Automatic extraction of concepts from texts and applications

The extraction of relevant terms from texts is an extensively researched task in Text- Mining. Relevant terms have been applied in areas such as Information Retrieval or document clustering and classification. However, relevance has a rather fuzzy nature since the classification of some terms as relevant or not relevant is not consensual. For instance, while words such as "president" and "republic" are generally considered relevant by human evaluators, and words like "the" and "or" are not, terms such as "read" and "finish" gather no consensus about their semantic and informativeness. Concepts, on the other hand, have a less fuzzy nature. Therefore, instead of deciding on the relevance of a term during the extraction phase, as most extractors do, I propose to first extract, from texts, what I have called generic concepts (all concepts) and postpone the decision about relevance for downstream applications, accordingly to their needs. For instance, a keyword extractor may assume that the most relevant keywords are the most frequent concepts on the documents. Moreover, most statistical extractors are incapable of extracting single-word and multi-word expressions using the same methodology. These factors led to the development of the ConceptExtractor, a statistical and language-independent methodology which is explained in Part I of this thesis. In Part II, I will show that the automatic extraction of concepts has great applicability. For instance, for the extraction of keywords from documents, using the Tf-Idf metric only on concepts yields better results than using Tf-Idf without concepts, specially for multi-words. In addition, since concepts can be semantically related to other concepts, this allows us to build implicit document descriptors. These applications led to published work. Finally, I will present some work that, although not published yet, is briefly discussed in this document.

Image processing for displacement measurements

Since the invention of photography humans have been using images to capture, store and analyse the act that they are interested in. With the developments in this field, assisted by better computers, it is possible to use image processing technology as an accurate method of analysis and measurement. Image processing's principal qualities are flexibility, adaptability and the ability to easily and quickly process a large amount of information. Successful examples of applications can be seen in several areas of human life, such as biomedical, industry, surveillance, military and mapping. This is so true that there are several Nobel prizes related to imaging. The accurate measurement of deformations, displacements, strain fields and surface defects are challenging in many material tests in Civil Engineering because traditionally these measurements require complex and expensive equipment, plus time consuming calibration. Image processing can be an inexpensive and effective tool for load displacement measurements. Using an adequate image acquisition system and taking advantage of the computation power of modern computers it is possible to accurately measure very small displacements with high precision. On the market there are already several commercial software packages. However they are commercialized at high cost. In this work block-matching algorithms will be used in order to compare the results from image processing with the data obtained with physical transducers during laboratory load tests. In order to test the proposed solutions several load tests were carried out in partnership with researchers from the Civil Engineering Department at Universidade Nova de Lisboa (UNL).

Mobile image processing to support educational geometry games

The mobile IT era is here, it is still growing and expanding at a steady rate and, most of all, it is entertaining. Mobile devices are used for entertainment, whether social through the so-called social networks, or private through web browsing, video watching or gaming. Youngsters make heavy use of these devices, and even small children show impressive adaptability and skill. However not much attention is directed towards education, especially in the case of young children. Too much time is usually spent in games which only purpose is to keep children entertained, time that could be put to better use such as developing elementary geometric notions. Taking advantage of this pocket computer scenario, it is proposed an application geared towards small children in the 6 – 9 age group that allows them to consolidate knowledge regarding geometric shapes, forming a stepping stone that leads to some fundamental mathematical knowledge to be exercised later on. To achieve this goal, the application will detect simple geometric shapes like squares, circles and triangles using the device’s camera. The novelty of this application will be a core real-time detection system designed and developed from the ground up for mobile devices, taking into account their characteristic limitations such as reduced processing power, memory and battery. User feedback was be gathered, aggregated and studied to assess the educational factor of the application.

