To solve the arrearage problem that puzzled most of the mobile corporations, we propose an approach to forecast and evaluate the credits for mobile clients, devising a method that is of the coalescence of genetic algo...To solve the arrearage problem that puzzled most of the mobile corporations, we propose an approach to forecast and evaluate the credits for mobile clients, devising a method that is of the coalescence of genetic algorithm and multidimensional distinguishing model. In the end of this paper, a result of a testing application in Zhuhai Branch, GMCC was provided. The precision of the forecasting and evaluation of the client’s credit is near 90%. This study is very significant to the mobile communication corporation at all levels. The popularization of the techniques and the result would produce great benefits of both society and economy.展开更多
The performance evaluation of the process industry, which has been a popular topic nowadays, can not only find the weakness and verify the resilience and reliability of the process, but also provide some suggestions t...The performance evaluation of the process industry, which has been a popular topic nowadays, can not only find the weakness and verify the resilience and reliability of the process, but also provide some suggestions to improve the process benefits and efficiency. Nevertheless, the performance assessment principally concentrates upon some parts of the entire system at present, for example the controller assessment. Although some researches focus on the whole process, they aim at discovering the relationships between profit, society, policies and so forth, instead of relations between overall performance and some manipulated variables, that is, the total plant performance. According to the big data of different performance statuses, this paper proposes a hierarchical framework to select some structured logic rules from monitored variables to estimate the current state of the process. The variables related to safety and profits are regarded as key factors to performance evaluation. To better monitor the process state and observe the performance variation trend of the process, a classificationvisualization method based on kernel principal component analysis(KPCA) and self-organizing map(SOM) is established. The dimensions of big data produced by the process are first reduced by KPCA and then the processed data will be mapped into a two-dimensional grid chart by SOM to evaluate the performance status. The monitoring method is applied to the Tennessee Eastman process. Monitoring results indicate that off-line and on-line performance status can be well detected in a two-dimensional diagram.展开更多
A scientific and rational evaluation on road-region ecosystem stability is the premise to properly deal with the relationship between highway constructing and ecological environment protecting to a sustainable develop...A scientific and rational evaluation on road-region ecosystem stability is the premise to properly deal with the relationship between highway constructing and ecological environment protecting to a sustainable development. Based on the connotative meaning and the procedure of evaluation on road-region ecosystem stability, this paper studied the principles and the method on determining the evaluation index system on road-region ecosystem stability. It put forward an index system for assessing road-region ecosystem stability as a reference. On the basis of detailed analyze of the multidimensional space of road-region ecosystem, a new multi-objective comprehensive evaluation method for road-region ecosystem stability is presented and a calculation tormula for multi-objective comprehensive level of road-region ecosystem stability. This method was used to evaluate road-region ecosystem stability of Lin-Chang highway. This method possessed definite theoretical value and reliability in practice.展开更多
Purpose:Based on the understanding of the characteristics of mobile services(m-services)provided by libraries,we attempt to develop a multidimensional and hierarchical model and a specifically designed measurement sca...Purpose:Based on the understanding of the characteristics of mobile services(m-services)provided by libraries,we attempt to develop a multidimensional and hierarchical model and a specifically designed measurement scale for the assessment of libraries' m-service quality.Design/methodology/approach:The research has been conducted sequentially in two stages.At the first stage,a multidimensional and hierarchical model of library m-service quality and a measurement scale are developed through literature review and focus group interviews.At the second stage the model is tested using partial disaggregation technique for an analysis of the data collected from over 400 library users in 3 Chinese universities.Findings:The proposed model is shown to fit the data well.The empirical analysis provides strong support for the model,which includes 4 dimensions(service environment,service interaction,information control and service effect) and 12 corresponding sub-dimensions.Research limitations:The sample size needs to be enlarged and the user types need to be expanded to make the sample more representative.Practical implications:The study provides a conceptual framework and measurement tool that can help library managers understand the users' needs in the context of mobile network environment,and boost their libraries' competitiveness by carrying out better services to meet the user demands.Originality/value:The proposed model and measurement scale specifically designed for the assessment of libraries' m-service quality fully reflect the hierarchical structure of libraries' m-service quality.In addition,by using partial disaggregation technique for model testing,we believe our research can serve as a practical reference to those engaged in the development and examination of a multidimensional and hierarchical model.展开更多
针对大规模开放在线课程(MOOC)质量评估维度单一、缺乏细粒度分析的问题,构建了一个以方面级情感分析为核心的语义切分至多维评估框架。基于中国大学MOOC平台中大数据与人工智能类课程的评论数据,利用通用信息抽取(universal informatio...针对大规模开放在线课程(MOOC)质量评估维度单一、缺乏细粒度分析的问题,构建了一个以方面级情感分析为核心的语义切分至多维评估框架。基于中国大学MOOC平台中大数据与人工智能类课程的评论数据,利用通用信息抽取(universal information extraction,UIE)工具抽取影响要素词,通过K-means聚类与变异系数法,构建了涵盖5个一级指标和10个二级指标的加权评价体系。设计了基于影响要素词定位的语义切分(impact element word-based targeted comment segmentation and classification,ITCSC)算法,将长评论切分为方面级短句,结合SKEP情感模型实现多维度量化分析,揭示了内容配置、服务评价等维度的表现特征。实验表明,该框架兼顾整体趋势与细节特征,为课程优化及选课提供数据支持,丰富了细粒度教育质量评估路径。展开更多
基金Guangdong Mobile Communication Company Limited Key Item(2001 and 2002)
文摘To solve the arrearage problem that puzzled most of the mobile corporations, we propose an approach to forecast and evaluate the credits for mobile clients, devising a method that is of the coalescence of genetic algorithm and multidimensional distinguishing model. In the end of this paper, a result of a testing application in Zhuhai Branch, GMCC was provided. The precision of the forecasting and evaluation of the client’s credit is near 90%. This study is very significant to the mobile communication corporation at all levels. The popularization of the techniques and the result would produce great benefits of both society and economy.
