A novel kernel learning method for object-oriented （00） software fault prediction is proposed in this paper. With this method, each set of classes that has inheritance relation named class hierarchy, is treated as a...A novel kernel learning method for object-oriented （00） software fault prediction is proposed in this paper. With this method, each set of classes that has inheritance relation named class hierarchy, is treated as an elemental software model. A layered kernel is introduced to handle the tree data structure corresponding to the class hierarchy models. This method was vali- dated using both an artificial dataset and a case of industrial software from the optical communication field. Preliminary experi- ments showed that our approach is very effective in learning structured data and outperforms the traditional support vector learning methods in accurately and correctly predicting the fault-prone class hierarchy model in real-life OO software.展开更多
An object-oriented approach is taken to the problem of formulating portable, easy-to-modify PDE solvers for realistic problems in three space dimensions. The resulting software library, Cogito, contains tools for writ...An object-oriented approach is taken to the problem of formulating portable, easy-to-modify PDE solvers for realistic problems in three space dimensions. The resulting software library, Cogito, contains tools for writing programs to be executed on MIMD computers with distributed memory. Difference methods on composite, structured grids are supported. Most of the Cogito classes have been implemented in Fortran 77, in such a way that the object-oriented design is visible. With respect to parallel performance, these tools yield code that is comparable to parallel solvers written in plain Fortran 77. The resulting programs are can be executed without modification on a large number of multicomputer platforms, and also on serial computers. The uppermost level of abstraction in Cogito concerns the problem of decoupling the numerical method from the PDE problem. The validity of these tools has been preliminarily demonstrated with a C++ implementation for one-dimensional problems.展开更多
Service-Oriented Architecture (SOA) is becoming the dominant approach for developing and organizing distributed enterprise-wide applications. Although the concepts of SOA have been extensively described in the literat...Service-Oriented Architecture (SOA) is becoming the dominant approach for developing and organizing distributed enterprise-wide applications. Although the concepts of SOA have been extensively described in the literature and in-dustry, the effects of adopting SOA on software quality are still unclear. The aim of the paper is to analyze how adopt-ing SOA can affect software quality as opposed to the Object-Oriented (OO) paradigm and expose the differential implications of adopting both paradigms on software quality. The paper provides a brief introduction of the architectural differences between the Service-Oriented (SO) and OO paradigms and a description of internal software quality metrics used for the comparison. The effects and differences are exposed by providing a case study architected for both paradigms. The quantitative measure concluded in the paper showed that a software system developed using SOA approach provides higher reusability and lower coupling among software modules, but at the same time higher complexity than those of the OO approach. It was also found that some of the existing OO software quality metrics are inapplicable to SOA software systems. As a consequence, new metrics need to be developed specifically to SOA software systems.展开更多
Most current object-oriented programming courses offered by domestic colleges and universities generally focus on the object-oriented programming language itself,i.e.,the programming grammar of the language,but ignore...Most current object-oriented programming courses offered by domestic colleges and universities generally focus on the object-oriented programming language itself,i.e.,the programming grammar of the language,but ignore the design pattern.However,design patterns are essential to software engineering because they can solve common problems in software design and improve code reuse,readability,extensibility,and reliability.Our Object-oriented Software Construction Course is creative since it aims at cultivating students’object-oriented thinking as well as basic abilities required to construct high-quality,object-oriented software.Specifically,we exploit the 5E teaching principle during the education of this course,and present the whole pipeline in the paper.We also provide one case of the factory pattern to further demonstrate the implementation of the 5E teaching principle in the course.The effect of the 5E teaching principle has also been demonstrated.展开更多
