Refined multi-channel inception network for automobile insurance fraud identification based on attention mechanism and dense connection structure

Deguang Wang; Ting Zhang; Fengqi Li; Ning Tong; Fengqiang Xu

doi:10.1117/12.3025930

8 April 2024 Refined multi-channel inception network for automobile insurance fraud identification based on attention mechanism and dense connection structure

Deguang Wang, Ting Zhang, Fengqi Li, Ning Tong, Fengqiang Xu

Author Affiliations +

Proceedings Volume 13090, International Conference on Computer Application and Information Security (ICCAIS 2023); 130904B (2024) https://doi.org/10.1117/12.3025930
Event: International Conference on Computer Application and Information Security (ICCAIS 2023), 2023, Wuhan, China

Abstract

Automobile insurance fraud causes huge economic losses to insurance companies, detection technology has become an urgent research topic. However, feature selection manually is prone to subjective judgment, which results in a decline in recognition accuracy. To settle this problem, a refined multi-channel Inception network for automobile insurance fraud identification based on an attention mechanism and dense connection architecture is proposed. Firstly, we redesign the backbone structure of inception network to strengthen feature extraction ability. Secondly, attention mechanism is fused to inception module, enabling network to pay attention to important features. Furthermore, a dense connection structure is introduced to Inception network, which strengthens the transmission of features. Finally, this paper carries out mass experiments on a real-world “carcalims.txt” dataset. Experimental results reveal that our proposed approach achieves impressive performance on automobile insurance fraud identification tasks and can reach 98.12% accuracy, 98.19% precision and 98.12% recall and 98.12% f1_score, respectively.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Deguang Wang, Ting Zhang, Fengqi Li, Ning Tong, and Fengqiang Xu "Refined multi-channel inception network for automobile insurance fraud identification based on attention mechanism and dense connection structure", Proc. SPIE 13090, International Conference on Computer Application and Information Security (ICCAIS 2023), 130904B (8 April 2024); https://doi.org/10.1117/12.3025930

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

Feature extraction

Performance modeling

Convolution

Tumor growth modeling

Deep learning

Network architectures

Show All Keywords

Keywords/Phrases

Search In:

Publication Years