Statistical biases may be introduced by imprecisely quantifying background radiation reference levels. It is, therefore, imperative to devise a simple, adaptable approach for precisely describing the reference backgro...Statistical biases may be introduced by imprecisely quantifying background radiation reference levels. It is, therefore, imperative to devise a simple, adaptable approach for precisely describing the reference background levels of naturally occurring radionuclides (NOR) in mining sites. As a substitute statistical method, we suggest using Bayesian modeling in this work to examine the spatial distribution of NOR. For naturally occurring gamma-induced radionuclides like 232Th, 40K, and 238U, statistical parameters are inferred using the Markov Chain Monte Carlo (MCMC) method. After obtaining an accurate subsample using bootstrapping, we exclude any possible outliers that fall outside of the Highest Density Interval (HDI). We use MCMC to build a Bayesian model with the resampled data and make predictions about the posterior distribution of radionuclides produced by gamma irradiation. This method offers a strong and dependable way to describe NOR reference background values, which is important for managing and evaluating radiation risks in mining contexts.展开更多
文摘Statistical biases may be introduced by imprecisely quantifying background radiation reference levels. It is, therefore, imperative to devise a simple, adaptable approach for precisely describing the reference background levels of naturally occurring radionuclides (NOR) in mining sites. As a substitute statistical method, we suggest using Bayesian modeling in this work to examine the spatial distribution of NOR. For naturally occurring gamma-induced radionuclides like 232Th, 40K, and 238U, statistical parameters are inferred using the Markov Chain Monte Carlo (MCMC) method. After obtaining an accurate subsample using bootstrapping, we exclude any possible outliers that fall outside of the Highest Density Interval (HDI). We use MCMC to build a Bayesian model with the resampled data and make predictions about the posterior distribution of radionuclides produced by gamma irradiation. This method offers a strong and dependable way to describe NOR reference background values, which is important for managing and evaluating radiation risks in mining contexts.
文摘为快速识别冒犯性评论文本中的用户热点主题,解决传统主题模型在处理评论文本时语义描述不充分、上下文信息丢失和主题连贯性不强,以及K-means聚类算法对K值和初始中心点敏感的问题。使用CoSENT(cosine sentence)模型获取包含冒犯性语言的评论文本的句子级向量特征,对通过统一流形逼近与投影算法即UMAP(uniform manifold approximation and projection)模型降维后的向量矩阵使用基于Canopy+的改进K-means算法进行类簇划分,用(class term frequency-inverse document frequency,c-TF-IDF)识别各主题簇的主题特征,进行主题建模。通过对比冒犯性评论文本数据集以及普通评论数据集的实验验证了方法有效性。结果表明本文方法能够得到更好的主题一致性。
