Search

Learning Bayesian networks from data aims to create a Directed Acyclic Graph that encodes significant statistical relationships between variables and their joint probability distributions. However, when using real-world data with limited knowledge of the original dynamical system, it is challenging to determine if the learned DAG accurately reflects the underlying relationships, especially when the data come from multiple independent sources. This paper describes a methodology capable of assessing the credible interval for the existence and direction of each edge within Bayesian networks learned from data, without previous knowledge of the underlying dynamical system. It offers several advantages over classical methods, such as data fusion from multiple sources, identification of latent variables, and extraction of the most prominent edges with their respective credible interval. The method is evaluated using simulated datasets of various sizes and a real use case. Our approach was verified to achieve results comparable to the most recent studies in the field, while providing more information on the model's credibility. [ABSTRACT FROM AUTHOR]

Recently, Computer Vision Techniques have been pushing the development of robust traffic monitoring systems. Such methods utilize images captured by video cameras to infer important traffic features, such as vehicle speed and traffic density. Frame Subtraction is currently the most used method to detect vehicles in a video stream, but there are scenarios where this method provides poor accuracy, given their struggle in handling disturbances caused by lighting changes, pedestrians in the scene, etc. In order to improve the accuracy of Traffic Monitoring Systems (TMS), this paper proposes a novel TMS design and implementation in which a Convolutional Neural Network is used to replace Frame Subtraction methods in the vehicles detection task. The results show up to 12% improvements on Vehicle Detection in comparison with Frame Subtraction-based systems, proving its effectiveness on challenging scenarios, while maintaining an error rate of 5% for speed detection. [ABSTRACT FROM AUTHOR]