Salesian Journal on Information Systems

2-9

Authors: NEIVA, A. C. B.; LINDEN, R.; GUEDES, V. G.; MASSA, C. L. S.

Maintenance is an important step that must be performed as soon as possible, to minimize the impact of failures. In this paper we discuss the concept of power curve fitting and deviation calculation to detect failures that cause the wind turbines to misperform (the so-called Type I failures). As mathematics and software applications evolution for predictive maintenance is growing fast, simple considerations will be made to enable the development of an advanced individual power curve, so the real time turbine performance analysis may be as accurate as possible. Past environmental and production data is subjected to outlier filtration and statistical analysis, prior to creation of a best fit that would allow for future failures to be detected early. The innovation relies on segregating a power curve for each directional sector and on the correction of the influence of the temperature on the power production, achieving an advanced power curve that really mimics as close as possible the real operational output.

31-50

Authors: LIMA, S. M. L.; SILVA, H. K. L.; LUZ, J. H. S ; et al.

Each second, 8 (eight) new malwares (malicious + software) are launched. Based on this finding, our goal is to propose an antivirus endowed with artificial intelligence, which can identify malware through models based on neural networks of rapid training and high accuracy. The proposed antivirus is equipped with morphological extreme learning machines (mELMs), which are inspired by the image processing theory of Mathematical Morphology. The results shown here are compared with classical approaches and evaluated through widely used classification metrics. On average, the antivirus proposed can distinguish malware from benign applications in 99.80% of cases, with a training time of 9.32 seconds. We found an average ratio between percentage accuracy and training time in reverse order. The proposed antivirus is 96 times better than state-of-the-art Deep Learning.

2-18

Authors: FERREIRA JR, D. A., CABRAL, J. P. O., MACEDO, C. J. A. et al.

The Internet of Things (IoT) is based on objects ("things"), which are able to communicate and transfer data. The fact generates an increase in the flow of data traffic over the network. In order to support this increase, the heterogeneity of devices and the geographic distribution have the need for an infrastructure which can handle this demand. The Institute of Informatics of the Federal University of Goias has proposed a software-defined IoT gateway thats supports for various wireless communication technologies and fog/cloud environment integration. A prototype was deployed for the queue at the University Restaurant using a single gateway IoT, which was afterwards evaluaed with good performance. In this article, the results of the evaluation of the prototype are presented, as well as the expansion of the system in a pilot project at Campus Samambaia (UFG), with the implementation of multiple gateways IoT, aiming to collect data on the amount of organic waste , monitoring of garbage levels in selective bins, temperature, humidity, gas level and video monitoring. The experiments carried out were intended to analyze the working and the capacity of the system to manage the data flow, from the sensors to the user's application.

28-41

Authors: NASCIMENTO, P. S.; KOMATI, K. S.; ANDRADE, J. O.

This paper describes the proposal of an archtecture and the comparison of regression methods for the analysis of personal loan proposals using machine learning algorithms. The case study presented here deals with data from a financial company that has a historical database of credit analyses, formed by the client's profile information, his previous relationship history with the financial company and the loan proposal data. It is important that the proposed architecture achieves the following objectives: decrease the cost associated with accessing credit protection agency's data, improve the accuracy compared to the existing process, allow the IT team keep a control variable over the approval or not of the proposal, and keep current employees' jobs. In order to meet all these requirements, a differential of this proposal is the usage of two stages of analysis, one without the data from credit protection agencies and the second with this type of data (if necessary). Another differential is that regression models will be used, whose results are converted into discrete results via comparison with denial/approval thresholds. In the first step, the result is approved { when it is above a pass threshold, denied { when it is below a fail threshold, or proceed to the second step. The second stage process is similar, except that cases that do not qualify as approved or denied continue for manual analysis. The methodology comprises exploratory analysis and pre-processing of data, calibration, validation and tests in two regression models: Random Forest and Partial Least Squares. The results of the experiments showed that the Random Forest achieved results that were better than both the Partial Least Squares and the existing system in the financial company. For this configuration, the first stage of the classification process is able to classify 86.56% of the proposals without manual intervention, and in the second stage, 4.04% are also classified automatically, in addition to reaching 97% accuracy at the end of the second stage.

56-65

Authors: BEZERRA, W.R., KOCH, F.L., WESTPHALL, C.B.

This work provides the basis to understand and select Cloud Computing models applied for the development of IoT solutions using Low-Power Wide Area Network (LPWAN). Cloud Computing paradigm has transformed how the industry implement solution, through the commoditization of shared IT infrastructures. The advent of massive Internet of Things (IoT) and related workloads brings new challenges to this scenario demanding malleable configurations where the resources are distributed closer to data sources. We introduce an analysis of existing solution architectures, along with an illustrative case from where we derive the lessons, challenges, and opportunities of combining these technologies for a new generation of Cloud-native solutions.

2-18

Authors: LINDO, O. D.

All benefits obtained from the implementation of investments in Information and Communication Technologies (ICTs) are sources of value for the investing firm. However, it has been considered that decision makers lack a structured methodology or a well-defined framework for evaluating said investments by integrating tangible and intangible benefits. Recent studies proffer empirical evidence that decision makers focus their analysis on quantifiable economic benefits while neglecting intangible benefits. A review of the specialized literature was conducted resulting in the identification of a gap between theory and practice in the evaluation of ICT investments. Even though theorists propose evaluation methods with quantitative and qualitative approaches, decision makers tend to focus their analysis on quantifiable economic benefits and limit the estimation of intangible benefits to subjective judgments. This paper organizes and structures the teachings of the specialized literature reviewed and provides a basis for future work that may aim to contribute to the development of new methodology for estimating the intangible value impact of ICT investments, and thus reduce the identified gap.