The brushstroke and materials of Amadeo de Souza-Cardoso combined in an authentication tool

Nowadays, authentication studies for paintings require a multidisciplinary approach, based on the contribution of visual features analysis but also on characterizations of materials and techniques. Moreover, it is important that the assessment of the authorship of a painting is supported by technical studies of a selected number of original artworks that cover the entire career of an artist. This dissertation is concerned about the work of modernist painter Amadeo de Souza-Cardoso. It is divided in three parts. In the first part, we propose a tool based on image processing that combines information obtained by brushstroke and materials analysis. The resulting tool provides qualitative and quantitative evaluation of the authorship of the paintings; the quantitative element is particularly relevant, as it could be crucial in solving authorship controversies, such as judicial disputes. The brushstroke analysis was performed by combining two algorithms for feature detection, namely Gabor filter and Scale Invariant Feature Transform. Thanks to this combination (and to the use of the Bag-of-Features model), the proposed method shows an accuracy higher than 90% in distinguishing between images of Amadeo’s paintings and images of artworks by other contemporary artists. For the molecular analysis, we implemented a semi-automatic system that uses hyperspectral imaging and elemental analysis. The system provides as output an image that depicts the mapping of the pigments present, together with the areas made using materials not coherent with Amadeo’s palette, if any. This visual output is a simple and effective way of assessing the results of the system. The tool proposed based on the combination of brushstroke and molecular information was tested in twelve paintings obtaining promising results. The second part of the thesis presents a systematic study of four selected paintings made by Amadeo in 1917. Although untitled, three of these paintings are commonly known as BRUT, Entrada and Coty; they are considered as his most successful and genuine works. The materials and techniques of these artworks have never been studied before. The paintings were studied with a multi-analytical approach using micro-Energy Dispersive X-ray Fluorescence spectroscopy, micro-Infrared and Raman Spectroscopy, micro-Spectrofluorimetry and Scanning Electron Microscopy. The characterization of Amadeo’s materials and techniques used on his last paintings, as well as the investigation of some of the conservation problems that affect these paintings, is essential to enrich the knowledge on this artist. Moreover, the study of the materials in the four paintings reveals commonalities between the paintings BRUT and Entrada. This observation is supported also by the analysis of the elements present in a photograph of a collage (conserved at the Art Library of the Calouste Gulbenkian Foundation), the only remaining evidence of a supposed maquete of these paintings. The final part of the thesis describes the application of the image processing tools developed in the first part of the thesis on a set of case studies; this experience demonstrates the potential of the tool to support painting analysis and authentication studies. The brushstroke analysis was used as additional analysis on the evaluation process of four paintings attributed to Amadeo, and the system based on hyperspectral analysis was applied on the painting dated 1917. The case studies therefore serve as a bridge between the first two parts of the dissertation.

Video metadata extraction in a videoMail system

Currently the world swiftly adapts to visual communication. Online services like YouTube and Vine show that video is no longer the domain of broadcast television only. Video is used for different purposes like entertainment, information, education or communication. The rapid growth of today’s video archives with sparsely available editorial data creates a big problem of its retrieval. The humans see a video like a complex interplay of cognitive concepts. As a result there is a need to build a bridge between numeric values and semantic concepts. This establishes a connection that will facilitate videos’ retrieval by humans. The critical aspect of this bridge is video annotation. The process could be done manually or automatically. Manual annotation is very tedious, subjective and expensive. Therefore automatic annotation is being actively studied. In this thesis we focus on the multimedia content automatic annotation. Namely the use of analysis techniques for information retrieval allowing to automatically extract metadata from video in a videomail system. Furthermore the identification of text, people, actions, spaces, objects, including animals and plants. Hence it will be possible to align multimedia content with the text presented in the email message and the creation of applications for semantic video database indexing and retrieving.

Antioxidant extraction process for Andean Oca by a photodiode array detector using response surface methodology

Application of Experimental Design techniques has proven to be essential in various research fields, due to its statistical capability of processing the effect of interactions among independent variables, known as factors, in a system’s response. Advantages of this methodology can be summarized in more resource and time efficient experimentations while providing more accurate results. This research emphasizes the quantification of 4 antioxidants extraction, at two different concentration, prepared according to an experimental procedure and measured by a Photodiode Array Detector. Experimental planning was made following a Central Composite Design, which is a type of DoE that allows to consider the quadratic component in Response Surfaces, a component that includes pure curvature studies on the model produced. This work was executed with the intention of analyzing responses, peak areas obtained from chromatograms plotted by the Detector’s system, and comprehending if the factors considered – acquired from an extensive literary review – produced the expected effect in response. Completion of this work will allow to take conclusions regarding what factors should be considered for the optimization studies of antioxidants extraction in a Oca (Oxalis tuberosa) matrix.

