Authors: Leonardo Carvalho, Eduardo Bezerra, Gustavo Guedes, Laura Assis, Leonardo Lima, Rafael Barbastefano, Artur Ziviani, Fabio Porto, Eduardo Ogasawara

Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)

National Laboratory for Scientific Computing (LNCC)

Abstract: Due to the constant innovations in communications tools, several organizations are constantly evaluating the adoption of new communication tools (NCT) with respect to current ones. Especially, many organizations are interested in checking if NCT is really bringing benefits in their production process. We can state an important problem that tackles this interest as for how to identify when NCT is providing a significantly different complementary communication flow with respect to the current communication tools (CCT). This paper presents the Mixed Graph Framework (MGF) to address the problem of measuring the complementarity of a NCT in the scenario where some CCT is already established. We evaluated MGF using synthetic data that represents an enterprise social network (ESN) in the context of well-established e-mail communication tool. Our experiments observed that the MGF was able to identify whether a NCT produces significant changes in the overall communications according to some centrality measures.

Acknowledgments: The authors thank CNPq, CAPES, and FAPERJ for partially sponsoring this research.

Experimental Evaluation:

The evaluation of the proposed MGF in measuring if a NCT brings complementarity to a CCT for scenarios of Small Medium Enterprises (SME). We used synthetic data to simulate both CCT and NCT usage to explore the MGF under different group configurations and enterprise scales. Both MGF and experimental evaluation is made available at https://github.com/eogasawara/mgf.

Preprint at https://peerj.com/preprints/3114v1/

Authors: Rebecca Salles, Patricia Mattos, Ana-Maria Dubois Iorgulescu, Eduardo Bezerra, Leonardo Lima, Eduardo Ogasawara

Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)

Abstract: Extreme environmental events such as droughts affect millions of people all around the world. Although it is not possible to prevent this type of event, its prediction under different time horizons enables the mitigation of eventual damages caused by its occurrence. An important variable for identifying occurrences of droughts is the sea surface temperature (SST). In the Tropical Atlantic Ocean, SST data are collected and provided by the Prediction and Research Moored Array in the Tropical Atlantic (PIRATA) Project, which is an observation network composed of sensor buoys arranged in this region. Sensors of this type, and more generally Internet of Things (IoT) sensors, commonly lead to data losses that influence the quality of datasets collected for adjusting prediction models. In this paper, we explore the influence of temporal aggregation in predicting step-ahead SST considering different prediction horizons and different sizes for training data sets. We have conducted several experiments using data collected by PIRATA Project. Our results point out scenarios for training datasets and prediction horizons indicating whether or not temporal aggregated SST time series may be beneficial for prediction.

Acknowledgments: The authors thank CNPq and FAPERJ for partially sponsoring this research.

Experimental Evaluation:

The sea surface temperature (SST) data and R-functions used to perform the experimental evaluation are available in the following RData files. Furthermore, we present scripts for generating CSV files with the computed SST prediction errors and the p-values of their statistical analysis, respectively.

Prediction Errors Generation:

Experiment.RData

#Load required packages
library(TSPred)
library(DMwR)
library(hydroGOF)

#Perform the experiment using ARIMA
PerChangeBuoysExp(SelectedBuoys,testyears=1,RW=FALSE,plot=FALSE)
#Perform the experiment using Random Walk
PerChangeBuoysExp(SelectedBuoys,testyears=1,RW=TRUE,plot=FALSE)

Statistical Analysis of the Prediction Errors:

ErrorsAnalysis.RData

library(nortest)

#Perform the statistical comparative analysis of each temporal aggregation approach
PredErrorsStats <- data.frame(BuoysExpStats(ErrorsBuoysPQ))[,c(1:4,8:10)]

#Perform the statistical comparative analysis of each temporal aggregation approach against daily Random Walk SST prediction
RWPredErrorsStats <- data.frame(BuoysExpStatsRW(ErrorsBuoysPQ,ErrorsBuoysRWPQ))[,c(1:4,8:10)]

Results:

• The results of the statistical tests performed for analysis of the SST time series in the experimental dataset: BuoysStatisticalAnalysisResults
• ARIMA models generated in the experimental evaluation: ARIMAModels
• The 173,040 SST prediction errors generated in the experimental evaluation: SST_PredErrors
• The normality tests result for the prediction errors generated in the experimental evaluation: NormalityTestsResults
• The results of the statistical tests performed for analysis and comparison of the prediction errors generated in the experimental evaluation: ComparisonStatsTestsResults

Authors: Paula Chaves, Luan Paschoal, Tauan Velasco, Tiago Bento Sampaio,
Julliany Brandão, Carlos Otávio Schocair, João Quadros, Talita Oliveira, Eduardo Ogasawara

Abstract

The new orthographic agreement introduces some changes in the vocabulary of the Portuguese language. Although these changes have modified a small percentage of the vocabulary words, people are struggling to adapt to some of the new orthographic rules. Aiming to mitigate this problem using a ludic approach, we developed Orthographic Educational Game (JOE). JOE focuses predominantly on the rules of accents and hyphens. The game is divided into two modes: training and playing. In the playing mode, the current level of knowledge of the player in orthography is checked and measured. In the training mode, each word comes with a hint related to the rule that is being practiced at the moment. The game was evaluated through an experiment with both undergraduates and high school students. The results indicated that more than 80\% of students enjoyed learning orthography through the game-based approach of JOE..

