Teses de Mestrado ESTiG
Permanent URI for this community
Browse
Browsing Teses de Mestrado ESTiG by Field of Science and Technology (FOS) "Ciências Naturais::Ciências da Computação e da Informação"
Now showing 1 - 9 of 9
Results Per Page
Sort Options
- An information system for a multiplayer geolocation gamePublication . Oghlukyan, Artur; Lopes, Rui Pedro; Usepyan, MarineA great deal of travel can educate tourists. As tourism becomes more accessible, many new technologies are being used to provide interesting, appealing, and efficient trips so that travelers can find what they want, avoid getting lost, and get the most out of their trip. Science, education, and culture all benefit from technological advancement. As many good ideas can now be turned into reality, interactive education has found a place in everyday life. Research and review of geolocation-based applications (such as hiking path providers) and guide applications were conducted to better understand the technologies and tools related to the topic. The best features were designed to solve the problem after summarizing the results of applications, their advantages and disadvantages. The purpose of this paper is to create a geolocation-based game that will allow travelers to explore nearby attractions, learn about local culture, and broaden their knowledge while traveling. To summarize, a dynamic platform that can be implemented in a variety of ways was created.
- Big data and analytics: the case study of students mobilityPublication . Mukhin, Dmitrii; Pereira, João PauloIt's no secret that the most important thing in our world is information. Nowadays, almost every action leaves a trace. And if we use this data correctly, we will get new knowledge and predictions. But this requires new specialized technologies such as Big Data. The work described in this dissertation focuses on three methods of Big Data analysis: descriptive analysis, correlation and predictive analysis. The purpose of the work is to explore these methods for practical application to a dataset containing information about IPB and Erasmus students. The following tasks were performed: collecting data from international students about their university practices and mobility, conducting descriptive analysis on general characteristics by year, course, gender, place of residence, degree, number of subjects studied and their grade point average. Correlation heat charts were constructed between the values in the dataset and dependencies were analyzed. The most important contribution of this paper is the practical application of three machine learning algorithms (Linear regression, Ridge regression, and Random forest) to predict the number of Erasmus students for the next year. The machine learning algorithms build a model from sample data, known as "training data," to make predictions or decisions without being explicitly programmed to do so.
- Digitization of industrial quality control procedures applied to visual and geometrical inspectionsPublication . Davanzo, Giuseppe Antonio Setem; Leitão, Paulo; Aikes Junior, JorgeIndustries quality control procedures are usually dependent on gauge inspection tools, and these tools are used to inspect visual and geometrical tolerance conformity. Operators are guided during an inspection by using paper tutorials that assist them in performing their tasks and registering the result of the performed analysis. This traditional method of registering information may be misleading, lowering the effectiveness of the quality control by providing inaccurate and error-prone inspection results. This work implements a system that uses emergent technologies (e.g., Human-Machine Interfaces, Virtual Reality, Distributed Systems, Cloud Computing, and Internet of Things (IoT)) to propose a costeffective solution that supports operators and quality control managers in the realization and data collection of gauge inspection control procedures. The final system was deployed in an industrial production plant, with the delivered results showing its efficiency, robustness, and highly positive feedback from the operators and managers. The software may offer a quicker and efficient execution of analysis tasks, significantly decreasing the setup time required to change the inspected product reference.
- DOTS - detection of covid-19 contagion symptoms and self-diagnosis in social networksPublication . Silva, Clístenes Fernandes da; Lopes, Rui Pedro; Junior, Arnaldo CandidoSocial media present ways for people to share emotions, feelings, ideas, and even symptoms of disease, and is a great source of data for a variety of analyses. At the end of 2019, an alert was raised for a global pandemic of a virus that has a very high contamination rate and can cause respiratory complications in the contaminated people. To help identify those who may have the symptoms of this disease or to control who are already infected, this paper analyzed the performance of KNN, Naive Bayes, Decision Tree, Random Forest, SVM, simple Multilayer Perceptron, Convolutional Neural Networks and BERT algorithms to classify tweets that contained reports of Covid-19 symptoms or selfreports of infection. The dataset was labeled using a set of disease symptom keywords taken from a list provided by the World Health Organization. The tests on these models showed that the Random Forest algorithm performed best when classifying the tweets in a small dataset. This work demonstrated a superior performance of the Random Forest algorithm over other more robust algorithms for this type of classification and dataset.
