Abstract
Carpooling is a car sharing practice first adopted in the United States of America during the fuel crisis in the 1970s. Since then, and after some ups and downs, this practice has been growing in recent years, being currently used throughout the world. With the evolution of mobile technologies, carpooling had the opportunity to expand, especially through mobile applications and web pages. With these technologies, it is possible for anyone in any part of the globe to search for others that wish to go to the same place and want to share their car. With this practice, people intend to save money, help preserve the environment, reduce congestions in cities, increase the number of places available to park and meet new people. This paper introduces MoCaS Mobile Carpooling System, a carpool service offered for registered users. In this system, each user can enter his travels and make appointments, assign ratings, register vehicles and add travel preferences. All this is possible via a web interface and also via a mobile application that together give greater support to those seeking such services. MoCaS distinguishes itself from other systems by offering innovative services, namely in the mobile component, that through location services allows for the booking of trips in real-time; in other words, not only trips that have not started, but trips that are already underway and that end up intersecting the user's position. Besides this novelty, this system provides a real-time map, where all trip stops are visible, as well as the location of carpoolers who are currently traveling. Both the web and the mobile applications were successfully developed, achieving good results in the performed tests, and are currently being prepared for deployment.

Abstract

Abstract
With an ever increasing number of vehicles traveling the roads, traffic problems such as congestions and increased travel times became a hot topic in the research community, and several approaches have been proposed to improve the performance of the traffic networks. This paper introduces the Inverted Ant Colony Optimization (IACO) algorithm, a variation of the classic Ant Colony algorithm that inverts its logic by converting the attraction of ants towards pheromones into a repulsion effect. IACO is then used in a decentralized traffic management system, where drivers become ants that deposit pheromones on the followed paths; they are then repelled by the pheromone scent, thus avoiding congested roads, and distributing the traffic through the network. Using SUMO (Simulation of Urban MObility), several experiments were conducted to compare the effects of using IACO with a shortest time algorithm in artificial and real world scenarios - using the map of a real city, and corresponding traffic data. The effect of the behavior caused by this algorithm is a decrease in traffic density in widely used roads, leading to improvements on the traffic network at a local and global level, decreasing trip time for drivers that adhere to the suggestions made by IACO as well as for those who do not. Considering different degrees of adhesion to the algorithm, IACO has significant advantages over the shortest time algorithm, improving overall network performance by decreasing trip times for both IACO-compliant vehicles (up to 84%) and remaining vehicles (up to 71%). Thus, it benefits individual drivers, promoting the adoption of IACO, and also the global road network. Furthermore, fuel consumption and CO2 emissions from both vehicle types decrease significantly when using IACO (up to 49%).

Abstract
Denial of Service attacks, which have become commonplace on the Information and Communications Technologies domain, constitute a class of threats whose main objective is to degrade or disable a service or functionality on a target. The increasing reliance of Cyber-Physical Systems upon these technologies, together with their progressive interconnection with other infrastructure and/or organizational domains, has contributed to increase their exposure to these attacks, with potentially catastrophic consequences. Despite the potential impact of such attacks, the lack of generality regarding the related works in the attack prevention and detection fields has prevented its application in real-world scenarios. This paper aims at reducing that effect by analyzing the behavior of classification algorithms with different dataset characteristics. © 2019, Springer Nature Switzerland AG.

Abstract
Fitness assignment is one of the biggest challenges in evolutionary art. Interactive evolutionary computation approaches put a significant burden on the user, leading to human fatigue. On the other hand, autonomous evolutionary art systems usually fail to give the users the opportunity to express and convey their artistic goals and preferences. Our approach empowers the users by allowing them to express their intentions through the design of fitness functions. We present a novel responsive interface for designing fitness function in the scope of evolutionary ant paintings. Once the evolutionary runs are concluded, further control is given to the users by allowing them to specify the rendering details of selected pieces. The analysis of the experimental results highlights how fitness function design influences the outcomes of the evolutionary runs, conveying the intentions of the user and enabling the evolution of a wide variety of images. © 2014 Springer-Verlag.

Abstract
Breast Cancer is the most common type of cancer in women worldwide. In spite of this fact, there are insufficient studies that, using data mining techniques, are capable of helping medical doctors in their daily practice. This paper presents a comparative study of three ensemble methods (TreeBagger, LPBoost and Subspace) using a clinical dataset with 25% missing values to predict the overall survival of women with breast cancer. To complete the absent values, the k-nearest neighbor (k-NN) algorithm was used with four distinct neighbor values, trying to determine the best one for this particular scenario. Tests were performed for each of the three ensemble methods and each k-NN configuration, and their performance compared using a Friedman test. Despite the complexity of this challenge, the produced results are promising and the best algorithmconfiguration (TreeBagger using 3 neighbors) presents a prediction accuracy of 73%. © Springer International Publishing Switzerland 2014.