Explanable Artificial Intelligence Study based on Blockchain Using Point Cloud
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Although the technology for prediction or analysis using artificial intelligence is constantly developing, a black-box problem does not interpret the decision-making process. Therefore, the decision process of the AI model can not be interpreted from the user's point of view, which leads to unreliable results. We investigated the problems of artificial intelligence and explainable artificial intelligence using Blockchain to solve them. Data from the decision-making process of artificial intelligence models, which can be explained with Blockchain, are stored in Blockchain with time stamps, among other things. Blockchain provides anti-counterfeiting of the stored data, and due to the nature of Blockchain, it allows free access to data such as decision processes stored in blocks. The difficulty of creating explainable artificial intelligence models is a large part of the complexity of existing models. Therefore, using the point cloud to increase the efficiency of 3D data processing and the processing procedures will shorten the decision-making process to facilitate an explainable artificial intelligence model. To solve the oracle problem, which may lead to data falsification or corruption when storing data in the Blockchain, a blockchain artificial intelligence problem was solved by proposing a blockchain-based explainable artificial intelligence model that passes through an intermediary in the storage process.
Abstract
Although the technology for prediction or analysis using artificial intelligence is constantly developing, a black-box problem does not interpret the decision-making process. Therefore, the decision process of the AI model can not be interpreted from the user's point of view, which leads to unreliable results. We investigated the problems of artificial intelligence and explainable artificial intelligence using Blockchain to solve them. Data from the decision-making process of artificial intelligence models, which can be explained with Blockchain, are stored in Blockchain with time stamps, among other things. Blockchain provides anti-counterfeiting of the stored data, and due to the nature of Blockchain, it allows free access to data such as decision processes stored in blocks. The difficulty of creating explainable artificial intelligence models is a large part of the complexity of existing models. Therefore, using the point cloud to increase the efficiency of 3D data processing and the processing procedures will shorten the decision-making process to facilitate an explainable artificial intelligence model. To solve the oracle problem, which may lead to data falsification or corruption when storing data in the Blockchain, a blockchain artificial intelligence problem was solved by proposing a blockchain-based explainable artificial intelligence model that passes through an intermediary in the storage process.
참고문헌 (15)
- M. Ridley, "Explainable Artificial Intelligence", Ethics of Artificial Intelligence, (299), pp.28~46 (2019)[DOI]
- A. Ignatiev, "Towards Trustable Explainable AI", Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (2020)
- S. Mahamood, "Explainable Artificial Intelligence and its potential within Industry", Proceedings of the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence (NL4XAI 2019) (2019)
- A. Holzinger, "From Machine Learning to Explainable AI", 2018 World Symposium on Digital Intelligence for Systems and Machines (DISA), pp.55~66 (2018), IEEE
- B. S. Miguel, "Putting Accountability of AI Systems into Practice", Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (2020)
- E. Dağlarli, "Explainable Artificial Intelligence(xAI)Approaches and Deep Meta-Learning Models", Advances and Applications in Deep Learning, 79 (2020)[DOI]
- Jo, T., "Machine Learning Foundations", pp.141~165 (2020)
- F. Mahan, "Chi-MFlexDT : Chi-squarebased multi flexible fuzzy decision tree for data stream classification", Applied Soft Computing, 105, pp.107301~ (2021)[DOI]
- L. H. Gilpin, "Explaining Explanations: An Overview of Interpretability of Machine Learning", 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) (2018)
- M. Langer, "What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research", Artificial Intelligence, 296, pp.103473~ (2021)[DOI]
- M. Nassar, "Blockchain for explainable and trustworthy artificial intelligence", Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(1), pp.e1340~ (2020)[DOI]
- Z. Zhang, "Deep learning based point cloud registration : an overview", Virtual Reality & Intelligent Hardware, 2(3), pp.222~246 (2020)[DOI]
- 김효종, "IoT 기기 보안을 위한 해시 기반의 SSDP", 한국융합학회논문지, 12(5), pp.9~16 (2021), 한국융합학회[DOI]
- G. Caldarelli, "The blockchain ORACLE problem in Decentralized finance - A Multivocal Approach", pp.1~ (2021)
- G. Caldarelli, "Understanding the Blockchain Oracle Problem : A Call for Action", Information, 11(11), pp.509~ (2020)[DOI]