Jose Viterbo

• Professor (Associate) at Fluminense Federal University

Public Procurement Processes (PPPs) involve substantial taxpayer money, necessitating efficiency and transparency. Artificial Intelligence (AI) is increasingly applied to fraud detection in PPPs, enhancing these processes. This work presents a literature review on AI’s role in PPP fraud detection, focusing on ethical and technical challenges, inclu...

Multi-agent Systems (MAS) are groups of autonomous agents that act in the same environment, competing or collaborating to achieve individual or collective goals. Such systems can be integrated into embedded devices to perform tasks that control hardware. The main challenges encountered between Embedded MAS are the connectionless protocols some IoT...

Multi-agent systems (MAS) applied to Embedded Systems enable cognitive agents to act in the physical world. However, the application of these systems has been little explored to automate communication during crisis events. With this approach, it would be possible to help collect real-time data and deploy rescue forces in risky locations. This paper...

Considering the gender disparities affecting the use and interaction with technological systems, females often face barriers. In terms of self-efficacy, for example, they commonly exhibit lower levels. This discrepancy, when translated to interface design, may pose a hurdle to female usage, particularly with more complex designs. To promote inclusi...

Although Multi-Agent Systems (MAS) can handle various problems in heterogeneous environments, unknown problems may arise at runtime due to their inherent heterogeneity when dealing with cyber-physical systems. Therefore, designers of intelligent cyber-physical systems must adopt approaches that enable adaptability and fault tolerance at runtime. Th...

The high turnover of employees in technology companies linked to innovation is a known problem of this sector, resulting in challenges for team management and knowledge management. Models based on Machine Learning are presented in the literature to predict turnover risk. Working on talent retention is a possible way to deal with turnover. We carrie...

This initial study investigates the complex ethical concerns surrounding the integration of artificial intelligence (AI) in education, with a particular focus on undergraduate students’ perceptions of AI tools in their academic efforts. A notable issue is the educational application of these tools, coupled with a pressing need for comprehensive pub...

During the COVID-19 pandemic, Google Classroom was among the most used systems selected as the virtual learning environment by Brazilian federal universities. We performed automated analyses using government-recommended tools and manual Google Classroom analysis to assess the accessibility of the system. The present paper compared the results obtai...

As the imperative for equitable representation in leadership roles within STEM grows more pronounced, the meticulous examination of existing policies that promote gender equality becomes increasingly vital. This scrutiny not only paves the way for progress but also fosters a culture of social inclusion. This research provides a snapshot of one face...

In Brazil, citizens have rights and duties provided by laws, statutes, and principles, and organized cities have authorities responsible for governing in line with society’s interests. However, achieving meaningful citizen participation is a complex process, requiring authorities to constantly create mechanisms to increase engagement. Various commu...

Modern research depends on software, and it is developed specifically for and during research. Moreover, a growing number of researchers develop and use software to conduct or support their research. However, an overall understanding of research software is still needed. Our goal is to characterize the publication landscape on research software use...

There are several tools focused on process mining with different functionalities and purposes of use, ranging from the most intuitive to the extremely complex, configuring a difficult task to choose the tool that best applies to your work. With this in mind, a comparative study of the process mining tools used in the commercial and academic environ...

As competências de Pensamento Computacional são essenciais para enfrentar os desafios do mundo contemporâneo e estão gradualmente sendo incorporadas nos currículos da educação básica e do ensino superior em diversos países, incluindo o Brasil, onde pesquisadores têm demonstrado crescente interesse pelo tema. Diante desse contexto, este estudo tem co...

In light of the already acknowledged underrepresentation of women in Computing, the ongoing project “Latin American Open Data for Gender Equality Policies Focusing on Leadership in STEM” aims to support the implementation of institutional policies to promote gender equality in STEM. Activity 4 of this project involves mapping 1the factors, actors a...

Modern research depends on software libraries, tools, and applications, specially in Artificial Intelligence (AI) to support science, engineering, and business. Research software is often developed in academia by academic researchers in Information and Communication Technology (ICT). However, this software rarely achieves effective success: it is o...

This study explores the perceptions and practices of undergraduates in Information Technology (IT) regarding privacy issues in digital games. This topic becomes relevant in the current scenario where artificial intelligence (AI) is increasingly integrated into digital games, providing an enhanced experience for players. However, this integration po...

