.png){kind=icon}
Return
A non-parametric Bayesian model for bounded data
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2014.12.019.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The intensity distribution of the observed data in many practical problems is digitalized and has bounded support. There has been growing research interest in model-based techniques to carry out on the non-Gaussian shape of observed data. However, users set remaining parameters in the existing models based on prior knowledge. Also, the distribution in the existing models is unbounded, which is not sufficiently flexible to fit different shapes of the bounded support data. In this paper, we present a non-parametric Bayesian model for modeling the probability density function of the bounded data. The advantage of our method is that the number of the parameters in the proposed model is variable and infinite, which makes the model conceptually simpler and more adaptable to the size of the data. We present numerical experiments in which we test the proposed model in various data from simulated to real data. (C) 2015 Elsevier Ltd. All rights reserved.
Keywords:
Bounded data
Non-parametric
Beta distribution
Variational Bayesian learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
ShareSaveShareSaveShareSaveShareSaveShareSaveA generalized multiclass histogram thresholding approach based on mixture modelling.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave
View more