Analyzing the future behaviors of currency pairs represents a priority for governments, financial institutions, and investors, who use this type of analysis to understand the economic situation of a country and determine when to sell and buy goods or services from a particular location. Several models are used to forecast this type of time series with reasonable accuracy. However, due to the random behavior of these time series, achieving good forecasting performance represents a significant challenge. In this paper, we compare forecasting models to evaluate their accuracy in the short term using data on the EUR/USD exchange rate. For this purpose, we used three methods: Autoregressive Integrated Moving Average (ARIMA), Recurrent Neural Network (RNN) of the Elman type, and Long Short-Term Memory (LSTM). The analyzed period spanned from 2 January 1998, to 31 December 2019, and was divided into training and validation datasets. We performed forecasting calculations to predict windows with six different forecasting horizons. We found that the window of one month with 22 observations better matched the validation dataset in the short term compared to the other windows. Theil’s U coefficients calculated for this window were 0.04743, 0.002625, and 0.001808 for the ARIMA, Elman, and LSTM networks, respectively. LSTM provided the best forecast in the short term, while Elman provided the best forecast in the long term.

In the obtention of medical images, the patients’ movement can modify the identification of the body components in an image. The combination of imaging techniques may not always be a solution to improve the imaging quality; therefore, an artifact analysis is commonly required prior to applying an imaging procedure in patients. In this work, we systematically evaluated the movements’ artifacts caused by the patients’ breathing during the images acquisition and their impact on the fusion of SPECT and CT modalities. We used a specific phantom placed on a platform to emulate the respiratory movement, finding artifacts not appreciable under the standard condition used to obtain the SPECT images due to its low spatial resolution. The artifacts produced a deformation of elements on the images. Therefore, image processing was necessary to identify the registration accuracy with SPECT and CT modalities in two states (phantom at rest and for a phantom with simulated respiratory movements). A systematic difference was obtained for the first case (11.7 mm), and a range of (7.4 mm to 16.1 mm) for the second one. For the volumes’ evaluation, the optimal threshold value for CT was 0.40 and for SPECT was 0.25, giving a rapid solution to reduce the artifacts’ impact on medical images.