The relevance of using social media in crisis scenarios has aroused the interest of researchers and teams responsible for crisis management. The aim of this study is to explore the experience and skills of social media users related to such events. To this end, we carried out an analysis of the social media functionalities used in this context, fol...

Este trabalho relata a adaptação do framework Scrum com o objetivo de melhorar a integração entre coordenador de curso e professor no acompanhamento das atividades de ensino desenvolvidas em sala de aula. Utilizando informações sobre o Scrum e as atividades dos professores e coordenador, foi desenvolvida uma abordagem chamada Scrum Adaptado para a...

Este artigo analisa o perfil dos estudantes ingressantes nos cursos Técnicos Integrados ao Ensino Médio em Informática para Internet e Rede de Computadores, com foco nas habilidades de programação e pensamento computacional. A pesquisa foi realizada por meio da aplicação de um questionário a 59 estudantes do primeiro ano desses cursos no Instituto...

Embedded artificial intelligence in IoT devices is presented as an option to reduce connectivity dependence, allowing decision-making directly at the edge computing layer. The Multi-agent Systems (MAS) embedded into IoT devices enables, in addition to the ability to perceive and act in the environment, new characteristics like pro-activity, deliber...

Embedded artificial intelligence in IoT devices is presented as an option to reduce connectivity dependence, allowing decision-making directly at the edge computing layer. The Multi-agent Systems (MAS) embedded into IoT devices enables, in addition to the ability to perceive and act in the environment, new characteristics like pro-activity, deliber...

An Embedded multi-agent system (Embedded MAS) is an embedded cognitive system based on agents cooperating to control hardware devices. These agents are autonomous and proactive entities capable of decision-making and can constantly acquire new knowledge via interaction with other agents and the environment. Since the interaction between agents is r...

Quality care during reception and risk stratification is essential for correctly referring pregnant women who arrive in obstetrical emergencies. The use of simplified and economically viable technologies in emergency obstetric care in public maternity hospitals is important for digitizing and improving the management of this process. We propose des...

Context: Research in various domains, such as engineering, sciences, and other fields, depends on software developed in academia by researchers. However, some software becomes a successful case, and others do not. Objective: The goal of this paper is to identify and understand the factors that determine successful research software, as well as inve...

Citizens are gaining broad access to public data sources, made available in Open Government Data Portals (OGDPs). While the number of OGDPs grows over the years, researchers identify recurrent problems in these portals regarding data delivery. We conducted preliminary studies for identifying recurrent issues in OGDPs and we identified that data gov...

The grade forecast is a very promising area of study in Educational Data Mining. We used the National High School Exam (ENEM) database, a national exam in Brazil, to study the effectiveness of essay grade forecast using machine learning algorithms. Different features configurations were explored in order to compare its utility. Considering the mean...

The box office forecast is a big challenge due to the characteristics of the sector. A good forecast can be used as an investment tool or as a tool to promote public policies. In this work we used the public database of the Agência Nacional do Cinema (Brazilian Film Agency) - Ancine, and data taken from websites to gather predictive variables for t...

Open Government Data Portals (OGDPs) are a way of keeping up the information about government’s actions, including how the collected taxes are used in favor of its citizens. However, one difficult in some of these portals is guaranteeing accountability on OGDP completeness according to different instruments specifying legal requirements and good pr...

Apresentação de artigo com Relatos de Experiência/Intervenção

Using hardware platforms combined with other paradigms stimulates learning and has become an apparent trend in education. The Multi-Agent Systems domain studies the use of autonomous entities to solve complex problems. When combined with the Belief-Desire-Intention (BDI), a cognitive model close to human thinking, it can contribute to facilitating...

A participação cidadã é amplamente considerada vital para a democracia. Nesse contexto, as Ouvidorias Públicas surgem como um avanço nas administrações governamentais, permitindo a tomada de decisões públicas em conjunto com a sociedade. Este estudo tem como objetivo avaliar os canais de comunicação e a disponibilidade de informações acessíveis aos...

A Inteligência Artificial (IA) tem sido adotada por governos em todo o mundo como ferramenta para o aumento de eficiência, redução de custos e melhoria na oferta de serviços públicos digitais. Embora a adoção da IA tenha aumentando significamente nos últimos anos, poucos estudos investigaram o uso da IA em governos, de modo a lançar luz sobre os de...

