RICH AND EFFICIENT VISUAL DATA REPRESENTATION

Increasing the size of training data in many computer vision tasks has shown to be very effective. Using large scale image datasets (e.g. ImageNet) with simple learning techniques (e.g. linear classifiers) one can achieve state-of-the-art performance in object recognition compared to sophisticated learning techniques on smaller image sets. Semantic search on visual data has become very popular. There are billions of images on the internet and the number is increasing every day. Dealing with large scale image sets is intense per se. They take a significant amount of memory that makes it impossible to process the images with complex algorithms on single CPU machines. Finding an efficient image representation can be a key to attack this problem. A representation being efficient is not enough for image understanding. It should be comprehensive and rich in carrying semantic information. In this proposal we develop an approach to computing binary codes that provide a rich and efficient image representation. We demonstrate several tasks in which binary features can be very effective. We show how binary features can speed up large scale image classification. We present learning techniques to learn the binary features from supervised image set (With different types of semantic supervision; class labels, textual descriptions). We propose several problems that are very important in finding and using efficient image representation.

Quadro Histórico dos Dispositivos Constitucionais : Art. 37, inciso X

Análise histórica das disposições constitucionais relacionadas ao Art. 37. " A administração pública direta, indireta ou fundacional, de qualquer dos Poderes da União, dos Estados, do Distrito Federal e dos Municípios obedecerá aos princípios de legalidade, impessoalidade, moralidade, publicidade e, também, ao seguinte: [...] X - a revisão geral da remuneração dos servidores públicos, sem distinção de índices entre servidores públicos civis e militares, far-se-á sempre na mesma data; [...]." Texto promulgado em 5/10/1988.

Contributions to 3D Data Registration and Representation

Nowadays, new computers generation provides a high performance that enables to build computationally expensive computer vision applications applied to mobile robotics. Building a map of the environment is a common task of a robot and is an essential part to allow the robots to move through these environments. Traditionally, mobile robots used a combination of several sensors from different technologies. Lasers, sonars and contact sensors have been typically used in any mobile robotic architecture, however color cameras are an important sensor due to we want the robots to use the same information that humans to sense and move through the different environments. Color cameras are cheap and flexible but a lot of work need to be done to give robots enough visual understanding of the scenes. Computer vision algorithms are computational complex problems but nowadays robots have access to different and powerful architectures that can be used for mobile robotics purposes. The advent of low-cost RGB-D sensors like Microsoft Kinect which provide 3D colored point clouds at high frame rates made the computer vision even more relevant in the mobile robotics field. The combination of visual and 3D data allows the systems to use both computer vision and 3D processing and therefore to be aware of more details of the surrounding environment. The research described in this thesis was motivated by the need of scene mapping. Being aware of the surrounding environment is a key feature in many mobile robotics applications from simple robotic navigation to complex surveillance applications. In addition, the acquisition of a 3D model of the scenes is useful in many areas as video games scene modeling where well-known places are reconstructed and added to game systems or advertising where once you get the 3D model of one room the system can add furniture pieces using augmented reality techniques. In this thesis we perform an experimental study of the state-of-the-art registration methods to find which one fits better to our scene mapping purposes. Different methods are tested and analyzed on different scene distributions of visual and geometry appearance. In addition, this thesis proposes two methods for 3d data compression and representation of 3D maps. Our 3D representation proposal is based on the use of Growing Neural Gas (GNG) method. This Self-Organizing Maps (SOMs) has been successfully used for clustering, pattern recognition and topology representation of various kind of data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models without considering time constraints. Self-organising neural models have the ability to provide a good representation of the input space. In particular, the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time consuming, specially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This thesis proposes a hardware implementation leveraging the computing power of modern GPUs which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). Our proposed geometrical 3D compression method seeks to reduce the 3D information using plane detection as basic structure to compress the data. This is due to our target environments are man-made and therefore there are a lot of points that belong to a plane surface. Our proposed method is able to get good compression results in those man-made scenarios. The detected and compressed planes can be also used in other applications as surface reconstruction or plane-based registration algorithms. Finally, we have also demonstrated the goodness of the GPU technologies getting a high performance implementation of a CAD/CAM common technique called Virtual Digitizing.

