연합학습 기반 자치구별 건물 변화탐지 알고리즘 성능 분석
Performance Analysis of Building Change Detection Algorithm for Each Autonomous District Based on Federated Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Although artificial intelligence and machine learning technologies have been used in various fields, problems with personal information protection have arisen based on centralized data collection and processing. Federated learning has been proposed to solve this problem. Federated learning is a process in which clients who own data in a distributed data environment learn a model using their own data and collectively create an artificial intelligence model by centrally collecting learning results. Unlike the centralized method, Federated learning has the advantage of not having to send the client's data to the central server. In this paper, we quantitatively present the performance improvement when federated learning is applied using the building change detection learning data. As a result, it has been confirmed that the performance when federated learning was applied was about 29% higher on average than the performance when it was not applied. As a future work, we plan to propose a method that can effectively reduce the number of federated learning rounds to improve the convergence time of federated learning.
Abstract
Although artificial intelligence and machine learning technologies have been used in various fields, problems with personal information protection have arisen based on centralized data collection and processing. Federated learning has been proposed to solve this problem. Federated learning is a process in which clients who own data in a distributed data environment learn a model using their own data and collectively create an artificial intelligence model by centrally collecting learning results. Unlike the centralized method, Federated learning has the advantage of not having to send the client's data to the central server. In this paper, we quantitatively present the performance improvement when federated learning is applied using the building change detection learning data. As a result, it has been confirmed that the performance when federated learning was applied was about 29% higher on average than the performance when it was not applied. As a future work, we plan to propose a method that can effectively reduce the number of federated learning rounds to improve the convergence time of federated learning.
참고문헌 (14)
- Z. Jan, "Artificial Intelligence for Industry 4.0:Systematic Review of Applications, Challenges, and Opportunities", ELSEVIER Expert Systems with Applications, 216, pp.1~21 (2023)
- S. AbdulRahman, "A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond", IEEE Internet of Things Journal, 8(7), pp.5476~5497 (2021)
- M. Aledhari, "Federated Learning : A Survey on Enabling Technologies, Protocols, and Applications", IEEE Access, 8, pp.140699~140725 (2020)
- S. Pandya, "Federated Learning for Smart Cities: A Comprehensive Survey", ELSEVIER Sustainable Energy Technologies and Assessments, 55, pp.1~13 (2023)
- M. F. Sohan, "A Systematic Review on Federated Learning in Medical Image Analysis", IEEE Access, 11, pp.28628~28644 (2023)
- D. C. Nguyen, "Federated Learning for Smart Healthcare: A Survey", ACM Computing Surveys, 55(3), pp.1~37 (2022)
- S. Pandya, "Federated Learning for Smart Cities: A Comprehensive Survey", ELSEVIER Sustainable Energy Technologies and Assessments, 55, pp.1~13 (2023)
- T. Zhang, "Federated Learning for the Internet of Things : Applications, Challenges, and Opportunities", IEEE Internet of Things Magazine, 5(1), pp.24~29 (2022)
- V. Mothukuri, "A Survey on Security and Privacy of Federated Learning", ELSEVIER Future Generation Computer Systems, 115, pp.619~640 (2021)
- 오재홍, "기구축 고해상도 위성 데이터를 이용한 정밀 시계열정사영상 자동 생성", 한국측량학회지, 41(1), pp.29~37 (2023), 한국측량학회[DOI]
- M. Xua, "A Comprehensive Survey of Image Augmentation Techniques for Deep Learning", ELSEVIER Pattern Recognition, 137, pp.1~12 (2023)
- B. Hou, "From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning Techniques", IEEE Transactions on Geoscience and Remote Sensing, 58(3), pp.1790~1802 (2020)
- X. Xia, "W-Net: A Deep Model for Fully Unsupervised Image Segmentation", ~ (2017)
- A. A. Taha, "Metrics for evaluating 3D medical image segmentation:analysis, selection, and tool", BMC Medical Imaging, 15(29), pp.1~28 (2015)