Possible applications of Embedded Multi-agent Systems for Social Good

Presentation of An IDE to Support the Development of Embedded Multi-Agent Systems

Distributed Ledger Technologies (DLT) characteristics can contribute to several domains, such as Multi-agent Systems (MAS), facilitating the agreement between agents, managing trust relationships, and distributed scenarios. Some contributions to this integration are in the theoretical stage, and the few existing practical contributions have limitat...

Embedded MAS development requires knowledge in different areas, such as agent-oriented programming, object-oriented programming, low-level programming, and basic electronics concepts. The literature has a consolidated Embedded MAS development architecture divided into four layers: Reasoning, Serial, Firmware, and Hardware. However, one of the main...

The gaming industry moves billions of dollars annually. However, there are still challenges to be overcome, such as player privacy, a need that has become evident with the emergence of new personal data protection legislation (e.g., GDPR, LGPD, CCPA). In this case, solutions that address privacy in the game creation process are increasingly constan...

Crowdsourcing initiatives have been used in diverse domains. When user-generated data is the foundation of the crowdsourced application, users need to engage with it and not use it sporadically. For a solution to have strong engagement from design, we developed an 18-card deck as part of a design thinking approach. This approach offers domain-speci...

The database project is the process of engineering a database model from conceptual modeling to database implementation. Existing tools allow the conceptual modeling of relational and geographical databases separately, but none integrates both in a single solution. This paper presents and Model-Driven Development framework for creating relational a...

The database project is the process of engineering a database model from conceptual modeling to database implementation. Existing tools allow the conceptual modeling of relational and geographical databases separately, but none integrates both in a single solution. This paper presents an Model-Driven Development framework for creating relational an...

The COVID-19 pandemic has shifted from traditional face-to-face teaching to technology-mediated distance learning, creating significant new challenges for teachers and students. The rapid integration of new technologies into the teaching and learning process can give rise to privacy issues. This study investigates how teachers and students of under...

Context: Before starting the development of a final thesis, there areseveral challenges for both faculty advisors and university students.For professors, notoriously, there is the great challenge of findingstudents who want to participate in the development of their academicprojects. For students, the difficulty of finding projects orteachers who w...

Context: Public Higher Education Institutions adopt managerialtechnological innovations to respond to their demands. However,some systems may or may not partially meet the institution’s needs,making system acceptance and university management difficult.Objective: The goal of this work is to evaluate the usability andsatisfaction of an institution’s...

Object detection (OD) is used for visual quality control in factories. Images that compose training datasets are often collected directly from the production line and labeled with bounding boxes manually. Such data represent well the inference context but might lack diversity, implying a risk of overfitting. To address this issue, we propose a data...

Machine learning (ML) solutions have been proposed to make public transportation more attractive. Works that employ ML in bus transportation focus on various problems, such as travel time prediction or passenger flow prediction. These solutions look to improve elements of transportation services, such as the availability of information on passenger...

An Embedded MultiAgent System (MAS) is a cognitive system embedded into a physical device responsible for controlling the existing resources and communicability with other devices. An Embedded MAS provides autonomy and proactivity to physical devices using the BDI model. Designing a device implies choosing sensors and actuators as resources and pro...

An Embedded MultiAgent System (MAS) is a cognitive system embedded into a physical device responsible for controlling the existing resources and communicability with other devices. An Embedded MAS provides autonomy and proactivity to physical devices using the BDI model. Designing a device implies choosing sensors and actuators as resources and pro...

Nowadays, constructing and interpreting data visualizations has become essential for simplifying access to information, improving data interpretability, and strengthening information literacy. The main objective of this paper is to propose a process to promote improvements in the generation of data visualization by exploring two aspects: quality of...

The heterogeneity of notices, the poor quality or the total absence of metadata, and the lack of format standardization make it difficult to unlock the total potential value of open data published in Official Gazettes, inhibiting civic engagement. To address these issues, we propose a unified vocabulary for Official Gazettes' procurement data. A sy...

Nas últimas décadas, a avaliação da experiência de usuário na utilização de sistemas ganhou importância. Existem diversos métodos de avaliação de experiência de usuário, entretanto identificar qual é o método mais indicado a ser aplicado em cada fase do ciclo de design de um sistema é um desafio. O objetivo desse minicurso teórico-prático é apresen...

