MDPI - Publisher of Open Access Journals

21 pages, 931 KiB

Open AccessArticle

Research on Integrated Learning Fraud Detection Method Based on Combination Classifier Fusion (THBagging): A Case Study on the Foundational Medical Insurance Dataset

by Jibing Gong, Hekai Zhang and Weixia Du

Electronics 2020, 9(6), 894; https://doi.org/10.3390/electronics9060894 - 27 May 2020

Cited by 6 | Viewed by 4269

Abstract

In recent years, the number of fraud cases in basic medical insurance has increased dramatically. We need to use a more efficient method to identify the fraudulent users. Therefore, we deploy the cloud edge algorithm with lower latency to improve the security and enforceability in the operation process. In this paper, a new feature extraction method and model fusion technology are proposed to solve the problem of basic medical insurance fraud identification. The feature second-level extraction algorithm proposed in this paper can effectively extract important features and improve the prediction accuracy of subsequent algorithms. In order to solve the problem of unbalanced simulation allocation in the medical insurance fraud identification scenario, a sample division method based on the idea of sample proportion equilibrium is proposed. Based on the above methods of feature extraction and sample division, a new training and fitting model fusion algorithm (tree hybrid bagging, THBagging) is proposed. This method makes full use of the balanced idea of the tree model algorithm based on Boosting to fuse, and finally achieves the effect of improving the accuracy of basic medical insurance fraud identification. Full article

(This article belongs to the Special Issue Recent Trends and Applications in Cybersecurity)

► Show Figures

Figure 1

22 pages, 2920 KiB

Open AccessArticle

Securing Health Sensing Using Integrated Circuit Metric

by Ruhma Tahir, Hasan Tahir and Klaus McDonald-Maier

Sensors 2015, 15(10), 26621-26642; https://doi.org/10.3390/s151026621 - 20 Oct 2015

Cited by 13 | Viewed by 6120

Abstract

Convergence of technologies from several domains of computing and healthcare have aided in the creation of devices that can help health professionals in monitoring their patients remotely. An increase in networked healthcare devices has resulted in incidents related to data theft, medical identity theft and insurance fraud. In this paper, we discuss the design and implementation of a secure lightweight wearable health sensing system. The proposed system is based on an emerging security technology called Integrated Circuit Metric (ICMetric) that extracts the inherent features of a device to generate a unique device identification. In this paper, we provide details of how the physical characteristics of a health sensor can be used for the generation of hardware “fingerprints”. The obtained fingerprints are used to deliver security services like authentication, confidentiality, secure admission and symmetric key generation. The generated symmetric key is used to securely communicate the health records and data of the patient. Based on experimental results and the security analysis of the proposed scheme, it is apparent that the proposed system enables high levels of security for health monitoring in resource optimized manner. Full article

(This article belongs to the Section Physical Sensors)

► Show Figures

Figure 1

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI