An agent-based simulator to estimate domestic energy use

Throughout recent years, there has been an increase in the population size, as well as a fast economic growth, which has led to an increase of the energy demand that comes mainly from fossil fuels. In order to reduce the ecological footprint, governments have implemented sustainable measures and it is expected that by 2035 the energy produced from renewable energy sources, such as wind and solar would be responsible for one-third of the energy produced globally. However, since the energy produced from renewable sources is governed by the availability of the respective primary energy source there is often a mismatch between production and demand, which could be solved by adding flexibility on the demand side through demand response (DR). DR programs influence the end-user electricity usage by changing its cost along the time. Under this scenario the user needs to estimate the energy demand and on-site production in advance to plan its energy demand according to the energy price. This work focuses on the development of an agent-based electrical simulator, capable of: (a) estimating the energy demand and on-site generation with a 1-min time resolution for a 24-h period, (b) calculating the energy price for a given scenario, (c) making suggestions on how to maximize the usage of renewable energy produced on-site and to lower the electricity costs by rescheduling the use of certain appliances. The results show that this simulator allows reducing the energy bill by 11% and almost doubling the use of renewable energy produced on-site.

Agent-based parking occupancy simulation

The existing parking simulations, as most simulations, are intended to gain insights of a system or to make predictions. The knowledge they have provided has built up over the years, and several research works have devised detailed parking system models. This thesis work describes the use of an agent-based parking simulation in the context of a bigger parking system development. It focuses more on flexibility than on fidelity, showing the case where it is relevant for a parking simulation to consume dynamically changing GIS data from external, online sources and how to address this case. The simulation generates the parking occupancy information that sensing technologies should eventually produce and supplies it to the bigger parking system. It is built as a Java application based on the MASON toolkit and consumes GIS data from an ArcGis Server. The application context of the implemented parking simulation is a university campus with free, on-street parking places.

Launching platforms for user-generated content

Field lab: Entrepreneurial and innovative ventures

Impact of mobile app user acquisition on managerial decisions: Evidence from empirical experiment

In this research we conducted a mixed research, using qualitative and quantitative analysis to study the relationship and impact between mobile advertisement and mobile app user acquisition and the conclusions companies can derive from it. Data was gathered from management of mobile advertisement campaigns of a portfolio of three different mobile apps. We found that a number of implications can be extracted from this intersection, namely to product development, internationalisation and management of marketing budget. We propose further research on alternative app users sources, impact of revenue on apps and exploitation of product segments: wearable technology and Internet of Things.

Who uses NHS saúde 24 hotline? Has the user changed over time?

There has been an increase in the use of telephone-based services and internet throughout the years and, therefore, the Saúde 24 Hotline has become an important service in Portugal. This service aims to screen, counsel and refer the patient in order to avoid unnecessary visits to health institutions and also to indicate the most appropriate resource according to the illness. This work has two different questions: the first one examines the determinants of satisfaction that have more influence on the overall satisfaction of the Saúde 24 Hotline users. The second one aims to analyze if the confidence level of the users is increasing over time, measured by following the recommendation. The first study was conducted on a random sample collected from June to October 2014, which was taken from the User Satisfaction Survey. The second approach includes data from January 2008 to December 2014 from the Clinical Data Base of all users who have called the Hotline. Findings suggest that the majority of users are very satisfied with the service and the variables with more impact on the overall satisfaction are commitment and availability from the nurse, adequacy of call duration and quick identification of the problem. The survey indicates that 94% of respondents follow the recommendation and on average people have called the hotline 3 times in the previous year. The results from the Clinical Database show that people who were recommended to go to the emergency room are more likely to follow the advice than the people who were recommended to book routine appointments

From user browsing behaviour to user demographics

A Internet conta hoje com mais de 3 mil milhões de utilizadores e esse valor não para de aumentar. Desta forma, proporcionar uma experiência online agradável aos seus utilizadores é cada vez mais importante para as empresas. De modo a tirar partido dos benefícios deste crescimento, as empresas devem ser capazes de identificar os seus clientes-alvo dentro do total de utilizadores; e, subsequentemente, personalizar a sua experiência online. Existem diversas formas de estudar o comportamento online dos utilizadores; no entanto, estas não são ideais e existe uma ampla margem para melhoria. A inovação nesta área pode comportar um grande potencial comercial e até ser disruptiva. Com isto em mente, proponho-me a estudar a possível criacão de um sistema de aprendizagem automática (machine learning) que permita prever informa ações demográficas dos utilizadores estritamente com base no seu comportamento online. Tal sistema poderia constituir uma alternativa às atuais opções, que são mais invasivas; mitigando assim preocupações ao nível da proteção de dados pessoais. No primeiro capítulo (Introdução) explico a motivação para o estudo do comportamento dos utilizadores online por parte de empresas, e descrevo as opções disponíveis atualmente. Apresento também a minha proposta e o contexto em que assenta. O capítulo termina com a identicação de limitações que possam existir a priori. O segundo capítulo (Machine Learning) fornece uma introdução sobre machine learning, com o estudo dos algoritmos que vão ser utilizados e explicando como analisar os resultados. O terceiro capítulo (Implementação) explica a implementação do sistema proposto e descreve o sistema que desenvolvi no decorrer deste estudo, e como integra-lo em sistemas já existentes. No quarto capítulo (Análise e manipulação dos dados), mostro os dados compilados e explico como os recolhi e manipulei para testar a hipótese. No quinto capítulo (Análise de dados e discussão) vemos como e que os dados recolhidos foram usados pelos vários algoritmos para descobrir como se correlacionam com dados dos utilizadores e analiso e discuto os resultados observados. Por fim, o sexto e último capítulo apresenta as conclusões. Dependendo dos resultados, mostro como a hipótese poderia ser melhor testada, ou então discuto os próximos passos para tornar o sistema realidade.