As redes sociais impulsionam o compartilhamento das informações pessoais e tornam a privacidade das pessoas cada vez mais vulnerável. Docentes e discentes de cursos de Tecnologia da Informação e Comunicação são consumidores e produtores de tecnologias digitais. Neste estudo, investigamos a frequência que docentes e discentes desse perfil se preocup...

An Embedded MAS (Multi-Agent Systems) can use different communication infrastructures, exchange information, and even transport internal agents to another system. These systems can interact with a dynamic environment through their resources (sensors and actuators). However, resources are static and defined at design time. The addition of a resource...

Developing an Embedded MAS is a task that requires knowledge in different areas; therefore, the architecture used in this work is divided into four layers: reasoning, serial, firmware, and hardware. Different knowledge is required at each project layer. This work seeks to raise the main solutions available and others still needed to simplify the de...

Developing an Embedded MAS is a task that requires the domain of several areas of knowledge; therefore, the Embedded MAS architecture used in this work is divided into four layers: reasoning, serial, firmware, and hardware. Different knowledge is required at each project layer: electronics, low-level programming, object-oriented and agent-oriented...

Developing an Embedded MAS is a task that requires knowledge in different areas; therefore, the architecture used in this work is divided into four layers: reasoning, serial, firmware, and hardware. Different knowledge is required at each project layer. This work seeks to raise the main solutions available and others still needed to simplify the de...

An Embedded MAS (Multi-Agent Systems) can use different communication infrastructures, exchange information, and even transport internal agents to another system. These systems can interact with a dynamic environment through their resources (sensors and actuators). However, resources are static and defined at design time. The addition of a resource...

Social media have been used to extract different types of information. The objective of this exploratory research was to investigate the characteristics necessary to identify crisis events with social media, analyzing the aptitude of messages produced in three crisis events that hit cities in the southeastern region of Brazil. In total, 3,042 Twitt...

New international regulations concerning personal management data guarantee the ‘Right to Be Forgotten’. One might request to have their data erased from third-party tools and services. This requirement is especially challenging when considering the behavior of machine learning estimators that will need to forget portions of their knowledge. In thi...

Open data portals can be used for several purposes, including transparency leverage, access to information, and decision-making support. Recently, the pandemic broke out in the new coronavirus, causing the whole world to suffer its effects. As a result, several countries, institutions, and research teams have worked to understand the behavior of th...

Nowadays, we can find Open Government Data Portals (OGDPs) from different governmental organizations. The increasing number of OGDPs brings opportunities for integrating these data. The vast majority of OGDPs distribute the data into different categories, and each portal uses its own set of categories. Therefore, due to the lack of homogeneous guid...

Developing an Embedded MAS is a task that requires the domain of several areas of knowledge; therefore, the Embedded MAS architecture used in this work is divided into four layers: reasoning, serial, firmware, and hardware. Different knowledge is required at each project layer: electronics, low-level programming , object-oriented and agent-oriented...

A adaptação do ensino presencial para o ensino remoto, devido à pandemia da COVID-19, gerou desafios de privacidade para professores e alunos. Entretanto, não encontramos muitas informações sobre como as instituições de ensino orientaram os envolvidos no processo na proteção e usos dos dados pessoais dos docentes e discentes. Por isso, através de u...

Despite the growing female interest in gaming, women still represent an alarmingly low percentage of game producers. Thus, a Systematic Literature Review has been carried out to understand what challenges women face within the games industry and what approaches have been made to promote more gender-aware companies. The studies encountered show that...

The number of malicious software applications, or malware programs, increases every year. Their development becomes more sophisticated as new techniques are used to bypass program scanning software applications, such as antiviruses. Thereby, deep learning‐based methods emerge as a new promising way to identify these threats. Our main purpose and co...

Human activity recognition (HAR) essentially uses (past) sensor data or complex context information for inferring the activities a user performs in his daily tasks. HAR has been extensively studied using different paradigms, such as different reasoning mechanisms, including probabilistic, rule-based, statistical, logical reasoning, or the machine l...

Traditionally, the geospatial regionalization task consists of aggregating into regions, geographically connected areas that share similar characteristics. Although various spatial optimization approaches have been proposed for finding exact regionalization solutions, these approaches are not practical when applied to a large number of areas or pro...

Citizens and developers are gaining full access to public data sources through open data portals (ODPs). These datasets allow the creation of applications for helping citizens in different ways, allowing them to actively participate in government processes such as decision-making and policymaking. However, researchers have identified several drawba...

