A5014320176- Innovative Teaching and Learning Methods
- Human Mobility and Location-Based Analysis
- Speech and dialogue systems
- Anomaly Detection Techniques and Applications
- Traffic Prediction and Management Techniques
- Geographic Information Systems Studies
- IoT and Edge/Fog Computing
- Data Management and Algorithms
- AI in Service Interactions
- Multi-Agent Systems and Negotiation
- Crime Patterns and Interventions
- Smart Cities and Technologies
- Online Learning and Analytics
- Advanced Computational Techniques and Applications
- Software System Performance and Reliability
- Mobile Crowdsensing and Crowdsourcing
- Geography and Environmental Studies
- Spam and Phishing Detection
- Impact of Light on Environment and Health
- Wildlife Conservation and Criminology Analyses
- Data Stream Mining Techniques
- Data Visualization and Analytics
- Intelligent Tutoring Systems and Adaptive Learning
- Data Quality and Management
- Imbalanced Data Classification Techniques
University of Twente
2021-2024
Universidade Federal do Rio Grande do Norte
2016-2020
Recently, patrol planning and other predictive policing strategies were improved for Smart Cities applications. In such public safety context, some police departments have been recording crime events in their databases to compose better understand predict incidence. This work presents the ROTA-Analytics, a web-based application which aims provide incidence forecasting as outputs. incident helps supervisors elaborate list of predefined locations (points) staying time at each vehicle must...
By monitoring crime incidence with quantitative techniques, many studies have shown that it is possible to improve decision making through pattern recognition and prediction. In a smart city scenario, such approaches can be used compose analytical background resource allocation. This work presents novel framework patrol planning precisely provides places times are likely more dangerous than short-term average using portfolio of machine learning algorithms. Our approach follows an...
Abstract Background Sustaining productive student–student dialogue in online collaborative inquiry learning is challenging, and teacher support limited when needed multiple groups simultaneously. Collaborative conversational agents (CCAs) have been used the past to student dialogue. Yet, research reveal characteristics effectiveness of such agents. Objectives To investigate extent which our analytics‐based Learning Agent for Interactive Reasoning (Clair) can improve productivity dialogue, we...
Nowadays, we are in the century of cities: there more people living cities than countryside. In general, overpopulated around world have common problems several areas, such as city administration, education, health care, public safety, transportation, utilities, etc. particular case Brazil, one major is high level violence. This paper describes how Brazilian Natal implementing technological systems context safety to transform itself into a smart city, cooperation between university and...
Computer-Supported Collaborative Learning (CSCL) is known to be productive if well structured. In CSCL, students construct knowledge by performing learning tasks while communicating about their work. This communication most often done through online written chats. Understanding what happening in chats important from both research and practical perspectives. From a perspective, insight into chat content offers window student interaction learning. more standpoint, can (potentially) used...
Teachers in online science laboratories frequently struggle to provide timely discussion support different groups.Collaborative conversational agents have been proposed bridge this gap and foster productive talk small-group discussions.Current implementations are usually highly configurable, but rather limited when modeling users' intent a transferable way.In paper, we propose new agent that supports while addressing these requirements.Also, discuss lessons learned from pilot study classroom...
Forecasting when and where crimes are more likely to occur based on years of historical record analysis is becoming a task which increasingly helping cities' safety departments with capacity planning, goal setting, anomaly detection. Crime geographically concentrated phenomena varies in intensity category over time. Despite its importance, there serious challenges associated producing reliable forecasts such as sub-regions sparse crime incident information. In this work, we address these...
Smart solutions that make use of machine learning and data analyses are on the rise. Big Data analysis is attracting more developers researchers, at least five requirements (Velocity, Volume, Value, Variety, Veracity) show challenges in deploying such solutions. Across globe, many City initiatives using Analytics as a tool for doing predictive analytics which can be helpful to human well being. This work presents generic architecture named Machine Learning Microservices Architecture (MLMA)...
The coronavirus pandemic challenged smart cities to encourage citizens towards the social distance, as well optimize health and policing resources allocation. Mobile apps have played an unprecedented role during this enable participate interact with issues while raising concerns about privacy surveillance. In a partnership of Natal city initiative university public ministry, we deployed "Tô de Olho" (TdO) platform for integrating different sectors society against spreading in state RN,...
During a criminal investigation, the evidence collection process produces an enormous amount of data. These data are present in many medias that extracted as crime evidences (USB flash drives, smartphones, hard computers, etc). Due to this volume, manual analysis is slow and costly. This work fulfills gap by presenting extraction processing platform for analysis, named INSIDE. Our proposed leverages lambda architecture uses set tools frameworks such Hadoop HDFS, Kafka, Spark Docker analyze...
Brazil's road traffic mortality rates have been increasing since the 1960s and in 2003 crashes Brazil were responsible for over 26 percent of fatal injuries. Some actions need to be taken make it safer, hence, we proposed, implemented, deployed a support system that predicts generates, based on prediction, program-card Federal agency patrolling highways which cross most big Brazilian cities. We used data from Highway Police (PRF) about accidents test performance generated models demonstrate...
Automated algorithm engineering has become an important asset for academia and industry. irace, instance, is configurator (AC) that successfully designed effective algorithms optimization problems. The major advantage of irace combining learning parallelization, but no fully-functional automated machine (AutoML) system powered by yet been proposed. This rather striking, as some the most relevant existing AutoML tools are ACs, which one examples.In this work, we propose iSklearn,...
O município de Mossoró, cidade do Semiárido Nordestino, possui elevada taxa urbanização e é caracterizada pelas altas temperaturas baixos teores umidade relativa ar durante todo o ano, corroborando para desconforto térmico em ambientes externos. Surgindo, portanto, interesse estudar comportamento da temperatura dois quintais residenciais bairro Abolição, a fim verificar influência das árvores no dos elementos climáticos nos e, por conseguinte conforto humano, procurando preencher uma lacuna...