Abstract
Metaheuristics (MH) aptitude to move past local optimums makes them an attractive technique to approach complex computational problems, such as the Travelling Salesman Problem (TSP), but there is lack of information on the parameterization procedure and the appropriate parameters to improve MHs' performance. In this paper the parameterization procedure of Simulated Annealing (SA) and Discrete Artificial Bee Colony (DABC) is addressed, with a focus on the Neighborhood Structure (NS). Numerous NS have been proposed for specific problems, which seem to indicate that the NS is a special parameter, whose optimization is independent of other parameters. The performance of eight NS was examined with SA and DABC under two optimization constraints, regarding computational time variation, to determine if there is one appropriate NS for the TSP problem, independent of the rest of the parameters of the optimization procedure. The computational study carried out for comparing the evaluation of the NS, including a statistical analysis, demonstrated a nonproportional increase in the performance of DABC with some NS. For SA the improvement of the solutions appeared to be more uniform with an almost nonexistent variance in improvement.

Abstract
We live in a world where data is becoming increasingly valuable and increasingly abundant in volume. All companies produce data from sales, sensors, and various other sources. The main challenges are how can we extract insights from such a rich data environment and if Deep Learning is capable of circumventing Big Data's challenges. To reach a conclusion, Social Network data is used as a case study for predicting sentiment changes in the Stock Market. The main objective of this paper is to develop a computational study and analyze its performance. Deep Learning was able to handle some challenges of Big Data, allowing results to be obtained and compared with real world situations. The outputs contribute to understand Deep Learning's usage with Big Data and how it acts in Sentiment Analysis.

Abstract
The domain of Production Planning and Control, or in a broader sence Production Management has been deserving a special and increasing attention by the companies, which intend to continuously achieve better results through continuous improvement, which also fits in the context of Industry 4.0. Companies tend to implement management systems with the purpose of achieving greater competitiveness and, consequently, greater sustainability in their sector. The selection of the appropriate production management system is a serious problem for the companies. The main objective of this study is to support companies in the correct choice of a Decision Support System. The method used to achieve the proposed objective consists on formulating a model for comparing functionalities and specifications, where selection of criteria were also defined and analyzed. Based on a large Company scenario, the model is applied to three production execution systems: SAP PP (Systems Applications and Products - Production Planning), Prodsmart and GenSYS.

Abstract

Abstract
In real manufacturing environments, scheduling can be defined as the problem of effectively and efficiently assigning tasks to specific resources. Metaheuristics are often used to obtain near-optimal solutions in an efficient way. The parameter tuning of metaheuristics allows flexibility and leads to robust results, but requires careful specifications. The a priori definition of parameter values is complex, depending on the problem instances and resources. This paper implements a novel approach to the automatic specification of metaheuristic parameters, for solving the scheduling problem. This novel approach incorporates two learning techniques, namely, racing and case-based reasoning (CBR), to provide the system with the ability to learn from previous cases. In order to evaluate the contributions of the proposed approach, a computational study was performed, focusing on comparing our results previous published results. All results were validated by analyzing the statistical significance, allowing us to conclude the statistically significant advantage of the use of the novel proposed approach.

Abstract
Disasters, both natural and man-made, are extreme and complex events with consequences that translate into a loss of life and/or destruction of properties. The advances in IT and Big Data analysis represent an opportunity for the development of resilient environments once the application of analytical methods allows extracting information from a significant amount of data, optimizing the decision-making processes. This research aims to apply the CRISP-DM methodology to extract information about incidents that occurred in the city of Lisbon with emphasis on occurrences that affected buildings, constituting a tool to assist in the management of the city. Through this research, it was verified that there are temporal and spatial patterns of occurrences that affected the city of Lisbon, with some types of occurrences having a higher incidence in certain periods of the year, such as floods and collapses that occur when there are high levels of precipitation. On the other hand, it was verified that the downtown area of the city is the area most affected by occurrences. Finally, machine learning models were applied to the data and the predictive model Random Forest obtained the best result with an accuracy of 58%.