31-38

Authors: LÊU M. O.; MORAIS, D. M. G. de, XAVIER, F., DIGIAMPIETRI, L. A.

Social bots are automated users who use social networks and messaging applications to interact with real users. These bots can be used for sharing important news such as weather information or in emergency situations. However, they can also be used for malicious purposes, such as spreading fake news. This paper presents a case study on bot penetration in electoral discussions during the second round of the 2018 Brazilian presidential elections. It was found that the number of bots participating in the electoral discussions may have exceeded 10% of the total users. The use of general user account characteristics proved to be very specic in identifying humans (it is estimated that over 97% of human users were correctly classified as humans), but bot recalls did not exceed 52.3%.

55-66

Authors: ALMEIDA, G. M. F., DIAS, E. S.

In this paper, we study the longest paths and their intersections in chordal graphs, weighted graphs, trees and complementary prism graphs. Theoretical results were obtained about the longest paths and their intersections and some factorial time algorithms in order to understand the problem and the behavior of the longest paths in the different graph types. Finally, we analyze the implementation of the algorithms and the tests made in the laboratory, showing the execution time and its performance given different graph sizes, where the reader can conclude the algorithms effciency and providing the test results for new ones. comparisons with future algorithms. This work is one of the results of a scientific initiation by the authors.

2-9

Authors: SILVA, R. C. C., FERNANDES, D. S. A., FERNANDES, M. G. C.

The development of social media and the Internet has given users a platform to express their beliefs and opinions with greater ease and outreach. Some of these opinions may be pejorative and discriminatory towards other users based only on characteristics such as the color of their skin. This article describe a process for the detection of traces of racism in Portuguese language messages on Twitter. It discusses racism in ethical and legal terms for conceptual definition, addresses Sentiment Analysis, its possible approaches and levels of analysis. It characterizes collected data regarding frequency and location. Finally, we discuss the facts perceived during the data collection and classification process.

24-31

Authors: FREITAS, R. de C.; DIAS, E. S.

Graphs are discrete mathematical structures whose theory is applicable to many problems. Alliances in graphs are a quite new field of study and in this paper we study the defensive alliances, which can be used as a mathematical model in web communities, social medias, food chain, etc. We describe theoretical results in wheel graphs and complementary prisms of complete graphs.

40-49

Authors: LOPES, V. H. L., ABREU, M. F. B. DE, SOUZA, P. F. A.

IoT will be based on the coexistence of devices and sensors that implements diverse wireless technologies, with different computational capacities, new security challenges arise. Hence, this work presents the ADISEH, a method for the authentication of IoT devices wich uses the characteristics of the electromagnetic signal in heterogeneous wireless networks, rendering these new environments safer. Simulations were performed to evaluate their use with ZigBee, Bluetooth and WiFi devices, considering different noise situations. The results provide evidence of its viability, both when an authorized device attempts to gain access to the network and when a malicious device tries to gain access by cloning the signal from the authorized device.

2-13

Authors: Ferreira, M. S., Dos Santos, K.C., Salgado, V. C. S.

Statistic are commonly used in football to analyze a players performance. Their application is done through the scout, a method of data collection that is seen as the actions of the athletes regarding the technical and/or tactical aspects. After reviewing the literature, we realized even though there are several softwares for scouting applications, they do not perform a thorough avaluation of a goalkeeper actions. The goal of this work is to develop a scout system with support to the evaluation of goalkeepers, called Goalkeeper. The purpose of the system is to assist physical education professionals and goalkeeping instructors in conducting their instructor's training by analyzing statistical statutes on a player's performance. The software was developed for the Android platform in order to allow the mobility of the user and use an application, since an evaluation can be performed through a videos, training camps or games. In order to evaluate the application, a questionnaire was applied to specialists. The results obtained were considered promising and allowed to observe the users' interest in the system.

26-34

Authors: SERPA, P; WEITZEL, L; CALADO, L.

Operational Oceanography is a reality nowadays, making it necessary for computer systems to improv the numerical models and the feasibility of numerical oceanographic systems. The main goal of this research is to study and design a system that uses Web Services paradigm in order to integrate oceanographic numerical modeling systems and autonomous computational systems. The system aims to provide an abstraction layer between applications such as Matlab, Fortran, Python, Java Script and the underlying network infrastructure. It is based on the REST architecture and the JavaScript Object Notation (JSON) protocol. Thus, both internal modules and external systems can communicate in a distributed, low-coupling and transparent manner, regardless of their location, development language and hardware platform. For Operational Oceanography, these characteristics bring some advantages including, for instance, the fact that it provides greater processing power for the execution of numerical models using specific hardware and it makes it possible to integrate new numerical models. Hence, the proposed system enables the evolution of the Numerical Oceanographic Prediction System, specially core operations of the Almirante Paulo Moreira Institute of Sea Studies (Brazilian Navy), as well as other oceanographic researches in general.

49-59

Authors: EBERMAM, E.; KROHLING, R.

Convolutional neural networks have been attracted great attention in the realm of complex tasks, mainly in image recognition. They were specifically designed to process images as inputs, as they act in local receptive fields, performing a convolution process. However, understanding the work principle of this network may not be an easy task, especially for beginners in the area of computational intelligence. Therefore, the objective of this work is to present in a didactic and intuitive way the convolutional neural networks. A case study involving alphabet character recognition is presented in order to ilustrate the feasibility of the approach.