Valorization of grape pomace through hot compressed water extraction/hydrolysis

The world energy consumption is expected to increase strongly in coming years, because of the emerging economies. Biomass is the only renewable carbon resource that is abundant enough to be used as a source of energy Grape pomace is one of the most abundant agro-industrial residues in the world, being a good biomass resource. The aim of this work is the valorization of grape pomace from white grapes (WWGP) and from red grapes (RWGP), through the extraction of phenolic compounds with antioxidant activity, as well as through the extraction/hydrolysis of carbohydrates, using subcritical water, or hot compressed water (HCW). The main focus of this work is the optimization of the process for WWGP, while for RWGP only one set of parameters were tested. The temperatures used were 170, 190 and 210 °C for WWGP, and 180 °C for RWGP. The water flow rates were 5 and 10 mL/min, and the pressure was always kept at 100 bar. Before performing HCW assays, both residues were characterized, revealing that WWGP is very rich in free sugars (around 40%) essentially glucose and fructose, while RWGP has higher contents of structural sugars, lignin, lipids and protein. For WWGP the best results were achieved at 210 °C and 10 mL/min: higher yield in water soluble compounds (69 wt.%), phenolics extraction (26.2 mg/g) and carbohydrates recovery (49.3 wt.% relative to the existing 57.8%). For RWGP the conditions were not optimized (180 °C and 5 mL/min), and the values of the yield in water soluble compounds (25 wt.%), phenolics extraction (19.5 mg/g) and carbohydrates recovery (11.4 wt.% relative to the existing 33.5%) were much lower. The antioxidant activity of the HCW extracts from each assay was determined, the best result being obtained for WWGP, namely for extracts obtained at 210 °C (EC50=20.8 μg/mL; EC50 = half maximum effective concentration; EC50 = 22.1 μg/mL for RWGP, at 180 ºC).

Production and characterization of Chitin-Glucan Complex by Komagataella pastoris

This thesis was focused on the production, extraction and characterization of chitin:β-glucan complex (CGC). In this process, glycerol byproduct from the biodiesel industry was used as carbon source. The selected CGC producing yeast was Komagataella pastoris (formerly known as Pichia pastoris), due the fact that to achieved high cell densities using as carbon source glycerol from the biodiesel industry. Firstly, a screening of K. pastoris strains was performed in shake flask assays, in order to select the strain of K. pastoris with better performance, in terms of growth, using glycerol as a carbon source. K. pastoris strain DSM 70877 achieved higher final cell densities (92-97 g/l), using pure glycerol (99%, w/v) and in glycerol from the biodiesel industry (86%, w/v), respectively, compared to DSM 70382 strain (74-82 g/l). Based on these shake flask assays results, the wild type DSM 70877 strain was selected to proceed for cultivation in a 2 l bioreactor, using glycerol byproduct (40 g/l), as sole carbon source. Biomass production by K. pastoris was performed under controlled temperature and pH (30.0 ºC and 5.0, respectively). More than 100 g/l biomass was obtained in less than 48 h. The yield of biomass on a glycerol basis was 0.55 g/g during the batch phase and 0.63 g/g during the fed-batch phase. In order to optimize the downstream process, by increasing extraction and purification efficiency of CGC from K. pastoris biomass, several assays were performed. It was found that extraction with 5 M NaOH at 65 ºC, during 2 hours, associated to neutralization with HCl, followed by successive washing steps with deionised water until conductivity of ≤20μS/cm, increased CGC purity. The obtained copolymer, CGCpure, had a chitin:glucan molar ratio of 25:75 mol% close to commercial CGC samples extracted from A. niger mycelium, kiOsmetine from Kitozyme (30:70 mol%). CGCpure was characterized by solid-state Nuclear Magnetic Resonance (NMR) spectroscopy and Differential Scanning Calorimetry (DCS), revealing a CGC with higher purity than a CGC commercial (kiOsmetine). In order to optimize CGC production, a set of batch cultivation experiments was performed to evaluate the effect of pH (3.5–6.5) and temperature (20–40 ºC) on the specific cell growth rate, CGC production and polymer composition. Statistical tools (response surface methodology and central composite design) were used. The CGC content in the biomass and the volumetric productivity (rp) were not significantly affected within the tested pH and temperature ranges. In contrast, the effect of pH and temperature on the CGC molar ratio was more pronounced. The highest chitin: β-glucan molar ratio (> 14:86) was obtained for the mid-range pH (4.5-5.8) and temperatures (26–33 ºC). The ability of K. pastoris to synthesize CGC with different molar ratios as a function of pH and temperature is a feature that can be exploited to obtain tailored polymer compositions.(...)