- Extracting temporal patterns from smart city dataPublication . Gubareva, Regina; Lopes, Rui Pedro; Burnakulova, G.S.In the modern world data and information become a powerful instrument of management, business, safety, medicine and others. The most fashionable sciences are the sciences which allow us to extract valuable knowledge from big volumes of information. Novel data processing techniques remains a trend for the last five years, in a way that continues to provide interesting results. This paper investigates the algorithms and approaches for processing smart city data, in particular, water consumption data for the city of Bragança, Portugal. Data from the last seven years was processed according to a rigorous methodology, that includes five stages: cleaning, preparation, exploratory analysis, identification of patterns and critical interpretation of the results. After understanding the data and choosing the best algorithms, a web-based data visualizing tools was developed, providing dashboards to geospatial data representation, useful in the decision making of municipalities.
- IT infrastructure & microservices authenticationPublication . Kadariya, Srison; Exposto, JoséBIOma - Integrated solutions in BIOeconomy for the Mobilization of the Agrifood chain project is structured in 6 PPS (Products, Processes, and Services) out of which, a part of PPS2 is covered in this work. This work resulted in the second deliverable of PPS2 which is defined as PPS2.A1.E2 - IT infrastructure design and graphical interface conceptual design. BIOma project is in the early stage and this deliverable is a design task of the project. For defining the system architecture, requirements, UML diagrams, physical architecture, and logical architecture have been proposed. The system architecture is based on microservices due to its advantages like scalability and maintainability for bigger projects like BIOma where several sensors are used for big data analysis. Special attention has been devoted to the research and study for the authentication and authorization of users and devices in a microservices architecture. The proposed authentication solution is a result of research made for microservices authentication where it was concluded that using a separate microservice for user authentication is the best solution. FIWARE is an open-source initiative defining a universal set of standards for context data management that facilitates the development of Smart solutions for different domains like Smart Cities, Smart Industry, Smart Agrifood, and Smart Energy. FIWARE’s PEP (Policy Enforcement Point) proxy solution has been proposed in this work for the better management of user’s identities, and client-side certificates have been proposed for authentication of IoT (Internet of Things) devices. The communication between microservices is done through AMQP (Advanced Message Queuing Protocol), and between IoT devices and microservices is done through MQTT (Message Queuing Telemetry Transport) protocol.
