Embedded Files
Certified by CNPq since 2014 and based at the Pato Branco Campus of the Federal University of Technology - Paraná (UTFPR), the group has a strong presence in graduate studies, operating within the PPGEEC, PPGCC, and CPGEI programs. Consolidated as an innovation hub, it develops projects through public-private partnerships and international cooperation initiatives, enabling high-impact scientific and technological production, the training of qualified human resources, and the effective transfer of knowledge to society. The team brings together 8 PhD researchers, over 30 students in training, and dozens of alumni. Its activities are structured around two central research lines: Neonatal Biometrics, focused on image processing, individual recognition, and artificial intelligence; and Event-driven Process and Systems Engineering, dedicated to the modeling, analysis, control, optimization, and process mining in complex systems.
For updated information, human resources, partner institutions, and other details, please consult the group's directory page at the link below:
Explore the research lines below:
Event-driven Process and Systems Engineering
Event-driven Process and Systems Engineering
This research line investigates science and engineering phenomena applied to event-based data, ranging from the modeling, control, and deployment of event-driven systems to process mining. Its direct motivation stems from the advent of generating large and complex volumes of event data originating from emerging computing approaches. These data, generally provided through electronic means, need to be properly captured, stored, and processed so that they can be converted into information and support advanced decision-making processes with a reasonable degree of autonomy and intelligence.
Keywords: Computational Intelligence; Process Mining; Event-Driven Systems; and Supervisory Control.
Neonatal Biometrics
Neonatal Biometrics
This research line investigates computational solutions to correlate patterns in children's fingerprints with signals from the same individual at older ages, in order to infer the expected biometric feature for a person regardless of their age, without re-collecting signals. This line has strong social relevance, industrial application, and is funded through public-private partnerships.
Keywords: Neonatal biometrics; Pattern recognition in images; Human recognition.
Page updated
Google Sites
Report abuse