Multi-model approach can significantly improve the prediction performance of soft sensors in the process with multiple operational conditions.However,traditional clustering algorithms may result in overlapping phenome...Multi-model approach can significantly improve the prediction performance of soft sensors in the process with multiple operational conditions.However,traditional clustering algorithms may result in overlapping phenomenon in subclasses,so that edge classes and outliers cannot be effectively dealt with and the modeling result is not satisfactory.In order to solve these problems,a new feature extraction method based on weighted kernel Fisher criterion is presented to improve the clustering accuracy,in which feature mapping is adopted to bring the edge classes and outliers closer to other normal subclasses.Furthermore,the classified data are used to develop a multiple model based on support vector machine.The proposed method is applied to a bisphenol A production process for prediction of the quality index.The simulation results demonstrate its ability in improving the data classification and the prediction performance of the soft sensor.展开更多
For measurement of component content in the extraction and separation process of praseodymium/neodymium(Pr/Nd), a soft measurement method was proposed based on modeling of ion color features, which is suitable for fas...For measurement of component content in the extraction and separation process of praseodymium/neodymium(Pr/Nd), a soft measurement method was proposed based on modeling of ion color features, which is suitable for fast estimation of component content in production field. Feature analysis on images of the solution is conducted,which are captured from Pr/Nd extraction/separation field. H/S components in the HSI color space are selected as model inputs, so as to establish the least squares support vector machine(LSSVM) model for Nd(Pr) content,while the model parameters are determined with the GA algorithm. To improve the adaptability of the model,the adaptive iteration algorithm is used to correct parameters of the LSSVM model, on the basis of model correction strategy and new sample data. Using the field data collected from rare earth extraction production, predictive methods for component content and comparisons are given. The results indicate that the proposed method presents good adaptability and high prediction precision, so it is applicable to the fast detection of element content in the rare earth extraction.展开更多
Software architectures shift the focus of developers from lines-of-code to coarser-grained architectural elements and their overall interconnection structure. There are, however, many features of the distributed softw...Software architectures shift the focus of developers from lines-of-code to coarser-grained architectural elements and their overall interconnection structure. There are, however, many features of the distributed software that make the developing methods of distributed software quite different from the traditional ways. Furthermore, the traditional centralized ways with fixed interfaces cannot adapt to the flexible requirements of distributed software. In this paper, the attributed grammar (AG) is extended to refine the characters of distributed software, and a distributed software architecture description language (DSADL) based on attributed grammar is introduced, and then a model of integrated environment for software architecture design is proposed. It can be demonstrated by the practice that DSADL can help the programmers to analyze and design distributed software effectively, so the efficiency of the development can be improved greatly.展开更多
Recently, some new characteristics of complex networks attract the attentions of scientist, in different fields, and lead to many kinds of emerging research directions. So far, most of the researcl work has been limit...Recently, some new characteristics of complex networks attract the attentions of scientist, in different fields, and lead to many kinds of emerging research directions. So far, most of the researcl work has been limited in discovery of complex network characteristics by structure analysis in large-scale software systems. This paper presents the theoretical basis, design method, algorithms and experiment results of the research. It firstly emphasizes the significance of design method of evolution growth for network topology of Object Oriented （OO） software systems, and argues that the selection and modulation of network models with various topology characteristics will bring un-ignorable effect on the process, of design and implementation of OO software systems. Then we analyze the similar discipline of ＂negation of negation and compromise＂ between the evolution of network models with different topology characteristics and the development of software modelling methods. According to the analysis of the growth features of software patterns, we propose an object-oriented software network evolution growth method and its algorithms in succession. In addition, we also propose the parameter systems for OO software system metrics based on complex network theory. Based on these parameter systems, it can analyze the features of various nodes, links and local-world, modulate the network topology and guide the software metrics. All these can be helpful to the detailed design, implementation and performance analysis. Finally, we focus on the application of the evolution algorithms and demonstrate it by a case study. Comparing the results from our early experiments with methodologies in empirical software engineering, we believe that the proposed software engineering design method is a computational software engineering approach based on complex network theory. We argue that this method should be greatly beneficial for the design, implementation, modulation and metrics of functionality, structure and performance in large-scale OO software complex system.展开更多
Mobile device manufacturers are rapidly producing miscellaneous Android versions worldwide. Simultaneously, cyber criminals are executing malicious actions, such as tracking user activities, stealing personal data, an...Mobile device manufacturers are rapidly producing miscellaneous Android versions worldwide. Simultaneously, cyber criminals are executing malicious actions, such as tracking user activities, stealing personal data, and committing bank fraud. These criminals gain numerous benefits as too many people use Android for their daily routines, including important communications. With this in mind, security practitioners have conducted static and dynamic analyses to identify malware. This study used static analysis because of its overall code coverage, low resource consumption, and rapid processing. However, static analysis requires a minimum number of features to efficiently classify malware. Therefore, we used genetic search（GS）, which is a search based on a genetic algorithm（GA）, to select the features among 106 strings. To evaluate the best features determined by GS, we used five machine learning classifiers, namely, Na？ve Bayes（NB）, functional trees（FT）, J48, random forest（RF）, and multilayer perceptron（MLP）. Among these classifiers, FT gave the highest accuracy（95%） and true positive rate（TPR）（96.7%） with the use of only six features.展开更多
基金Supported by the National Natural Science Foundation of China(61273070)the Foundation of Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘Multi-model approach can significantly improve the prediction performance of soft sensors in the process with multiple operational conditions.However,traditional clustering algorithms may result in overlapping phenomenon in subclasses,so that edge classes and outliers cannot be effectively dealt with and the modeling result is not satisfactory.In order to solve these problems,a new feature extraction method based on weighted kernel Fisher criterion is presented to improve the clustering accuracy,in which feature mapping is adopted to bring the edge classes and outliers closer to other normal subclasses.Furthermore,the classified data are used to develop a multiple model based on support vector machine.The proposed method is applied to a bisphenol A production process for prediction of the quality index.The simulation results demonstrate its ability in improving the data classification and the prediction performance of the soft sensor.