O museu virtual Google Art Project : um estudo de caso em contexto de ensino-aprendizagem da educação visual

A educação na arte e pela arte confere a todos os seus intervenientes a estimulação da sua criatividade e da sua consciência cultural, proporcionando meios para se exprimirem e participarem ativamente no mundo que nos rodeia. A integração das tecnologias de informação e comunicação no processo de ensino-aprendizagem veio alargar o papel que a arte pode desempenhar neste processo, promovendo novas formas de aprender, de ensinar e de pensar. Assim, a utilização de ambientes virtuais em contexto educativo tem revelado um enorme potencial, sobretudo ao nível da comunicação e da interação entre alunos e obras de arte. Neste sentido, considerou-se importante desenvolver um estudo de caso em contexto de sala de aula da Educação Visual, promovendo uma aprendizagem baseada na articulação entre a observação, interpretação e análise da obra de arte e o museu virtual. Assim o principal objetivo deste estudo foi avaliar as potencialidades do Google Art Project, enquanto objeto de aprendizagem, na promoção da aprendizagem na área da literacia em artes. Para além disso, procurámos ainda avaliar se a utilização de ferramentas multimédia como o referido Google Art Project e o Quadro Interativo, constituem fatores de motivação na aprendizagem da disciplina de Educação Visual. Do ponto de vista metodológico desenvolvemos uma estratégia baseada na investigação-ação. Procurámos, por um lado, descobrir e compreender o significado de uma realidade vivida por um grupo de alunos e, por outro lado, refletir sobre a prática educativa com o intuito de a melhorar e transformar. Este estudo envolveu cinco turmas do sexto ano do ensino público. Para a recolha de dados utilizámos técnicas baseadas na conversação e na observação, no questionário e nas notas de campo. Os resultados deste estudo revelam que as ferramentas tecnológicas utilizadas podem efetivamente contribuir para a promoção da aprendizagem dos alunos na área da Educação Visual, mais concretamente ao nível do domínio da literacia artística, da representação e da interpretação visual.

WordPress as a framework for automated data capture, filtering and structuring processes

The Exhibitium Project , awarded by the BBVA Foundation, is a data-driven project developed by an international consortium of research groups . One of its main objectives is to build a prototype that will serve as a base to produce a platform for the recording and exploitation of data about art-exhibitions available on the Internet . Therefore, our proposal aims to expose the methods, procedures and decision-making processes that have governed the technological implementation of this prototype, especially with regard to the reuse of WordPress (WP) as development framework.

Neuroscience and Hindu Aesthetics: A Critical Analysis of V.S. Ramachandran’s “Science of Art”

Neuroaesthetics is the study of the brain’s response to artistic stimuli. The neuroscientist V.S. Ramachandran contends that art is primarily “caricature” or “exaggeration.” Exaggerated forms hyperactivate neurons in viewers’ brains, which in turn produce specific, “universal” responses. Ramachandran identifies a precursor for his theory in the concept of rasa (literally “juice”) from classical Hindu aesthetics, which he associates with “exaggeration.” The canonical Sanskrit texts of Bharata Muni’s Natya Shastra and Abhinavagupta’s Abhinavabharati, however, do not support Ramachandran’s conclusions. They present audiences as dynamic co-creators, not passive recipients. I believe we could more accurately model the neurology of Hindu aesthetic experiences if we took indigenous rasa theory more seriously as qualitative data that could inform future research.

Classi cation of new electricity customers based on surveys and smart metering data

This paper proposes a process for the classifi cation of new residential electricity customers. The current state of the art is extended by using a combination of smart metering and survey data and by using model-based feature selection for the classifi cation task. Firstly, the normalized representative consumption profi les of the population are derived through the clustering of data from households. Secondly, new customers are classifi ed using survey data and a limited amount of smart metering data. Thirdly, regression analysis and model-based feature selection results explain the importance of the variables and which are the drivers of diff erent consumption profi les, enabling the extraction of appropriate models. The results of a case study show that the use of survey data signi ficantly increases accuracy of the classifi cation task (up to 20%). Considering four consumption groups, more than half of the customers are correctly classifi ed with only one week of metering data, with more weeks the accuracy is signifi cantly improved. The use of model-based feature selection resulted in the use of a signifi cantly lower number of features allowing an easy interpretation of the derived models.

