Chest X-ray images are useful for early COVID-19 diagnosis with the advantage that X-ray devices are already available in health centers and images are obtained immediately. Some datasets containing X-ray images with cases (pneumonia or COVID-19) and controls have been made available to develop machine-learning-based methods to aid in diagnosing the disease. However, these datasets are mainly composed of different sources coming from pre-COVID-19 datasets and COVID-19 datasets. Particularly, we have detected a significant bias in some of the released datasets used to train and test diagnostic systems, which might imply that the results published are optimistic and may overestimate the actual predictive capacity of the techniques proposed. In this article, we analyze the existing bias in some commonly used datasets and propose a series of preliminary steps to carry out before the classic machine learning pipeline in order to detect possible biases, to avoid them if possible and to report results that are more representative of the actual predictive power of the methods under analysis.

Vulnerable Road User (VRU) detection is a major application of object detection with the aim of helping reduce accidents in advanced driver-assistance systems and enabling the development of autonomous vehicles. Due to intrinsic complexity present in computer vision and to limitations in processing capacity and bandwidth, this task has not been completely solved nowadays. For these reasons, the well established YOLOv3 net and the new YOLOv4 one are assessed by training them on a huge, recent on-road image dataset (BDD100K), both for VRU and full on-road classes, with a great improvement in terms of detection quality when compared to their MS-COCO-trained generic correspondent models from the authors but with negligible costs in forward pass time. Additionally, some models were retrained when replacing the original Leaky ReLU convolutional activation functions from original YOLO implementation with two cutting-edge activation functions: the self-regularized non-monotonic function (MISH) and its self-gated counterpart (SWISH), with significant improvements with respect to the original activation function detection performance. Additionally, some trials were carried out including recent data augmentation techniques (mosaic and cutmix) and some grid size configurations, with cumulative improvements over the previous results, comprising different performance-throughput trade-offs.

Data drift can significantly impact the outcome of a model. Early detection of data drift is crucial for ensuring user confidence in predictions. It allows the user to check if a particular model needs retraining using updated data to adapt to the evolving process dynamics. This study compares five different statistical tests, namely four unidimensional and a new multidimensional test (MSPC), to identify data drift in both mean and deviation. While some are designed to detect drift in mean only, like our multidimensional proposal, others respond to changes in both mean and deviation. However, our Hotelling multidimensional method can be trained once and then applied in a single stage to any data stream with several attributes, and it can identify the most relevant variables causing a data drift with one execution, thus avoiding the need for a single univariate test for each attribute. Moreover, our method yields the relative importance of each attribute for drift and allows users to increase or decrease the relative weight of each variable regarding drift detection. It also may be capable of detecting drift due to changes in multivariate interactions. This behavior is especially suitable for real-world scenarios, such as industry, finance, or healthcare environments.

En la actualidad, la interacción persona-ordenador busca ser cada vez más intuitiva. En el caso de la realidad mixta, el uso de gestos emerge como una solución factible para lograr interacciones más naturales y fluidas. En este trabajo, implementamos un sistema completo de reconocimiento de gestos de las manos para las Microsoft HoloLens 2, basado en un par de clasificadores en cascada. Para el entrenamiento de los modelos, utilizamos la parte disponible públicamente del conjunto de datos SHREC22, que cuenta con un número limitado de muestras, convirtiendo esta tarea en un problema de aprendizaje con pocos ejemplos, ya que solo disponemos de 36 muestras por clase. Exploramos diversas arquitecturas de redes neuronales para identificar la más adecuada en este contexto. Al evaluar el sistema en su conjunto, logramos una tasa de error de gestos (GER) del 9.6%, lo que demuestra el potencial del enfoque propuesto, si bien su rendimiento podría optimizarse con futuros ajustes y más datos de entrenamiento.