Classification of web services using data mining algorithms and improved learning model

M. Swami Das, A. Govardhan, D. Vijaya Lakshmi
2019 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
As per the global digital report, 52.9% of the world population is using the internet, and 42% of the world population is actively using e-commerce, banking, and other online applications. Web services are software components accessed using networked communications and provide services to end users. Software developers provide a high quality of web service. To meet the demands of user requirements, it is necessary for a developer to ensure quality architecture and quality of services. To meet
more » ... e demands of user measure service quality by the ranking of web services, in this paper, we analyzed QWS dataset and found important parameters are best practices, successability, availability, response time, reliability and throughput, and compliance. We have used various data mining techniques and conducted experiments to classify QWS data set into four categorical values as class1, 2, 3, and 4. The results are compared with various techniques random forest, artificial neural network, J48 decision tree, extreme gradient boosting, K-nearest neighbor, and support vector machine. Multiple classifiers analyzed, and it was observed that the classifier technique eXtreme gradient boosting got the maximum accuracy of 98.44%, and random forest got the accuracy of 98.13%. In future, we can extend the quality of web service for mixed attributes. 3192 increasing very rapidly the designer and developer to ensure the quality design and development of applications which meet the client demands of user satisfaction of services [2]. Web service uses a dynamic business environment and user interactions, service quality, and satisfaction. For example, e-commerce, web service using SOA architecture, interactions of type and applictions used in large, medium, and small service users, features with service components have properties, functions, and operations [3] . Day to day business activities by web services made with quality of services, web service selection is the most important for the consumer to access applications. The rest of the paper deals with section 2 as related works, section 3 is the proposed approach, section 4 provide the results and discussions and finally section 5 ends with a conclusion and future scope Related Work M A Almulla et al. [4] proposed a model to classify into specific domains operated on text, similar service by the Fuzzy expert system; the results are compared with other methods. The WS quality dataset UDDI registries have 205 services which are classified into 11 classes or domains such as business, communication, and communication and others. Makhlughian et al. [5] use of CBA tool the services on demand, quality constraints, execution time, and accuracy of selections. Limitations do not know the importance of specific quality parameters. Mohanty et al. [6] used QWS dataset contains web services which can be classified into four categorical values using Markov Blanket, Naive Bayes, and Tabu search, the WSRF from data, naive Bayes is 85.62% using QWS data, and others methods used. The limitations are a quality model available, but prediction accuracy is low. Chen Li. et al. [7] use of models Naive Bayes, supporting vector machine 391 web services into service classifications using rough set theory classification of web pages into nine different classes like education, food, economy and weapons, limitations do not provide the best quality of web service. The Guosheng Kang et al. [8] use of collaborative model filtering (CF) is a method to predict the interest of users, choice, preference, likes, and dislikes. In CF approach there are three concepts first, functional relations (keywords, input, and output), second is the score of the cosine similarity metricsof the users, and third is the utility operations the QoS into high and low values. Mohan Patro, et al. [9] used classifiers to classify the WS on QWS data set that are Fuzzy related techniques with feature selection, Gain ratio and Information gain with three methods which are compared. Hussein Al-Helal et al. [10] proposed an algorithm reparability as a metric to determine the web services plans equal or more tolerant plans. To discover and re-use web services in the organization to select the services which are business and quality of service (QoS) needs. The QWS dataset is used for experiments.
doi:10.12928/telkomnika.v17i6.11510 fatcat:xfk3g4jisfa2hhrhqd6bkxdfui