Due to the exploding growth in the number of web services, mashup has emerged as a service composition technique to reuse existing services and create new applications with the least amount of effort. Service recommen...Due to the exploding growth in the number of web services, mashup has emerged as a service composition technique to reuse existing services and create new applications with the least amount of effort. Service recommendation is essential to facilitate mashup developers locating desired component services among a large collection of candidates. However, the majority of existing methods utilize service profiles for content matching, not mashup descriptions. This makes them suffer from vocabulary gap and cold-start problem when recommending components for new mashups. In this paper, we propose a two-step approach to generate high-quality service representation from mashup descriptions. The first step employs a linear discriminant function to assign each term with a component service such that a coarse-grained service representation can be derived. In the second step, a novel probabilistic topic model is proposed to extract relevant terms from coarse-grained service representation. Finally, a score function is designed based on the final high-quality representation to determine recommendations. Experiments on a data set from ProgrammableWeb.com show that the proposed model significantly outperforms state-of-the-art methods.展开更多
An increasing number of web services are being invoked by users to create user applications(e.g.,mashups). However, over time, a few good services in service systems have become deprecated, i.e., the service is init...An increasing number of web services are being invoked by users to create user applications(e.g.,mashups). However, over time, a few good services in service systems have become deprecated, i.e., the service is initially available and is invoked by service users, but later becomes unavailable. Therefore, the prediction of service deprecation has become a key issue in creating reliable long-term user applications. Most existing research has overlooked service deprecation in service systems and has failed to consider long-term service reliability when making service recommendations. In this paper, we propose a method for predicting service deprecation, which comprises two components: Service Comprehensive Feature Modeling(SCFM) for extracting service features relevant to service deprecation and Deprecated Service Prediction(DSP) for building a service deprecation prediction model. Our experimental results on a real-world dataset demonstrate that our method yields an improved Area-Under-the-Curve(AUC) value over existing methods and thus has better accuracy in service deprecation prediction.展开更多
In recent years,scholars have made many research results on job-shop scheduling(JSP)problem,especially in single objective such as the maximum completion time.But most of the actual system scheduling problems are more...In recent years,scholars have made many research results on job-shop scheduling(JSP)problem,especially in single objective such as the maximum completion time.But most of the actual system scheduling problems are more than one object.Therefore,the research of multi-objective scheduling problem is very important and meaningful.In this paper,we proposed a multi-objective scheduling model which adopts weighted sum method to optimize two important indexes(makespan and total flow time).Genetic algorithm(GA)has diversified global search ability,while simulated annealing(SA)combined with tabu search(TS)have intensified capabilities in local neighborhood search.To overcome the drawback of the GA,we proposed a new hybrid GA(NewHGA)which produces initial solutions by GA firstly,and then take SA operator incorporate TS operator to search in the local space.By adding the novel local search strategy,the diversity of solutions will be improved greatly so that it can ensure the algorithm jump out of the local optimal value.We test this algorithm using the benchmark instances of different sizes taken from the OR-Library,and the results show that the algorithm is efficient than another hybrid algorithm.展开更多
基金supported in part by the National Natural Science Foundation of China(No.61673230)
文摘Due to the exploding growth in the number of web services, mashup has emerged as a service composition technique to reuse existing services and create new applications with the least amount of effort. Service recommendation is essential to facilitate mashup developers locating desired component services among a large collection of candidates. However, the majority of existing methods utilize service profiles for content matching, not mashup descriptions. This makes them suffer from vocabulary gap and cold-start problem when recommending components for new mashups. In this paper, we propose a two-step approach to generate high-quality service representation from mashup descriptions. The first step employs a linear discriminant function to assign each term with a component service such that a coarse-grained service representation can be derived. In the second step, a novel probabilistic topic model is proposed to extract relevant terms from coarse-grained service representation. Finally, a score function is designed based on the final high-quality representation to determine recommendations. Experiments on a data set from ProgrammableWeb.com show that the proposed model significantly outperforms state-of-the-art methods.
文摘An increasing number of web services are being invoked by users to create user applications(e.g.,mashups). However, over time, a few good services in service systems have become deprecated, i.e., the service is initially available and is invoked by service users, but later becomes unavailable. Therefore, the prediction of service deprecation has become a key issue in creating reliable long-term user applications. Most existing research has overlooked service deprecation in service systems and has failed to consider long-term service reliability when making service recommendations. In this paper, we propose a method for predicting service deprecation, which comprises two components: Service Comprehensive Feature Modeling(SCFM) for extracting service features relevant to service deprecation and Deprecated Service Prediction(DSP) for building a service deprecation prediction model. Our experimental results on a real-world dataset demonstrate that our method yields an improved Area-Under-the-Curve(AUC) value over existing methods and thus has better accuracy in service deprecation prediction.
基金support of the National Science and Technology Supporting Plan of China(No.2013BAF02B09)for the work done in this paper.
文摘In recent years,scholars have made many research results on job-shop scheduling(JSP)problem,especially in single objective such as the maximum completion time.But most of the actual system scheduling problems are more than one object.Therefore,the research of multi-objective scheduling problem is very important and meaningful.In this paper,we proposed a multi-objective scheduling model which adopts weighted sum method to optimize two important indexes(makespan and total flow time).Genetic algorithm(GA)has diversified global search ability,while simulated annealing(SA)combined with tabu search(TS)have intensified capabilities in local neighborhood search.To overcome the drawback of the GA,we proposed a new hybrid GA(NewHGA)which produces initial solutions by GA firstly,and then take SA operator incorporate TS operator to search in the local space.By adding the novel local search strategy,the diversity of solutions will be improved greatly so that it can ensure the algorithm jump out of the local optimal value.We test this algorithm using the benchmark instances of different sizes taken from the OR-Library,and the results show that the algorithm is efficient than another hybrid algorithm.