Advancing digital healthcare research and machine learning-aided knowledge extraction amidst the COVID-19 pandemic

The rapid progression of biomedical research coupled with the explosion of scientific literature has generated an exigent need for efficient and reliable systems of knowledge extraction. This dissertation contends with this challenge through a concentrated investigation of digital health, Artificial Intelligence, and specifically Machine Learning and Natural Language Processing's (NLP) potential to expedite systematic literature reviews and refine the knowledge extraction process. The surge of COVID-19 complicated the efforts of scientists, policymakers, and medical professionals in identifying pertinent articles and assessing their scientific validity. This thesis presents a substantial solution in the form of the COKE Project, an initiative that interlaces machine reading with the rigorous protocols of Evidence-Based Medicine to streamline knowledge extraction. In the framework of the COKE (“COVID-19 Knowledge Extraction framework for next-generation discovery science”) Project, this thesis aims to underscore the capacity of machine reading to create knowledge graphs from scientific texts. The project is remarkable for its innovative use of NLP techniques such as a BERT + bi-LSTM language model. This combination is employed to detect and categorize elements within medical abstracts, thereby enhancing the systematic literature review process. The COKE project's outcomes show that NLP, when used in a judiciously structured manner, can significantly reduce the time and effort required to produce medical guidelines. These findings are particularly salient during times of medical emergency, like the COVID-19 pandemic, when quick and accurate research results are critical.

Atividade motora adaptada : o conhecimento produzido nos programas Stricto Sensu em Educação Física no Brasil

Universidade Estadual de Campinas . Faculdade de Educação Física

Adaptação e validação da escla ASKAS - Aging Sexual Knowledge and Attitudes Scale em idosos brasileiros

Universidade Estadual de Campinas . Faculdade de Educação Física

Genome Survey Sequence Analysis and Identification of Homologs of Major Surface Protease (gp63) Genes in Trypanosoma rangeli

In this study, 222 genome survey sequences were generated for Trypanosoma rangeli strain P07 isolated from an opossum (Didelphis albiventris) in Minas Gerais State, Brazil. T. rangeli sequences were compared by BLASTX (Basic Local Alignment Search Tool X) analysis with the assembled contigs of Leishmania braziliensis, Leishmania infantum, Leishmania major, Trypanosoma brucei, and Trypanosoma cruzi. Results revealed that 82% (182/222) of the sequences were associated with predicted proteins described, whereas 18% (40/222) of the sequences did not show significant identity with sequences deposited in databases, suggesting that they may represent T. rangeli-specific sequences. Among the 182 predicted sequences, 179 (80.6%) had the highest similarity with T. cruzi, 2 (0.9%) with T. brucei, and 1 (0.5%) with L. braziliensis. Computer analysis permitted the identification of members of various gene families described for trypanosomatids in the genome of T. rangeli, such as trans-sialidases, mucin-associated surface proteins, and major surface proteases (MSP or gp63). This is the first report identifying sequences of the MSP family in T. rangeli. Multiple sequence alignments showed that the predicted MSP of T. rangeli presented the typical characteristics of metalloproteases, such as the presence of the HEXXH motif, which corresponds to a region previously associated with the catalytic site of the enzyme, and various cysteine and proline residues, which are conserved among MSPs of different trypanosomatid species. Reverse transcriptase-polymerase chain reaction analysis revealed the presence of MSP transcripts in epimastigote forms of T. rangeli.

Closing the gap in curriculum development leadership

“Closing the gap in curriculum development leadership” is a Carrick-funded University of Queensland project which is designed to address two related gaps in current knowledge and in existing professional development programs for academic staff. The first gap is in our knowledge of curriculum and pedagogical issues as they arise in relation to multi-year sequences of study, such as majors in generalist degrees, or core programs in more structured degrees. While there is considerable knowledge of curriculum and pedagogy at the course or individual unit of study level (e.g. Philosophy I), there is very little properly conceptualised, empirically informed knowledge about student learning (and teaching) over, say, a three-year major sequence in a traditional Arts or Sciences subject. The Carrick-funded project aims to (begin to) fill this gap through bottom-up curriculum development projects across the range of UQ’s offerings. The second gap is in our professional development programs and, indeed, in our recognition and support for the people who are in charge of such multi-year sequences of study. The major convener or program coordinator is not as well supported, in Australian and overseas professional development programs, as the lecturer in charge of a single course (or unit of study). Nor is her work likely to be taken account of in workload calculations or for the purposes of promotion and career advancement more generally. The Carrick-funded project aims to fill this gap by developing, in consultation with crucial stakeholders, amendments to existing university policies and practices. The attached documents provide a useful introduction to the project. For more information, please contact Fred D’Agostino at f.dagostino@uq.edu.au.

