A Personalized QoS Prediction Approach for CPS Service Recommendation Based on Reputation and Location-Aware Collaborative Filtering

Kuang, Li; Yu, Long; Huang, Lan; Wang, Yin; Ma, Pengju; Li, Chuanbin; Zhu, Yujia

doi:10.3390/s18051556

Cited by 54 publications

(38 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, health is only one aspect of quality. We will explore the factors affecting the quality of ecosystem services of open source software in order to maintain the sustainable development of ecosystems [23].…”

Section: Discussionmentioning

confidence: 99%

Healthy or Not: A Way to Predict Ecosystem Health in GitHub

Liao

Yan

et al. 2019

Symmetry

View full text Add to dashboard Cite

With the development of open source community, through the interaction of developers, the collaborative development of software, and the sharing of software tools, the formation of open source software ecosystem has matured. Natural ecosystems provide ecological services on which human beings depend. Maintaining a healthy natural ecosystem is a necessity for the sustainable development of mankind. Similarly, maintaining a healthy ecosystem of open source software is also a prerequisite for the sustainable development of open source communities, such as GitHub. This paper takes GitHub as an example to analyze the health condition of open source ecosystem and, also, it is a research area in Symmetry. Firstly, the paper presents the healthy definition of GitHub open source ecosystem health and, then, according to the main components of natural ecosystem health, the paper proposes the health indicators and health indicators evaluation method. Based on the above, the GitHub ecosystem health prediction method is proposed. By analyzing the projects and data collected in GitHub, it is found that, using the proposed evaluation indicators and method, we can analyze the healthy development trend of the GitHub ecosystem and contribute to the stability of ecosystem development. Symmetry 2019, 11, 144 3 of 16 sustainability in natural ecosystems. Liao et al. [20] measured the sustainability of open source software ecosystem from the aspects of openness, stability, activity, and extensibility, and applied the assessment method of open source software ecosystem sustainability from the target level, criterion level, and measurement level to stack overflow.At present, the research of software ecosystem mainly focuses on system structure, participants, and ecosystem characteristics. The research on ecosystem health is mainly based on its theoretical research, and there is less quantitative analysis of the health indicators. Therefore, it is worthwhile to get into the questions of how to analyze the GitHub ecosystem health quantitatively, and how to predict the healthiness of the ecosystem. GitHub Ecosystem Health Prediction MethodIn this section, the working process of GitHub ecosystem and the various behaviors of users in the GitHub ecosystem will be introduced in Section 3.1, and then followed by the Health Prediction Model of GitHub Ecosystem (HPGE model). Figure 1 is an overview of the HPGE model. Symmetry 2019, 11, x FOR PEER REVIEW 3 of 16 sustainability in natural ecosystems. Liao et al. [20] measured the sustainability of open source software ecosystem from the aspects of openness, stability, activity, and extensibility, and applied the assessment method of open source software ecosystem sustainability from the target level, criterion level, and measurement level to stack overflow.At present, the research of software ecosystem mainly focuses on system structure, participants, and ecosystem characteristics. The research on ecosystem health is mainly based on its theoretical research, and there is less quantitative analysis o...

show abstract

Section: Discussionmentioning

confidence: 99%

Healthy or Not: A Way to Predict Ecosystem Health in GitHub

Liao

Yan

et al. 2019

Symmetry

View full text Add to dashboard Cite

show abstract

“…Wu et al [7] used the invocation record between users and services, and a generalized context-sensitive matrix factorization method was proposed to predict QoS values for services. Kuang et al [8] took advantage of the user's reputation and the user's and the service's location information, and a personalized QoS prediction method was proposed to solve the problem of data sparsity, cold start, and data incredibility.…”

Section: Location-aware Qos Prediction Users' and Web Services'mentioning

confidence: 99%

“…Thus, taking location factors into account is useful to improve the QoS prediction results. Recently, a few works [7][8][9][10][11][12] have noticed the effect of users' location on QoS values. These investigations are mainly based on the observation that when invoking the same Web service, users in different places may go through distinct experience due to the diverse physical infrastructure.…”

Section: Introductionmentioning

confidence: 99%

Predicting Quality of Service via Leveraging Location Information

et al. 2019

View full text Add to dashboard Cite

QoS (Quality of Service) (our approach can be applied to a wide variety of services; in this paper, we focus on Web services) performance is intensively relevant to locations due to the network distance and the Internet connection between users and services. Thus, considering the location information of services and users is necessary. However, the location information has been ignored by most previous work. In this paper, we take both services’ and users’ location information into account. Specifically, we propose a location-aware QoS prediction approach, called LANFM, by exploiting neural network techniques and factorization machine to improve user-perceived experience. First of all, the information (e.g., id and location) of services and users is expressed as embedding vectors by leveraging neural network techniques. Then, the inner product of various embedding vectors, along with the weighted sum of feature vectors, is used to predict the QoS values. It should be noted that the inner product operation could capture the interactions between services and users, which is helpful to predict QoS values of services that have not been invoked by users. A collection of extensive experiments have been carried out on a real-world dataset to validate the effectiveness of the LANFM model.

show abstract

“…Crowdsourcing is used to find high-quality workers in the masses through the Internet; workers can get paid when they complete tasks. Crowdsourcing makes use of people's cognitive advantages to solve difficult problems that computers are unable to, such as data collection and data analyses [1,2] for data mining and knowledge acquisition [3]; it can be used to select high-quality workers from a large number of people at a small cost. Furthermore, such services from people of the group only cost a small amount of money.…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Game Theoretic Strategy for Developers in Software Crowdsourcing: A Case Study

Liao

Zhang

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Crowdsourcing has the advantages of being cost-effective and saving time, which is a typical embodiment of collective wisdom and community workers’ collaborative development. However, this development paradigm of software crowdsourcing has not been used widely. A very important reason is that requesters have limited knowledge about crowd workers’ professional skills and qualities. Another reason is that the crowd workers in the competition cannot get the appropriate reward, which affects their motivation. To solve this problem, this paper proposes a method of maximizing reward based on the crowdsourcing ability of workers, they can choose tasks according to their own abilities to obtain appropriate bonuses. Our method includes two steps: Firstly, it puts forward a method to evaluate the crowd workers’ ability, then it analyzes the intensity of competition for tasks at Topcoder.com—an open community crowdsourcing platform—on the basis of the workers’ crowdsourcing ability; secondly, it follows dynamic programming ideas and builds game models under complete information in different cases, offering a strategy of reward maximization for workers by solving a mixed-strategy Nash equilibrium. This paper employs crowdsourcing data from Topcoder.com to carry out experiments. The experimental results show that the distribution of workers’ crowdsourcing ability is uneven, and to some extent it can show the activity degree of crowdsourcing tasks. Meanwhile, according to the strategy of reward maximization, a crowd worker can get the theoretically maximum reward.

show abstract

A Personalized QoS Prediction Approach for CPS Service Recommendation Based on Reputation and Location-Aware Collaborative Filtering

Cited by 54 publications

References 43 publications

Healthy or Not: A Way to Predict Ecosystem Health in GitHub

Healthy or Not: A Way to Predict Ecosystem Health in GitHub

Predicting Quality of Service via Leveraging Location Information

A Data-Driven Game Theoretic Strategy for Developers in Software Crowdsourcing: A Case Study

Contact Info

Product

Resources

About