Semantic relations extraction from unstructured information for domain ontologies enrichment

Based in internet growth, through semantic web, together with communication speed improvement and fast development of storage device sizes, data and information volume rises considerably every day. Because of this, in the last few years there has been a growing interest in structures for formal representation with suitable characteristics, such as the possibility to organize data and information, as well as the reuse of its contents aimed for the generation of new knowledge. Controlled Vocabulary, specifically Ontologies, present themselves in the lead as one of such structures of representation with high potential. Not only allow for data representation, as well as the reuse of such data for knowledge extraction, coupled with its subsequent storage through not so complex formalisms. However, for the purpose of assuring that ontology knowledge is always up to date, they need maintenance. Ontology Learning is an area which studies the details of update and maintenance of ontologies. It is worth noting that relevant literature already presents first results on automatic maintenance of ontologies, but still in a very early stage. Human-based processes are still the current way to update and maintain an ontology, which turns this into a cumbersome task. The generation of new knowledge aimed for ontology growth can be done based in Data Mining techniques, which is an area that studies techniques for data processing, pattern discovery and knowledge extraction in IT systems. This work aims at proposing a novel semi-automatic method for knowledge extraction from unstructured data sources, using Data Mining techniques, namely through pattern discovery, focused in improving the precision of concept and its semantic relations present in an ontology. In order to verify the applicability of the proposed method, a proof of concept was developed, presenting its results, which were applied in building and construction sector.

An agent based architecture to support monitoring in plug and produce manufacturing systems using knowledge extraction

In recent years a set of production paradigms were proposed in order to capacitate manufacturers to meet the new market requirements, such as the shift in demand for highly customized products resulting in a shorter product life cycle, rather than the traditional mass production standardized consumables. These new paradigms advocate solutions capable of facing these requirements, empowering manufacturing systems with a high capacity to adapt along with elevated flexibility and robustness in order to deal with disturbances, like unexpected orders or malfunctions. Evolvable Production Systems propose a solution based on the usage of modularity and self-organization with a fine granularity level, supporting pluggability and in this way allowing companies to add and/or remove components during execution without any extra re-programming effort. However, current monitoring software was not designed to fully support these characteristics, being commonly based on centralized SCADA systems, incapable of re-adapting during execution to the unexpected plugging/unplugging of devices nor changes in the entire system’s topology. Considering these aspects, the work developed for this thesis encompasses a fully distributed agent-based architecture, capable of performing knowledge extraction at different levels of abstraction without sacrificing the capacity to add and/or remove monitoring entities, responsible for data extraction and analysis, during runtime.

La Cène ou la figure du banquet comme image de crise morale chez Zeng Fanzhi

Les yeux et les masques sont prévalents dans les oeuvres du peintre chinois contemporain Zeng Fanzhi (né en 1964), comme métaphore du jeu de pouvoir qui oppose les individus à l’appareil social et politique. Son oeuvre La Cène, d’après Leonard de Vinci, est un exemple frappant de cette préoccupation. Cet essai examine l’utilisation par l’artiste de cette représentation occidentale d’une crise morale (une trahison qui mène à la mort du Christ) pour exprimer la dystopie qui marque la Chine contemporaine. L’interprétation par Zeng de l’oeuvre de Vinci témoigne d’une compréhension profonde de sa signification à la Renaissance comme conflit entre le pouvoir terrestre et spirituel, auquel il surimpose la fonction du banquet dans la culture chinoise comme lieu de lutte politique. Un nihilisme détaché imprègne ce travail, à l’instar de l’interprétation métaphorique du banquet de Platon par Søren Kierkegaard, In Vino Veritas.