Adaptive method for complete random forest

Yong Zheng; Shuyin Xia; Qun Liu

doi:10.1117/12.2624355

19 December 2021 Adaptive method for complete random forest

Yong Zheng, Shuyin Xia, Qun Liu

Proceedings Volume 12128, Second International Conference on Industrial IoT, Big Data, and Supply Chain; 121280M (2021) https://doi.org/10.1117/12.2624355
Event: 2nd International Conference on Industrial IoT, Big Data, and Supply Chain, 2021, Macao, China

Abstract

This paper presents an adaptive method to search best number of trees (Ntree) in complete random forest (CRF). Ada- CRF can automatically determine whether the forest has reached a stable state during the establishment of the forest, thereby avoiding inaccurate results caused by too small Ntree, or low efficiency caused by too large Ntree. As a general sampling method, Ada-CRF can not only effectively compress the amount of data, but also filter label noise to improve data quality. Ada-CRF can identify the noise points in the data by automatically searching for the results of the complete random tree division of the data. To improve the data quality, it filters the noise points of the label and retains valid data.

Citation Download Citation

Yong Zheng, Shuyin Xia, and Qun Liu "Adaptive method for complete random forest", Proc. SPIE 12128, Second International Conference on Industrial IoT, Big Data, and Supply Chain, 121280M (19 December 2021); https://doi.org/10.1117/12.2624355

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available