Multi-objective optimization has many important applications and becomes a challenging issue in applied science. In typical multi-objective optimization algorithms, such as Indicator-based Evolutionary Algorithm(IBEA)...Multi-objective optimization has many important applications and becomes a challenging issue in applied science. In typical multi-objective optimization algorithms, such as Indicator-based Evolutionary Algorithm(IBEA), all of parents and offspring need to be evaluated in every generation, and then the better solutions of them are selected as the next generation candidates. This leads to a large amount of calculation and slows down convergence rate for IBEA related applications. Our discovery is that the evaluation of evolutionary algorithm is a binary classi?cation in nature and a meaningful preselection method will accelerate the convergence rate. Therefore this paper presents a novel preselection approach to improve the performance of the IBEA, in which a SVM(Support Vector Machine) classi?er is adopted to sort the promising solutions from unpromising solutions and then the newly generated solutions are conversely added as train sample to increase the accuracy of the classi?er. Firstly, we proposed an online and asynchronous training method for SVM model with empirical kernel. The initial population is randomly generated among population size, which is used as initial training. In the process of training, SVM classi?er is modi?ed and perfected to adapt to the evolutionary algorithm sample. Secondly, the classi?er divides all the new generated solutions from the whole solution spaces into promising solutions and unpromising ones. And only the promising ones are forwarded for evaluation. In this way, the evaluation time can be greatly reduced and the solution quality can be obviously improved. Thirdly, the promising and unpromising solutions are labeled as new train samples in next generation to re?ne classi?er model. A number of experiments on benchmark functions validates the proposed approach. The results show that IBEA-SVM can signi?cantly outperform previous works.展开更多
Technical debt(TD)happens when project teams carry out technical decisions in favor of a short-term goal(s)in their projects,whether deliberately or unknowingly.TD must be properly managed to guarantee that its negati...Technical debt(TD)happens when project teams carry out technical decisions in favor of a short-term goal(s)in their projects,whether deliberately or unknowingly.TD must be properly managed to guarantee that its negative implications do not outweigh its advantages.A lot of research has been conducted to show that TD has evolved into a common problem with considerable financial burden.Test technical debt is the technical debt aspect of testing(or test debt).Test debt is a relatively new concept that has piqued the curiosity of the software industry in recent years.In this article,we assume that the organization selects the testing artifacts at the start of every sprint.Implementing the latest features in consideration of expected business value and repaying technical debt are among candidate tasks in terms of the testing process(test cases increments).To gain the maximum benefit for the organization in terms of software testing optimization,there is a need to select the artifacts(i.e.,test cases)with maximum feature coverage within the available resources.The management of testing optimization for large projects is complicated and can also be treated as a multi-objective problem that entails a trade-off between the agile software’s short-term and long-term value.In this article,we implement a multi-objective indicatorbased evolutionary algorithm(IBEA)for fixing such optimization issues.The capability of the algorithm is evidenced by adding it to a real case study of a university registration process.展开更多
IbeA is an important invasion determinant contributing to Escherichia coli K1 entry into brain microvascular endothelial cells (BMEC) that is a key step in the pathogenesis of E. coli meningitis. Our previous studies ...IbeA is an important invasion determinant contributing to Escherichia coli K1 entry into brain microvascular endothelial cells (BMEC) that is a key step in the pathogenesis of E. coli meningitis. Our previous studies have shown that IbeA-induced signaling and E. coli K1 invasion is mediated by two IbeA-binding proteins, vimentin, which is constitutively present in the surface of human BMECs (HBMECs), and PSF, which is inducibly expressed in both mesenchymal (endothelium) and non-mesenchymal (epithelium) cells. However, it is unknown whether p54nrb, a PSF partner protein, could contribute to the pathogenesis of E. coli K1 meningitis. Here, we reported that a 54-kDa protein was identified by copurification with PSF through IbeA-affinity chromatography as an IbeA-binding protein, which is identical to p54nrb. Both p54nrb and PSF are RNA-binding proteins and share significant sequence homology. The specific interaction between IbeA and p54nrb was confirmed by Western blot and ligand overlay assays. Recombinant p54nrb blocked E. coli K1 invasion of human BMEC very effectively. Overexpressed p54nrb as a GFP fusion protein in the transfected 293T cells significantly enhanced E. coli K1 invasion. Furthermore, higher levels of surface p54nrb in the transfected 293T cells were detected by flow cytometry. These results suggest that the IbeA invasion protein of E. coli K1 interacts with p54nrb for bacterial invasion of human BMEC.展开更多
