Abstract
This paper presents a method to identify the status (open or closed) of breakers in network branches, in the absence of status signal or electric measurements on the branch including the breaker. Indirect power measurements from the SCADA are combined to form a 2D image array, which is fed into a Convolutional Neural Network. The image construction is based on ranking measurements with the Cauchy-Schwarz divergence between two signal distributions (for breaker open and closed). The success rate obtained with this technique is close to 100% in the IEEE testbed adopted. © 2019 IEEE.

Abstract
Pedestrian behaviour modelling and simulation play a fundamental role in reducing traffic risks and new policies implementation costs. However, representing human behaviour in this dynamic environment is not a trivial task and such models require an accurate representation of pedestrian behaviour. Virtual environments have been gaining notoriety as a behaviour elicitation tool, but it is still necessary to understand the validity of this technique in the context of pedestrian studies, as well as to create guidelines for its use. This work proposes a proper methodology for pedestrian behaviour elicitation using virtual reality environments in conjunction with surveys or questionnaires. The methodology focuses on gathering data about the subject, the context, and the action taken, as well as on analyzing the collected data to finally output a behavioural model. The resulting model can be used as a feedback signal to improve environment conditions for experiment iterations. A concrete implementation was built based on this methodology, serving as an example for future studies. A virtual reality traffic environment and two surveys were used as data sources for pedestrian crossing experiments. The subjects controlled a virtual avatar using an HTC Vive and were asked to traverse the distance between two points in a city. The data collected during the experiment was analyzed and used as input to a machine learning model capable of predicting pedestrian speed, taking into account their actions and perceptions. The proposed methodology allowed for the successful data gathering and its use to predict pedestrian behaviour with fairly acceptable accuracy.

Abstract
LinkedIn is undoubtedly a market leader when it comes to social networks that are aimed for professional use, demonstrating over time that it is a highly valued instrument used by recruiters, as well as a successful way to complement/replace organic recruitment. One of the areas with the most current demand and specific requirements/skills is Information and Communication Technologies (ICT) and, as in all scientific fields, there is a huge focus on recruiting the best candidate in the shortest time possible. The key goals of this article are to understand the relevance of LinkedIn use by an ICT recruiter taking into account the specific requirements/skills often desired by companies, to perceive if ICT students and workers with an updated LinkedIn profile are contacted by recruiters, and comprehend if it is true to say that recruitment via a social network is faster and does not detract from the quality of the hired candidate, compared with organic recruitment. A survey was performed focusing on students and workers in the ICT field and two semi-structured interviews were conducted in a consulting firm as well as in a software house. The results obtained suggest that LinkedIn is an essential recruitment tool for the ICT companies/consulting firms, but it is important to emphasize that most companies combine organic recruitment with LinkedIn recruitment. In our study, 89% of the respondents with an updated LinkedIn account have already been contacted by recruiters, proving that LinkedIn can certainly increase the probability of being hired. © 2019, Springer Nature Switzerland AG.

Abstract
In today’s world, technology is an indispensable part of our daily life. More and more products are produced to satisfy the needs of a growing population and the Internet is creating new services every day. However, to be able to keep up with the growing demand, new technologies needed to be invented to increase the pace of production and to lower costs. Automating tasks was the solution and for many years machines did repetitive tasks, replaced people and created new and better jobs to substitute the old ones. Nowadays automation is reaching incredible levels and it is not creating enough jobs to replace the old ones. Will unemployment increase in the upcoming years or will humanity be able to adapt to a different job market? Our study focuses on the types of unemployment caused by automation and on the possible solutions that society needs to implement. The research also points out how people from different social classes face the changing job market and how all can benefit from it. A new form of governance of society may be needed, in view of previous failed forms including fascism, communism, and, more recently, liberalism. In the future there will be fewer and fewer jobs that cannot be replaced by a robot. With this, the probability of mass unemployment is very high. An ideology promoting a Universal Basic Income could be a solution to combat the massive unemployment that automation may cause in the future, especially in medium-skilled jobs. © Springer Nature Switzerland AG 2019.

Abstract
Diabetic Retinopathy (DR) is a leading cause of blindness in working age adults. DR lesions can be challenging to identify in fundus images, and automatic DR detection systems can offer strong clinical value. Of the publicly available labeled datasets for DR, the Indian Diabetic Retinopathy Image Dataset (IDRiD) presents retinal fundus images with pixel-level annotations of four distinct lesions: microaneurysms, hemorrhages, soft exudates and hard exudates. We utilize the HEDNet edge detector to solve a semantic segmentation task on this dataset, and then propose an end-to-end system for pixel-level segmentation of DR lesions by incorporating HEDNet into a Conditional Generative Adversarial Network (cGAN). We design a loss function that adds adversarial loss to segmentation loss. Our experiments show that the addition of the adversarial loss improves the lesion segmentation performance over the baseline.

Abstract
Robotics competitions are increasing in complexity and number challenging the researchers, roboticists and enthusiastic to address the robot applications. One of the well-known competition is the micromouse where the fastest mobile robot to solve a maze is the winner. There are several topics addressed in this competition such as robot prototyping, control, electronics, path planning, optimization, among others. A simulation can be used to speed-up the development and testing algorithms but faces the gap between the reality in the dynamics behaviour. In this paper, an open source realistic simulator tool is presented where the dynamics of the robot, the slippage of the wheels, the friction and the 3D visualization can be found. The complete simulator with the robot model and an example is available that allow the users to test, implement and change all the environment. The presented results validate the proposed simulator.