Dynamic Embeddings for Efficient Parameter Learning of Bayesian Network with Multiple Latent Variables

Author(s):  
Zhiwei Qi ◽  
Kun Yue ◽  
Liang Duan ◽  
Kuang Hu ◽  
Zhihong Liang
2021 ◽  
Vol 2021 (1) ◽  
pp. 1054-1064
Author(s):  
Salwa Rizqina Putri ◽  
Thosan Girisona Suganda ◽  
Setia Pramana

Untuk mendukung pertumbuhan ekonomi hijau Indonesia, diperlukan analisis lebih lanjut terkait aktivitas ekonomi di masa pandemi dan keterkaitannya dengan kondisi lingkungan. Penelitian ini bertujuan untuk menerapkan pendekatan Bayesian Network dalam memodelkan kondisi ekonomi hijau Indonesia di masa pandemi berdasarkan variabel-variabel yang disinyalir dapat berpengaruh seperti aktivitas ekonomi, kualitas udara, tingkat mobilitas penduduk, dan kasus positif COVID-19 yang diperoleh melalui big data. Model Bayesian Network yang dikonstruksi secara manual dengan algoritma Maximum Spanning Tree dipilih sebagai model terbaik dengan rata-rata akurasi 5-cross validation dalam memprediksi empat kelas PDRB sebesar 0,83. Model terbaik yang dipilih menunjukkan bahwa kondisi ekonomi Indonesia di era pandemi secara langsung dipengaruhi oleh intensitas cahaya malam (NTL) yang menunjukkan aktivitas ekonomi, kualitas udara (AQI), dan kasus positif COVID-19. Analisis parameter learning menunjukkan bahwa pertumbuhan ekonomi provinsi-provinsi Indonesia masih cenderung belum sejalan dengan terpeliharanya kualitas udara sehingga usaha untuk mencapai kondisi ekonomi hijau masih harus ditingkatkan.


Author(s):  
R. Mishra ◽  
L. Uotinen ◽  
M. Rinne

SYNOPSIS Underground mining gives rise to geotechnical hazards. A formal geotechnical risk assessment can help to forecast and mitigate these hazards. Frequentist probability methods can be used when the hazard does not have many variables and a lot of data is available. However, often there is not enough data for probability distributions, such as in the case of new projects. The risk assessment is often subjective and qualitative, based on expert judgement. The purpose of this research is to present the use of Bayesian networks (BNs) as an alternative to existing risk assessment methods in underground mines by combining expert knowledge with data as it becomes available. Roof fall frequency forecasting using parameter learning is demonstrated with 1141 sets of roof fall data across 12 coal mines in the USA. The prediction is nearly identical for individual mines, but when multiple mines are evaluated it is difficult to find a single best fit distribution for annual roof fall frequency. The BN approach with TNormal distribution was twice as likely to fit the observed data compared to the Poisson distribution assumed in the past. A hybrid approach using BN combining multiple probability distribution curves from historical data to predict annual roof fall is proposed. The BN models can account for variability for multiple parameters without increasing the complexity of the calculation. BNs can work with varying amounts of data, which makes them a good tool for real-time risk assessment in mines. Keywords: Bayesian network; expert opinion models; geotechnical risk; incident forecasting; parameter learning; roof fall risk.


Sign in / Sign up

Export Citation Format

Share Document