基金Supported by the National Natural Science Foundation of China(51174091,61364013,61164013)Earlier Research Project of the State Key Development Program for Basic Research of China(2014CB360502)
文摘For measurement of component content in the extraction and separation process of praseodymium/neodymium(Pr/Nd), a soft measurement method was proposed based on modeling of ion color features, which is suitable for fast estimation of component content in production field. Feature analysis on images of the solution is conducted,which are captured from Pr/Nd extraction/separation field. H/S components in the HSI color space are selected as model inputs, so as to establish the least squares support vector machine(LSSVM) model for Nd(Pr) content,while the model parameters are determined with the GA algorithm. To improve the adaptability of the model,the adaptive iteration algorithm is used to correct parameters of the LSSVM model, on the basis of model correction strategy and new sample data. Using the field data collected from rare earth extraction production, predictive methods for component content and comparisons are given. The results indicate that the proposed method presents good adaptability and high prediction precision, so it is applicable to the fast detection of element content in the rare earth extraction.
基金Project (No. 2000K08-G12) supported by Shaanxi Provincial Science and Technology Development Plan, China
文摘Software architectures shift the focus of developers from lines-of-code to coarser-grained architectural elements and their overall interconnection structure. There are, however, many features of the distributed software that make the developing methods of distributed software quite different from the traditional ways. Furthermore, the traditional centralized ways with fixed interfaces cannot adapt to the flexible requirements of distributed software. In this paper, the attributed grammar (AG) is extended to refine the characters of distributed software, and a distributed software architecture description language (DSADL) based on attributed grammar is introduced, and then a model of integrated environment for software architecture design is proposed. It can be demonstrated by the practice that DSADL can help the programmers to analyze and design distributed software effectively, so the efficiency of the development can be improved greatly.
基金Supported by the National Natural Science Foundation of China under Grant No.60373086IS0/IEC SC32 Standardization Project No.1.32.22.01.03.00+3 种基金"Tenth Five-Year Plan"National Key Project of Science and Technology under Grant No.2002BA906A21Hubei Province Key Project under Grant No.2004AA103A02Wuhan City Key Project under Grant No.200210020430pen Foundation of SKLSE under Grant No.SKLSE05-19.
文摘Recently, some new characteristics of complex networks attract the attentions of scientist, in different fields, and lead to many kinds of emerging research directions. So far, most of the researcl work has been limited in discovery of complex network characteristics by structure analysis in large-scale software systems. This paper presents the theoretical basis, design method, algorithms and experiment results of the research. It firstly emphasizes the significance of design method of evolution growth for network topology of Object Oriented （OO） software systems, and argues that the selection and modulation of network models with various topology characteristics will bring un-ignorable effect on the process, of design and implementation of OO software systems. Then we analyze the similar discipline of ＂negation of negation and compromise＂ between the evolution of network models with different topology characteristics and the development of software modelling methods. According to the analysis of the growth features of software patterns, we propose an object-oriented software network evolution growth method and its algorithms in succession. In addition, we also propose the parameter systems for OO software system metrics based on complex network theory. Based on these parameter systems, it can analyze the features of various nodes, links and local-world, modulate the network topology and guide the software metrics. All these can be helpful to the detailed design, implementation and performance analysis. Finally, we focus on the application of the evolution algorithms and demonstrate it by a case study. Comparing the results from our early experiments with methodologies in empirical software engineering, we believe that the proposed software engineering design method is a computational software engineering approach based on complex network theory. We argue that this method should be greatly beneficial for the design, implementation, modulation and metrics of functionality, structure and performance in large-scale OO software complex system.
基金supported by the Ministry of Science,Technology and Innovation of Malaysia,under the Grant e Science Fund(No.01-01-03-SF0914)
文摘Mobile device manufacturers are rapidly producing miscellaneous Android versions worldwide. Simultaneously, cyber criminals are executing malicious actions, such as tracking user activities, stealing personal data, and committing bank fraud. These criminals gain numerous benefits as too many people use Android for their daily routines, including important communications. With this in mind, security practitioners have conducted static and dynamic analyses to identify malware. This study used static analysis because of its overall code coverage, low resource consumption, and rapid processing. However, static analysis requires a minimum number of features to efficiently classify malware. Therefore, we used genetic search（GS）, which is a search based on a genetic algorithm（GA）, to select the features among 106 strings. To evaluate the best features determined by GS, we used five machine learning classifiers, namely, Na？ve Bayes（NB）, functional trees（FT）, J48, random forest（RF）, and multilayer perceptron（MLP）. Among these classifiers, FT gave the highest accuracy（95%） and true positive rate（TPR）（96.7%） with the use of only six features.
