“…The following two methods resorting to clustering technique are similar to that of Reference 15. Gao et al 12 presented in Reference 16 a manifold ranking approach for API recommendation via categorizing existing apps into functionally similar clusters by means of in‐depth analysis about the important semantic information between apps and APIs, which results in that the problem of long‐tail API recommendation is alleviated to a great extent. Rahman et al 13 proposed a novel Matrix Factorization‐based APIs recommendation approach using a two‐level topic model for clustering mashup services to produce better performance in terms of accuracy and diversity.…”
Section: Related Workmentioning
confidence: 99%
“…Furthermore, out of consideration that a set of services with complementary functions rather than a set of ones with similar services is more attractive to developers in the procedure of mashup creation, the complex or latent semantic relationship among web APIs can be mined in Reference 6 through analyzing discourse of underlying mashups' functional specifications. Subsequently, the authors in Reference 20 formulized the service set recommendation as multiobjective search problem and employ the nondominated sorting genetic algorithm (NSGA‐II), a meta‐heuristic search, to extract an optimal and functionality‐diverse set of services with three optimization objectives to create a desired application 16 …”
Summary
With the ever‐increasing popularity of web application programming interfaces (APIs) sharing communities, it is becoming a promising way for software developers to design and create their interesting Apps through composing a set of selected web APIs that can collectively fulfill the App functions expected by the App developer. However, the App developer's web APIs selection decision‐makings are often nontrivial due to the massive candidate APIs as well as their diverse functions. Furthermore, it is difficult to guarantee that the selected web APIs are compatible enough. Moreover, traditional web APIs recommendation approaches only return a recommended APIs list, which are often not sufficient to accommodate the App developer's undetermined and fuzzy personalized preferences. Considering the above challenges, a novel keywords‐driven web APIs recommendation approach called keywords‐driven and compatibility‐aware multiple API group recommendation is proposed in this article for green and compatible software, which cannot only satisfy the App developer's functional requirements, but also return a group of web APIs recommended lists. Each returned list includes a set of compatible web APIs. Finally, we design a series of experiments based on a real‐world web APIs dataset, that is, PW dataset crawled from www.programmableWeb.com. Experimental reports compared with other competitive approaches in existing literatures indicate the effectiveness and efficiency of our proposal in this work.
“…The following two methods resorting to clustering technique are similar to that of Reference 15. Gao et al 12 presented in Reference 16 a manifold ranking approach for API recommendation via categorizing existing apps into functionally similar clusters by means of in‐depth analysis about the important semantic information between apps and APIs, which results in that the problem of long‐tail API recommendation is alleviated to a great extent. Rahman et al 13 proposed a novel Matrix Factorization‐based APIs recommendation approach using a two‐level topic model for clustering mashup services to produce better performance in terms of accuracy and diversity.…”
Section: Related Workmentioning
confidence: 99%
“…Furthermore, out of consideration that a set of services with complementary functions rather than a set of ones with similar services is more attractive to developers in the procedure of mashup creation, the complex or latent semantic relationship among web APIs can be mined in Reference 6 through analyzing discourse of underlying mashups' functional specifications. Subsequently, the authors in Reference 20 formulized the service set recommendation as multiobjective search problem and employ the nondominated sorting genetic algorithm (NSGA‐II), a meta‐heuristic search, to extract an optimal and functionality‐diverse set of services with three optimization objectives to create a desired application 16 …”
Summary
With the ever‐increasing popularity of web application programming interfaces (APIs) sharing communities, it is becoming a promising way for software developers to design and create their interesting Apps through composing a set of selected web APIs that can collectively fulfill the App functions expected by the App developer. However, the App developer's web APIs selection decision‐makings are often nontrivial due to the massive candidate APIs as well as their diverse functions. Furthermore, it is difficult to guarantee that the selected web APIs are compatible enough. Moreover, traditional web APIs recommendation approaches only return a recommended APIs list, which are often not sufficient to accommodate the App developer's undetermined and fuzzy personalized preferences. Considering the above challenges, a novel keywords‐driven web APIs recommendation approach called keywords‐driven and compatibility‐aware multiple API group recommendation is proposed in this article for green and compatible software, which cannot only satisfy the App developer's functional requirements, but also return a group of web APIs recommended lists. Each returned list includes a set of compatible web APIs. Finally, we design a series of experiments based on a real‐world web APIs dataset, that is, PW dataset crawled from www.programmableWeb.com. Experimental reports compared with other competitive approaches in existing literatures indicate the effectiveness and efficiency of our proposal in this work.
“…Web Mashups are Web applications developed using the contents and services available online [1]. Compared with traditional "developer-centric" composition technologies, such as BPEI and WSCI, Mashup provides a flexible and easy-of-use way for service composition on Web [2].…”
When service business is in evolution from B2B to B2C model, a coldstart problem raises for service composition due to the completely new clients with no historical records. Therefore, it is of great importance to solve the cold-start problem brought by completely new users. In this paper, we propose a recommendation framework for completely new users in Mashup creation based on deeplearning technology. Firstly, this framework extracts the mapping relationship between Mashup description and APIs offline by the deep neural network. Then, when the completely new users have the Mashup demands online, the matching APIs are recommended for them by using the mapping relationship. The experimental results with real-world datasets show that our proposed model outperforms the state-of-the-art ones in term of both accuracy and recall rate. The accuracy of the proposed method is 1.34 times higher than that of the state-of-the-art methods, and the recall rate is 1.55 times higher than that of the state-of-the-art methods. Moreover, considering that the new user history invocational data is very sparse, the performance of the proposed method can be greatly improved on the denser dataset.
“…In the field of cloud services, work [4] proposed a distributed cloud service method based on distributed sensitive hashing in multisource data. Work [5] proposed a big data-driven mashup building method that supports economic software developments. In the field of the Internet of Things, work [6] proposed a multidimensional data processing and query method, work [7] studied IoT offloading utilities that support edge computing.…”
Data mining technology has been applied in many fields. Prototype-based cluster analysis is an important data mining method, but its ability to discover knowledge is limited because of the need to know the number of target data categories and cluster prototypes in advance. Artificial immune evolutionary network clustering is a clustering method based on network structure. Compared with prototype-based cluster analysis, it has the advantage of realizing unsupervised learning and clustering without any prior knowledge of data. However, artificial immune evolutionary network clustering also has problems such as a lack of guidance in the clustering process, fuzzy boundary sensitivity, and difficulty in determining parameters. To solve these problems, an artificial immune network clustering algorithm based on a cultural algorithm is proposed. First, three kinds of knowledge are constructed: normative knowledge is used to regulate the spatial range of population initialization to avoid blindness; state knowledge is used to distinguish the type of antigen, and immune defense measures are taken to prevent the network structure caused by noise and boundaries from being unclear; topology knowledge is used to guide the antigen for optimal antibody search. Second, topology knowledge in the cultural algorithm is used to characterize the distribution of antigens and antibodies in space, and elite learning is used to improve the traditional clone mutation operator. Based on the shadow set theory, a method for adaptively determining the compression threshold is proposed. Finally, the results of simulation experiments show that the proposed algorithm can effectively overcome the above problems, and the clustering performances on a synthetic dataset and an actual dataset are satisfactory.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.