The Iron Age Clay Figurines from Karkemish (2011-2015 Campaigns) and the Coroplastic Art of the Syro-Anatolian Region

This is a study concerning the Iron Age coroplastic production in the Northern Levant. The research is mostly based on new data gathered from the Joint Turco-Italian Expedition at Karkemish (Gaziantep, Turkey). Figurines presented in this study are limited to the 2011-2015 excavation seasons and they are analyzed from a range of aspects. The work in fact primarily focuses on contextual data, being the starting point for the research. A preliminary typological and chronological framing is also provided, while a tentative functional interpretation is suggested by means of a careful examination of the local iconographic and written repertoires. Furthermore, ethnographic comparisons are sometimes used in order to better define the semantic meaning beyond this production. Comparisons with other key sites located in the Middle Euphrates basin are also presented with the main aim to define a peculiar regional pattern. A minor part of this dissertation is also dedicated to the study of the coroplastic art in the entire northern Levantine region. The aim, in this case, is evidently that of identifying different regional productions, which at the state of the research could be traced back just for a few regions. Thus new important data are provided for the Amuq Plain, the Islahiye Valley and the rest of Inner Syria.

On the role of Computational Logic in Data Science: representing, learning, reasoning, and explaining knowledge

In this thesis we discuss in what ways computational logic (CL) and data science (DS) can jointly contribute to the management of knowledge within the scope of modern and future artificial intelligence (AI), and how technically-sound software technologies can be realised along the path. An agent-oriented mindset permeates the whole discussion, by stressing pivotal role of autonomous agents in exploiting both means to reach higher degrees of intelligence. Accordingly, the goals of this thesis are manifold. First, we elicit the analogies and differences among CL and DS, hence looking for possible synergies and complementarities along 4 major knowledge-related dimensions, namely representation, acquisition (a.k.a. learning), inference (a.k.a. reasoning), and explanation. In this regard, we propose a conceptual framework through which bridges these disciplines can be described and designed. We then survey the current state of the art of AI technologies, w.r.t. their capability to support bridging CL and DS in practice. After detecting lacks and opportunities, we propose the notion of logic ecosystem as the new conceptual, architectural, and technological solution supporting the incremental integration of symbolic and sub-symbolic AI. Finally, we discuss how our notion of logic ecosys- tem can be reified into actual software technology and extended towards many DS-related directions.

Development of new immunochemical and spectroscopic analytical methods for the characterization and conservation of works of art

Cultural heritage is constituted by complex and heterogenous materials, such as paintings but also ancient remains. However, all ancient materials are exposed to external environment and their interaction produces different changes due to chemical, physical and biological phenomena. The organic fraction, especially the proteinaceous one, has a crucial role in all these materials: in archaeology proteins reveal human habits, in artworks they disclose technics and help for a correct restoration. For these reasons the development of methods that allow the preservation of the sample as much as possible and a deeper knowledge of the deterioration processes is fundamental. The research activities presented in this PhD thesis have been focused on the development of new immunochemical and spectroscopic approaches in order to detect and identify organic substances in artistic and archaeological samples. Organic components could be present in different cultural heritage materials as constituent element (e.g., binders in paintings, collagen in bones) and their knowledge is fundamental for a complete understanding of past life, degradation processes and appropriate restauration approaches. The combination of immunological approach with a chemiluminescence detection and Laser Ablation-Inductively Coupled Plasma-Mass Spectrometry allowed a sensitive and selective localization of collagen and elements in ancient bones and teeth. Near-infrared spectrometer and hyper spectral imaging have been applied in combination with chemometric data analysis as non-destructive methods for bones prescreening for the localization of collagen. Moreover, an investigation of amino acids in enamel has been proposed, in order to clarify teeth biomolecules survival overtime through the optimization and application of High-Performance Liquid Chromatography on modern and ancient enamel powder. New portable biosensors were developed for ovalbumin identification in paintings, thanks to the combination between biocompatible Gellan gel and electro-immunochemical sensors, to extract and identify painting binders with the contact only between gel and painting and between gel and electrodes.

