TSVM-PI: transductive support vector machine based on privileged information learning

Ruiyu An; Zhibin Hao

doi:10.1117/12.2656578

20 October 2022 TSVM-PI: transductive support vector machine based on privileged information learning

Ruiyu An, Zhibin Hao

Proceedings Volume 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022); 1245150 (2022) https://doi.org/10.1117/12.2656578
Event: 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 2022, Chongqing, China

Abstract

In semi-supervised classification tasks, there are often a large number of unlabeled data and unavoidable noise in the training dataset. Using the structural distribution information in the data or the privileged information of a feature to guide the classifier learning can make the model have better performance. Based on this consideration, this paper proposes a transductive support vector machine model using privileged information(TSVM-PI). The new model adds the regularization term of the privileged information guidance group on the basis of transductive support vector machine(TSVM), and uses the privileged information constraint term to constrain the slack variables. The introduction of privileged information can effectively improve the prediction accuracy of the new model, and make the model have a stronger anti-noise ability. In order to verify the classification performance of the algorithm, and data sets in artificial data set and UCI data set are used to conduct multiple sets of experiments. The noise was added to one of the UCI experimental data, and different proportions of noise group experiments were designed to explore the sensitivity of the model to noise. The experimental results show that the new model has better classification performance and is less sensitive to noise data than TSVM.

Citation Download Citation

Ruiyu An and Zhibin Hao "TSVM-PI: transductive support vector machine based on privileged information learning", Proc. SPIE 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 1245150 (20 October 2022); https://doi.org/10.1117/12.2656578

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Performance modeling

Lawrencium

Breast cancer

Computer programming

Copper

Statistical modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years