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.

Risk of employing an evolvable production system

Nowadays manufacturing companies are facing a more challenging environment due to the unpredictability of the markets in order to survive. Enterprises need to keep innovating and deliver products with new internal or external characteristics. There are strategies and solutions, to different organisational level from strategic to operational, when technology is growing faster in operational level, more specifically in manufacturing system. This means that companies have to deal with the changes of the emergent manufacturing systems while it can be expensive and not easy to be implement. An agile manufacturing system can help to cope with the markets changeability. Evolvable Production Systems (EPS) is an emergent paradigm which aims to bring new solutions to deal with changeability. The proposed paradigm is characterised by modularity and intends to introduce high flexibility and dynamism at shop floor level through the use of the evolution of new computational devices and technology. This new approach brings to enterprises the ability to plug and unplug new devices and allowing fast reformulation of the production line without reprogramming. There is no doubt about the advantages and benefits of this emerging technology but the feasibility and applicability is still under questioned. Most researches in this area are focused on technical side, explaining the advantages of those systems while there are no sufficient works discussing the implementation risks from different perspective, including business owner. The main objective of this work is to propose a methodology and model to identify, classify and measure potential risk associated with an implementation of this emergent paradigm. To quantify the proposed comprehensive risk model, an Intelligent Decision system is developed employing Fuzzy Inference System to deal with the knowledge of experts, as there are no historical data and sufficient research on this area. The result can be the vulnerability assessment of implementing EPS technology in manufacturing companies when the focus is more on SMEs. The present dissertation used the experts’ knowledge and experiences, who were involved in FP7 project IDEAS, which is one of the leading projects in this area.

Benchmarking sobre técnicas de otimização para modelos de apoio à decisão na medicina intensiva

Dissertação de mestrado integrado em Engenharia e Gestão de Sistemas de Informação

Segmentação de imagens fetais com potencial para desenvolvimento de ferramentas de apoio ao diagnóstico

Programa Doutoral em Engenharia Eletrónica e de Computadores

Refinement in hybridised institutions

Hybrid logics, which add to the modal description of transition structures the ability to refer to specific states, offer a generic framework to approach the specification and design of reconfigurable systems, i.e., systems with reconfiguration mechanisms governing the dynamic evolution of their execution configurations in response to both external stimuli or internal performance measures. A formal representation of such systems is through transition structures whose states correspond to the different configurations they may adopt. Therefore, each node is endowed with, for example, an algebra, or a first-order structure, to precisely characterise the semantics of the services provided in the corresponding configuration. This paper characterises equivalence and refinement for these sorts of models in a way which is independent of (or parametric on) whatever logic (propositional, equational, fuzzy, etc) is found appropriate to describe the local configurations. A Hennessy–Milner like theorem is proved for hybridised logics.