JOE at PlayStore

• Evaluation procedure
• Evaluation form
• Experimental evaluation

Student: Rebecca Pontes Salles (rebeccapsalles@acm.org)

Advisor: Eduardo Ogasawara (eogasawara@ieee.org)

Description: Functions for time series prediction and accuracy assessment using automatic linear modeling. The generated linear models and its yielded prediction errors can be used for benchmarking other time series prediction methods and for creating a demand for the refinement of such methods. For this purpose, benchmark data from prediction competitions may be used.

Available at CRAN: https://CRAN.R-project.org/package=TSPred

Code repository at Git-Hub: https://github.com/RebeccaSalles/TSPred

Reference manual: TSPred.pdf

Acknowledgments: The authors thank CNPq for partially sponsoring this work.

Students: Ana Beatriz Cruz, Sabrina Seriques, and Leonardo Preuss

Advisor: Eduardo Ogasawara

Abstract:

Computer Science students are usually enthusiastic about learning Artificial Intelligence (AI) due to the possibility of developing computer games that incorporate AI behaviors. Under this scenario, Search Algorithms (SA) are a fundamental AI subject for various games. Implementing deterministic games, varying from tic-tac-toe to chess games, are common used to teach AI. Considering the perspective of game playing, however, stochastic games are usually more fun to play and are not much explored during the AI learning process. Other approaches in AI learning include developing search algorithms to compete against each other. These approaches are relevant and engaging but lack an environment that features both algorithm design and benchmarking capabilities. To address this issue, we present Amê – an environment to support the learning process and analysis of adversarial search algorithms using a stochastic card game. We have conducted a pilot experiment with Computer Science students that developed different adversarial search algorithms for Hanafuda (a traditional Japanese card game).

Data Privacy

While playing and using AME, no user data is sent or stored at AME. Only scores associated with your gameplay are sent so that you can access your ranking data.

Published paper

Amê at Google Playstore

Manual

Students: Diego Vaz Caetano, Josué Dias Cardoso and Luana Guimarães Piani Ferreira
Collaborators: Raphael Abreu, João Quadros, Joel Santos
Advisors: Leonardo Lignani, Eduardo Ogasawara

Abstract

The use of simulators as educational tools aims to increase students’ engagement in classes and seems to help them to understand difficult concepts. They can be used in natural science classes as an alternative for practical or experimental approaches when the time and space scales required are not compatible with the scholar environment. Through interactive simulators, students can explore the topic under study. Discoveries are made, predictions are confirmed or refuted by subsequent simulations, enhancing the comprehension of the phenomenon. This article presents Sim-Evolution, an educational simulator to help teachers presenting Charles Darwin’s Theory of Evolution by Natural Selection (TENS). Our intention with Sim-Evolution is to enable students to practice and comprehend TENS as a process that occurs at the population level. Given that it focuses on High School level, its interface was designed to be joyful, helping to engage students. We developed Sim-Evolution focusing on three basic biological principles that structure TENS: (i) variation, (ii) heredity and (iii) selection. Also, simulation design is based on Mendelian Genetics and population genetics. However, we intended that knowledge of these areas should not be a requisite for using Sim-Evolution. Therefore, students can observe laws of evolution and the genetic properties (genotypes) by analyzing species phenotypes and surviving populations. Sim-Evolution was evaluated by High-School students in a Biology class. Experiments indicate that students could observe TENS as a population process and were able to identify the principles of variation, heredity, and selection by indirect analysis from living species phenotypes.

App

Sim-Evolution at Google Play store
User manual

Experimental Evaluation

Evaluation Procedure

Evaluation Form

Source code at GitHub

Privacy policy

We understand that user privacy must be protected and, while our application does not collect any personal information from the user or device, we are committed to transparency and therefore feel obligated to develop this Privacy Policy, the To help the user understand what data we collect, why we collect them, and what we do with them.

Information we collect and how we use it

Our application has educational purposes and was developed under the coordination of the Computer Science Departament of CEFET/RJ (http://eic.cefet-rj.br). We collect the following application information for statistical research purposes:

• Application Name
• Application version
• Date / Time of application usage
• Simulation duration time (reported in simulation time counter)
• Type of environment used for the simulation (Forest, Savannah or Custom)
• Types of birds selected for the beginning of the simulation
• Types of birds existing at the close of the simulation, with their respective quantities
  

The information is collected and transmitted automatically at the end of each simulation when the user exits the simulation screen.

We use this information for application usage search purposes and also for possible application feature enhancements.

When this Privacy Policy applies

Our Privacy Policy applies to Sim-Evolution and its built-in features but excludes services that Google offers on Android devices.

Our Privacy Policy does not apply to services offered by other companies or individuals, including products or websites that may be displayed to the user in search results, sites that may include Sim-Evolution services or other sites with links to our services. Our Privacy Policy does not control the information practices of other companies and organizations that advertise our services and may use cookies, pixel tags, and other technologies to deliver relevant ads.

If you have any questions or concerns about our privacy policy or our practices, please contact us at gpcacefetrj@gmail.com.

Pattern discovery is an important task in time series mining. A particular pattern that occurs a significant number of times in a time series is called a motif. Several approaches have been developed to discover motifs in time series. However, we can observe a clear gap regarding the exploration of the spatial-time series data according to the literature review. Also, it is challenging to understand and characterize the real meaning of the motif obtained concerning the data domain, comparing different approaches and analyzing the quality of the results obtained.

We propose STMotif Explorer, a spatial-time motif analysis system that aims to interactively discover, analyze, and visualize spatial-time motifs in different domains, offering insight to users. STMotif Explorer enables users to use and implement different spatiotemporal motif detection techniques and then run this across various domains. Besides, STMotif Explorer offers the users a set of interactive resources where it is possible to visualize and analyze the discovered motifs and compare the results from different techniques. We demonstrate the features of our system with different approaches using real data.

Demonstration Video