The Internet of Things (IoT) allows the sharing of information among devices in a network. Hardware evolutions have enabled the employment of cognitive agents on top of such devices, which could help to adopt pro-active and autonomous IoT systems. Agents are autonomous entities from Artificial Intelligence capable of sensing (perceiving) the enviro...

Intense social media interaction, wearable devices, mobile applications, and pervasive use of sensors have created a personal information ecosystem for gathering traces of individual behavior. These traces are the digital legacy individuals build all through their lives. Advances in artificial intelligence have fed our dream to build artificial age...

Open data portals are growing in scope, and the development of this initiative remains one of the main ways to help create new value for society and the economy. Citizens can use the open data made available on these portals to participate more effectively in democratic processes. For that, they have to be able to access, manipulate and interpret s...

Os Recursos Educacionais Abertos (REA) visam tornar o conhecimento mais livre e acessível para todos. É fundamental a disponibilização de repositórios que promovem a descoberta, o uso e a reutilização de REAs para que estes possam ser melhor utilizados. Diante disso, é relevante avaliar se, no Brasil, os Repositórios de REA (RREA) possuem qualidade...

O distanciamento social face a pandemia do coronavírus acelerou as transformações no ensino e nas práticas didático-pedagógicas. O ensino presencial migrou para o ensino remoto aliado ao uso de Tecnologia de Informação e Comunicação para realizar aulas. Entretanto, a falta da interação entre professor e alunos pode tornar a aprendizagem cansativa e...

Who wants to be immortal? While this rhetorical question seems to haunt humans, digital immortality is already a reality. Social networks have allowed and facilitated our digital footprints to remain forever at reach of Internet users. We will all die, on the other hand, our digital self may remain forever. Social media technology has also allowed...

In this article, we analyze how the Brazilian Act for the Protection of Personal Data --- Lei Geral de Proteção de Dados Pessoais (LGPD) in Portuguese --- can contribute to handling some situations involving post-mortem digital legacy. For that purpose, we investigate some aspects of this act that can concur with the development of software and int...

No decorrer de suas vidas, usuários geram grandes quantidades de dados que podem ser deixados como herança para terceiros, se assim for desejado. Sistemas Dedicados de Gerenciamento de Legado Digitais (SDGLD) são aqueles desenvolvidos com o objetivo primário de permitir a gestão de bens digitais de seus usuários, permitindo a destinação desejada qu...

As tarefas realizadas por órgãos governamentais produzem quantidades exorbitantes de dados brutos diariamente. Entretanto, o valor que estes dados poderiam proporcionar para os diversos setores da sociedade pode se perder caso estes não sejam devidamente coletados e gerenciados. Mesmo com a adoção de políticas de abertura de dados, as instituições...

Centros urbanos apresentam continuamente problemas estruturais que demandam manutenção. Os canais para o cidadão relatar estes problemas são diversos e em cidades de grande porte podem existir aplicações eficientes. Entretanto, o estudo da viabilidade do uso destes recursos em cidades de pequeno e médio porte é fundamental para o apoio à gestão púb...

Object Detection (OD) is an important computer vision problem for industry, which can be used for quality control in the production lines, among other applications. Recently, Deep Learning (DL) methods have enabled practitioners to train OD models performing well on complex real world images. However, the adoption of these models in industry is sti...

The objective of this work is to propose protocols inspired by ecological relations for transferring agents between distinct Embodied MAS to exchange or preserve the integrity of the agent's knowledge.

Bio-inspired approaches and techniques are being used in different domains and applications in artificial intelligence, including the agent domain. Some agents are able to move from one system to another to establish new relationships. In biology, ecological relations are concepts responsible for classifying the relationships between living beings...

A pandemia de COVID-19 impactou no comportamento das pessoas também no domínio religioso, em que o apoio social e o relacionamento entre membros das comunidades de fé foram restringidos pelo distanciamento social. Neste cenário, redes sociais potencializaram a interação entre as pessoas mediada por tecnologia. Esse trabalho teve por objetivo identi...

In recent years, bitcoin has become a very attractive investment in financial industry, which is not controlled by governments, but is based on trust between transfers under the technology of block chain. Hence, forecasting future bitcoin cryptocurrency values is a problem that has attracted the attention of many researchers in the field, while pro...