Abstract
The agribusiness volatility is related to the uncertainty of the environment, rising demand, falling prices and new technologies. However, generation of agriculture data has increased over past years and can be used for a growing number of applications of data mining techniques in agriculture. The multidisciplinary approach of integrating computer science with agriculture will support the necessary decisions to be taken in order to mitigate risks and maximize profits. The present study analyzes different methods of regression applied in the study case of grapes production forecast. The selected methods were multivariate linear regression, regression trees, lasso and random forest. Their performance were compared against the predictions obtained by the company through the mean squared error and the coefficient of variation. The four regression methods used obtained better predictive results than the method used by the company with statistical significance < 0.5%.

Abstract
This paper presents a control method for modular multilevel converters (MMCs) as an interface between renewable energy sources and the grid. With growing penetration of renewable energy sources in the power grid, the developments in converter technologies and controller designs become more prominent. In this regard, dynamic and steady state analysis of the proposed model for an MMC use in a renewable energy based power system are provided through dc, 1st, and 2nd harmonic models of the converter in dq reference frame. This detailed configuration is then used to accomplish converter modulation and controller design. The first novel contribution of this control method is to provide an accurate pulse width modulation (PWM) strategy based on network and converter parameters, in order to achieve a stable operation for the interfaced MMC during connection of renewable energy sources into the power grid. In addition, the proposed method is able to mitigate the converter circulating current by inserting a second harmonic reference in the modulation process of the MMC, which is the second contribution this paper provides over other control techniques. A capacitor voltage balancing algorithm is also included in this control method to adjust each sub-module (SM) voltage within an acceptable range. Finally, converter's maximum stable operation range is determined based on the dynamic equations of the proposed model. The functionality of the proposed control method is demonstrated by detailed mathematical analysis and comprehensive simulations with MATLAB/Simulink.

Abstract
This paper proposes an adaptive Biased Random-key Genetic Algorithm (A-BRKGA), a new method with on-line parameter control for combinatorial optimization problems. A-BRKGA has only one problem-dependent component, the decoder and all other parts can be reused. To control diversification and intensification, a novel adaptive strategy for parameter tuning is introduced. This strategy is based on deterministic rules and self adaptive schemes. For exploitation of specific regions of the solution space we propose a local search in promising communities. The proposed method is evaluated on the Capacitated Centered Clustering Problem (CCCP), which is an NP-hard problem where a set of n points, each having a given demand, is partitioned into m clusters each with a given capacity. The objective is to minimize the sum of the Euclidean distances between the points and their geometric cluster centroids. Computational results show that the A-BRKGA with local search is competitive with other methods of literature.

Abstract
This paper presents a methodology based on random forest algorithm to predict the undergraduate academic performance of students from a polytechnic institution. The approach followed enabled to select 11 explanatory variables, starting from an initial set of around fifty, which allow to obtain a good predictive performance (R-2=0.79). These variables reveal crucial aspects for the definition of management strategies focused on promoting academic success.

Abstract
The applications of the blockchain technology are still being discovered. When a new potential disruptive technology emerges, there is a tendency to try to solve every problem with that technology. However, it is still necessary to determine what approach is the best for each type of application. To find how distributed ledgers solve existing problems, this study looks for blockchain frameworks in the academic world. Identifying the existing frameworks can demonstrate where the interest in the technology exists and where it can be missing. This study encountered several blockchain frameworks in development. However, there are few references to operational needs, testing, and deploy of the technology. With the widespread use of the technology, either integrating with pre-existing solutions, replacing legacy systems, or new implementations, the need for testing, deploying, exploration, and maintenance is expected to intensify.

Abstract
Tomographic wavefront reconstruction is the main computational bottleneck to realize real-time correction for turbulence-induced wavefront aberrations in future laser-assisted tomographic adaptive-optics (AO) systems for ground-based giant segmented mirror telescopes because of its unprecedented number of degrees of freedom, N, i.e., the number of measurements from wavefront sensors. In this paper, we provide an efficient implementation of the minimum-mean-square error (MMSE) tomographic wavefront reconstruction, which is mainly useful for some classes of AO systems not requiring multi-conjugation, such as laser-tomographic AO, multi-object AO, and ground-layer AO systems, but is also applicable to multi-conjugate AO systems. This work expands that by Conan [Proc. SPIE 9148, 91480R (2014)] to the multi-wavefront tomographic case using natural and laser guide stars. The new implementation exploits the Toeplitz structure of covariance matrices used in an MMSE reconstructor, which leads to an overall ON log N real-time complexity compared with ON2 of the original implementation using straight vector-matrix multiplication. We show that the Toeplitz-based algorithm leads to 60 nm rms wavefront error improvement for the European Extremely Large Telescope laser-tomography AO system over a well-known sparse-based tomographic reconstruction; however, the number of iterations required for suitable performance is still beyond what a real-time system can accommodate to keep up with the time-varying turbulence.