Machine Learning (ML) is a field of Artificial Intelligence, which applies the principles of statistics to predict the outcome of process by utilizing the historical data. Each ML model is built on a specific Data Set and programming language, however the knowledge obtained by the model is restricted to that particular Dataset. Web Service Composition (WSC) process of combining the available web services (WS) and arriving at a new web service based on the required inputs and preconditions. The paper presents an approach to represent a ML model as web service and automatically composing them with other ML models to utilize the knowledge gained on different data sets. The MLWSC approach consists of two stages. In stage one, semantic networks are created among the ML services to form a network. In stage two, MLWSC compositions are constructed based on the requirement of the user.

Web Service Composition, Machine Learning, Data Sets

[1] Rik Eshuis, Freddy Lecue, and Nikolay Mehandjiev, “Flexible Construction of Complex Service Compositions from Reusable Semantic Knowledge”, In the Proceedings of IEEE 19th International Conference on Web Services, pp.631-632, 2012.
[2] Paolo Traverso and Marco Pistore, “Automated Composition of Semantic Web Services into Executable Processes”, In the Proceedings Third International Semantic Web Conference, Hiroshima, Japan, pp.380-394, 2004.
[3] Mohan H G, Chetan K R, “Semantic Based Automatic Web Service Composition”, International Journal of Applied Research and Studies, Vol.3, Issue.6, 2014.
[4] Mohan H G and Devaraj F V, “A Survey on Semantic Based Automatic Web Service Compositions”, European Journal of Advances in Engineering and Technology, pp.73-79, 2014.
[5] Chatti Subbalakshmi, Rishi Sayal , H. S. Saini, “S-REST: A design of Secured Protocol for Implementation of RESTful Webservices”. International Journal of Computer Sciences and Engineering Vol.7(1), Jan 2019.
[6] Felix Mohr, Marcel Wever, Eyke Hullermeier, Amin Faez, “Towards the Automated Composition of Machine Learning Services”, In the IEEE International Conference on Services Computing, 2018.
[7] Igor Lavrov and Jenny Domashova, “Constructor of compositions of machine learning models for solving classification problems”, In the Postproceedings of the 10th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2019.
[8] Kailash Chander Bhardwaj and R K Sharma, “Machine Learning In Efficient And Effective Web Service Discovery”, Journal of Web Engineering, Vol. 14, No.3&4, pp.196-214, 2015.
[9] Y. Yang, X. Li, Z. Liu, and W. Ke, “RM2PT: A tool for automated prototype generation from requirements model”, In the Proceedings of International Conference on Software Engineering, May 2019.
[10] L. Zeng, B. Benatallah, M. Dumas, J. Kalagnanam, and Q. Z. Sheng, “Quality driven web services composition”, In the Proceedings of the 12th international conference on World Wide Web. ACM, pp.411–421, 2003.
[11] F. Mohr, A. Jungmann, and H. Kleine Buning, “Automated online service composition”, In the Proceedings of the International Conference on Services Computing, IEEE, pp.57-64, 2015.
[12] Berardi, D. Calvanese, G. De Giacomo, M. Lenzerini, and M. Mecella, “Automatic Composition of e-services that export their behavior”, In the Proceedings of the International Conference on Service-Oriented Computing. Springer, pp.43-58, 2003.
[13] Freddy Lécué and Alain Léger, “Semantic Web Service Composition through a Match making of Domain”, In the Proceedings of IEEE 4th European Conference on Web Services, pp.171-180, 2006.
[14] Yilong Yang, Nafees Qamar, Peng Liu, Katarina Grolinger, Weiru Wang, Zhi Li, Zhifang Liao, “ServeNet: A Deep Neural Network for Web Services Classification”, In the 12th International Conferences on Web Services, China, Oct. 2020.
[15] Jing Zhang, Yang Chen, Yilong Yang, Changran Lei, Deqiang Wang, “ServeNet-LT: A Normalized Multi-head Deep Neural Network for Long-tailed Web Services Classification”, In the IEEE International Conferences on Web Services, Sep. 2021.