The increasing use of digital video everyday in a multitude of electronic devices, including mobile phones, tablets and laptops, poses the need for quick development of cross-platform video software. However current a...The increasing use of digital video everyday in a multitude of electronic devices, including mobile phones, tablets and laptops, poses the need for quick development of cross-platform video software. However current approaches to this direction usually require a long learning curve, and their development lacks standardization. This results in software components that are difficult to reuse, and hard to maintain or extend. In order to overcome such issues, we propose a novel object-oriented framework for efficient development of software systems for video analysis. It consists of a set of four abstract components, suitable for the implementation of independent plug-in modules for video acquisition, preprocessing, analysis and output handling. The extensibility of each module can be facilitated by sub-modules specifying additional functionalities. This architecture enables quick responses to changes and re-configurability;thus conforming to the requirements of agile software development practices. Considering the need for platform independency, the proposed Java Video Analysis (JVA) framework is implemented in Java. It is publicly available through the web as open-access software, supported by a growing collection of implemented modules. Its efficiency is empirically validated for the development of a representative video analysis system.展开更多
This paper uses three size metrics,which are collectable during the design phase,to analyze the potentially confounding effect of class size on the associations between object-oriented（OO）metrics and maintainability...This paper uses three size metrics,which are collectable during the design phase,to analyze the potentially confounding effect of class size on the associations between object-oriented（OO）metrics and maintainability.To draw as many general conclusions as possible,the confounding effect of class size is analyzed on 127 C＋＋ systems and 113 Java systems.For each OO metric,the indirect effect that represents the distortion of the association caused by class size and its variance for individual systems is first computed.Then,a statistical meta-analysis technique is used to compute the average indirect effect over all the systems and to determine if it is significantly different from zero.The experimental results show that the confounding effects of class size on the associations between OO metrics and maintainability generally exist,regardless of whatever size metric is used.Therefore,empirical studies validating OO metrics on maintainability should consider class size as a confounding variable.展开更多
Detecting well-known design patterns in object-oriented program source code can help maintainers understand the design of a program. Through the detection, the understandability, maintainability, and reusability of ob...Detecting well-known design patterns in object-oriented program source code can help maintainers understand the design of a program. Through the detection, the understandability, maintainability, and reusability of object-oriented programs can be improved. There are automated detection techniques;however, many existing techniques are based on static analysis and use strict conditions composed on class structure data. Hence, it is difficult for them to detect and distinguish design patterns in which the class structures are similar. Moreover, it is difficult for them to deal with diversity in design pattern applications. To solve these problems in existing techniques, we propose a design pattern detection technique using source code metrics and machine learning. Our technique judges candidates for the roles that compose design patterns by using machine learning and measurements of several metrics, and it detects design patterns by analyzing the relations between candidates. It suppresses false negatives and distinguishes patterns in which the class structures are similar. As a result of experimental evaluations with a set of programs, we confirmed that our technique is more accurate than two conventional techniques.展开更多
This paper empirically investigates the relationships between 15 design metrics and maintainability of 148 Java open source software. The results show that size and complexity metrics are strongly related to the maint...This paper empirically investigates the relationships between 15 design metrics and maintainability of 148 Java open source software. The results show that size and complexity metrics are strongly related to the maintainability of open source software. However, cohesion and coupling, as currently captured by existing metrics, do not seem to have a significant impact on maintainability. When used together, these metrics can predict system maintainability fairly accurately （mean MREs below 30%）.展开更多
Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detecti...Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detection approaches, ranging from traditional heuristic algorithms to machine learning methods, are used to identify these defects. Ensemble learning methods have strengthened the detection of these defects. However, existing approaches do not simultaneously exploit the capabilities of extracting relevant features from pre-trained models and the performance of neural networks for the classification task. Therefore, our goal has been to design a model that combines a pre-trained model to extract relevant features from code excerpts through transfer learning and a bagging method with a base estimator, a dense neural network, for defect classification. To achieve this, we composed multiple samples of the same size with replacements from the imbalanced dataset MLCQ1. For all the samples, we used the CodeT5-small variant to extract features and trained a bagging method with the neural network Roberta Classification Head to classify defects based on these features. We then compared this model to RandomForest, one of the ensemble methods that yields good results. Our experiments showed that the number of base estimators to use for bagging depends on the defect to be detected. Next, we observed that it was not necessary to use a data balancing technique with our model when the imbalance rate was 23%. Finally, for blob detection, RandomForest had a median MCC value of 0.36 compared to 0.12 for our method. However, our method was predominant in Long Method detection with a median MCC value of 0.53 compared to 0.42 for RandomForest. These results suggest that the performance of ensemble methods in detecting structural development defects is dependent on specific defects.展开更多
