In this paper we investigate the effectiveness of ensemble-based learners for web robot session identification from web server logs. We also perform multi fold robot session labeling to improve the performance of lear...In this paper we investigate the effectiveness of ensemble-based learners for web robot session identification from web server logs. We also perform multi fold robot session labeling to improve the performance of learner. We conduct a comparative study for various ensemble methods (Bagging, Boosting, and Voting) with simple classifiers in perspective of classification. We also evaluate the effectiveness of these classifiers (both ensemble and simple) on five different data sets of varying session length. Presently the results of web server log analyzers are not very much reliable because the input log files are highly inflated by sessions of automated web traverse software’s, known as web robots. Presence of web robots access traffic entries in web server log repositories imposes a great challenge to extract any actionable and usable knowledge about browsing behavior of actual visitors. So web robots sessions need accurate and fast detection from web server log repositories to extract knowledge about genuine visitors and to produce correct results of log analyzers.展开更多
Motivated by recent results in multiple description image coding over wireless networks, we propose a scheme for transmission of multiple descriptions through hybrid packet loss and additive white Gaussian noise chann...Motivated by recent results in multiple description image coding over wireless networks, we propose a scheme for transmission of multiple descriptions through hybrid packet loss and additive white Gaussian noise channel. Each description is coded into multiple bitstreams by applying SPIHT coding on wavelet trees along spatial orientations and each stream is further compressed using arithmetic code. Use of error resilient entropy coding (EREC) is proposed in literature for synchronization requirement of variable length codes, but EREC is not compatible with iterative soft-in soft-out decoding of arithmetic code at the receiver. We propose the application of EREC assisted by state and tail bits (ERECST) in conjunction with iterative decoding of arithmetic code at receiver for reconstructing the multiple description coded image over packet loss and Gaussian noise channel. Experimental results demonstrate that an additional gain of 7 dB in PSNR is obtained over existing scheme.展开更多
In this paper a team member ranking technique is presented for software bug repositories. Member ranking is performed using numbers of attributes available in software bug repositories, and a ranked list of developers...In this paper a team member ranking technique is presented for software bug repositories. Member ranking is performed using numbers of attributes available in software bug repositories, and a ranked list of developers is generated who are participating in development of software project. This ranking is generated from the contribution made by the individual developers in terms of bugs fixed, severity and priority of bugs, reporting newer problems and comments made by the developers. The top ranked developers are the best contributors for the software projects. The proposed algorithm can also be used for classifying and rating the software bugs using the ratings of members participating in the software bug repository.展开更多
In this paper, a multi label variant of CLUBAS [1] algorithm, ML-CLUBAS (Multi Label-Classification of software Bugs Using Bug Attribute Similarity) is presented. CLUBAS is a hybrid algorithm, and is designed by using...In this paper, a multi label variant of CLUBAS [1] algorithm, ML-CLUBAS (Multi Label-Classification of software Bugs Using Bug Attribute Similarity) is presented. CLUBAS is a hybrid algorithm, and is designed by using text clustering, frequent term calculations and taxonomic terms mapping techniques, and is an example of classification using clustering technique. CLUBAS is a single label algorithm, where one bug cluster is exactly mapped to a single bug category. However a bug cluster can be mapped into the more than one bug category in case of cluster label matches with the more than one category term, for this purpose ML-CLUBAS a multi label variant of CLUBAS is presented in this work. The designed algorithm is evaluated using the performance parameters F-measures and accuracy, number of clusters and purity. These parameters are compared with the CLUBAS and other multi label text clustering algorithms.展开更多
In this paper, a software bug classification algorithm, CLUBAS (Classification of Software Bugs Using Bug Attribute Similarity) is presented. CLUBAS is a hybrid algorithm, and is designed by using text clustering, fre...In this paper, a software bug classification algorithm, CLUBAS (Classification of Software Bugs Using Bug Attribute Similarity) is presented. CLUBAS is a hybrid algorithm, and is designed by using text clustering, frequent term calculations and taxonomic terms mapping techniques. The algorithm CLUBAS is an example of classification using clustering technique. The proposed algorithm works in three major steps, in the first step text clusters are created using software bug textual attributes data and followed by the second step in which cluster labels are generated using label induction for each cluster, and in the third step, the cluster labels are mapped against the bug taxonomic terms to identify the appropriate categories of the bug clusters. The cluster labels are generated using frequent and meaningful terms present in the bug attributes, for the bugs belonging to the bug clusters. The designed algorithm is evaluated using the performance parameters F-measures and accuracy. These parameters are compared with the standard classification techniques like Na?ve Bayes, Naive Bayes Multinomial, J48, Support Vector Machine and Weka’s classification using clustering algorithms. A GUI (Graphical User Interface) based tool is also developed in java for the implementation of CLUBAS algorithm.展开更多
文摘In this paper we investigate the effectiveness of ensemble-based learners for web robot session identification from web server logs. We also perform multi fold robot session labeling to improve the performance of learner. We conduct a comparative study for various ensemble methods (Bagging, Boosting, and Voting) with simple classifiers in perspective of classification. We also evaluate the effectiveness of these classifiers (both ensemble and simple) on five different data sets of varying session length. Presently the results of web server log analyzers are not very much reliable because the input log files are highly inflated by sessions of automated web traverse software’s, known as web robots. Presence of web robots access traffic entries in web server log repositories imposes a great challenge to extract any actionable and usable knowledge about browsing behavior of actual visitors. So web robots sessions need accurate and fast detection from web server log repositories to extract knowledge about genuine visitors and to produce correct results of log analyzers.
