Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  Algorithms  /  Vol: 13 Par: 12 (2020)  /  Artículo
ARTÍCULO
TITULO

Hard and Soft EM in Bayesian Network Learning from Incomplete Data

Andrea Ruggieri    
Francesco Stranieri    
Fabio Stella and Marco Scutari    

Resumen

Incomplete data are a common feature in many domains, from clinical trials to industrial applications. Bayesian networks (BNs) are often used in these domains because of their graphical and causal interpretations. BN parameter learning from incomplete data is usually implemented with the Expectation-Maximisation algorithm (EM), which computes the relevant sufficient statistics (?soft EM?) using belief propagation. Similarly, the Structural Expectation-Maximisation algorithm (Structural EM) learns the network structure of the BN from those sufficient statistics using algorithms designed for complete data. However, practical implementations of parameter and structure learning often impute missing data (?hard EM?) to compute sufficient statistics instead of using belief propagation, for both ease of implementation and computational speed. In this paper, we investigate the question: what is the impact of using imputation instead of belief propagation on the quality of the resulting BNs? From a simulation study using synthetic data and reference BNs, we find that it is possible to recommend one approach over the other in several scenarios based on the characteristics of the data. We then use this information to build a simple decision tree to guide practitioners in choosing the EM algorithm best suited to their problem.

 Artículos similares

       
 
Hao Wang and Nanfeng Xiao    
In order to better utilize and protect marine organisms, reliable underwater object detection methods need to be developed. Due to various influencing factors from complex and changeable underwater environments, the underwater object detection is full of... ver más
Revista: Applied Sciences

 
Kuan Ren, Annan Jiang, Xinping Guo and Qinghua Min    
The section of Jialingjiang Road Station to Xiangjiang Road Station along Qingdao Metro Line 13 is located in Qingdao, China. All of them show obvious characteristics, being soft on the top and hard on the bottom, and the interval tunnel is faced with th... ver más
Revista: Applied Sciences

 
Xicai Gao, Shuai Liu, Tengfei Ma, Cheng Zhao, Xichen Zhang, Huan Xia and Jianhui Yin    
The main Jurassic coal seams of the Ordos Basin of northwest mining area have special hosting conditions and complex hydrogeological conditions, and the high-intensity coal mining of the coal seams is likely to cause groundwater loss and negative effects... ver más
Revista: Applied Sciences

 
Liangxing Jin, Tian Qin and Pingting Liu    
Considering the change of different soil layer parameters of a two?layered strip foundation, a planar kinematically permissible multi?block failure mechanism of a two?layered strip foundation under vertical uniform load is formulated. Based on upper?boun... ver más
Revista: Applied Sciences

 
Izabela Maria Burda and Lucyna Nyka    
Waterfront areas in cities are subject to constant changes. The desire to integrate the transformed waterside areas with the urban fabric involves shaping high-quality public spaces related to water, which are often referred to as urban blue spaces (UBS)... ver más
Revista: Water