8 results

Export current results
CSV Excel JSON Up to 2٬000 records.
Not stated in source 2026 Needs review Available

Efficient deep learning for mobile weed classification

Author
Leonardo G. Sanches
University
Federal University of Technology – Paraná
Country
Brazil
Main specialisation
AI in Healthcare › AI in Agriculture

Agricultural production across regions faces several challenges in cultivation, including climate variability, pests, diseases, and weeds. Deep neural network models have proven efficient in addressing some of these challenges, for example, in identifying and…

Not stated in source 2025 Needs review Available

Control of a Furuta pendulum with reinforcement learning

Author
Fernando Luiz Klein de Souza
University
Federal University of Technology – Paraná
Country
Brazil
Main specialisation
Reinforcement Learning › AI in Smart Cities

This work proposed the control of a Furuta pendulum using reinforcement learning, addressing challenges such as underactuation, non-linearities, and instabilities. The classical control approach for this system involves positioning the pendulum close to the eq…

Not stated in source 2025 Needs review Available

Study of ensemble methods applied to semantic segmentation masks

Author
João Pedro da Silva de Andrade
University
Federal University of Technology – Paraná
Country
Brazil
Main specialisation
AI in Healthcare › Image Segmentation

Semantic segmentation is a fundamental technique for automating the detection of objects of interest in images. However, its application faces a major challenge: the need for a large amount of annotated data for training, a process that requires significant ef…

Not stated in source 2025 Needs review Available

Human brain tumor classification using images of magnetic resonance and deep learning architectures

Author
Pedro Lavarda Zorel
University
Federal University of Technology – Paraná
Country
Brazil
Main specialisation
AI in Healthcare › Medical Image Analysis

As the population and life expectancy around the world increase, diseases like cancer are becoming increasingly common. Research conducted by the National Cancer Institute indicates that in 2022 alone, more than 625,000 cancer cases were registered in Brazil,…

Not stated in source 2024 Needs review Available

Sentiment analysis for portuguese with BERT models

Author
Vinícius Pinheiro Winter
University
Federal University of Technology – Paraná
Country
Brazil
Main specialisation
Deep Learning & Neural Networks › Transformers

This paper presents the development and application of the BERT model (Bidirectional Encoder Representations from Transformers) for sentiment analysis in Portuguese texts, focusing on data from social networks. The study is justified by the need to understand…

Not stated in source 2024 Needs review Available

Semantic segmentation of mammals in forest regions with U-NET

Author
Jhonatan Guilherme de Oliveira Cunha
University
Federal University of Technology – Paraná
Country
Brazil
Main specialisation
AI in Healthcare › Image Segmentation

Environmental monitoring is vital for preserving animal biodiversity, providing researchers with essential metrics on environmental health and aiding efforts to combat extinction. Mapping the fauna of forest regions is, therefore, essential for informed decisi…

Not stated in source 2023 Needs review Available

Machine learning for predictive maintenance applied in a teaching plant

Author
João Guilherme Menuzzo Silva
University
Federal University of Technology – Paraná
Country
Brazil
Main specialisation
Machine Learning › Predictive Analytics & Time Series

The new technologies from Industry 4.0 allow factories to become smart. It is understood that material, human and financial resources are better used and consequently there is an increase in efficiency and sustainability of processes. It is essential that an i…

Not stated in source 2023 Needs review Available

LSTM recurrent neural network for identification of a thermal system

Author
Guilherme Nomura Mateus Leite
University
Federal University of Technology – Paraná
Country
Brazil
Main specialisation
Deep Learning & Neural Networks › Recurrent Neural Networks / LSTM

The focus of this graduation thesis is the application of a Long Short-Term Memory (LSTM) recurrent neural network (RNN) in the context of identifying and modeling a complex thermal system consisting of two heaters and two sensors. The proposed approach is bas…