To better evaluate the quality of software architecture,a metrics suite is proposed to measure the coupling of software architecture models,in which CBC is used to measure the coupling between components,CBCC is used ...To better evaluate the quality of software architecture,a metrics suite is proposed to measure the coupling of software architecture models,in which CBC is used to measure the coupling between components,CBCC is used to measure the coupling of transferring message between components,CBCCT is used to measure the coupling of software architecture,WCBCC is used to measure the coupling of transferring message with weight between components,and WCBCCT is used to measure the coupling of message transmission with weight in the whole software architecture. The proposed algorithm for the coupling metrics is applied to the design of serve software architecture. Analysis of an example validates the feasibility of this metrics suite.展开更多
Architectural design is a crucial issue in software engineering. It makes testing more effective as it contribute to carry out the testing in an early stage of the software development. To improve software testability...Architectural design is a crucial issue in software engineering. It makes testing more effective as it contribute to carry out the testing in an early stage of the software development. To improve software testability, the software architect should consider different testability metrics while building the software architecture. The main objective of this research is to conduct an early assessment of the software architecture for the purpose of its improvement in order to make the testing process more effective. In this paper, an evaluation model to assess software architecture (Architecture Design Testability Evaluation Model (ADTEM)) is presented. ADTEM is based on two different testability metrics: cohesion and coupling. ADTEM consists of two phases: software architecture evaluation phase, and component evaluation phase. In each phase, a fuzzy inference system is used to perform the evaluation process based on cohesion and coupling testing metrics. The model is validated by using a case study: Elders Monitoring System. The experimental results show that ADTEM is efficient and gave a considerable improvement to the software testability process.展开更多
Software protection technology has been universally emphasized, with the development of reverse engineering and static analysis techniques. So, it is important to research how to quantitatively evaluate the security o...Software protection technology has been universally emphasized, with the development of reverse engineering and static analysis techniques. So, it is important to research how to quantitatively evaluate the security of the protected software. However, there are some researchers evaluating the security of the proposed protect techniques directly by the traditional complexity metrics, which is not suffident. In order to better reflect security from software complexity, a multi-factor complexity metric based on control flow graph （CFG） is proposed, and the corresponding calculating procedures are presented in detail. Moreover, complexity density models are constructed to indicate the strength of software resisting reverse engineering and code analysis. Instance analysis shows that the proposed method is simple and practical, and can more objectively reflect software security from the perspective of the complexity.展开更多
A desirable software engineering goal is the prediction of software module complexity (a qualitative concept) using automatically generated software metrics (quantitative measurements). This goal may be couched in the...A desirable software engineering goal is the prediction of software module complexity (a qualitative concept) using automatically generated software metrics (quantitative measurements). This goal may be couched in the language of pattern classification;namely, given a set of metrics (a pattern) for a software module, predict the class (level of complexity) to which the module belongs. To find this mapping from metrics to complexity, we present a classification strategy, stochastic metric selection, to determine the subset of software metrics that yields the greatest predictive power with respect to module complexity. We demonstrate the effectiveness of this strategy by empirically evaluating it using a publicly available dataset of metrics compiled from a medical imaging system and comparing the prediction results against several classification system benchmarks.展开更多
