Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 3.61 MB
Add to list
  1. Search results
  2. Performance of unsupervised machine l...

Performance of unsupervised machine learning methods using chi-squared weights for LiDAR point cloud filtering in urban areas

Alper Sen (UGent) , Baris Suleymanoglu and Metin Soycan
(2023) JOURNAL OF SPATIAL SCIENCE. 68(3). p.397-414
Author
Organization
Abstract
In this study, we compared the LiDAR filtering performances of unsupervised machine learning methods, such as linkage, K-means, and self-organizing maps, for urban areas to provide a practical guide to researchers. The input parameters (x-y-z and intensity) were normalized and weighted using a chi-squared independence test to improve the classification accuracy. The best successful results were obtained using the weighted linkage method in terms of the total error of 13.53%, 3.96%, and 1.07% for the three samples, respectively. In comparison with other approaches, methods weighted by chi-squared have significant potential for classification and filtering and outperform many popular approaches.
Keywords
Atmospheric Science, General Energy, Geography, Planning and Development, Airborne LiDAR, point cloud filtering, K-means, linkage, SOM, PROGRESSIVE TIN DENSIFICATION, MORPHOLOGICAL FILTER, EXTRACTION, ALGORITHMS, CLASSIFICATION

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.61 MB

Citation

Please use this url to cite or link to this publication:

MLA
Sen, Alper, et al. “Performance of Unsupervised Machine Learning Methods Using Chi-Squared Weights for LiDAR Point Cloud Filtering in Urban Areas.” JOURNAL OF SPATIAL SCIENCE, vol. 68, no. 3, 2023, pp. 397–414, doi:10.1080/14498596.2021.2013329.
APA
Sen, A., Suleymanoglu, B., & Soycan, M. (2023). Performance of unsupervised machine learning methods using chi-squared weights for LiDAR point cloud filtering in urban areas. JOURNAL OF SPATIAL SCIENCE, 68(3), 397–414. https://doi.org/10.1080/14498596.2021.2013329
Chicago author-date
Sen, Alper, Baris Suleymanoglu, and Metin Soycan. 2023. “Performance of Unsupervised Machine Learning Methods Using Chi-Squared Weights for LiDAR Point Cloud Filtering in Urban Areas.” JOURNAL OF SPATIAL SCIENCE 68 (3): 397–414. https://doi.org/10.1080/14498596.2021.2013329.
Chicago author-date (all authors)
Sen, Alper, Baris Suleymanoglu, and Metin Soycan. 2023. “Performance of Unsupervised Machine Learning Methods Using Chi-Squared Weights for LiDAR Point Cloud Filtering in Urban Areas.” JOURNAL OF SPATIAL SCIENCE 68 (3): 397–414. doi:10.1080/14498596.2021.2013329.
Vancouver
1.
Sen A, Suleymanoglu B, Soycan M. Performance of unsupervised machine learning methods using chi-squared weights for LiDAR point cloud filtering in urban areas. JOURNAL OF SPATIAL SCIENCE. 2023;68(3):397–414.
IEEE
[1]
A. Sen, B. Suleymanoglu, and M. Soycan, “Performance of unsupervised machine learning methods using chi-squared weights for LiDAR point cloud filtering in urban areas,” JOURNAL OF SPATIAL SCIENCE, vol. 68, no. 3, pp. 397–414, 2023.
@article{8732504,
  abstract     = {{In this study, we compared the LiDAR filtering performances of unsupervised machine learning methods, such as linkage, K-means, and self-organizing maps, for urban areas to provide a practical guide to researchers. The input parameters (x-y-z and intensity) were normalized and weighted using a chi-squared independence test to improve the classification accuracy. The best successful results were obtained using the weighted linkage method in terms of the total error of 13.53%, 3.96%, and 1.07% for the three samples, respectively. In comparison with other approaches, methods weighted by chi-squared have significant potential for classification and filtering and outperform many popular approaches.}},
  author       = {{Sen, Alper and Suleymanoglu, Baris and Soycan, Metin}},
  issn         = {{1449-8596}},
  journal      = {{JOURNAL OF SPATIAL SCIENCE}},
  keywords     = {{Atmospheric Science,General Energy,Geography,Planning and Development,Airborne LiDAR,point cloud filtering,K-means,linkage,SOM,PROGRESSIVE TIN DENSIFICATION,MORPHOLOGICAL FILTER,EXTRACTION,ALGORITHMS,CLASSIFICATION}},
  language     = {{eng}},
  number       = {{3}},
  pages        = {{397--414}},
  title        = {{Performance of unsupervised machine learning methods using chi-squared weights for LiDAR point cloud filtering in urban areas}},
  url          = {{http://doi.org/10.1080/14498596.2021.2013329}},
  volume       = {{68}},
  year         = {{2023}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: