Objective To predict the total flavonoids concentration of Aurantii Fructus fried with bran in its extraction process. Methods Ultraviolet spectrophotometry was used to determine the concentration of total flavonoids ...Objective To predict the total flavonoids concentration of Aurantii Fructus fried with bran in its extraction process. Methods Ultraviolet spectrophotometry was used to determine the concentration of total flavonoids in different extraction time (t) and solvent load (M). Then the predicted procedure was carried out using the following data: 1 ) based on Ficks second law, the parameters of the kinetic model could be deduced and the equation was established; 2) Locally weighted regression (LWR) code was developed in the WEKA software environment to predict the concentration. And then we used both methods to predict the concentration of total flavonoids in new experiments. Results After comparing the predicted results with the experimental data, the LWR model had better accuracy and performance in the prediction. Conclusion LWR is applied to analyze the extraction process of Chinese herb for the first time, and it is totally fit for the extraction. LWR-based system is a more simple and accurate way to predict than the established equation. It is a good choice especially for a process which exists no clear rules, and can be used in the real-time control during the process.展开更多
Triadic closure is a simple and fundamental kind of link formulation mechanism in network.Local closure coefficient(LCC),a new network property,is to measure the triadic closure with respect to the fraction of length-...Triadic closure is a simple and fundamental kind of link formulation mechanism in network.Local closure coefficient(LCC),a new network property,is to measure the triadic closure with respect to the fraction of length-2 paths for link prediction.In this paper,a weighted format of LCC(WLCC)is introduced to measure the weighted strength of local triadic structure,and a statistic similari-ty-based link prediction metric is proposed to incorporate the definition of WLCC.To prove the metrics effectiveness and scalability,the WLCC formula-tion was further investigated under weighted local Naive Bayes(WLNB)link prediction framework.Finally,extensive experimental studies was conducted with weighted baseline metrics on various public network datasets.The results demonstrate the merits of the proposed metrics in comparison with the weighted baselines.展开更多
针对光伏出力和电动汽车充电特性的随机特性对电力系统的冲击不断增强,准确及时的源荷预测是实现增强电力系统适应性和稳定性的重要课题。因此,提出一种基于共享权重长短期记忆网络(shared weight long short-term networks,SWLSTM)与St...针对光伏出力和电动汽车充电特性的随机特性对电力系统的冲击不断增强,准确及时的源荷预测是实现增强电力系统适应性和稳定性的重要课题。因此,提出一种基于共享权重长短期记忆网络(shared weight long short-term networks,SWLSTM)与Stacking集成模型相结合的源荷区间预测方法。首先,光伏出力存在时序性特征,采用局部线性嵌入改进k-means算法聚类提取特征日,在实现数据降维同时,减少了网络训练难度;其次,在Stacking集成模型的框架下,将SWLSTM作为元学习器,并通过Q统计量筛选合适的基学习器模型,从而实现多模型融合的多异学习器Stacking集成学习的源荷预测;紧接着,为了得到预测的不确定信息,引入置信度区间预测;最后,采用实测数据对本文所提方法进行验证。结果表明改进k-means算法能够降低其求解难度,加快求解速度,可以快速获取聚类特征;所引入集成学习模型和置信度区间,有效表征源荷预测的不确定性,提升区间预测模型的泛化能力。展开更多
Soft sensors are widely used to predict quality variables which are usually hard to measure.It is necessary to construct an adaptive model to cope with process non-stationaries.In this study,a novel quality-related lo...Soft sensors are widely used to predict quality variables which are usually hard to measure.It is necessary to construct an adaptive model to cope with process non-stationaries.In this study,a novel quality-related locally weighted soft sensing method is designed for non-stationary processes based on a Bayesian network with latent variables.Specifically,a supervised Bayesian network is proposed where quality-oriented latent variables are extracted and further applied to a double-layer similarity meas-urement algorithm.The proposed soft sensing method tries to find a general approach for non-stationary processes via quality-related information where the concepts of local similarities and window confidence are explained in detail.The performance of the developed method is demonstrated by application to a numerical example and a debutanizer column.It is shown that the proposed method outperforms competitive methods in terms of the accuracy of predicting key quality variables.展开更多
基金National Nature Science Foundation of China(surface project)(81173563)
文摘Objective To predict the total flavonoids concentration of Aurantii Fructus fried with bran in its extraction process. Methods Ultraviolet spectrophotometry was used to determine the concentration of total flavonoids in different extraction time (t) and solvent load (M). Then the predicted procedure was carried out using the following data: 1 ) based on Ficks second law, the parameters of the kinetic model could be deduced and the equation was established; 2) Locally weighted regression (LWR) code was developed in the WEKA software environment to predict the concentration. And then we used both methods to predict the concentration of total flavonoids in new experiments. Results After comparing the predicted results with the experimental data, the LWR model had better accuracy and performance in the prediction. Conclusion LWR is applied to analyze the extraction process of Chinese herb for the first time, and it is totally fit for the extraction. LWR-based system is a more simple and accurate way to predict than the established equation. It is a good choice especially for a process which exists no clear rules, and can be used in the real-time control during the process.