In this paper, we investigate empirically the relationship between object-oriented design metrics and testability of classes. We address testability from the point of view of unit testing effort. We collected data fro...In this paper, we investigate empirically the relationship between object-oriented design metrics and testability of classes. We address testability from the point of view of unit testing effort. We collected data from three open source Java software systems for which JUnit test cases exist. To capture the testing effort of classes, we used metrics to quantify the corresponding JUnit test cases. Classes were classified, according to the required unit testing effort, in two categories: high and low. In order to evaluate the relationship between object-oriented design metrics and unit testing effort of classes, we used logistic regression methods. We used the univariate logistic regression analysis to evaluate the individual effect of each metric on the unit testing effort of classes. The multivariate logistic regression analysis was used to explore the combined effect of the metrics. The performance of the prediction models was evaluated using Receiver Operating Characteristic analysis. The results indicate that: 1) complexity, size, cohesion and (to some extent) coupling were found significant predictors of the unit testing effort of classes and 2) multivariate regression models based on object-oriented design metrics are able to accurately predict the unit testing effort of classes.展开更多
Software is an important part of automotive product development, and it is commonly known that software quality assurance consumes considerable effort in safety-critical embedded software development. Increasing the e...Software is an important part of automotive product development, and it is commonly known that software quality assurance consumes considerable effort in safety-critical embedded software development. Increasing the effectiveness and efficiency of this effort thus becomes more and more important. Identifying problematic code areas which are most likely to fail and therefore require most of the quality assurance attention is required. This article presents an exploratory study investigating whether the faults detected by static analysis tools combined with code complexity metrics can be used as software quality indicators and to build pre-release fault prediction models. The combination of code complexity metrics with static analysis fault density was used to predict the pre-release fault density with an accuracy of 78.3%. This combination was also used to separate high and low quality components with a classification accuracy of 79%.展开更多
Software testing is an integral part of software development. Not only that testing exists in each software iteration cycle, but it also consumes a considerable amount of resources. While resources such as machinery a...Software testing is an integral part of software development. Not only that testing exists in each software iteration cycle, but it also consumes a considerable amount of resources. While resources such as machinery and manpower are often restricted, it is crucial to decide where and how much effort to put into testing. One way to address this problem is to identify which components of the subject under the test are more error-prone and thus demand more testing efforts. Recent development in machine learning techniques shows promising potential to predict faults in different components of a software system. This work conducts an empirical study to explore the feasibility of using static software metrics to predict software faults. We apply four machine learning techniques to construct fault prediction models from the PROMISE data set and evaluate the effectiveness of using static software metrics to build fault prediction models in four continuous versions of Apache Ant. The empirical results show that the combined software metrics generate the least misclassification errors. The fault prediction results vary significantly among different machine learning techniques and data set. Overall, fault prediction models built with the support vector machine (SVM) have the lowest misclassification errors.展开更多
In order to investigate the mechanical behavior of systems with complex architecture and a large number of contacting bodies,a finite element software,named LiToTac,has been developed by using the object-oriented prog...In order to investigate the mechanical behavior of systems with complex architecture and a large number of contacting bodies,a finite element software,named LiToTac,has been developed by using the object-oriented programming technique.This software,with an interactive graphical user interface,is able to handle highly non-linear problems including multiple contacts and large deformation.More importantly,the contact detection based on a hybrid three-stages methodology can be performed automatically,which is more efficient than the common strategies of pre-defining contact zones in commercial FEM software like ANSYS,ABAQUS,etc.In addition,the contact solver in LiToTac is portable between dynamic and quasi-static codes and can accurately solve contact coupled with friction in a reduced system.Several numerical examples are carried out to illustrate the functionality and capacity of the software package.展开更多
An essential objective of software development is to locate and fix defects ahead of schedule that could be expected under diverse circumstances. Many software development activities are performed by individuals, whic...An essential objective of software development is to locate and fix defects ahead of schedule that could be expected under diverse circumstances. Many software development activities are performed by individuals, which may lead to different software bugs over the development to occur, causing disappointments in the not-so-distant future. Thus, the prediction of software defects in the first stages has become a primary interest in the field of software engineering. Various software defect prediction (SDP) approaches that rely on software metrics have been proposed in the last two decades. Bagging, support vector machines (SVM), decision tree (DS), and random forest (RF) classifiers are known to perform well to predict defects. This paper studies and compares these supervised machine learning and ensemble classifiers on 10 NASA datasets. The experimental results showed that, in the majority of cases, RF was the best performing classifier compared to the others.展开更多