- Otimização de plataformas informáticas no setor bancárioPublication . Pereira, João Paulo Baptista; Exposto, José; Silva, Manuel Pinto Teixeira daA importância do acesso a informação de qualidade em tempo real é um fator critico de sucesso em qualquer setor de atividade. No caso do setor bancário, a concorrência é extremamente agressiva, levando os bancos a recorrer a plataformas informáticas capazes de integrar todo o processo organizacional e permitir uma melhor a ligação/iteração aos seus clientes. Os bancos estão a adaptar-se a esta revolução digital, o que implica levar a cabo uma alteração significativa nos modelos de negócio e na cultura interna das organizações. Para conseguir sobreviver, a banca tradicional está a adaptar-se através da simplificação e digitalização dos seus processos, tornando-os menos burocráticos e desta forma conseguir reduzir custos (redução do número de balcões físicos). A utilização de TI permite ao setor bancário, não só uma redução de custos, através da simplificação dos seus processos operacionais, e redução de recursos humanos, como também uma maior adaptação aos clientes dos dias de hoje e melhorar a sua relação com eles com recurso a técnicas de data-mining e AI. Os serviços E-Banking e M-Banking permitem-nos realizar um conjunto variado de operações bancárias através da internet e dos dispositivos móveis e que têm vindo a substituir os serviços tradicionais. Desta forma, a utilização de plataformas à medida do cliente, torna as empresas de TI extremamente importantes neste contexto atual. O presente relatório descreve o trabalho realizado, ao longo do estágio profissional realizado no âmbito do segundo ano do mestrado de Informática, na empresa ITSector (01/09/2021 a 31/03/2022), na área de suporte a plataformas informáticas do setor bancário. Na primeira parte do estágio foi necessário proceder à instalação e configuração dos cinco projetos internacionais atribuídos. Numa segunda parte, foram atribuídos tickets de baixa/media complexidade, onde já foi necessário reunir com os clientes, identificar requisitos, desenhar a solução, e implementar. Na última parte do estágio, foi atribuída a responsabilidade pela manutenção/otimização de um projeto internacional, onde foi necessário desenvolver novos módulos, alterar código existente (correções evolutivas personalizadas que surgiram por parte do cliente), e otimizar bases de dados.
- Secure data exchange in IIoTPublication . Sukiasyan, Anna; Pedrosa, TiagoIndustrial Internet of Things (IIoT) plays a central role for the Fourth Industrial Revolution. In the scope of Industry 4.0 many specialists of the field are working together towards implementing large scalable, reliable and secure Industrial environments. However, existing environments are lacking security standards and have limited resources per component which results in various security britches such as trust in between the components, partner factories or remote control units with the system. Due to the resilience and it’s security properties, combining blochchain-based solutions with IIoT environments is gaining popularity. Despite that, chain-structured classic blockchain solutions are extremely resource-intensive and are not suitable for power-constrained IoT devices. To mitigate the security challenges presented above a secure architecture is proposed by using a DAG-structured asynchronous blockchain which can provide system security and transactions efficiency at the same time. Use-cases and sequence diagrams were created to model the solution and a security threat analysis of the architecture is made. Threat analysis is performed based on STRIDE methodology and provides us in depth understanding how our security architecture mitigates the threats and reveals also open challenges. The results are robust, supported by extensive security evaluation, which foster future development over the proposed architecture. Therefore, the contributions made are valid, and as the architecture is generic, will be possible to deploy it in diverse custom industrial environments. The flexibility of the architecture will allow incorporation of future hardware and software development in the field.
- Webfolio - portfólio digital seguro para a educação de infânciaPublication . Silva, Willian de Oliveira; Lopes, Rui Pedro; Mesquita, Cristina; Beuren, Arlete TeresinhaNa educação infantil há diversas técnicas para avaliar o desenvolvimento das crianças através de experiência e de seu conhecimento acumulado durante o semestre letivo. Uma dessas técnicas utilizadas para avaliar o desenvolvimento das crianças é por meio de Portfólios. O uso do portfólio na educação infantil permite a avaliação formativa do aluno, possibilitando a reflexão por parte do aluno, dos professores e dos pais da criança a fim de compreender o processo escolar da criança. Este trabalho tem como objetivo principal o desenvolvimento de uma aplicação web, que permite o suporte para a construção de uma plataforma de armazenamento e partilha de portfólios digitais para a educação infantil. Além disso, pretende-se que seja feito um controle de acesso dos utilizadores para que seja possível o gerenciamento de acessos a determinados portfólios. Para o desenvolvimento da aplicação, foram utilizadas tecnologias como TypeScript, React, Node.js, MongoDB e Redis. O sistema deve possuir funcionalidades como: criar portfólios, criar observações e gerenciar permissões de utilizador. Após a implementação da aplicação, foram realizados testes de usabilidade no sistema, com pessoas que trabalham na área de educação infantil. Posteriormente, foram implementadas sugestões de melhoria para experiência do utilizador na aplicação.