Abstract
In this work, a cross-validation procedure is used to identify an appropriate Autoregressive Integrated Moving Average model and an appropriate state space model for a time series. A minimum size for the training set is specified. The procedure is based on one-step forecasts and uses different training sets, each containing one more observation than the previous one. All possible state space models and all ARIMA models where the orders are allowed to range reasonably are fitted considering raw data and log-transformed data with regular differencing (up to second order differences) and, if the time series is seasonal, seasonal differencing (up to first order differences). The value of root mean squared error for each model is calculated averaging the one-step forecasts obtained. The model which has the lowest root mean squared error value and passes the Ljung-Box test using all of the available data with a reasonable significance level is selected among all the ARIMA and state space models considered. The procedure is exemplified in this paper with a case study of retail sales of different categories of women's footwear from a Portuguese retailer, and its accuracy is compared with three reliable forecasting approaches. The results show that our procedure consistently forecasts more accurately than the other approaches and the improvements in the accuracy are significant.

Abstract
Deterministic models based on most likely forecasts can bring simplicity to the electricity power planning but do not explicitly consider uncertainties and risks which are always present on the electricity systems. Stochastic models can account for uncertain parameters that are critical to obtain a robust solution, requiring however higher modelling and computational effort. The aim of this work was to propose a methodology to identify major uncertainties presented in the electricity system and demonstrate their impact in the long-term electricity production mix, through scenario analysis. The case of an electricity system with high renewable contribution was used to demonstrate how renewables uncertainty can be included in long term planning, combining Monte Carlo Simulation with a deterministic optimization model. This case showed that the problem, of including risk in electricity planning could be explored in short running time even for large real systems. The results indicate that high growth demand rate combined with climate uncertainty represent major sources of risk for the definition of robust optimal technology mixes for the future. This is particularly important for the case of electricity systems with high share of renewables as climate change can have a major role on the expected power output.

Abstract
By 2050 it is expected that 66% of the world population will reside in cities, compared to 54% in 2014. One particular challenge associated to urban population growth refers to transportation systems, and as an approach to face it, governments are investing significant efforts enhancing public transport services. An important aspect of public transport is ensuring that licensing of such services fulfill existing government regulations. Due to the differences in government regulations, and to the difficulties in ensuring the fulfillment of their specific features, many local governments develop tailored Information and Communication Technology (ICT) solutions to automate the licensing of public transport services. In this paper we propose an ontology for licensing such services following the REFSENO methodology. In particular, the ontology captures common concepts involved in the application and processing stage of licensing public bus passenger services. The main contribution of the proposed ontology is to define a common vocabulary to share knowledge between domain experts and software engineers, and to support the definition of a software product line for families of public transport licensing services.

Abstract
The Oil and Gas Exploration & Production (E&P) field deals with high-dimensional heterogeneous data, collected at different stages of the E&P activities from various sources. Over the years different soft-computing algorithms have been proposed for data-driven oil and gas applications. The most popular by far are Artificial Neural Networks, but there are applications of Fuzzy Logic systems, Support Vector Machines, and Evolutionary Algorithms (EAs) as well. This article provides an overview of the applications of EAs in the oil and gas E&P industry. The relevant literature is reviewed and categorised, showing an increasing interest amongst the geoscience community.

Abstract
In classification, when there is a disproportion in the number of observations in each class, the data is said to be class imbalance. Class imbalance is pervasive in real world applications of data classification and has been the focus of much research. The minority class contributes too little to the decision boundary because the learning process learns from each observation in isolation. In this paper, we discuss the application of learning pairwise rankers as a solution to class imbalance. We compare ranking models to alternatives from the literature.

Abstract
Object representation is one of the most challenging tasks in robotics because it must provide reliable information in real-time to enable the robot to physically interact with the objects in its environment. To ensure reliability, a global object descriptor must be computed based on a unique and repeatable object reference frame. Moreover, the descriptor should contain enough information enabling to recognize the same or similar objects seen from different perspectives. This paper presents a new object descriptor named Global Orthographic Object Descriptor (GOOD) designed to be robust, descriptive and efficient to compute and use. The performance of the proposed object descriptor is compared with the main state-of-the-art descriptors. Experimental results show that the overall classification performance obtained with GOOD is comparable to the best performances obtained with the state-ofthe-art descriptors. Concerning memory and computation time, GOOD clearly outperforms the other descriptors. Therefore, GOOD is especially suited for real-time applications.