Rede social académica

O processo de Bolonha apresenta directivas para a construção de um espaço europeu de ensino superior. A adopção destas directivas requer uma abordagem que favoreça, na prática, a mobilidade dos estudantes que têm dificuldades em compreenderem as oportunidades que lhes são oferecidas. Neste contexto, esta dissertação explora a hipótese de utilização de uma rede social para apoiar a mobilidade de estudantes no espaço europeu. No âmbito desta dissertação propõe-se um modelo de conhecimento para representar os membros de uma rede social vocacionada para apoiar cenários de mobilidade, designada por rede social académica. Este modelo foi obtido pela fusão da ontologia Academic Ontology to Support the Bologna Mobility Process com a ontologia Friend of a Friend Ontology. Para efeitos de avaliação experimental, foi criado um demonstrador numa rede social disponível publicamente na Internet que utiliza uma versão simplificada do modelo proposto. Os cenários usados nas experiências representam situações reais às quais foi aplicado um processo rudimentar de descoberta de conhecimento

Teaching with Moodle in higher education

Nowadays, with the use of technology and the Internet, education is undergoing significant changes, contemplating new ways of teaching and learning. One of the widely methods of teaching used to promote knowledge, consists in the use of virtual environments available in various formats, taking as example the teaching-learning platforms, which are available online. The Internet access and use of Laptops have created the technological conditions for teachers and students can benefit from the diversity of online information, communication, collaboration and sharing with others. The integration of Internet services in the teaching practices can provide thematic, social and digital enrichment for the agents involved. In this paper we will talk about the advantages of LMS (Learning Management Systems) such as Moodle, to support the presential lectures in higher education. We also will analyse its implications for student support and online interaction, leading educational agents to a mixing of different learning environments, where they can combine face-to-face instruction with computer-mediated instruction, blended-learning, and increases the options for better quality and quantity of human interaction in a learning environment. We also will present some tools traditionally used in online assessment and that are part of the functionalities of Moodle. These tools can provide interesting alternatives to promote a more significant learning and contribute to the development of flexible and customized models of an evaluation which we want to be more efficient.

Definition of MV Load Diagrams via Weighted Evidence Accumulation Clustering using Subsampling

A definition of medium voltage (MV) load diagrams was made, based on the data base knowledge discovery process. Clustering techniques were used as support for the agents of the electric power retail markets to obtain specific knowledge of their customers’ consumption habits. Each customer class resulting from the clustering operation is represented by its load diagram. The Two-step clustering algorithm and the WEACS approach based on evidence accumulation (EAC) were applied to an electricity consumption data from a utility client’s database in order to form the customer’s classes and to find a set of representative consumption patterns. The WEACS approach is a clustering ensemble combination approach that uses subsampling and that weights differently the partitions in the co-association matrix. As a complementary step to the WEACS approach, all the final data partitions produced by the different variations of the method are combined and the Ward Link algorithm is used to obtain the final data partition. Experiment results showed that WEACS approach led to better accuracy than many other clustering approaches. In this paper the WEACS approach separates better the customer’s population than Two-step clustering algorithm.

Data mining contributions to characterize MV consumers and to improve the suppliers-consumers settlements

This paper deals with the establishment of a characterization methodology of electric power profiles of medium voltage (MV) consumers. The characterization is supported on the data base knowledge discovery process (KDD). Data Mining techniques are used with the purpose of obtaining typical load profiles of MV customers and specific knowledge of their customers’ consumption habits. In order to form the different customers’ classes and to find a set of representative consumption patterns, a hierarchical clustering algorithm and a clustering ensemble combination approach (WEACS) are used. Taking into account the typical consumption profile of the class to which the customers belong, new tariff options were defined and new energy coefficients prices were proposed. Finally, and with the results obtained, the consequences that these will have in the interaction between customer and electric power suppliers are analyzed.

Symbolic Knowledge Extraction from Trained Neural Networks Governed by Lukasiewicz Logics

This work describes a methodology to extract symbolic rules from trained neural networks. In our approach, patterns on the network are codified using formulas on a Lukasiewicz logic. For this we take advantage of the fact that every connective in this multi-valued logic can be evaluated by a neuron in an artificial network having, by activation function the identity truncated to zero and one. This fact simplifies symbolic rule extraction and allows the easy injection of formulas into a network architecture. We trained this type of neural network using a back-propagation algorithm based on Levenderg-Marquardt algorithm, where in each learning iteration, we restricted the knowledge dissemination in the network structure. This makes the descriptive power of produced neural networks similar to the descriptive power of Lukasiewicz logic language, minimizing the information loss on the translation between connectionist and symbolic structures. To avoid redundance on the generated network, the method simplifies them in a pruning phase, using the "Optimal Brain Surgeon" algorithm. We tested this method on the task of finding the formula used on the generation of a given truth table. For real data tests, we selected the Mushrooms data set, available on the UCI Machine Learning Repository.

The verification of temporal KBS: SPARSE - a case study in power systems

In this paper we present VERITAS, a tool that focus time maintenance, that is one of the most important processes in the engineering of the time during the development of KBS. The verification and validation (V&V) process is part of a wider process denominated knowledge maintenance, in which an enterprise systematically gathers, organizes, shares, and analyzes knowledge to accomplish its goals and mission. The V&V process states if the software requirements specifications have been correctly and completely fulfilled. The methodologies proposed in software engineering have showed to be inadequate for Knowledge Based Systems (KBS) validation and verification, since KBS present some particular characteristics. VERITAS is an automatic tool developed for KBS verification which is able to detect a large number of knowledge anomalies. It addresses many relevant aspects considered in real applications, like the usage of rule triggering selection mechanisms and temporal reasoning.

