DSpace Coleção:https://repositorio.pucgoias.edu.br/jspui/handle/123456789/622026-09-22T22:41:07Z2026-09-22T22:41:07ZConfiguração de serviço acadêmico no sistema Lyceum: uma abordagem para a modernização da gestão educacionalhttps://repositorio.pucgoias.edu.br/jspui/handle/123456789/111692026-09-21T17:27:17Z2026-06-08T00:00:00ZTítulo: Configuração de serviço acadêmico no sistema Lyceum: uma abordagem para a modernização da gestão educacional
Tipo: Trabalho de Conclusão de Curso2026-06-08T00:00:00ZUm estudo de centro em grafoshttps://repositorio.pucgoias.edu.br/jspui/handle/123456789/111682026-09-21T15:15:23Z2026-06-11T00:00:00ZTítulo: Um estudo de centro em grafos
Tipo: Trabalho de Conclusão de Curso2026-06-11T00:00:00ZIdentificação de melanomas utilizando redes neurais convolucionaishttps://repositorio.pucgoias.edu.br/jspui/handle/123456789/111212026-09-09T11:48:38Z2026-01-09T00:00:00ZTítulo: Identificação de melanomas utilizando redes neurais convolucionais
Abstract: This study aimed to develop and evaluate a model for the automated classification of melanoma and other skin lesions using dermoscopic images. The EfficientNet-B3 architecture with transfer learning was trained on the public HAM10000 dataset, which contains 10,015 images distributed across seven skin-lesion classes. To address class imbalance, the selected configuration included class-weighted Focal Loss, mixup, dropout, weighted sampling, and progressive fine-tuning. The processing workflow also included color-marker and hair removal, contrast enhancement, resizing, and image normalization. On the validation set, the selected configuration achieved an accuracy of 82.38%, a weighted F1-score of 0.828, and a macro F1-score of 0.708. For melanoma, precision was 0.565, recall was 0.609, and the F1-score was 0.586. The results indicate discrimination capability across the seven evaluated categories; however, the moderate melanoma performance and the absence of external validation limit the generalizability of the findings. Therefore, the model should be regarded as an experimental computational prototype for skin-lesion classification, without inference of clinical use at this stage.
Tipo: Trabalho de Conclusão de Curso2026-01-09T00:00:00ZImputação multivariada de séries semporais meteorológicas do INMET com reanálise ERA5-land e self-attentionhttps://repositorio.pucgoias.edu.br/jspui/handle/123456789/110972026-09-11T17:51:46Z2026-01-12T00:00:00ZTítulo: Imputação multivariada de séries semporais meteorológicas do INMET com reanálise ERA5-land e self-attention
Abstract: Missing values in meteorological time series compromise climate analyses and predictive models. This work investigates a multivariate imputation pipeline for observational data from the Brazilian National Institute of Meteorology (INMET), using ERA5-Land as a source of auxiliary features. SAITS was adopted as the main model and compared with Median, LOCF, MissForest, XGBoost, Transformer and ImputeFormer. MCAR scenarios ranging from 10% to 80% artificial missingness were generated and evaluated using MAE, RMSE, and MASE. The results show that SAITS achieves the best performance under low missingness, while XGBoost obtains the lowest global errors from 40% to 80% missingness, indicating greater robustness under severe data degradation.
Tipo: Trabalho de Conclusão de Curso2026-01-12T00:00:00Z