Federated Data Pipelines Enabling Continuous Contract and Asset State Traceability
Main Article Content
Abstract
The growing number of demands associated with secure and real-time tracking of the contracts and asset conditions has required elaboration of the sophisticated data processing frameworks. A new pattern is suggested in this paper that uses Federated Data Pipelines to provide the possibility of tracing the contracts and assets state continuously and at the same time maintain the data privacy. Data Normalization/Standardization is integrated in the methodology to provide homogenous distribution of data to all the decentralized nodes and then Principal Component Analysis (PCA) is used to reduce the dimensionality efficiently. To forecast contract conditions and asset transition correctly a Support Vector Machine (SVM) classifier is used. The system exploits Federated Learning alongside Privacy-Preserving Computation using secure computation techniques such as Homomorphic Encryption. Experimental findings show that the experimental results are more accurate, with lesser latency and better privacy when compared to the traditional centralized systems. The suggested framework offers a flexible and effective answer to the real-time traceability, and, therefore, can be applied to supply chain management, financial contract, and asset monitoring systems.
Article Details
Section
How to Cite
References
[1]. H. B. McMahan et al., “Communication-Efficient Learning of Deep Networks from Decentralized Data,” Proc. AISTATS, 2017, doi: 10.48550/arXiv.1602.05629.
[2]. J. Konečný et al., “Federated Learning: Strategies for Improving Communication Efficiency,” NIPS Workshop, 2016, doi: 10.48550/arXiv.1610.05492.
[3]. Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated Machine Learning: Concept and Applications,” ACM Trans. Intell. Syst. Technol., vol. 10, no. 2, 2019, doi: 10.1145/3298981.
[4]. P. Voigt and A. von dem Bussche, The EU General Data Protection Regulation (GDPR), Springer, 2017, doi: 10.1007/978-3-319-57959-7.
[5]. M. Mohri, G. Sivek, and A. T. Suresh, “Agnostic Federated Learning,” ICML, 2019, doi: 10.48550/arXiv.1902.00146.
[6]. B. McMahan and D. Ramage, “Federated Learning: Collaborative Machine Learning without Centralized Training Data,” Google AI Blog, 2017, doi: 10.48550/arXiv.1812.02903.
[7]. S. Nakamoto, “Bitcoin: A Peer-to-Peer Electronic Cash System,” 2008, doi: 10.48550/arXiv.0802.1565.
[8]. K. Christidis and M. Devetsikiotis, “Blockchains and Smart Contracts for the Internet of Things,” IEEE Access, vol. 4, 2016, doi: 10.1109/ACCESS.2016.2566339.
[9]. V. Mnih et al., “Human-level Control through Deep Reinforcement Learning,” Nature, vol. 518, 2015, doi: 10.1038/nature14236.
[10]. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016, doi: 10.7551/mitpress/10243.001.0001.
[11]. I. T. Jolliffe, Principal Component Analysis, Springer, 2002, doi: 10.1007/b98835.
[12]. B. Schölkopf and A. J. Smola, Learning with Kernels, MIT Press, 2002, doi: 10.7551/mitpress/4175.001.0001.
[13]. C. Dwork, “Differential Privacy,” ICALP, 2006, doi: 10.1007/11787006_1.
[14]. R. Shokri and V. Shmatikov, “Privacy-Preserving Deep Learning,” ACM CCS, 2015, doi: 10.1145/2810103.2813687.
[15]. A. Gandomi and M. Haider, “Beyond the Hype: Big Data Concepts, Methods, and Analytics,” Int. J. Inf. Manage., vol. 35, 2015, doi: 10.1016/j.ijinfomgt.2014.10.007.
[16]. D. C. Montgomery, Introduction to Statistical Quality Control, Wiley, 2007, doi: 10.1002/9781118146811.
[17]. A. Vaswani et al., “Attention Is All You Need,” NIPS, 2017, doi: 10.48550/arXiv.1706.03762.
[18]. Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, 2015, doi: 10.1038/nature14539.