting emotional cues occurring during Human-Computer Interaction (HCI) and synthesizing emotional responses. In the last decades, most of the studies on emotion assessment have focused on the analysis of facial expressions and speech to determine the emotional state of a person. Physiological activity also includes emotional information that can be used for emotion assessment but has received less attention despite of its advantages (for instance it can be less easily faked than facial expressions). This thesis reports on the use of two types of physiological activities to assess emotions in the context of affective computing: the activity ...

The use of machine-learning for multimedia forensics is gaining more and more consensus, especially due to the amazing possibilities offered by modern machine learning techniques. By exploiting deep learning tools, new approaches have been proposed whose performance remarkably exceed those achieved by state-of-the-art methods based on standard machine-learning and model-based techniques. However, the inherent vulnerability and fragility of machine learning architectures pose new serious security threats, hindering the use of these tools in security-oriented applications, and, among them, multimedia forensics. The analysis of the security of machine learning-based techniques in the presence of an adversary attempting to impede the forensic analysis, and the development of new solutions capable to improve the security of such techniques is then of primary importance, and, recently, has marked the birth of a new discipline, named Adversarial Machine Learning. By focusing on Image Forensics and ...

The interest for the intelligent vehicle field has been increased during the last years, must probably due to an important number of road accidents. Many accidents could be avoided if a device attached to the vehicle would assist the driver with some warnings when dangerous situations are about to appear. In recent years, leading car developers have recorded significant efforts and support research works regarding the intelligent vehicle field where they propose solutions for the existing problems, especially in the vision domain. Road detection and following, pedestrian or vehicle detection, recognition and tracking, night vision, among others are examples of applications which have been developed and improved recently. Still, a lot of challenges and unsolved problems remain in the intelligent vehicle domain. Our purpose in this thesis is to design an Obstacle Recognition system for improving the road security by ...

In this thesis, the power of Machine Learning (ML) algorithms is combined with brain connectivity patterns, using Magnetic Resonance Imaging (MRI), for classification and prediction of Multiple Sclerosis (MS). White Matter (WM) as well as Grey Matter (GM) graphs are studied as connectome data types. The thesis addresses three main research objectives. The first objective aims to generate realistic brain connectomes data for improving the classification of MS clinical profiles in cases of data scarcity and class imbalance. To solve the problem of limited and imbalanced data, a Generative Adversarial Network (GAN) was developed for the generation of realistic and biologically meaningful connec- tomes. This network achieved a 10% better MS classification performance compared to classical approaches. As second research objective, we aim to improve classification of MS clinical profiles us- ing morphological features only extracted from GM brain tissue. ...

Hyperspectral (HS) imaging, which consists of acquiring a same scene in several hundreds of contiguous spectral bands (a three dimensional data cube), has opened a new range of relevant applications, such as target detection [MS02], classification [C.-03] and spectral unmixing [BDPD+12]. However, while HS sensors provide abundant spectral information, their spatial resolution is generally more limited. Thus, fusing the HS image with other highly resolved images of the same scene, such as multispectral (MS) or panchromatic (PAN) images is an interesting problem. The problem of fusing a high spectral and low spatial resolution image with an auxiliary image of higher spatial but lower spectral resolution, also known as multi-resolution image fusion, has been explored for many years [AMV+11]. From an application point of view, this problem is also important as motivated by recent national programs, e.g., the Japanese next-generation space-borne ...

In the world of Information and communications technology (ICT), strategies for innovation and development are increasingly focusing on applications that require spatial representation and real-time interaction with and within 3D-media environments. One of the major challenges that such applications have to address is user-centricity, reflecting e.g. on developing complexity-hiding services so that people can personalize their own delivery of services. In these terms, multimodal interfaces represent a key factor for enabling an inclusive use of new technologies by everyone. In order to achieve this, multimodal realistic models that describe our environment are needed, and in particular models that accurately describe the acoustics of the environment and communication through the auditory modality are required. Examples of currently active research directions and application areas include 3DTV and future internet, 3D visual-sound scene coding, transmission and reconstruction and teleconferencing systems, to name but ...

Advances in compression techniques, decreasing cost of storage, and high-speed transmission have facilitated the way videos are created, stored and distributed. As a consequence, videos are now being used in many applications areas. The increase in the amount of video data deployed and used in today's applications reveals not only the importance as multimedia data type, but also led to the requirement of efficient management of video data. This management paved the way for new research areas, such as indexing and retrieval of video with respect to their spatio-temporal, visual and semantic contents. This thesis presents work towards a unified framework for semi-automated video indexing and interactive retrieval. To create an efficient index, a set of representative key frames are selected which capture and encapsulate the entire video content. This is achieved by, firstly, segmenting the video into its constituent ...

Gliomas represent about 80% of all malignant primary brain tumors. Despite recent advancements in glioma research, patient outcome remains poor. The 5 year survival rate of the most common and most malignant subtype, i.e. glioblastoma, is about 5%. Magnetic resonance imaging (MRI) has become the imaging modality of choice in the management of brain tumor patients. Conventional MRI (cMRI) provides excellent soft tissue contrast without exposing the patient to potentially harmful ionizing radiation. Over the past decade, advanced MRI modalities, such as perfusion-weighted imaging (PWI), diffusion-weighted imaging (DWI) and magnetic resonance spectroscopic imaging (MRSI) have gained interest in the clinical field, and their added value regarding brain tumor diagnosis, treatment planning and follow-up has been recognized. Tumor segmentation involves the imaging-based delineation of a tumor and its subcompartments. In gliomas, segmentation plays an important role in treatment planning as well ...

Standard signal processing techniques are implicitly based on the assumption that the signal lies on a regular, homogeneous domain. In practice, however, many signals lie on an irregular or inhomogeneous domain. An application area where data are naturally defined on an irregular or inhomogeneous domain is human brain neuroimaging. The goal in neuroimaging is to map the structure and function of the brain using imaging techniques. In particular, functional magnetic resonance imaging (fMRI) is a technique that is conventionally used in non-invasive probing of human brain function. This doctoral dissertation deals with the development of signal processing schemes that adapt to the domain of the signal. It consists of four papers that in different ways deal with exploiting knowledge of the signal domain to enhance the processing of signals. In each paper, special focus is given to the analysis of ...

This thesis deals with problems of Pattern Recognition in the framework of Machine Learning (ML) and, specifically, Statistical Learning Theory (SLT), using Support Vector Machines (SVMs). The focus of this work is on the geometric interpretation of SVMs, which is accomplished through the notion of Reduced Convex Hulls (RCHs), and its impact on the derivation of new, efficient algorithms for the solution of the general SVM optimization task. The contributions of this work is the extension of the mathematical framework of RCHs, the derivation of novel geometric algorithms for SVMs and, finally, the application of the SVM algorithms to the field of Medical Image Analysis and Diagnosis (Mammography). Geometric SVM Framework's extensions: The geometric interpretation of SVMs is based on the notion of Reduced Convex Hulls. Although the geometric approach to SVMs is very intuitive, its usefulness was restricted by ...

The subject of this PhD thesis is the efficient and robust processing and analysis of the audio recordings that are derived from a call center. The thesis is comprised of two parts. The first part is dedicated to dialogue/non-dialogue detection and to speaker segmentation. The systems that are developed are prerequisite for detecting (i) the audio segments that actually contain a dialogue between the system and the call center customer and (ii) the change points between the system and the customer. This way the volume of the audio recordings that need to be processed is significantly reduced, while the system is automated. To detect the presence of a dialogue several systems are developed. This is the first effort found in the international literature that the audio channel is exclusively exploited. Also, it is the first time that the speaker utterance ...