Abstract
Deep learning (DL) incorporates a modern technique for image processing and big data analysis with large potential. Deep learning is a recent tool in the agricultural domain, being already successfully applied to other domains. This article performs a survey of different deep learning techniques applied to various agricultural problems, such as disease detection/identification, fruit/plants classification and fruit counting among other domains. The paper analyses the specific employed models, the source of the data, the performance of each study, the employed hardware and the possibility of real-time application to study eventual integration with autonomous robotic platforms. The conclusions indicate that deep learning provides high accuracy results, surpassing, with occasional exceptions, alternative traditional image processing techniques in terms of accuracy.

Abstract
A significant number of search and optimisation techniques whose principles seek inspiration from nature and biology phenomena have been proposed in the last decades. These methods have been successfully applied to solve a wide range of engineering problems. This is also the case of greenhouse environment control, which has been incorporating this type of techniques into its design. This paper addresses evolutionary and bio-inspired methods in the context of greenhouse environment control. Algorithm principles for reference techniques are reviewed, namely: simulated annealing, genetic algorithm, differential evolution and particle swarm optimisation. The last three techniques are considered using single and multiple objective formulations. A review of these algorithms within greenhouse environment control applications is presented, considering single and multiple objective problems, as well as their current trends.

Abstract
The design of Multi-Input Multi-Output nonlinear control systems for a quadrotor can be a difficult task. Nature inspired optimization techniques can greatly improve the design of non-linear control systems. Two recently proposed hunting-based swarm intelligence inspired techniques are the Grey Wolf Optimizer (GWO) and the Ant Lion Optimizer (ALO). This paper proposes the use of both GWO and ALO techniques to design a Sliding Mode Control (SMC) flight system for tracking improvement of altitude and attitude in a quadrotor dynamic model. SMC is a nonlinear technique which requires that its strictly coupled parameters related to continuous and discontinuous components be correctly adjusted for proper operation. This requires minimizing the tracking error while keeping the chattering effect and control signal magnitude within suitable limits. The performance achieved with both GWO and ALO, considering realistic disturbed flight scenarios are presented and compared to the classical Particle Swarm Optimization (PSO) algorithm. Simulated results are presented showing that GWO and ALO outperformed PSO in terms of precise tracking, for ideal and disturbed conditions. It is shown that the higher stochastic nature of these hunting-based algorithms provided more confidence in local optima avoidance, suggesting feasibility of getting a more precise tracking for practical use.

Abstract
Agricultural robotics is nowadays a complex, challenging, and exciting research topic. Some agricultural environments present harsh conditions to robotics operability. In the case of steep slope vineyards, there are several challenges: terrain irregularities, characteristics of illumination, and inaccuracy/unavailability of signals emitted by the Global Navigation Satellite System (GNSS). Under these conditions, robotics navigation becomes a challenging task. To perform these tasks safely and accurately, the extraction of reliable features or landmarks from the surrounding environment is crucial. This work intends to solve this issue, performing accurate, cheap, and fast landmark extraction in steep slope vineyard context. To do so, we used a single camera and an Edge Tensor Processing Unit (TPU) provided by Google & x2019;s USB Accelerator as a small, high-performance, and low power unit suitable for image classification, object detection, and semantic segmentation. The proposed approach performs object detection using Deep Learning (DL)-based Neural Network (NN) models on this device to detect vine trunks. To train the models, Transfer Learning (TL) is used on several pre-trained versions of MobileNet V1 and MobileNet V2. A benchmark between the two models and the different pre-trained versions is performed. The models are pre-trained in a built in-house dataset, that is publicly available containing 336 different images with approximately 1,600 annotated vine trunks. There are considered two vineyards, one using camera images with the conventional infrared filter and others with an infrablue filter. Results show that this configuration allows a fast vine trunk detection, with MobileNet V2 being the most accurate retrained detector, achieving an overall Average Precision of 52.98 & x0025;. We briefly compare the proposed approach with the state-of-the-art Tiny YOLO-V3 running on Jetson TX2, showing the outperformance of the adopted system in this work. Additionally, it is also shown that the proposed detectors are suitable for the Localization and Mapping problems.

Abstract
The objective is to investigate the tools and methodologies used in Higher Education (HE) of Electrical and Computer Engineering (ECE), identifying the curricular units that used them. The analysis was based on the perception of the course coordinators. Triangulation between multiple methodologies and different methods of analysis was used, combining lexical analysis, analysis of keywords and content analysis. Course coordinators were interviewed at three universities in Portugal and Brazil. In the content analysis, two categories emerged: the coordinators' perception of non-traditional methodologies, and the perception of software tools as didactic resources. The initiatives using non-traditional teaching processes and methodologies were reduced and punctual, with individual actions by teachers and not of educational standards discussed and institutionalized. The precariousness of laboratory infrastructure and software licenses was a common report.

Abstract
Bioinspired search algorithms are widely used for solving optimization problems. The evolution progress isusially measured by the fitness value of the population fittest element. The search stops when the algorithm reaches a predetermined number of iterations, or when no improvement is achieved after some iterations. Usually, no information, behind the best global objective value, is fed into the algorithm to influence its behavior. In this paper, a entropy metric is proposed to measure the algorithm convergence. Several experiments are carried out using a particle swarm optimization to analyze the metric relevance. Moreover, the proposed metric is used to implement a strategy to prevent premature convergence to suboptimal solutions. The results show that the index is useful for analyzing and improving the algorithm convergence during the evolution. © 2020, Springer Nature Switzerland AG.