Extreme Gradient Boost Classification Based Interesting User Patterns Discovery for Web Service Composition

Chakravarthy, D. Gowtham; Kannimuthu, S.

doi:10.1007/s11036-019-01385-6

Cited by 11 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the later mentioned metric is specifically employed to determine the ratio between user web patterns and total web patterns. Web Pattern Identification Accuracy (WPIA) [24] 5 Discussion This section presents a discussion on the results obtained in this review paper. Fig.…”

Section: Wpia ¼mentioning

confidence: 96%

“…Best composition patterns' mining with less time is still the central research area. The ensemble of the 'best first decision tree' (BFDT) and extreme boosting models is proposed in a recent research [24]. The proposed approach is aimed to extract and mine the users' interesting patterns.…”

Section: Rq1-what Are State-of-the-art Approaches That Employed Ensemble Learning Models In the Context Of Web Services Classification Anmentioning

confidence: 99%

“…Only two papers [22,23] have used the RMSE metric. Other than these metrics, Mathews' correlation coefficient and WPIA metrics were used in Raza et al [17] and Chakravarthy et al [24] studies, respectively. This illustrates that accuracy-based metrics were mostly used in the literature.…”

Section: Rq3-what Are the Performance Metrics Reported In The Chosen Studies?mentioning

confidence: 99%

“…Eq. ( 3) is adopted from Chakravarthy et al [24] where research is mainly focused on web services composition from interesting user patterns. This metric depends on other techniques to enhance its performance.…”

Section: Wpia ¼mentioning

confidence: 99%

See 3 more Smart Citations

Ensemble Learning Models for Classification and Selection of Web Services: A Review

Hasnain¹,

Ghani²,

Jeong³

et al. 2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

This paper presents a review of the ensemble learning models proposed for web services classification, selection, and composition. Web service is an evolutionary research area, and ensemble learning has become a hot spot to assess web services' earlier mentioned aspects. The proposed research aims to review the state of art approaches performed on the interesting web services area. The literature on the research topic is examined using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) as a research method. The study reveals an increasing trend of using ensemble learning in the chosen papers within the last ten years. Naïve Bayes (NB), Support Vector Machine' (SVM), and other classifiers were identified as widely explored in selected studies. Core analysis of web services classification suggests that web services' performance aspects can be investigated in future works. This paper also identified performance measuring metrics, including accuracy, precision, recall, and f-measure, widely used in the literature.

show abstract

Section: Wpia ¼mentioning

confidence: 96%

Section: Rq1-what Are State-of-the-art Approaches That Employed Ensemble Learning Models In the Context Of Web Services Classification Anmentioning

confidence: 99%

Section: Rq3-what Are the Performance Metrics Reported In The Chosen Studies?mentioning

confidence: 99%

Section: Wpia ¼mentioning

confidence: 99%

See 2 more Smart Citations

Ensemble Learning Models for Classification and Selection of Web Services: A Review

Hasnain¹,

Ghani²,

Jeong³

et al. 2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…Research that developed the notion of pattern discovery and classifications in WS has been proposed in [12]. The authors used data mining techniques to classify services through specific non-functional requirements.…”

Section: Web Service Compositionmentioning

confidence: 99%

QoS-Based Pattern Recognition Approach for Web Service Discovery: Ar_WSDS

Adarme

Jimeno

2021

Applied Sciences

View full text Add to dashboard Cite

Web service composition requires high levels of integration and reliability of the services involved in its operation, which must meet specific quality criteria to ensure their proper execution and deployment. The discovery and selection of web services currently face optimization problems. Many services might satisfy a requirement with similar quality criteria. Because of this, software developers have to choose the most appropriate services for a given composition, complicated by the rapid increase in providers and services available in the cloud. Service composition also implies coupling according to a composition flow and non-functional requirement criteria. Such requirements make selection and composition a complex task not previously solved in the literature. This paper presents Ar_WSDS, a computational approach for web services discovery and selection in cloud environments, which bases its implementation on the brain’s pattern recognition systematic functioning. This process allows classifying web services through recognition modules created dynamically based on their quality parameters, resulting in a set of web services suitable for a web service composition. This approach allows a solution to the selection problem using less complex tasks. This paper introduces an architectural and procedural definition that provides the web service description with a pattern to recognize and select services using different recognition levels. We simulated our approach and evaluated it using a dataset from the QWS project that offers a set of quality criteria collected from different providers. The web services are recognized and classified using different quality criteria for the composition and each of their services. The results demonstrate the effectiveness of the discovery and selection process compared to other approaches. Furthermore, Ar_WSDS allows us to recognize and filter out web services with ambiguity and similarity in their provider information, a process that minimizes the discovery space for services.

show abstract

A study of detection of abnormal network traffic: A comparison of multiple algorithms

2021

Security and Privacy

View full text Add to dashboard Cite

The detection of abnormal traffic in networks is of great value for maintaining network security. This article gives a brief introduction of abnormal traffic and compares the performance of three algorithms, the support vector domain description algorithm, the gradient boosting decision tree algorithm, and the extreme learning machine-k-nearest neighbor (ELM-KNN) algorithm. Experiments were carried out on the NSL-KDD dataset. It was found that the accuracies of the three algorithms were 0.8327, 0.8679, and 0.9468, the recall rates were 0.6764, 0.7236, and 0.8997, the F1-scores were 0.7898, 0.8364, and 0.9578, and the false alarm rates were 0.3236, 0.2764, and 0.1003. The running time of the ELM-KNN algorithm was far less than the other two algorithms. The experimental results verify the effectiveness of the ELM-KNN algorithm in abnormal network traffic detection. The ELM-KNN algorithm can be further promoted and applied in practice.

show abstract

Extreme Gradient Boost Classification Based Interesting User Patterns Discovery for Web Service Composition

Cited by 11 publications

References 25 publications

Ensemble Learning Models for Classification and Selection of Web Services: A Review

Ensemble Learning Models for Classification and Selection of Web Services: A Review

QoS-Based Pattern Recognition Approach for Web Service Discovery: Ar_WSDS

A study of detection of abnormal network traffic: A comparison of multiple algorithms

Contact Info

Product

Resources

About