https://repositorio.ufu.br/handle/123456789/18792 2026-04-08T03:28:45Z https://repositorio.ufu.br/handle/123456789/48290 Title: O uso de contraste na Tomografia Computadorizada 2025-12-17T00:00:00Z https://repositorio.ufu.br/handle/123456789/47797 Title: Estudo de séries temporais e suas aplicações em econofísica usando redes neurais artificiais Abstract: This work falls within the field of Econophysics and aimed to create and evaluate the effectiveness of an Artificial Neural Network (ANN) with a Long Short-Term Memory (LSTM) architecture in forecasting time series of stock prices in the Brazilian capital market. For this purpose, historical daily data were collected for the assets Petrobras (PETR4.SA), Vale (VALE3.SA), and Itaú (ITUB4.SA) over the period from 2005 to 2025. The methodology involved the use of advanced computational models to analyze complex financial systems and included, as part of the data preprocessing, normalization using the MinMaxScaler function and structuring the data into 60-day time windows to feed a deep LSTM model. This model consists of four layers and was regularized using the Dropout technique (with a rate of 0.2) to prevent overfitting. The results on the test set showed varied performance: high accuracy was achieved for the banking sector asset (Itaú), good trend forecasting ability for the oil sector asset (Petrobras), and a quantitatively significant failure for the mining sector asset (Vale), evidenced by a notable error and a "cluster"at the end of the training epoch, occurring only for the Vale asset. It is concluded that, although LSTM networks show great potential for modeling financial time series, their effectiveness strongly depends on the particular characteristics and stability of each asset. This reinforces the idea that the financial market is a complex and non-universal system. 2025-09-22T00:00:00Z https://repositorio.ufu.br/handle/123456789/47770 Title: Métodos biofísicos utilizados para isolamento de toxinas botrópicas com potencial antitumoral 2025-09-23T00:00:00Z https://repositorio.ufu.br/handle/123456789/47756 Title: Aplicação da técnica de imagens via ressonância magnética no diagnóstico de câncer: uma revisão bibliográfica Abstract: The use of magnetic resonance imaging (MRI) has grown significantly, mainly due to its effectiveness in diagnosing various pathologies, resulting from its high sensitivity in detecting morphological and functional alterations in tissues. Unlike other modalities, such as computed tomography and radiography, MRI does not use ionizing radiation, making it a safe and effective option, especially for repetitive or follow-up examinations. MRI is particularly useful in the evaluation of tumors in soft tissues, such as the brain, liver, breast, and prostate, enabling early detection and accurate disease staging. Furthermore, new techniques, such as functional MRI, spectroscopy, and diffusion imaging, have expanded its role in oncology. The examination is based on the use of an extremely strong magnetic field combined with the application of radiofrequency pulses to generate images with high resolution and detail. During the process, the patient’s body interacts with this field and the radio waves, producing specific signals that are captured by highly sensitive coils. These signals are then transmitted to a specialized computerized system, where they undergo a conversion process: first, they are transformed into electrical signals, then digitized, and finally processed by advanced software. The result of this complex procedure is the formation of clear and precise images, which are displayed on the equipment monitor and can be analyzed by healthcare professionals, significantly assisting in medical diagnosis. Based on the analysis of scientific studies, this work highlights the relevance of MRI in clinical oncology practice, demonstrating that its use contributes significantly to therapeutic planning and monitoring of treatment response. Therefore, MRI is an essential tool in the diagnosis and follow-up of cancer, with growing potential as new technologies and applications are developed. 2025-09-17T00:00:00Z