Spatial Crowdsourcing Quality Control Model Based on K-Anonymity Location Privacy Protection and ELM Spammer Detection

Mengjia Zeng,Bo Zheng,Zhaolin Cheng,Xu Huang

doi:10.1155/2019/2723686

Abstract

The spatial crowdsourcing task places workers at a risk of privacy leakage. If positional information is not required to submit, it will result in an increased error rate and number of spammers, which together affects the quality of spatial crowdsourcing. In this paper, a spatial crowdsourcing quality control model is proposed, called SCQCM. In the model, the spatial k-anonymity algorithm is used to protect the position privacy of the general spatial crowdsourcing workers. Next, an ELM (extreme learning machine) algorithm is used to detect spammers, while an EM (expectation maximization) algorithm is used to estimate the error rate. Finally, different parameters are selected, and the efficiency of the model is simulated. The results showed that the spatial crowdsourcing model proposed in this paper guaranteed the quality of crowdsourcing projects on the premise of protecting the privacy of workers.

Highlights

Computer-supported collaborative work is an exciting research field [1], wherein “crowdsourcing” is an importantE topic
At the request of the authors, the article titled “Spatial Crowdsourcing Quality Control Model Based on K-Anonymity Location Privacy Protection and extreme learning machine (ELM) Spammer Detection” [1] has been retracted. e authors found in a recent experiment that a serious error was caused by the server hardware failure, so the paper was written based on incorrect data and there was a big deviation in the argument
What we aim to find is a balance between privacy protection and the quality control of workers in SC

Summary

Introduction

Computer-supported collaborative work is an exciting research field [1], wherein “crowdsourcing” is an important. In 2002, Sweeney [7] put forward the K-anonymity privacy protection technology to solve the problem of personal and sensitive data leakage On this basis, additional researchers further proposed a number of improved algorithms, such as the L-diversity method [8],. All the above studies have proved that K-anonymity algorithms can solve the privacy leakage problem in spatial crowdsourcing scenarios. In practical application scenarios of SC, workers need to submit their own location information to the crowdsourcing service platform, which has the risk of privacy leakages.

Problem Solving Ideas

Privacy Protection Model Based on Spatial Anonymity

D Quality control

(7) 3. Experiments

E Figure 4

Analysis of the Experimental Results