Pre-clustering active learning method for automatic classification of building structures in urban areas

被引：1
作者：
Zhou P. [1 ]
Zhang T. [2 ]
Zhao L. [3 ]
Qi Y. [1 ]
Chang Y. [1 ]
Bai L. [4 ,5 ]
机构：
[1] School of Management Science and Engineering, Central University of Finance and Economics, Beijing
[2] Postal Savings Bank of China Co., Ltd., Beijing
[3] Industry Internet Operation Center, China United Network Communications Corporation Beijing Branch, Beijing
[4] School of Artificial Intelligence, Beijing Normal Universit, Beijing
[5] School of Information, Central University of Finance and Economics, Beijing
来源：
Engineering Applications of Artificial Intelligence | 2023年 / 123卷
基金：
中国国家自然科学基金;
关键词：
Active learning; Automated classification; Machine learning; Pre-clustering; Urban building structures;
D O I：
10.1016/j.engappai.2023.106382
中图分类号：
学科分类号：
摘要：
Identifying the structures of buildings in urban areas is a prerequisite for robust urban planning and regeneration. Owing to the diverse structural designs of urban buildings, automated approaches are required to classify building structures. Supervised machine learning is usually employed to classify various building characteristics. However, this approach requires significant labeling effort. Therefore, this paper proposes a new pre-clustering active learning method for building structure classification. The proposed method captures the statistical characteristics of samples and enhances the recognition of the most valuable training samples, thereby substantially reducing the labeling workload and improving the efficiency and effectiveness of classification. This method was tested via the classification of 3718 buildings in Beijing, China, into five common structures. The results showed that the proposed method could reduce labeling effort by 60% while achieving a promising 90% F1 score for overall classification performance, thus indicating its effectiveness. © 2023 Elsevier Ltd
引用
收藏
相关论文
共 64 条
  • [1] Aghdam H.H., Gonzalez-Garcia A., Weijer J.V.D., Lopez A.M., Active learning for deep detection neural networks, Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3672-3680, (2019)
  • [2] Arthur D., Vassilvitskii S., K-means++: the advantages of careful seeding, Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1027-1035, (2006)
  • [3] AutoNavi, AutoNavi POI codes, (2017)
  • [4] AutoNavi, AutoNavi map, (2022)
  • [5] Bachman P., Sordoni A., Trischler A., Learning algorithms for active learning, Proceedings of the International Conference on Machine Learning, pp. 301-310, (2017)
  • [6] Belgiu M., Tomljenovic I., Lampoltshammer T.J., Blaschke T., Hofle B., Ontology-based classification of building types detected from airborne laser scanning data, Remote Sens., 6, 2, pp. 1347-1366, (2014)
  • [7] Bolon-Canedo V., Alonso-Betanzos A., Ensembles for feature selection: a review and future trends, Inf. Fusion, 52, pp. 1-12, (2019)
  • [8] Budd S., Robinson E.C., Kainz B., A survey on active learning and human-in-the-loop deep learning for medical image analysis, Med. Image Anal., 71, (2021)
  • [9] Campello R.J.G.B., Moulavi D., Sander J., Density-based clustering based on hierarchical density estimates, Proceedings of Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2013), pp. 160-172, (2013)
  • [10] Cao Y.Y., Cao Y.T., Synchronization of multiple neural networks with reaction–diffusion terms under cyber–physical attacks, Knowl.-Based Syst., 239, (2022)
1234567