基金Supported by the National Science Foundation of China(Grant No.61472289)Hubei Province Science Foundation(Grant No.2015CFB254)
文摘Multi-objective optimization has many important applications and becomes a challenging issue in applied science. In typical multi-objective optimization algorithms, such as Indicator-based Evolutionary Algorithm(IBEA), all of parents and offspring need to be evaluated in every generation, and then the better solutions of them are selected as the next generation candidates. This leads to a large amount of calculation and slows down convergence rate for IBEA related applications. Our discovery is that the evaluation of evolutionary algorithm is a binary classi?cation in nature and a meaningful preselection method will accelerate the convergence rate. Therefore this paper presents a novel preselection approach to improve the performance of the IBEA, in which a SVM(Support Vector Machine) classi?er is adopted to sort the promising solutions from unpromising solutions and then the newly generated solutions are conversely added as train sample to increase the accuracy of the classi?er. Firstly, we proposed an online and asynchronous training method for SVM model with empirical kernel. The initial population is randomly generated among population size, which is used as initial training. In the process of training, SVM classi?er is modi?ed and perfected to adapt to the evolutionary algorithm sample. Secondly, the classi?er divides all the new generated solutions from the whole solution spaces into promising solutions and unpromising ones. And only the promising ones are forwarded for evaluation. In this way, the evaluation time can be greatly reduced and the solution quality can be obviously improved. Thirdly, the promising and unpromising solutions are labeled as new train samples in next generation to re?ne classi?er model. A number of experiments on benchmark functions validates the proposed approach. The results show that IBEA-SVM can signi?cantly outperform previous works.
基金The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:(22UQUyouracademicnumberDSRxx).
文摘Technical debt(TD)happens when project teams carry out technical decisions in favor of a short-term goal(s)in their projects,whether deliberately or unknowingly.TD must be properly managed to guarantee that its negative implications do not outweigh its advantages.A lot of research has been conducted to show that TD has evolved into a common problem with considerable financial burden.Test technical debt is the technical debt aspect of testing(or test debt).Test debt is a relatively new concept that has piqued the curiosity of the software industry in recent years.In this article,we assume that the organization selects the testing artifacts at the start of every sprint.Implementing the latest features in consideration of expected business value and repaying technical debt are among candidate tasks in terms of the testing process(test cases increments).To gain the maximum benefit for the organization in terms of software testing optimization,there is a need to select the artifacts(i.e.,test cases)with maximum feature coverage within the available resources.The management of testing optimization for large projects is complicated and can also be treated as a multi-objective problem that entails a trade-off between the agile software’s short-term and long-term value.In this article,we implement a multi-objective indicatorbased evolutionary algorithm(IBEA)for fixing such optimization issues.The capability of the algorithm is evidenced by adding it to a real case study of a university registration process.
文摘IbeA is an important invasion determinant contributing to Escherichia coli K1 entry into brain microvascular endothelial cells (BMEC) that is a key step in the pathogenesis of E. coli meningitis. Our previous studies have shown that IbeA-induced signaling and E. coli K1 invasion is mediated by two IbeA-binding proteins, vimentin, which is constitutively present in the surface of human BMECs (HBMECs), and PSF, which is inducibly expressed in both mesenchymal (endothelium) and non-mesenchymal (epithelium) cells. However, it is unknown whether p54nrb, a PSF partner protein, could contribute to the pathogenesis of E. coli K1 meningitis. Here, we reported that a 54-kDa protein was identified by copurification with PSF through IbeA-affinity chromatography as an IbeA-binding protein, which is identical to p54nrb. Both p54nrb and PSF are RNA-binding proteins and share significant sequence homology. The specific interaction between IbeA and p54nrb was confirmed by Western blot and ligand overlay assays. Recombinant p54nrb blocked E. coli K1 invasion of human BMEC very effectively. Overexpressed p54nrb as a GFP fusion protein in the transfected 293T cells significantly enhanced E. coli K1 invasion. Furthermore, higher levels of surface p54nrb in the transfected 293T cells were detected by flow cytometry. These results suggest that the IbeA invasion protein of E. coli K1 interacts with p54nrb for bacterial invasion of human BMEC.