文摘Motivated by recent results in multiple description image coding over wireless networks, we propose a scheme for transmission of multiple descriptions through hybrid packet loss and additive white Gaussian noise channel. Each description is coded into multiple bitstreams by applying SPIHT coding on wavelet trees along spatial orientations and each stream is further compressed using arithmetic code. Use of error resilient entropy coding (EREC) is proposed in literature for synchronization requirement of variable length codes, but EREC is not compatible with iterative soft-in soft-out decoding of arithmetic code at the receiver. We propose the application of EREC assisted by state and tail bits (ERECST) in conjunction with iterative decoding of arithmetic code at receiver for reconstructing the multiple description coded image over packet loss and Gaussian noise channel. Experimental results demonstrate that an additional gain of 7 dB in PSNR is obtained over existing scheme.
文摘In this paper a team member ranking technique is presented for software bug repositories. Member ranking is performed using numbers of attributes available in software bug repositories, and a ranked list of developers is generated who are participating in development of software project. This ranking is generated from the contribution made by the individual developers in terms of bugs fixed, severity and priority of bugs, reporting newer problems and comments made by the developers. The top ranked developers are the best contributors for the software projects. The proposed algorithm can also be used for classifying and rating the software bugs using the ratings of members participating in the software bug repository.
文摘In this paper, a multi label variant of CLUBAS [1] algorithm, ML-CLUBAS (Multi Label-Classification of software Bugs Using Bug Attribute Similarity) is presented. CLUBAS is a hybrid algorithm, and is designed by using text clustering, frequent term calculations and taxonomic terms mapping techniques, and is an example of classification using clustering technique. CLUBAS is a single label algorithm, where one bug cluster is exactly mapped to a single bug category. However a bug cluster can be mapped into the more than one bug category in case of cluster label matches with the more than one category term, for this purpose ML-CLUBAS a multi label variant of CLUBAS is presented in this work. The designed algorithm is evaluated using the performance parameters F-measures and accuracy, number of clusters and purity. These parameters are compared with the CLUBAS and other multi label text clustering algorithms.
文摘In this paper, a software bug classification algorithm, CLUBAS (Classification of Software Bugs Using Bug Attribute Similarity) is presented. CLUBAS is a hybrid algorithm, and is designed by using text clustering, frequent term calculations and taxonomic terms mapping techniques. The algorithm CLUBAS is an example of classification using clustering technique. The proposed algorithm works in three major steps, in the first step text clusters are created using software bug textual attributes data and followed by the second step in which cluster labels are generated using label induction for each cluster, and in the third step, the cluster labels are mapped against the bug taxonomic terms to identify the appropriate categories of the bug clusters. The cluster labels are generated using frequent and meaningful terms present in the bug attributes, for the bugs belonging to the bug clusters. The designed algorithm is evaluated using the performance parameters F-measures and accuracy. These parameters are compared with the standard classification techniques like Na?ve Bayes, Naive Bayes Multinomial, J48, Support Vector Machine and Weka’s classification using clustering algorithms. A GUI (Graphical User Interface) based tool is also developed in java for the implementation of CLUBAS algorithm.
