Search
Now showing items 41-50 of 65
Avanços recentes em caracterização e classificação de imagens de texturas: explorando teoria da informação, aprendizado profundo e de variedades
(Universidade Federal de São Carlos, 2020-04-30)
The task of extracting features from images is a very important activity for many computer vision and image processing applications. Especially the characterization and identification of textures is a fundamental issue in ...
Detecção de câncer de próstata em imagens de microscopia utilizando grafos de contexto glandular
(Universidade Federal de São Carlos, 2021-04-19)
Every year a large part of the male population is affected by Prostate Cancer (PCa), with many cases of deaths occurring especially in men over 40 years old. PCa is a pervasive condition that diffuses and manifests itself ...
Caracterização de um dataset de mobilidade dos ônibus da cidade de São Paulo
(Universidade Federal de São Carlos, 2021-01-28)
Simulation is a widely used technique for validation and testing of routing protocols in vehicular networks (VANETs). These simulations are based on mobility models that must follow the real movement patterns of vehicles ...
Auditchain: um mecanismo para atestar a integridade de logs baseado na prova de existência em blockchain pública
(Universidade Federal de São Carlos, 2021-04-12)
Digital data are critical to people and companies, acting as a crucial element in the decisionmaking process in different areas. Thus, attesting to data integrity is crucial because forgery can result in significant losses. ...
Redução de ruído Poisson com o algoritmo BM3D utilizando distâncias estocásticas
(Universidade Federal de São Carlos, 2021-06-02)
Noise is a problem constantly present in digital images incoming from multiple sources, being important to study noise filters to improve the quality of images. When dealing with radiographic images, Poisson noise is an ...
Critérios para adoção de soluções de desenvolvimento multiplataforma móvel na perspectiva de desenvolvedores de software
(Universidade Federal de São Carlos, 2020-04-03)
Cross-platform Development Tools are a technology that emerged to meetthe demand of development teams that operate simultaneously with more than onemobile platform. This technology mainly benefits small and medium-sized ...
Método para classificação de sementes agrícolas em imagens obtidas por tomografia de raios-X em alta resolução
(Universidade Federal de São Carlos, 2020-05-20)
This research produced a method for classifying agricultural oil seeds based on tomography (CT) assays. Oilseeds may present good or poor quality for planting, the latter being related to the presence of defects associated ...
Data preparation pipeline recommendation via meta-learning
(Universidade Federal de São Carlos, 2021-05-26)
Data preparation is a essential stage in the machine learning pipeline, aiming to convert noisy and disordered data into refined data compatible with the algorithms. However, data preparation is time-consuming and requires ...
Curriculum learning applied to the combined algorithm selection and hyperparameter optimization problem
(Universidade Federal de São Carlos, 2021-05-25)
AutoML has the goal to find the best Machine Learning (ML) pipeline in a complex and high dimensional search space by evaluating multiple algorithm configurations. Training multiple ML algorithms is time costly, and as ...
GSA: operacionalizando a gamificação em atividades do processo de desenvolvimento de software
(Universidade Federal de São Carlos, 2021-04-22)
Context: Software development companies are constantly seeking practices that improve the execution of their activities and, consequently, their processes. Several initiatives for using gamification have been observed in ...