Interpretable Convolutional Neural Networks for Decoding and Analyzing Neural Time Series Data

Machine learning is widely adopted to decode multi-variate neural time series, including electroencephalographic (EEG) and single-cell recordings. Recent solutions based on deep learning (DL) outperformed traditional decoders by automatically extracting relevant discriminative features from raw or minimally pre-processed signals. Convolutional Neural Networks (CNNs) have been successfully applied to EEG and are the most common DL-based EEG decoders in the state-of-the-art (SOA). However, the current research is affected by some limitations. SOA CNNs for EEG decoding usually exploit deep and heavy structures with the risk of overfitting small datasets, and architectures are often defined empirically. Furthermore, CNNs are mainly validated by designing within-subject decoders. Crucially, the automatically learned features mainly remain unexplored; conversely, interpreting these features may be of great value to use decoders also as analysis tools, highlighting neural signatures underlying the different decoded brain or behavioral states in a data-driven way. Lastly, SOA DL-based algorithms used to decode single-cell recordings rely on more complex, slower to train and less interpretable networks than CNNs, and the use of CNNs with these signals has not been investigated. This PhD research addresses the previous limitations, with reference to P300 and motor decoding from EEG, and motor decoding from single-neuron activity. CNNs were designed light, compact, and interpretable. Moreover, multiple training strategies were adopted, including transfer learning, which could reduce training times promoting the application of CNNs in practice. Furthermore, CNN-based EEG analyses were proposed to study neural features in the spatial, temporal and frequency domains, and proved to better highlight and enhance relevant neural features related to P300 and motor states than canonical EEG analyses. Remarkably, these analyses could be used, in perspective, to design novel EEG biomarkers for neurological or neurodevelopmental disorders. Lastly, CNNs were developed to decode single-neuron activity, providing a better compromise between performance and model complexity.

Data sensitivity detection in chat interactions for privacy protection

In recent years, there has been exponential growth in using virtual spaces, including dialogue systems, that handle personal information. The concept of personal privacy in the literature is discussed and controversial, whereas, in the technological field, it directly influences the degree of reliability perceived in the information system (privacy ‘as trust’). This work aims to protect the right to privacy on personal data (GDPR, 2018) and avoid the loss of sensitive content by exploring sensitive information detection (SID) task. It is grounded on the following research questions: (RQ1) What does sensitive data mean? How to define a personal sensitive information domain? (RQ2) How to create a state-of-the-art model for SID?(RQ3) How to evaluate the model? RQ1 theoretically investigates the concepts of privacy and the ontological state-of-the-art representation of personal information. The Data Privacy Vocabulary (DPV) is the taxonomic resource taken as an authoritative reference for the definition of the knowledge domain. Concerning RQ2, we investigate two approaches to classify sensitive data: the first - bottom-up - explores automatic learning methods based on transformer networks, the second - top-down - proposes logical-symbolic methods with the construction of privaframe, a knowledge graph of compositional frames representing personal data categories. Both approaches are tested. For the evaluation - RQ3 – we create SPeDaC, a sentence-level labeled resource. This can be used as a benchmark or training in the SID task, filling the gap of a shared resource in this field. If the approach based on artificial neural networks confirms the validity of the direction adopted in the most recent studies on SID, the logical-symbolic approach emerges as the preferred way for the classification of fine-grained personal data categories, thanks to the semantic-grounded tailor modeling it allows. At the same time, the results highlight the strong potential of hybrid architectures in solving automatic tasks.

