Abstract
Background: BioTextRetriever is a Web-based search tool for retrieving relevant literature in Molecular Biology and related domains from MEDLINE. The core of BioTextRetriever is the dynamic construction of a classifier capable of selecting relevant papers among the whole MEDLINE bibliographic database. “Relevant” papers, in this context, means papers related to a set of DNA or protein sequences provided as input to the tool by the user. Methods: Since the number of retrieved papers may be very large, BioTextRetriever uses a novel ranking algorithm to retrieve the most relevant papers first. We have developed a new methodology that enables the automation of the assessment process based on a multi-criteria ranking function. This function combines six factors: MeSH terms, paper’s number of citations, author’s h-index, journals impact factor, author number of publications and journal similarity function. Results: The best results highlight the number of citations and the h-index factors. Conclusions: We have developed and a multi-criteria ranking function, that contemplates six factors, and that seems appropriate to retrieve relevant papers out of a huge repository such as MEDLINE. © 2014, Gonçalves et al.; licensee Springer.

Abstract
Operational planning at public transport companies is a complex process that usually comprises several phases. In the planning phase, schedules are constructed considering that buses arrive and depart as scheduled. Obviously, several disruptions frequently occur, but their impact on the operating conditions is not easy to estimate. This difficulty arises mostly due to the impossibility of testing different solutions under the same conditions. Indeed, typically, the available data are a result of the current plan, while new proposed solutions have not produced real data yet. Along this chapter we discuss the assessment of the impact of changes in the operational planning on the real operating conditions, before their occurrence. We present a framework for such assessment, which includes two components: the impact on costs, and the impact on revenues. We believe that this framework will be useful in future works on operational planning of public transport companies. © Springer International Publishing Switzerland 2014.

Abstract
How to improve the performance of a simulated soccer team using final game statistics? This is the question this research aims to answer using model-based collaborative techniques and a robotic team - FC Portugal - as a case study. After developing a framework capable of automatically calculating the final game statistics through the RoboCup log files, a feature selection algorithm was used to select the variables that most influence the final game result. In the next stage, given the statistics of the current game, we rank the strategies that obtained the maximum average of goal difference in similar past games. This is done by splitting offline past games into different k-clusters. Then, for each cluster, the expected best strategy was assigned. The online phase consists in the selection of the expected best strategy for the cluster in which the current game best fits. Regarding the final results, our approach proved that it is possible to improve the performance of a robotic team by more than 35%, even in a competitive environment such as the RoboCup 2D simulation league.

Abstract
This paper presents a comparison between listwise and pointwise approaches for instance ranking using Multiple Linear Models. A theoretical review of both approaches is performed, including the evaluation methods. Experiments done in seven datasets from 4 different problems show that the pointwise approach is slightly better or similar than the listwise approach. However the models obtained with the listwise approach are more interpretable because they have in average fewer features than the models obtained with the pointwise approach. The obtained results are important for problems where interpretable ranking models are necessary.

Abstract
Under the scope of a Portuguese regional maize ear competition (the "Sousa Valley Best Ear Competition"), an ear value (EV) formula was developed in 1993 based on published maize trait correlations. This formula had two main purposes, ears evaluation for the ear competition and maize improvement selection. The EV formula included only ear length, kernel weight at 15% moisture, number of rows and number of kernels/ear, with no direct inputs from farmers maize yield. In order to add a more scientific dimension to this popular maize evaluation approach, four main goals were defined: (1) to test alternative interpretable regression methods to provide new ear value formulas that better estimates the yield potential using ear traits; (2) to develop a new instance ranking method, allowing to select the best new ear value formula to be used on the ear competition; (3) to identify a set of traits that will help farmers on selection toward better yield; and (4) to compare the ranking results obtained by the original EV formula and the newly one developed, using data from the "Sousa Valley Best Ear" competition. To achieve these goals we analyzed some of the competition winning maize populations, on a multilocation field trial, collecting not only ear, but also field traits and yield. This data was analyzed using multiple linear regression (MLR) and multiple adaptive regression splines (MARS). A new ranking evaluation measure (PR.NDCG measure) was developed to rank the eleven interpretable regression methods obtained, and our results indicated that the most appropriate formula for yield potendal estimation included the original EV traits, but with different coefficients and was entitled adjusted EV (EVA). Ear weight, kernel depth and rachis 2, followed by cob and ear diameters and number of kernels per row were also considered traits of major importance to define potential EV formulas, i.e., contributing to yield increase. Plant stand was the most important field variable for yield potential estimation. We also observed, from comparing EV and EVA ranking, that four of the top ranks maize ears using EV were included on the EVA top ten ranks. From all the above and due to its simplicity, we conclude that the new EVA formula is a valid starting point for a long term engagement of farmers with maize germplasm development and improvement and an open door to their better understanding of maize quantitative genetics.

Abstract
Collaborative filtering techniques have been used for some years, almost exclusively in Internet environments, helping users find items they are expected to like by using the user's past purchases to provide such recommendations. With this concept in mind, this research uses a collaborative filtering technique to automatically improve the performance of a simulated soccer team. Many studies have attempted to address this problem over the last years but none has shown meaningful improvements in the performance of the soccer team. Using a collaborative filtering technique based on nearest neighbors and the FC Portugal team as the test subject (in the context of the RoboCup 2D Simulation League), several simulations were run for matches against different teams with much better, better and worse performance than FC Portugal. The strategy used by FC Portugal was to combine 8 set-plays and 2 team formations. The simulation results revealed an improvement in performance between 32% and 384%. In the future, there are plans to expand this approach to other contexts, such as the 3D Simulation League.