This paper addresses the challenge of estimating eventual software system size during a development project. The ap-proach is to build a family of estimation models that use information about architectural design char...This paper addresses the challenge of estimating eventual software system size during a development project. The ap-proach is to build a family of estimation models that use information about architectural design characteristics of the evolving software product as leading indicators of system size. Four models were developed to provide an increasingly accurate size estimate throughout the design process. Multivariate regression analyses were conducted using 21 Ada subsystems, totaling 183,000 lines of code. The models explain from 47% of the variation in delivered software size early in the design phase, to 89% late in the design phase.展开更多
文摘A novel kernel learning method for object-oriented （00） software fault prediction is proposed in this paper. With this method, each set of classes that has inheritance relation named class hierarchy, is treated as an elemental software model. A layered kernel is introduced to handle the tree data structure corresponding to the class hierarchy models. This method was vali- dated using both an artificial dataset and a case of industrial software from the optical communication field. Preliminary experi- ments showed that our approach is very effective in learning structured data and outperforms the traditional support vector learning methods in accurately and correctly predicting the fault-prone class hierarchy model in real-life OO software.
文摘An object-oriented approach is taken to the problem of formulating portable, easy-to-modify PDE solvers for realistic problems in three space dimensions. The resulting software library, Cogito, contains tools for writing programs to be executed on MIMD computers with distributed memory. Difference methods on composite, structured grids are supported. Most of the Cogito classes have been implemented in Fortran 77, in such a way that the object-oriented design is visible. With respect to parallel performance, these tools yield code that is comparable to parallel solvers written in plain Fortran 77. The resulting programs are can be executed without modification on a large number of multicomputer platforms, and also on serial computers. The uppermost level of abstraction in Cogito concerns the problem of decoupling the numerical method from the PDE problem. The validity of these tools has been preliminarily demonstrated with a C++ implementation for one-dimensional problems.
文摘Service-Oriented Architecture (SOA) is becoming the dominant approach for developing and organizing distributed enterprise-wide applications. Although the concepts of SOA have been extensively described in the literature and in-dustry, the effects of adopting SOA on software quality are still unclear. The aim of the paper is to analyze how adopt-ing SOA can affect software quality as opposed to the Object-Oriented (OO) paradigm and expose the differential implications of adopting both paradigms on software quality. The paper provides a brief introduction of the architectural differences between the Service-Oriented (SO) and OO paradigms and a description of internal software quality metrics used for the comparison. The effects and differences are exposed by providing a case study architected for both paradigms. The quantitative measure concluded in the paper showed that a software system developed using SOA approach provides higher reusability and lower coupling among software modules, but at the same time higher complexity than those of the OO approach. It was also found that some of the existing OO software quality metrics are inapplicable to SOA software systems. As a consequence, new metrics need to be developed specifically to SOA software systems.
基金supported by Guangdong Hardware and System Teaching and Research Office(Quality Engineeringproject No.HITSZERP22002)+2 种基金Guangdong Province Education Science Planning Project(Higher Education Project,Project No.2022GXJK431)Harbin Institute of Technology(Shenzhen)Course Ideological and Political Project(Project No.HITSZIP21003)Construction Project of Teachers College of Harbin Institute of Technology(Shenzhen)(Project No.HITSZSFXY202201)。
文摘Most current object-oriented programming courses offered by domestic colleges and universities generally focus on the object-oriented programming language itself,i.e.,the programming grammar of the language,but ignore the design pattern.However,design patterns are essential to software engineering because they can solve common problems in software design and improve code reuse,readability,extensibility,and reliability.Our Object-oriented Software Construction Course is creative since it aims at cultivating students’object-oriented thinking as well as basic abilities required to construct high-quality,object-oriented software.Specifically,we exploit the 5E teaching principle during the education of this course,and present the whole pipeline in the paper.We also provide one case of the factory pattern to further demonstrate the implementation of the 5E teaching principle in the course.The effect of the 5E teaching principle has also been demonstrated.
