Data-driven Bayesian network modelling to explore the relationships between SDG 6 and the 2030 Agenda

It is now a matter of scientific consensus that priming, a recency effect of activation in memory, has a significant impact on language users’ choice of linguistic means. However, it has long remained unclear how priming effects coexist with the creative aspect of language use, and the importance of the latter has been somewhat downplayed. By introducing the results of two experiments, for English and Russian native speakers, this paper seeks to explain the mechanisms establishing balance of priming and language creativity. In study 1, I discuss the notion of collective language creativity that I understand as a product of two major factors interacting: cognitive priming effects and the unsolicited desire of the discourse participants to be linguistically creative, that is, to say what one wants to say using the words that have not yet been used. In study 2, I explore how priming and antipriming effects work together to produce collective language creativity. By means of cluster analysis and Bayesian network modelling, I show that patterns of repetition for both languages differ drastically depending on whether participants of the experiment had to communicate their messages being or not being able to see what others had written before them.

Download Full-text

Data-Driven Bayesian Network Learning: A Bi-Objective Approach to Address the Bias-Variance Decomposition

Mathematical and Computational Applications ◽

10.3390/mca25020037 ◽

2020 ◽

Vol 25 (2) ◽

pp. 37 ◽

Cited By ~ 1

Author(s):

Vicente-Josué Aguilera-Rueda ◽

Nicandro Cruz-Ramírez ◽

Efrén Mezura-Montes

Keyword(s):

Bayesian Networks ◽

Bayesian Network ◽

Variance Decomposition ◽

Data Driven ◽

End User ◽

Learning Problem ◽

Nsga Ii ◽

Bias Variance ◽

Core Idea ◽

Nondominated Sorting

We present a novel bi-objective approach to address the data-driven learning problem of Bayesian networks. Both the log-likelihood and the complexity of each candidate Bayesian network are considered as objectives to be optimized by our proposed algorithm named Nondominated Sorting Genetic Algorithm for learning Bayesian networks (NS2BN) which is based on the well-known NSGA-II algorithm. The core idea is to reduce the implicit selection bias-variance decomposition while identifying a set of competitive models using both objectives. Numerical results suggest that, in stark contrast to the single-objective approach, our bi-objective approach is useful to find competitive Bayesian networks especially in the complexity. Furthermore, our approach presents the end user with a set of solutions by showing different Bayesian network and their respective MDL and classification accuracy results.

Download Full-text

Bayesian Network Modelling of ATC Complexity Metrics for Future SESAR Demand and Capacity Balance Solutions

Entropy ◽

10.3390/e21040379 ◽

2019 ◽

Vol 21 (4) ◽

pp. 379 ◽

Cited By ~ 1

Author(s):

Victor Gomez Comendador ◽

Rosa Arnaldo Valdés ◽

Manuel Villegas Diaz ◽

Eva Puntero Parla ◽

Danlin Zheng

Keyword(s):

Bayesian Network ◽

Traffic Control ◽

Air Traffic ◽

Network Modelling ◽

Traffic Demand ◽

Complexity Metrics ◽

Dynamic Airspace Configuration ◽

Input Variables ◽

The Impact

Demand & Capacity Management solutions are key SESAR (Single European Sky ATM Research) research projects to adapt future airspace to the expected high air traffic growth in a Trajectory Based Operations (TBO) environment. These solutions rely on processes, methods and metrics regarding the complexity assessment of traffic flows. However, current complexity methodologies and metrics do not properly take into account the impact of trajectories’ uncertainty to the quality of complexity predictions of air traffic demand. This paper proposes the development of several Bayesian network (BN) models to identify the impacts of TBO uncertainties to the quality of the predictions of complexity of air traffic demand for two particular Demand Capacity Balance (DCB) solutions developed by SESAR 2020, i.e., Dynamic Airspace Configuration (DAC) and Flight Centric Air Traffic Control (FCA). In total, seven BN models are elicited covering each concept at different time horizons. The models allow evaluating the influence of the “complexity generators” in the “complexity metrics”. Moreover, when the required level for the uncertainty of complexity is set, the networks allow identifying by how much uncertainty of the input variables should improve.

Download Full-text