Abstract
This paper addresses the problem of finding the best Brain Emotional Learning (BEL) controller parameters in order to improve the response of a single degree-of-freedom (SDOF) structural system under an earthquake excitation. The control paradigm considered is based on a semi-active system to control the dynamics of a lumped mass-damper-spring model, being carried out by changing the damping force of a magneto-rheological (MR) damper. A typical BEL based controller requires the definition of several parameters which can be proved difficult and non-intuitive to obtain. For this reason, an evolutionary based search technique has been added to the current problem framework in order to automate the controller design. In particular, the particle swarm optimization (PSO) method was chosen as the evolutionary based technique to be integrated within the current control paradigm. The obtained results suggest that, indeed, it is possible to parametrize a BEL controller using an evolutionary based algorithm. Moreover, simulation shows that the obtained results can outperform the ones obtained by manual tuning each controller parameter individually.

Abstract
Supply chains are complex interdependent structures in which tasks' accomplishment is the result of a compromise between all the entities involved. This complexity is particularly pronounced when dealing with chipping and transportation tasks within a forest-based biomass energy production supply chain. The logistic costs involved are significant and the number of network nodes are usually in a considerable number. For this reason, efficient optimization tools should be used in order to derive cost effective scheduling. In this work, soft computing optimization tools, namely genetic algorithms (GA) and particle swarm optimization (PSO), are integrated within a discrete event simulation model to define the vehicles operational schedule in a typical forest biomass supply chain. The presented simulation results show the proposed methodology effectiveness in dealing with the addressed systems.

Abstract
This work presents the state-of-the-art of visual sensing systems for monitoring and control purposes in both agriculture and forest areas. Regarding agricultural activities, four main topics are explored: robotics and autonomous vehicles, plant protection, feature extraction and yield prediction. Although vast literature can be found on image processing and computer vision applied to agriculture, its applications in forest-based systems are less frequent. Throughout this article, several research areas such as diseases control, post-processing, parameters estimation, UAVs and satellites will be addressed.

Abstract
The constant search for methods that allow the production processes improvement is a driving force for the development and integration of current technological solutions in systems which are, currently, still purely human based. It is in this context that the company "Factoryplay" comes forward with the challenge to upgrade its current sewing stations by adding a set of mechanization and automation solutions. This article documents the steps carried out to provide the current solution with the required technical attributes. In this paper, the instrumentation and actuation devised solutions, as well as the method employed to design an embedded PI controller, will be presented. The PI controller allows the closed-loop control of the station movement speed as a function of the sewing machine speed. The practical results obtained, regarding the dynamic response of the sewing station, are in line with the simulated ones.

Abstract
The present paper addresses the use of evolutionary based algorithms for off-line fractional-order controller tuning. In particular, a linearized model of a motor-rotor propulsion device was assumed whose representativeness is supported by laboratorial measurements. Initially, the controller was calibrated, using the devised linear model, by a procedure that uses a cost function defined as the linear combination between the sum of the squared error and the sum of the absolute error. In this work, it was shown that this process can be improved by using an evolutionary based algorithm in order to find the best controller parameters. This strategy allows a more automatic tuning procedure isolating it from the user intervention. Moreover, the results achieved by this process, lead to an improved rotational speed regulation.

Abstract
The present paper addresses the use of evolutionary based algorithms for off-line fractional-order controller tuning. In particular, a linearized model of a motor-rotor propulsion device was assumed whose representativeness is supported by laboratorial measurements. Initially, the controller was calibrated, using the devised linear model, by a procedure that uses a cost function defined as the linear combination between the sum of the squared error and the sum of the absolute error. In this work, it was shown that this process can be improved by using an evolutionary based algorithm in order to find the best controller parameters. This strategy allows a more automatic tuning procedure isolating it from the user intervention. Moreover, the results achieved by this process, lead to an improved rotational speed regulation. © 2018 IEEE.