Marilton Sanchotene de Aguiar

An evolutionary spatial game-based approach for the self-regulation of social exchanges in MAS

An open problem in social simulation and MAS applications is the self-regulation of social exchange processes, aiming at the achievement/maintenance of equilibrated exchanges by the agents themselves, providing the continuation of the interactions in time. This paper faces this problem through an approach based on the proposed spatial and evolutionary Game of Self-Regulation of Social Exchange Processes. The agents, adopting different social exchange strategies, which take into account both the short and long-term aspects of interactions, evolve such strategies by themselves in time, in order to maximize their respective strategy-based fitness functions. In consequence, the agents happen to perform more equilibrated and fair interactions, increasing the number of successful exchanges.

An Extension of Fuzzy C-Means Applied to Spot Recognition in Images of Two-Dimensional Electrophoresis

Proteomics is defined as the large-scale characterization of protein sets expressed in a cell or tissue. Lately, proteomics has been broadly using two-dimensional gel electrophoresis for its analysis. It consists of migration and separation of molecules, placed in a gel, according to the strength of an electric field. In order to see these proteins, it is necessary to use some kind of reagent of revelation, which ends up resulting in a two-dimensional profile of spots. Afterwards, this gel is scanned and produces an image, and then this image may be analyzed. Usually, there is noise in this kind of image. Thinking on it, this work presents a technique using Fuzzy Logics to find spots.

Mobile ACORoute—Route Recommendation Based on Communication by Pheromones

Urban mobility problems affects the vast majority of cities nowadays. Thus, systems that provide real time information to assist in planning routes and choosing the most appropriate paths are essential to make transport more effective. As an alternative solution to problems related to mobility in cities, there are the so-called Intelligent Transportation Systems (ITS) which include the Route Recommendation Systems (RRS) and methodologies for congestion prediction that combine Information and Communication Technology (ICT) with Artificial Intelligence (AI) technology to improve the quality of transport systems. In this context, this work proposes the use of pheromone-based communication for building an ITS that offers information about real time traffic flow, taking into account the mobility of vehicles and passengers and the traffic dynamics. The general goal is to provide an Android solution able to suggest users routes calculated by the hybrid algorithm between A* and pheromone mechanism. The idea is to avoid areas of heavy traffic congestion.

A legislation-oriented VLE-MAS system applied to MOODLE

The Virtual Learning Environments (VLE) are considered virtual sites that have a vast amount of resources that allow it to host courses that occur as Distance Education (EaD in Portuguese) or blended mode, favoring communication between the actors involved in these arrangements. Assign Artificial Intelligence to VLEs using Multi-Agent Systems (MAS) is a way to facilitate the learning process. By analyzing the state of the art of existing VLEs today, it can be seen that they all work as tools to aid students, but none works the management aspects of distance education supporting legislation. Therefore, this article presents a model and VLE-MAS integration system that can make the VLE able to assist managers of distance education in their tasks incorporating legislation representation. In addition, this system will work in an evolutionary way where the machine-learning method called the nearest neighbors algorithm will be applied to help the dead-time warning mechanism.

Propagação de incêndios florestais: um modelo para o Netlogo integrado ao Spring e ao Google Earth

Resumo—The fire spread is a phenomenon that deserves much attention. Not just for their environmental, economic and social importance, but also because of its complexity, difficulty of modeling and computational power required for the simulation. Multiagent Systems exploit the behavior of a group of independent agents, with distinct features, evolving in a common environment. In this work, we apply this artificial intelligence technique to simulate fire spread in forests. We propose a hybrid model developed in the environment Netlogo and integrated to Spring GIS, for data collection, and to Google Earth, for visualization of the simulation.

An Architecture Proposal Based in Intelligent Algorithms for Motifs Discovery in Genetic Expressions

Motifs are not random entities found in DNA chains. A motif can also be defined as not a single phenomenon. Already motifs, besides having recurring patterns in the analyzed sequence, also have a biological function. Intelligent algorithms are search techniques widely used to find approximate solutions to optimization and search patterns in the science area of computing. Finding motifs in gene sequences is one of the most important problems in bioinformatics and belongs to the class NP-Complete. Therefore, it is plausible to investigate the hybridization of consolidated tools, but limited in their performance, in combination with intelligent systems techniques. This work has the premise to show a research of the main techniques and concepts of intelligent algorithms used in discovery of patterns (motifs) in gene expression and also an in-depth study of the major bioinformatics algorithms that are used for this function in recent years by researchers. It is understood that such techniques in combination, can achieve interesting results for research in bioinformatics. Thus proposing an optimized architecture for motifs discovery in genetic expressions of promoter regions of a bacteria. Using as many intelligent algorithms such as bioinformatics algorithms and refining techniques of its main data provided by the algorithms used. Thus forming an architecture with better performance due to hybridization of consolidated tools to search for patterns in genetic expressions.

Computational Techniques to Manage Natural Resources

To manage the natural resource, many aspect must be treat, because this are evolve all flora and fauna in planet. Mainly, how this management could improve the life quality in present and future, for all species not just for human begins. In literature, there are three computational challenges in natural resources management: data management and communication; data analysis; and optimization and control. In this paper, the authors present four case studies where some techniques could help in the management of natural resources and to solve these challenges.