Applied deep learning and data science with a human-centric and data-centric approach

The term Artificial intelligence acquired a lot of baggage since its introduction and in its current incarnation is synonymous with Deep Learning. The sudden availability of data and computing resources has opened the gates to myriads of applications. Not all are created equal though, and problems might arise especially for fields not closely related to the tasks that pertain tech companies that spearheaded DL. The perspective of practitioners seems to be changing, however. Human-Centric AI emerged in the last few years as a new way of thinking DL and AI applications from the ground up, with a special attention at their relationship with humans. The goal is designing a system that can gracefully integrate in already established workflows, as in many real-world scenarios AI may not be good enough to completely replace its humans. Often this replacement may even be unneeded or undesirable. Another important perspective comes from, Andrew Ng, a DL pioneer, who recently started shifting the focus of development from “better models” towards better, and smaller, data. He defined his approach Data-Centric AI. Without downplaying the importance of pushing the state of the art in DL, we must recognize that if the goal is creating a tool for humans to use, more raw performance may not align with more utility for the final user. A Human-Centric approach is compatible with a Data-Centric one, and we find that the two overlap nicely when human expertise is used as the driving force behind data quality. This thesis documents a series of case-studies where these approaches were employed, to different extents, to guide the design and implementation of intelligent systems. We found human expertise proved crucial in improving datasets and models. The last chapter includes a slight deviation, with studies on the pandemic, still preserving the human and data centric perspective.

Data assimilation for advanced cross-scale unstructured-grid ocean modeling.

The coastal ocean is a complex environment with extremely dynamic processes that require a high-resolution and cross-scale modeling approach in which all hydrodynamic fields and scales are considered integral parts of the overall system. In the last decade, unstructured-grid models have been used to advance in seamless modeling between scales. On the other hand, the data assimilation methodologies to improve the unstructured-grid models in the coastal seas have been developed only recently and need significant advancements. Here, we link the unstructured-grid ocean modeling to the variational data assimilation methods. In particular, we show results from the modeling system SANIFS based on SHYFEM fully-baroclinic unstructured-grid model interfaced with OceanVar, a state-of-art variational data assimilation scheme adopted for several systems based on a structured grid. OceanVar implements a 3DVar DA scheme. The combination of three linear operators models the background error covariance matrix. The vertical part is represented using multivariate EOFs for temperature, salinity, and sea level anomaly. The horizontal part is assumed to be Gaussian isotropic and is modeled using a first-order recursive filter algorithm designed for structured and regular grids. Here we introduced a novel recursive filter algorithm for unstructured grids. A local hydrostatic adjustment scheme models the rapidly evolving part of the background error covariance. We designed two data assimilation experiments using SANIFS implementation interfaced with OceanVar over the period 2017-2018, one with only temperature and salinity assimilation by Argo profiles and the second also including sea level anomaly. The results showed a successful implementation of the approach and the added value of the assimilation for the active tracer fields. While looking at the broad basin, no significant improvements are highlighted for the sea level, requiring future investigations. Furthermore, a Machine Learning methodology based on an LSTM network has been used to predict the model SST increments.

Digital 3D reconstruction as a research environment in art and architecture history: uncertainty classification and visualisation

The dissertation addresses the still not solved challenges concerned with the source-based digital 3D reconstruction, visualisation and documentation in the domain of archaeology, art and architecture history. The emerging BIM methodology and the exchange data format IFC are changing the way of collaboration, visualisation and documentation in the planning, construction and facility management process. The introduction and development of the Semantic Web (Web 3.0), spreading the idea of structured, formalised and linked data, offers semantically enriched human- and machine-readable data. In contrast to civil engineering and cultural heritage, academic object-oriented disciplines, like archaeology, art and architecture history, are acting as outside spectators. Since the 1990s, it has been argued that a 3D model is not likely to be considered a scientific reconstruction unless it is grounded on accurate documentation and visualisation. However, these standards are still missing and the validation of the outcomes is not fulfilled. Meanwhile, the digital research data remain ephemeral and continue to fill the growing digital cemeteries. This study focuses, therefore, on the evaluation of the source-based digital 3D reconstructions and, especially, on uncertainty assessment in the case of hypothetical reconstructions of destroyed or never built artefacts according to scientific principles, making the models shareable and reusable by a potentially wide audience. The work initially focuses on terminology and on the definition of a workflow especially related to the classification and visualisation of uncertainty. The workflow is then applied to specific cases of 3D models uploaded to the DFG repository of the AI Mainz. In this way, the available methods of documenting, visualising and communicating uncertainty are analysed. In the end, this process will lead to a validation or a correction of the workflow and the initial assumptions, but also (dealing with different hypotheses) to a better definition of the levels of uncertainty.