Percorrer por autor "Bezerra, Eduardo"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Assessing the 3D Position of a Car with a Single 2D Camera Using Siamese NetworksPublication . Yahia, Youssef; Lopes, Júlio Castro; Bezerra, Eduardo; Rodrigues, Pedro João; Lopes, Rui PedroUsing computer vision for the classification of an object’s 3D position using a 2D camera is a topic that has received some attention from researchers over the years. Visual data is interpreted by the computer to recognize the objects found. In addition, it is possible to infer their orientation, evaluating their spatial arrangement, rotation, or alignment in the scene. The work presented in this paper describes the training and selection of a siamese neural network for classifying the 3D orientation of cars using 2D images. The neural network is composed of an initial phase for feature selection through convolutional neural networks followed by a dense layer for embedding generation. For feature selection, four architectures were tested: VGG16, VGG19, ResNet18 and ResNet50. The best result of 95.8% accuracy was obtained with the VGG16 and input images preprocessed for background removal.
- NailP at eRisk 2023: search for symptoms of depressionPublication . Bezerra, Eduardo; Santos, Leonardo Ferreira dos; Nascimento, Rodolpho F.; Lopes, Rui Pedro; Guedes, Gustavo PaivaDepression is a global health concern with severe consequences for individuals, making its recognition and understanding crucial. Recently, there has been a growing interest in utilizing social media platforms as valuable sources of information to gain insights into individuals’ experiences with depression. Analyzing textual data from diverse user populations enables the identification of common symptoms, triggers, coping mechanisms, and potential warning signs. Researchers have developed algorithms and machine learning models to automate the detection of depressive symptoms in text, facilitating more efficient screening and early intervention. This paper describes the participation of team NailP in the CLEF eRisk 2023 task 1, which focuses on ranking sentences from user writings based on their relevance to symptoms of depression. The goal is to evaluate the sentences and determine their level of relevance to each symptom outlined in the Beck Depression Questionnaire-II. Such participation contributes to the development of effective methods and tools for identifying and predicting potential risks and dangers associated with depression in online environments.