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

Abstract
In the past years, data has become increasingly fast and volatile, making the ability to track its evolution an highly significant part of the value extraction process. In this work we present a framework to monitor evolution of clusters and present its use on real world data. We develop a framework over a previous one by Oliveira and Gama from 2013. Its biggest contribution is the addition of the concept of control area. This area will create a region around the cluster where it is still possible to establish associations with clusters from other time points. It aims to expand the search scope for cluster associations while diminishing the number of false positives. Changes to the transition definitions and detection algorithm are also introduced to accommodate the existence of this area. We demonstrate this framework at work in a real world scenario testing it with a telecom industry dataset and make a detailed analysis of the obtained results.

Abstract

Abstract
VASO is a Portuguese participatory maize breeding project (1984), where several maize landraces such as Pigarro have been selected both by a farmer's (phenotypic recurrent selection) and a breeder's approach (S2 lines recurrent selection). The objectives of this study were to determine the phenotypic and genotypic responses to participatory selection using these two different approaches, to clarify to which extent both selection methods preserve genetic diversity, and conclude what is the preferred method to apply in sustainable farming systems. The results, obtained via ANOVA, regression analyses and molecular markers, indicate that for both selection methods, genetic diversity was not significantly reduced, even with the most intensive breeder's selection. Although there were some common outputs, such as the determinated versus indeterminated ears, cob and ear weight ratio per ear and rachis 2, specific phenotypic traits evolved in opposite directions between the two selection approaches. Yield increase was only detected during farmer selection, indicating its interest on PPB. Candidate genes were identified for a few of the traits under selection as potential functional markers in participatory plant breeding.