文摘The increasing use of digital video everyday in a multitude of electronic devices, including mobile phones, tablets and laptops, poses the need for quick development of cross-platform video software. However current approaches to this direction usually require a long learning curve, and their development lacks standardization. This results in software components that are difficult to reuse, and hard to maintain or extend. In order to overcome such issues, we propose a novel object-oriented framework for efficient development of software systems for video analysis. It consists of a set of four abstract components, suitable for the implementation of independent plug-in modules for video acquisition, preprocessing, analysis and output handling. The extensibility of each module can be facilitated by sub-modules specifying additional functionalities. This architecture enables quick responses to changes and re-configurability;thus conforming to the requirements of agile software development practices. Considering the need for platform independency, the proposed Java Video Analysis (JVA) framework is implemented in Java. It is publicly available through the web as open-access software, supported by a growing collection of implemented modules. Its efficiency is empirically validated for the development of a representative video analysis system.
基金The National Natural Science Foundation of China(No.60425206,60633010)
文摘This paper uses three size metrics,which are collectable during the design phase,to analyze the potentially confounding effect of class size on the associations between object-oriented（OO）metrics and maintainability.To draw as many general conclusions as possible,the confounding effect of class size is analyzed on 127 C＋＋ systems and 113 Java systems.For each OO metric,the indirect effect that represents the distortion of the association caused by class size and its variance for individual systems is first computed.Then,a statistical meta-analysis technique is used to compute the average indirect effect over all the systems and to determine if it is significantly different from zero.The experimental results show that the confounding effects of class size on the associations between OO metrics and maintainability generally exist,regardless of whatever size metric is used.Therefore,empirical studies validating OO metrics on maintainability should consider class size as a confounding variable.
文摘Detecting well-known design patterns in object-oriented program source code can help maintainers understand the design of a program. Through the detection, the understandability, maintainability, and reusability of object-oriented programs can be improved. There are automated detection techniques;however, many existing techniques are based on static analysis and use strict conditions composed on class structure data. Hence, it is difficult for them to detect and distinguish design patterns in which the class structures are similar. Moreover, it is difficult for them to deal with diversity in design pattern applications. To solve these problems in existing techniques, we propose a design pattern detection technique using source code metrics and machine learning. Our technique judges candidates for the roles that compose design patterns by using machine learning and measurements of several metrics, and it detects design patterns by analyzing the relations between candidates. It suppresses false negatives and distinguishes patterns in which the class structures are similar. As a result of experimental evaluations with a set of programs, we confirmed that our technique is more accurate than two conventional techniques.
基金Supported by the National Natural Science Foundation of China (60425206, 60633010)the High Technology Research Project of Jiangsu Province (BG2005032)the Specialized Research Fund for the Doctoral Program of Higher Education of China (20060286020)
文摘This paper empirically investigates the relationships between 15 design metrics and maintainability of 148 Java open source software. The results show that size and complexity metrics are strongly related to the maintainability of open source software. However, cohesion and coupling, as currently captured by existing metrics, do not seem to have a significant impact on maintainability. When used together, these metrics can predict system maintainability fairly accurately （mean MREs below 30%）.
