Browsing by Issue Date, starting with "2022-01-06"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Air Transport Performance and Global Decision AnalysisPublication . Baltazar, Maria Emília da Silva; Silva, Jorge Miguel dos ReisSince the beginning of aviation, airports have played a pivotal role in Aeronautical Engineering. The airport concept has changed a lot over the past century from small airfields to international hubs. These airport infrastructures have played a significant role in the economic development of the regions they operate. The emergence of the airport city concept as a new successful organisational model suggests that any infrastructure of this kind to be competitive should adopt it. With all its inputs and outputs, the airport industry significantly influences the global economy. The balance between the public interest in general, shareholders, and airport operators must seek to be reconciled. I was investigated how it would be possible to determine whether an airport would have the expected impact on the economy at different scales. Those scales could be that of a continent, a country, a region, or even a city and establish the decision criteria for building (or not) new airport infrastructures and making improvements (or not) in them. Searching for tools that would allow an appropriate evaluation of the management processes of an airport, the measurement of the position of the airport compared to its counterparts (benchmarking) is essential. However, the complexity of the models used makes this tool unfriendly for airport administration. Apart from that, the essential focus of this type of study is the land side of the airport. Nevertheless, there are other types of studies for evaluating the performance of airport processes. Still, these are also complex and do not involve all operational, financial and agent components near the airport. The studies review reinforces the idea that a global analytical tool is essential to find the global perspective (airside, landside, and agents) of any airport's performance beyond the challenges that will be put to them soon and a complete benchmark of direct competitors. The construction of a new methodology requires that airport, land, and airside infrastructures be considered, and agents near the airport, customers, shareholders and airport operators. Thus, a well-founded analysis for a Global Decision Analysis (GDA) incorporates all the infrastructure stakeholders' interconnections in a single tool. GDA is, therefore, friendlier to stakeholders given the management and optimization of decisions based on an analysis system based on the MACBETH multi-criteria methodology, the PESA-AGB. This tool was built and applied to an airport with dimensions identical to Lisbon airport, demonstrating and comparing the evolution of performance and efficiency over 11 years from 2003 to 2013 by six key performance areas of the airport and the respective key performance indicators. The development of an airport efficiency tag for each year of assessment was implemented. An APE-Label implementation, applied to any airport, is presented, and discussed in this study regardless of its size and location. The main obstacle to implementing this APE-Label is the heterogeneity of the airport infrastructure since it differs in the number of runways for public, private or even public-private property, among others. However, with the PESA-AGB methodology, it was possible to mitigate this factor. The main proposal is to provide a graphical APE-Label that informs all interested parties which infrastructure assessment is analysed across the six key performance areas each year that will help to maximize performance and efficiency standards. For the airport case study, a self-benchmarking analysis was carried out for the airport's study with distinctive characteristics representing the central Portuguese air infrastructure. The airport in study is considered the largest in terms of passengers, movements and cargo and is associated with Lisbon airport. Finally, the results of PESA-AGB and GDA have been presented in two visual analysis panels. The dashboards and the GDA report and recommendation are prepared.
- Fake News Explosion in Portugal and Brazil the Pandemic and Journalists’ Testimonies on DisinformationPublication . Canavilhas, João; Jorge, Thaïs de MendonçaOrchestrated manipulations spread lies and can create an environment of uncertainty in society, leading to concerns from politicians, scholars, educators, and journalists, among others. In this paper we explore what the emergence of fake news (understood as false news) represents for journalists, trying to answer the following question: Does false news pose a threat to the credibility of good journalism, causing a disruption of the traditional work? To answer it, we interviewed a sample of journalists from various media organizations in Portugal and Brazil. Among the main findings, journalists are aware that fake news is a problem to be faced, as the blame for the dissemination of false news erroneously lies with the profession. They are conscious that something must be done and agree that the best way to fight against fake news is to invest in media literacy. Most of the journalists of our sample think they must be also more cautious to check sources for veracity and for political motivations. The results show that there is a resolve to reinforce the role of journalism in society
- Churn Rate Prediction in Telecommunications CompaniesPublication . Lima, Ana Lúcia de Morais; Inácio, Pedro Ricardo Morais; Neves, João Carlos RaposoCustomer churn is a central concern for companies operating in industries with low switching costs. Among all industries, the one that suffers most from this problem is the telecommunications sector, with an annual churn rate of approximately 30%. As operators grow, so does the volume of data, and understanding and interpreting this data is necessary for operators to understand why customer churn is happening. Through data science, machine learning, and artificial intelligence techniques, the possibilities of predicting customer churn have increased significantly. In this research, the proposed methodology consists of six phases. In its first phases, data preprocessing and feature analysis are performed. In the third phase, feature selection is performed. Then, the data were divided into two parts of training and testing, in the proportion of 80% and 20%, respectively. For the prediction process, the most popular prediction models were applied, i.e. logistic regression, vector machine, naive bays, random forest, decision trees, etc. In the training set, boosting and ensemble techniques were applied to achieve better model accuracy. In the training set, Kfold crossvalidation was used to avoid overlapping models. The results are evaluated using the confusion matrix and the AUC curve. The Adaboost, Catboost and XGBoost classifiers obtained the highest accuracy in the range of 85% and 92%. The highest AUC score was 98% obtained by Random Forest and 93% XGBoost which outperformed the other models.