Tên bài báo:

A comparison of Support Vector Machines and Bayesian algorithms for landslide susceptibility modelling
Tác giả:
Phạm Thái Bình
Tham gia cùng:
Ngô Quốc Trinh
Tạp chí:
Geocarto International
Năm xuất bản:
Từ trang 1 đến trang 23
Lĩnh vực:
Kỹ thuật xây dựng công trình giao thông
Phạm vi:
Quốc tế

Tóm tắt:

In this study, the main goal is to compare the predictive capability of Support Vector Machines (SVM) with four Bayesian algorithms namely Naïve Bayes Tree (NBT), Bayes network (BN), Naïve Bayes (NB), Decision Table Naïve Bayes (DTNB) for identifying landslide susceptibility zones in Pauri Garhwal district (India). First, landslide inventory map was built using 1295 historical landslide data, then in total sixteen influencing factors were selected and tested for landslide susceptibility modelling. Performance of the model was evaluated and compared using Statistical based index methods, Area under the Receiver Operating Characteristic (ROC) curve named AUC, and Chi-square method. Analysis results show that that the SVM has the highest prediction capability, followed by the NBT, DTNBT, BN and NB, respectively. Thus, this study confirms that the SVM is one of the benchmark models for the assessment of susceptibility of landslides.

Từ khóa:

Naïve Bayes Trees Bayes network Naïve Bayes Decision Table Naïve Bayes Support Vector Machines
Thông tin tác giả
Phạm Thái Bình

Phạm Thái Bình

Thạc sĩ kỹ thuật

Lý lịch khoa học