文摘Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detection approaches, ranging from traditional heuristic algorithms to machine learning methods, are used to identify these defects. Ensemble learning methods have strengthened the detection of these defects. However, existing approaches do not simultaneously exploit the capabilities of extracting relevant features from pre-trained models and the performance of neural networks for the classification task. Therefore, our goal has been to design a model that combines a pre-trained model to extract relevant features from code excerpts through transfer learning and a bagging method with a base estimator, a dense neural network, for defect classification. To achieve this, we composed multiple samples of the same size with replacements from the imbalanced dataset MLCQ1. For all the samples, we used the CodeT5-small variant to extract features and trained a bagging method with the neural network Roberta Classification Head to classify defects based on these features. We then compared this model to RandomForest, one of the ensemble methods that yields good results. Our experiments showed that the number of base estimators to use for bagging depends on the defect to be detected. Next, we observed that it was not necessary to use a data balancing technique with our model when the imbalance rate was 23%. Finally, for blob detection, RandomForest had a median MCC value of 0.36 compared to 0.12 for our method. However, our method was predominant in Long Method detection with a median MCC value of 0.53 compared to 0.42 for RandomForest. These results suggest that the performance of ensemble methods in detecting structural development defects is dependent on specific defects.
基金Sponsored by the Science and Technology Department Term of Education of Heilongjiang Province(Grant No. 10541098)
文摘To better evaluate the quality of software architecture,a metrics suite is proposed to measure the coupling of software architecture models,in which CBC is used to measure the coupling between components,CBCC is used to measure the coupling of transferring message between components,CBCCT is used to measure the coupling of software architecture,WCBCC is used to measure the coupling of transferring message with weight between components,and WCBCCT is used to measure the coupling of message transmission with weight in the whole software architecture. The proposed algorithm for the coupling metrics is applied to the design of serve software architecture. Analysis of an example validates the feasibility of this metrics suite.
文摘Architectural design is a crucial issue in software engineering. It makes testing more effective as it contribute to carry out the testing in an early stage of the software development. To improve software testability, the software architect should consider different testability metrics while building the software architecture. The main objective of this research is to conduct an early assessment of the software architecture for the purpose of its improvement in order to make the testing process more effective. In this paper, an evaluation model to assess software architecture (Architecture Design Testability Evaluation Model (ADTEM)) is presented. ADTEM is based on two different testability metrics: cohesion and coupling. ADTEM consists of two phases: software architecture evaluation phase, and component evaluation phase. In each phase, a fuzzy inference system is used to perform the evaluation process based on cohesion and coupling testing metrics. The model is validated by using a case study: Elders Monitoring System. The experimental results show that ADTEM is efficient and gave a considerable improvement to the software testability process.
基金Key Project of the National Eleventh-Five Year Research Program of China(No.2006BAD10A07)
文摘Software protection technology has been universally emphasized, with the development of reverse engineering and static analysis techniques. So, it is important to research how to quantitatively evaluate the security of the protected software. However, there are some researchers evaluating the security of the proposed protect techniques directly by the traditional complexity metrics, which is not suffident. In order to better reflect security from software complexity, a multi-factor complexity metric based on control flow graph （CFG） is proposed, and the corresponding calculating procedures are presented in detail. Moreover, complexity density models are constructed to indicate the strength of software resisting reverse engineering and code analysis. Instance analysis shows that the proposed method is simple and practical, and can more objectively reflect software security from the perspective of the complexity.
文摘A desirable software engineering goal is the prediction of software module complexity (a qualitative concept) using automatically generated software metrics (quantitative measurements). This goal may be couched in the language of pattern classification;namely, given a set of metrics (a pattern) for a software module, predict the class (level of complexity) to which the module belongs. To find this mapping from metrics to complexity, we present a classification strategy, stochastic metric selection, to determine the subset of software metrics that yields the greatest predictive power with respect to module complexity. We demonstrate the effectiveness of this strategy by empirically evaluating it using a publicly available dataset of metrics compiled from a medical imaging system and comparing the prediction results against several classification system benchmarks.
文摘In this paper, we investigate empirically the relationship between object-oriented design metrics and testability of classes. We address testability from the point of view of unit testing effort. We collected data from three open source Java software systems for which JUnit test cases exist. To capture the testing effort of classes, we used metrics to quantify the corresponding JUnit test cases. Classes were classified, according to the required unit testing effort, in two categories: high and low. In order to evaluate the relationship between object-oriented design metrics and unit testing effort of classes, we used logistic regression methods. We used the univariate logistic regression analysis to evaluate the individual effect of each metric on the unit testing effort of classes. The multivariate logistic regression analysis was used to explore the combined effect of the metrics. The performance of the prediction models was evaluated using Receiver Operating Characteristic analysis. The results indicate that: 1) complexity, size, cohesion and (to some extent) coupling were found significant predictors of the unit testing effort of classes and 2) multivariate regression models based on object-oriented design metrics are able to accurately predict the unit testing effort of classes.