基金Supported by the National Natural Science Foundation of China(61590923,61422303,21376077)
文摘The performance evaluation of the process industry, which has been a popular topic nowadays, can not only find the weakness and verify the resilience and reliability of the process, but also provide some suggestions to improve the process benefits and efficiency. Nevertheless, the performance assessment principally concentrates upon some parts of the entire system at present, for example the controller assessment. Although some researches focus on the whole process, they aim at discovering the relationships between profit, society, policies and so forth, instead of relations between overall performance and some manipulated variables, that is, the total plant performance. According to the big data of different performance statuses, this paper proposes a hierarchical framework to select some structured logic rules from monitored variables to estimate the current state of the process. The variables related to safety and profits are regarded as key factors to performance evaluation. To better monitor the process state and observe the performance variation trend of the process, a classificationvisualization method based on kernel principal component analysis(KPCA) and self-organizing map(SOM) is established. The dimensions of big data produced by the process are first reduced by KPCA and then the processed data will be mapped into a two-dimensional grid chart by SOM to evaluate the performance status. The monitoring method is applied to the Tennessee Eastman process. Monitoring results indicate that off-line and on-line performance status can be well detected in a two-dimensional diagram.
文摘A scientific and rational evaluation on road-region ecosystem stability is the premise to properly deal with the relationship between highway constructing and ecological environment protecting to a sustainable development. Based on the connotative meaning and the procedure of evaluation on road-region ecosystem stability, this paper studied the principles and the method on determining the evaluation index system on road-region ecosystem stability. It put forward an index system for assessing road-region ecosystem stability as a reference. On the basis of detailed analyze of the multidimensional space of road-region ecosystem, a new multi-objective comprehensive evaluation method for road-region ecosystem stability is presented and a calculation tormula for multi-objective comprehensive level of road-region ecosystem stability. This method was used to evaluate road-region ecosystem stability of Lin-Chang highway. This method possessed definite theoretical value and reliability in practice.
基金supported by the Social Science Foundation of China(Grant No.:12CTQ005)
文摘Purpose:Based on the understanding of the characteristics of mobile services(m-services)provided by libraries,we attempt to develop a multidimensional and hierarchical model and a specifically designed measurement scale for the assessment of libraries' m-service quality.Design/methodology/approach:The research has been conducted sequentially in two stages.At the first stage,a multidimensional and hierarchical model of library m-service quality and a measurement scale are developed through literature review and focus group interviews.At the second stage the model is tested using partial disaggregation technique for an analysis of the data collected from over 400 library users in 3 Chinese universities.Findings:The proposed model is shown to fit the data well.The empirical analysis provides strong support for the model,which includes 4 dimensions(service environment,service interaction,information control and service effect) and 12 corresponding sub-dimensions.Research limitations:The sample size needs to be enlarged and the user types need to be expanded to make the sample more representative.Practical implications:The study provides a conceptual framework and measurement tool that can help library managers understand the users' needs in the context of mobile network environment,and boost their libraries' competitiveness by carrying out better services to meet the user demands.Originality/value:The proposed model and measurement scale specifically designed for the assessment of libraries' m-service quality fully reflect the hierarchical structure of libraries' m-service quality.In addition,by using partial disaggregation technique for model testing,we believe our research can serve as a practical reference to those engaged in the development and examination of a multidimensional and hierarchical model.
文摘针对大规模开放在线课程(MOOC)质量评估维度单一、缺乏细粒度分析的问题,构建了一个以方面级情感分析为核心的语义切分至多维评估框架。基于中国大学MOOC平台中大数据与人工智能类课程的评论数据,利用通用信息抽取(universal information extraction,UIE)工具抽取影响要素词,通过K-means聚类与变异系数法,构建了涵盖5个一级指标和10个二级指标的加权评价体系。设计了基于影响要素词定位的语义切分(impact element word-based targeted comment segmentation and classification,ITCSC)算法,将长评论切分为方面级短句,结合SKEP情感模型实现多维度量化分析,揭示了内容配置、服务评价等维度的表现特征。实验表明,该框架兼顾整体趋势与细节特征,为课程优化及选课提供数据支持,丰富了细粒度教育质量评估路径。
