UM  > GRADUATE SCHOOL
Status已發表Published
Prediction on Uniaxial Compressive Strength of Rock: Bayesian Inference and Outlier Analysis
Mu, H.Q.; Yuen, K. V.; Ng, I. T.
2017-06-01
Source PublicationInternational Conference on Structural Safety and Reliability (ICOSSAR) 2017
AbstractThis study conducts a two-stage analysis of model development and prediction for the uniaxial compressive strength (UCS) estimation. In the first stage, the optimal predictive model is developed based on the training dataset, using Bayesian infer-ence with the automatic relevance determination (ARD) prior. In the second stage, based on the optimal predictive model of the first stage, outlier analysis for model prediction reliability assessment is performed for the test datasets. The results show that the model for the Grade III granite depends on the point load index, P-wave velocity, effective porosity, and this model is not fully applicable to the prediction on the Grade I & II granite.
KeywordBayesian outlier
Language英語English
The Source to ArticlePB_Publication
PUB ID33664
Document TypeConference paper
CollectionGRADUATE SCHOOL
Recommended Citation
GB/T 7714
Mu, H.Q.,Yuen, K. V.,Ng, I. T.. Prediction on Uniaxial Compressive Strength of Rock: Bayesian Inference and Outlier Analysis[C], 2017.
APA Mu, H.Q.., Yuen, K. V.., & Ng, I. T. (2017). Prediction on Uniaxial Compressive Strength of Rock: Bayesian Inference and Outlier Analysis. International Conference on Structural Safety and Reliability (ICOSSAR) 2017.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Mu, H.Q.]'s Articles
[Yuen, K. V.]'s Articles
[Ng, I. T.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Mu, H.Q.]'s Articles
[Yuen, K. V.]'s Articles
[Ng, I. T.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Mu, H.Q.]'s Articles
[Yuen, K. V.]'s Articles
[Ng, I. T.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.