Universidades da terceira idade: duas décadas de intervenção em Portugal

Dissertação apresentada à Escola Superior de Educação de Lisboa para a obtenção do grau de mestre em Ciências da Educação - Especialidade em Educação Social e Intervenção Comunitária

An architecture for ambient intelligent environments

This paper presents the proposal of an architecture for developing systems that interact with Ambient Intelligence (AmI) environments. This architecture has been proposed as a consequence of a methodology for the inclusion of Artificial Intelligence in AmI environments (ISyRAmI - Intelligent Systems Research for Ambient Intelligence). The ISyRAmI architecture considers several modules. The first is related with the acquisition of data, information and even knowledge. This data/information knowledge deals with our AmI environment and can be acquired in different ways (from raw sensors, from the web, from experts). The second module is related with the storage, conversion, and handling of the data/information knowledge. It is understood that incorrectness, incompleteness, and uncertainty are present in the data/information/knowledge. The third module is related with the intelligent operation on the data/information/knowledge of our AmI environment. Here we include knowledge discovery systems, expert systems, planning, multi-agent systems, simulation, optimization, etc. The last module is related with the actuation in the AmI environment, by means of automation, robots, intelligent agents and users.

Mental health research in Brazil: policies, infrastructure, financing and human resources

The objective of this descriptive study was to map mental health research in Brazil, providing an overview of infrastructure, financing and policies mental health research. As part of the Atlas-Research Project, a WHO initiative to map mental health research in selected low and middle-income countries, this study was carried out between 1998 and 2002. Data collection strategies included evaluation of governmental documents and sites and questionnaires sent to key professionals for providing information about the Brazilian mental health research infrastructure. In the year 2002, the total budget for Health Research was US$101 million, of which US$3.4 million (3.4) was available for Mental Health Research. The main funding sources for mental health research were found to be the São Paulo State Funding Agency (Fapesp, 53.2%) and the Ministry of Education (CAPES, 30.2%). The rate of doctors is 1.7 per 1,000 inhabitants, and the rate of psychiatrists is 2.7 per 100,000 inhabitants estimated 2000 census. In 2002, there were 53 postgraduate courses directed to mental health training in Brazil (43 in psychology, six in psychiatry, three in psychobiology and one in psychiatric nursing), with 1,775 students being trained in Brazil and 67 overseas. There were nine programs including psychiatry, neuropsychiatry, psychobiology and mental health, seven of them implemented in Southern states. During the five-year period, 186 students got a doctoral degree (37 per year) and 637 articles were published in Institute for Scientic Information (ISI)-indexed journals. The investment channeled towards postgraduate and human resource education programs, by means of grants and other forms of research support, has secured the country a modest but continuous insertion in the international knowledge production in the mental health area.

Descoberta de conhecimento em Logs de tentativas de intrusão. Um estudo de caso em Instituições de Ensino Superior

Perante a evolução constante da Internet, a sua utilização é quase obrigatória. Através da web, é possível conferir extractos bancários, fazer compras em países longínquos, pagar serviços sem sair de casa, entre muitos outros. Há inúmeras alternativas de utilização desta rede. Ao se tornar tão útil e próxima das pessoas, estas começaram também a ganhar mais conhecimentos informáticos. Na Internet, estão também publicados vários guias para intrusão ilícita em sistemas, assim como manuais para outras práticas criminosas. Este tipo de informação, aliado à crescente capacidade informática do utilizador, teve como resultado uma alteração nos paradigmas de segurança informática actual. Actualmente, em segurança informática a preocupação com o hardware é menor, sendo o principal objectivo a salvaguarda dos dados e continuidade dos serviços. Isto deve-se fundamentalmente à dependência das organizações nos seus dados digitais e, cada vez mais, dos serviços que disponibilizam online. Dada a mudança dos perigos e do que se pretende proteger, também os mecanismos de segurança devem ser alterados. Torna-se necessário conhecer o atacante, podendo prever o que o motiva e o que pretende atacar. Neste contexto, propôs-se a implementação de sistemas de registo de tentativas de acesso ilícitas em cinco instituições de ensino superior e posterior análise da informação recolhida com auxílio de técnicas de data mining (mineração de dados). Esta solução é pouco utilizada com este intuito em investigação, pelo que foi necessário procurar analogias com outras áreas de aplicação para recolher documentação relevante para a sua implementação. A solução resultante revelou-se eficaz, tendo levado ao desenvolvimento de uma aplicação de fusão de logs das aplicações Honeyd e Snort (responsável também pelo seu tratamento, preparação e disponibilização num ficheiro Comma Separated Values (CSV), acrescentando conhecimento sobre o que se pode obter estatisticamente e revelando características úteis e previamente desconhecidas dos atacantes. Este conhecimento pode ser utilizado por um administrador de sistemas para melhorar o desempenho dos seus mecanismos de segurança, tais como firewalls e Intrusion Detection Systems (IDS).