文摘Software is an important part of automotive product development, and it is commonly known that software quality assurance consumes considerable effort in safety-critical embedded software development. Increasing the effectiveness and efficiency of this effort thus becomes more and more important. Identifying problematic code areas which are most likely to fail and therefore require most of the quality assurance attention is required. This article presents an exploratory study investigating whether the faults detected by static analysis tools combined with code complexity metrics can be used as software quality indicators and to build pre-release fault prediction models. The combination of code complexity metrics with static analysis fault density was used to predict the pre-release fault density with an accuracy of 78.3%. This combination was also used to separate high and low quality components with a classification accuracy of 79%.
文摘Software testing is an integral part of software development. Not only that testing exists in each software iteration cycle, but it also consumes a considerable amount of resources. While resources such as machinery and manpower are often restricted, it is crucial to decide where and how much effort to put into testing. One way to address this problem is to identify which components of the subject under the test are more error-prone and thus demand more testing efforts. Recent development in machine learning techniques shows promising potential to predict faults in different components of a software system. This work conducts an empirical study to explore the feasibility of using static software metrics to predict software faults. We apply four machine learning techniques to construct fault prediction models from the PROMISE data set and evaluate the effectiveness of using static software metrics to build fault prediction models in four continuous versions of Apache Ant. The empirical results show that the combined software metrics generate the least misclassification errors. The fault prediction results vary significantly among different machine learning techniques and data set. Overall, fault prediction models built with the support vector machine (SVM) have the lowest misclassification errors.
基金We gratefully acknowledge the financial support of the National Key R&D Program of China(Grant No.2017YFB0703200)the National Natural Science Foundation of China(Grant No.11772274).
文摘In order to investigate the mechanical behavior of systems with complex architecture and a large number of contacting bodies,a finite element software,named LiToTac,has been developed by using the object-oriented programming technique.This software,with an interactive graphical user interface,is able to handle highly non-linear problems including multiple contacts and large deformation.More importantly,the contact detection based on a hybrid three-stages methodology can be performed automatically,which is more efficient than the common strategies of pre-defining contact zones in commercial FEM software like ANSYS,ABAQUS,etc.In addition,the contact solver in LiToTac is portable between dynamic and quasi-static codes and can accurately solve contact coupled with friction in a reduced system.Several numerical examples are carried out to illustrate the functionality and capacity of the software package.
文摘An essential objective of software development is to locate and fix defects ahead of schedule that could be expected under diverse circumstances. Many software development activities are performed by individuals, which may lead to different software bugs over the development to occur, causing disappointments in the not-so-distant future. Thus, the prediction of software defects in the first stages has become a primary interest in the field of software engineering. Various software defect prediction (SDP) approaches that rely on software metrics have been proposed in the last two decades. Bagging, support vector machines (SVM), decision tree (DS), and random forest (RF) classifiers are known to perform well to predict defects. This paper studies and compares these supervised machine learning and ensemble classifiers on 10 NASA datasets. The experimental results showed that, in the majority of cases, RF was the best performing classifier compared to the others.
文摘This paper addresses the challenge of estimating eventual software system size during a development project. The ap-proach is to build a family of estimation models that use information about architectural design characteristics of the evolving software product as leading indicators of system size. Four models were developed to provide an increasingly accurate size estimate throughout the design process. Multivariate regression analyses were conducted using 21 Ada subsystems, totaling 183,000 lines of code. The models explain from 47% of the variation in delivered software size early in the design phase, to 89% late in the design phase.
