Reliability prediction and QoS selection for web service composition

Chen, Liping; Ha, Weitao

doi:10.1504/ijcse.2018.090442

Cited by 9 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To evaluate the prediction accuracy of our model, we compared it with several well-known QoS prediction models, as listed below. 3 The results are shown in Table 6 and Table 7.…”

Section: Comparisonmentioning

confidence: 98%

“…These can be broadly classified into two categories, i.e., collaborative filtering (CF) methods and content-based methods. Most of the proposed methods are extended from CF algorithm [3], [34]. In this section, we introduce a literature review about CF-based QoS prediction method, deep learning-based QoS prediction method, and autoencoder based QoS prediction method.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

QoS prediction for service selection and recommendation with a deep latent features autoencoder

Zohra

Benmerzoug

2022

ComSIS

View full text Add to dashboard Cite

The number of services on the Internet has increased rapidly in recent years. This makes it increasingly difficult for users to find the right services from a large number of the functionally equivalent candidate. In many cases, the number of services invoked by a user is quite limited, resulting in a large number of miss ing QoS values and sparseness of data. Consequently, predicting QoS values of the services is important for users to find the exact service among many functionally similar services. However, improving the accuracy of QoS prediction is still a prob lem. Despite the successful results of the proposed QoS prediction methods, there are still a set of issues that should be addressed, such as Sparsity and Overfitting. T address these issues and improve prediction accuracy. In this paper, we propose a novel framework for predicting QoS values and reduce prediction error. This frame work named auto-encoder for neighbor features (Auto-NF) consists of three steps. In the first step, we propose an extended similarity computation method based on Euclidean distance to compute the similarity between users and find similar neigh bors. In the second step, we form clusters of similar neighbors and partition the initial matrix into sub-matrices based on these clusters to reduce the data sparsity problem. In the third step, we propose a simple neural network autoencoder that can learn deep features and select an ideal number of latent factors to reduce the over fitting phenomenon. To validate and evaluate our method, we conduct a series of experiments use a real QoS dataset with different data densities. The experimental results demonstrate that our method achieves higher prediction accuracy compared to existing methods.

show abstract

“…To evaluate the prediction accuracy of our model, we compared it with several well-known QoS prediction models, as listed below. 3 The results are shown in Table 6 and Table 7.…”

Section: Comparisonmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 99%

QoS prediction for service selection and recommendation with a deep latent features autoencoder

Zohra

Benmerzoug

2022

ComSIS

View full text Add to dashboard Cite

show abstract

“…In this paper, the latest N records of QoS are regarded as a group of various random variables. Calculate the coefficient of variation value DU of the service, as shown in equation (1), (2) and (3) The average value of attributes is denoted byȲ ,Ȳ = 0; p n represents the n th record in the latest N QoS record. The mean value (standard deviation) of the attribute is represented by σ j , and DU j represents the j th attribute's coefficient of variation value.…”

Section: B Service Filtering Modelmentioning

confidence: 99%

“…The results of abundant production activities have gradually begun to be shown to us in the form of services, and servicing has become an inevitable trend of industrial development. In this environment,it is difficult for users to choose the services they need due to the large number of services available.Therefore, how to quickly and accurately recommend the most close to the target and good service quality for users, that is, to meet the needs of customers in all aspects of the service, is our ultimate goal.Therefore, service recommendation technology has begun to gain attention [1], [2], [3], [4].…”

Section: Introductionmentioning

confidence: 99%

A Two-Tier Service Filtering Model for Web Service QoS Prediction

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

“…As Redes de Petri (do inglês Petri Nets -PNs) são ferramentas de modelagem gráfica e matemática usadas para representar diferentes tipos de sistemas, caracterizados por simultaneidade, assincronia, distribuição, paralelismo, não determinismo, e/ou processos estocásticos [Chen and Ha 2018]. As SPNs (Redes de Petri Estocásticas) são uma das classes de PNs mais comumente usadas.…”

Section: Redes De Petri Estocásticasunclassified

Modelo Estocástico para Avaliação de Disponibilidade de Hospitais Inteligentes

Rodrigues¹,

Gonçalves²,

Fé³

et al. 2020

Anais Do Workshop Em Desempenho De Sistemas Computacionais E De Comunicação (WPerformance 2020)

View full text Add to dashboard Cite

Smart hospitals need local and remote servers to efficiently process and store data. However, there is a significant difficulty in assessing the availability of such systems in real contexts, because failures are not tolerated and the cost of prototyping is high. This paper adopts Stochastic Petri Nets (SPNs) to assess the availability of an smart hospital system, avoiding premature investment in real equipment. In addition, this work presents a sensitivity analysis that identifies the most critical architecture components. The proposed model has the potential to assist hospital systems administrators in planning more optimized architectures according to their needs.

show abstract

Reliability prediction and QoS selection for web service composition

Cited by 9 publications

References 0 publications

QoS prediction for service selection and recommendation with a deep latent features autoencoder

QoS prediction for service selection and recommendation with a deep latent features autoencoder

A Two-Tier Service Filtering Model for Web Service QoS Prediction

Modelo Estocástico para Avaliação de Disponibilidade de Hospitais Inteligentes

Contact Info

Product

Resources

About