基金This work is supported by Basic and Applied Basic Research Foundation of Guangdong Province(No.2020A1515011495)Guangzhou Science and Technology Foundation Project(No.202002030266).
文摘Triadic closure is a simple and fundamental kind of link formulation mechanism in network.Local closure coefficient(LCC),a new network property,is to measure the triadic closure with respect to the fraction of length-2 paths for link prediction.In this paper,a weighted format of LCC(WLCC)is introduced to measure the weighted strength of local triadic structure,and a statistic similari-ty-based link prediction metric is proposed to incorporate the definition of WLCC.To prove the metrics effectiveness and scalability,the WLCC formula-tion was further investigated under weighted local Naive Bayes(WLNB)link prediction framework.Finally,extensive experimental studies was conducted with weighted baseline metrics on various public network datasets.The results demonstrate the merits of the proposed metrics in comparison with the weighted baselines.
文摘针对光伏出力和电动汽车充电特性的随机特性对电力系统的冲击不断增强,准确及时的源荷预测是实现增强电力系统适应性和稳定性的重要课题。因此,提出一种基于共享权重长短期记忆网络(shared weight long short-term networks,SWLSTM)与Stacking集成模型相结合的源荷区间预测方法。首先,光伏出力存在时序性特征,采用局部线性嵌入改进k-means算法聚类提取特征日,在实现数据降维同时,减少了网络训练难度;其次,在Stacking集成模型的框架下,将SWLSTM作为元学习器,并通过Q统计量筛选合适的基学习器模型,从而实现多模型融合的多异学习器Stacking集成学习的源荷预测;紧接着,为了得到预测的不确定信息,引入置信度区间预测;最后,采用实测数据对本文所提方法进行验证。结果表明改进k-means算法能够降低其求解难度,加快求解速度,可以快速获取聚类特征;所引入集成学习模型和置信度区间,有效表征源荷预测的不确定性,提升区间预测模型的泛化能力。
基金the National Key Research and Development Program of China(No.2016YFC0301404)the National Natural Science Foundation of China(Nos.51379198 and 61903352)+5 种基金the Natural Science Foundation of Zhejiang Province,China(No.LQ19F030007)the Natural Science Foundation of Jiangsu Province,China(No.BK20180594)the Project of Department of Education of Zhejiang Province,China(No.Y202044960)the China Postdoctoral Science Foundation(No.2020M671721)the Foundation of Key Laboratory of Advanced Process Control for Light Industry(No.APCLI1803)the Fundamental Research Funds for the Provincial Universities of Zhejiang,China(Nos.2021YW18 and 2021YW80)。
文摘Soft sensors are widely used to predict quality variables which are usually hard to measure.It is necessary to construct an adaptive model to cope with process non-stationaries.In this study,a novel quality-related locally weighted soft sensing method is designed for non-stationary processes based on a Bayesian network with latent variables.Specifically,a supervised Bayesian network is proposed where quality-oriented latent variables are extracted and further applied to a double-layer similarity meas-urement algorithm.The proposed soft sensing method tries to find a general approach for non-stationary processes via quality-related information where the concepts of local similarities and window confidence are explained in detail.The performance of the developed method is demonstrated by application to a numerical example and a debutanizer column.It is shown that the proposed method outperforms competitive methods in terms of the accuracy of predicting key quality variables.
基金教育部留学回国人员科研启动基金(The Project-sponsored by SRF for ROCS SEM No.2004.176.4)+1 种基金山东省自然科学基金( the Natural Science Foundation of Shandong Province of China under Grant No.2004G01 No.2004ZRC03016)