A5073335805- E-Government and Public Services
- Smart Cities and Technologies
- Data Stream Mining Techniques
- Big Data and Business Intelligence
- Data Quality and Management
- Technology Adoption and User Behaviour
- Data Mining Algorithms and Applications
- Text and Document Classification Technologies
- Imbalanced Data Classification Techniques
- Anomaly Detection Techniques and Applications
- IoT and Edge/Fog Computing
- Education and Digital Technologies
- Machine Learning and Data Classification
- Sentiment Analysis and Opinion Mining
- Knowledge Management and Sharing
- Impact of Technology on Adolescents
- Topic Modeling
- Privacy, Security, and Data Protection
- Innovative Approaches in Technology and Social Development
- Time Series Analysis and Forecasting
- Human Mobility and Location-Based Analysis
- Data Visualization and Analytics
- Network Security and Intrusion Detection
- Privacy-Preserving Technologies in Data
- Rough Sets and Fuzzy Logic
Universidade Federal Fluminense
2015-2024
United Nations Economic Commission for Europe
2023
Instituto Federal Fluminense
2022
Intel (United States)
2008-2019
Prefeitura Municipal de Rio das Ostras
2010-2018
Departamento de Ciência e Tecnologia
2010
Universidade de São Paulo
2005-2006
Brazilian Society of Computational and Applied Mathematics
2005
Identifying malware has always been a great challenge. Much money and time invested by companies governments to mitigate the impact of these threats. Nowadays, with increasing amount data available, it is possible use more precise classification techniques. However, most large datasets that include malicious non-malicious softwares are not public, which hinders quest for solutions based in technologies rely on availability amounts data, such as deep learning. To overcome this limitation,...
This work presents a study for assessing the technology acceptance of contact tracing app, also proposed by us, which is hybrid crowdsensing application (opportunistic and participatory). The goal app that users are notified if they were in with others infected. It allows creating heat map identifying streets, squares, commercial locations to contaminated were, allowing more assertive hygiene actions eliminating infectious disease outbreaks. Our methodology aimed on finding whether people...
Urban data is gradually being opened to the public. Tools for exploitation, analysis and discovery of new knowledge in large sets are key enable citizens make sense such amount data. The purpose this work analyze how associated with visualization techniques different levels can lead improvement interpretability open With support machine learning techniques, these visualizations may improve pattern identification urban sets. To guide our discussion, a case study was conducted analyzing...
The use of Crowdsourcing to solve public problems is called Citizen-Sourcing and shows the potential increase citizen participation in context e-government. Successful implementations applications require continuously engage with each other government through these applications. In general, citizens expect, among things, that responds their comments an application by immediately solving pointed out or indicating when how they would be solved. a literature review, we could not find any model...
Open data portals are fundamental tools for governments to achieve public transparency. Hence, several countries around the world have issued Freedom of Information (FOI) laws and acts, imposing that city administrations develop their own open publish local data. However, many cities, specially in developing countries, lack financial resources even invest basic IT services. These cities quite often do not qualified people best practices, transparency solutions constructing these portals,...
Information and Communication Technologies are indispensable components of smart cities. Its applications present in several areas, such as urban mobility, environmental issues medical systems. In this scenario, the use crowdsourcing technologies comes to help people contribute development improvement digital services. However, using crowdsourced data cities solutions can lead problems with security privacy user's data. The setting comprehensive Functional Requirements (FR) ensure is an...
Machine learning (ML) solutions have been proposed to make public transportation more attractive. Works that employ ML in bus focus on various problems, such as travel time prediction or passenger flow prediction. These look improve elements of services, the availability information passengers’ and reliability regularity service. An analysis literature for by can reveal opportunities data scientists professionals, highlight problems only slightly explored. In addition, mapping about modeling...
The physical and operational properties of pipelines vary greatly. There is thus no universally applicable method, external or internal, which possesses all the features functionality required for a perfect leak detection performance. authors this paper know quite well that traditional methods, in low uncertainty environment, overcome artificial intelligence methods systems. If one considers real world as creator uncertainties, neural networks fuzzy systems emerge important promising...
Two main characteristics of multi-label dataset are cardinality and density, related to the number labels (each instance of) a dataset. The relation between these learning performance has been observed with different datasets. However, difference in domain attributes also interfere on performance. In this work, we use real dataset, named Million Song Dataset, available internet, which presents property having too many associated their instances (songs), as well so instances. work present...
Citizens and developers are gaining broad access to public data sources, made available in open portals. These machine-readable datasets enable the creation of applications that help population several ways, giving them opportunity actively participate governance processes, such as decision taking policy-making. While number portals grows over years, researchers have been able identify recurrent problems with they provide, lack standards, difficulty poor understandability. Such issues make...
People usually spend several hours per day inside buildings, and they require great amounts of energy resources to operate. Although there are numerous studies about smart is still a need for new intelligent techniques efficient building management. This paper proposes the use Wi-Fi network association information as basis design systems buildings. We propose unified experimental methodology evaluate machine learning (ML) models on their capacity accurately predict access point demand...
Smart Cities theme has evolved in the last years, leading cities to implement initiatives related technical aspects improve quality of life. Another focus on this is how measure added value these population. The Brazilian Network and Human (RBCIH) was created order join both approaches Brazil, putting together members from academy, private initiative local (municipality) government. Nowadays, RBCIH composed by 350 (in a universe 5570 cities), indicating that long-term work be executed...
The use of social media data to mine opinions during elections has emerged as an alternative traditional election polls. However, relying on in electoral scenarios comes with a number challenges, such tackling sentences domain specific terms, texts full hate speech, noisy, informal vocabulary, sarcasm and irony. Also, Twitter, for instance, loss context may occur due the imposed limit characters posts. Furthermore, prediction tasks that machine learning require labeled datasets it is not...
Transparency is a key factor in maintaining the trust of societies their governments. The open data approach can be used to increase transparency public administrations. Hence, thousands datasets published by governments, organizations and companies, were made available through portals on internet. In recent years, growth number amount information has increased users' difficulty obtaining useful for conducting analyzes or studies. majority are distributed across selected topics categories....
The use of the latent factor models technique overcomes two major problems most collaborative filtering approaches: scalability and sparseness user's profile matrix.The successful realizations are based on matrix factorization.Among algorithms for factorization, alternating least squares (ALS) stands out due to its easily parallelizable computations.In this work we propose a methodology comparing performance parallel implementations ALS algorithm, one executed with MapReduce in Apache Hadoop...