Dynamic Bayesian Network

Dynamic Bayesian Networks (DBNs) are probabilistic graphical models used to represent and reason about complex systems evolving over time. Current research focuses on improving the scalability and accuracy of DBN structure learning, particularly for high-dimensional datasets, often employing divide-and-conquer strategies or integrating machine learning techniques like graph neural networks to enhance performance. DBNs find applications in diverse fields, including autonomous vehicle navigation, healthcare (e.g., predicting acute kidney injury), finance (e.g., cryptocurrency price prediction), and systems biology, offering valuable tools for modeling, prediction, and decision support in dynamic and uncertain environments.