In this paper, the interaction parameters in the subregular solution model, λ1 and λ2, are regarded as a linear function of temperature, T. Therefore, the molar excess Gibbs energy of A-B binary system may be reexpr...In this paper, the interaction parameters in the subregular solution model, λ1 and λ2, are regarded as a linear function of temperature, T. Therefore, the molar excess Gibbs energy of A-B binary system may be reexpressed as follows:Gm^E=xAxB[(λ11+λ12T)+(λ21+λ22T)xB]The calculation of the model parameters, λ11, λ12, λ21and λ22, was carried out numerically from the phase diagrams for 11 alkali metal-alkali halide or alkali earth metal-halide systems. In addition, artificial neural network trained by known data has been used to predict the values of these model parameters. The predicted results are in good agreement with the .calculated ones. The applicability of the subregular solution model to the alkali metal-alkali halide or alkali earth metal-halide systems were tested by comparing the available experimental composition along the boundary of miscibility gap with the calculated ones which were obtained by using genetic algorithm. The good agreement between the calculated and experimental results across the entire liquidus is valid evidence in support of the model.展开更多
This paper proposes a proper methodology in data modification by using AHP （analytical hierarchy process） technique and FCM （fuzzy c-mean） model in the ICU （intensive care unit）. The binary data were created fro...This paper proposes a proper methodology in data modification by using AHP （analytical hierarchy process） technique and FCM （fuzzy c-mean） model in the ICU （intensive care unit）. The binary data were created from continuous data using FCM model, while the continuous data were constructed from binary data using AHP technique. The models used in this study are FCRM （fuzzy c-regression model）. A case study in scale of health at the ICU ward using the AI-IP, FCM model and FCRM models was conducted. There are six independent variables in this study. There are four cases which are considered as the result of using AHP technique and FCM model against independent data. After comparing the four cases, it was found that case 4 appeared to be the best model, because it has the lowest MSE （mean square error） value. The original data have the MSE value of 97.33, while the data in case 4 have the MSE value of 82.75. This means that the use of AHP technique can reduce the MSE value, while the use of FCM model can not reduce the MSE value. In other words, it can be proved that the AHP technique can increase the accuracy of prediction in modeling scale of health which is associated with the mortality rate in the ICU.展开更多
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。
文摘In this paper, the interaction parameters in the subregular solution model, λ1 and λ2, are regarded as a linear function of temperature, T. Therefore, the molar excess Gibbs energy of A-B binary system may be reexpressed as follows:Gm^E=xAxB[(λ11+λ12T)+(λ21+λ22T)xB]The calculation of the model parameters, λ11, λ12, λ21and λ22, was carried out numerically from the phase diagrams for 11 alkali metal-alkali halide or alkali earth metal-halide systems. In addition, artificial neural network trained by known data has been used to predict the values of these model parameters. The predicted results are in good agreement with the .calculated ones. The applicability of the subregular solution model to the alkali metal-alkali halide or alkali earth metal-halide systems were tested by comparing the available experimental composition along the boundary of miscibility gap with the calculated ones which were obtained by using genetic algorithm. The good agreement between the calculated and experimental results across the entire liquidus is valid evidence in support of the model.
文摘This paper proposes a proper methodology in data modification by using AHP （analytical hierarchy process） technique and FCM （fuzzy c-mean） model in the ICU （intensive care unit）. The binary data were created from continuous data using FCM model, while the continuous data were constructed from binary data using AHP technique. The models used in this study are FCRM （fuzzy c-regression model）. A case study in scale of health at the ICU ward using the AI-IP, FCM model and FCRM models was conducted. There are six independent variables in this study. There are four cases which are considered as the result of using AHP technique and FCM model against independent data. After comparing the four cases, it was found that case 4 appeared to be the best model, because it has the lowest MSE （mean square error） value. The original data have the MSE value of 97.33, while the data in case 4 have the MSE value of 82.75. This means that the use of AHP technique can reduce the MSE value, while the use of FCM model can not reduce the MSE value. In other words, it can be proved that the AHP technique can increase the accuracy of prediction in modeling scale of health which is associated with the mortality rate in the ICU.
