Affiliation:
1. Shree Dhanvantary College of Engineering and Technology, Kim Surat, India
2. Bennett University, Greater Noida, India
Abstract
Big data and AI/ML pipeline models provide a good basis for analyzing and selecting technical architectures for big data and AI systems. The experience of many big data projects has shown that many projects use similar architectural models that differ only in the selection of different technological components in the same diagram. The big data and AI/ML pipeline framework are used to describe pipeline stages in big data and AI and ML projects, and supports the benchmark classification. This includes four pipeline stages: data acquisition/collection and storage, data preparation and storage, data analysis with artificial intelligence/machine learning, and performance and interaction, including data visualization, user interaction, and API access. The authors have also created a toolkit to help identify and leverage existing models by following the steps below and the two different technical areas and different data types within the framework.
Reference15 articles.
1. Brandenburger, J., Schirm, C., Melcher, J., Hancke, E., Vannucci, M., Colla, V., Cateni, S., Sellami, R., Dupont, S., Majchrowski, A. (2020). Quality4. 0–transparent product quality supervision in the age of industry 4.0. arXiv preprint arXiv:2011.06502
2. De Amorim, R. C. (2012). IEEE 13th International Symposium on Computational Intelligence and Informatics (CINTI), (pp. 13–17). IEEE.
3. Endo. (2019). Introductory remarks by Commissioner Toshihide Endo. Endo.
4. Gaba, G. Kumar, G., Monga, H., Kim, T., Liyanage, M., & Kumar. P. (2020). Robust and lightweight key exchange (lke) protocol for industry 4.0. IEEE Access, (vol. 8, pp. 132). IEEE.
5. Machine Learning Models for Secure Data Analytics: A taxonomy and threat model