scholarly journals Detection of fake-video uploaders on social media using Naive Bayesian model with social cues

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xiaojun Li ◽  
Shaochen Li ◽  
Jia Li ◽  
Junping Yao ◽  
Xvhao Xiao
Keyword(s):  
Bayesian Model ◽  
Rapid Development ◽  
Social Cues ◽  
The Internet ◽  
Feature Combination ◽  
Naive Bayesian ◽  
Naïve Bayesian ◽  
Proposed Model ◽  
Optimal Feature ◽  
Search And Recognition

AbstractWith the rapid development of the Internet, the wide circulation of disinformation has considerably disrupted the search and recognition of information. Despite intensive research devoted to fake text detection, studies on fake short videos that inundate the Internet are rare. Fake videos, because of their quick transmission and broad reach, can increase misunderstanding, impact decision-making, and lead to irrevocable losses. Therefore, it is important to detect fake videos that mislead users on the Internet. Since it is difficult to detect fake videos directly, we probed the detection of fake video uploaders in this study with a vision to provide a basis for the detection of fake videos. Specifically, a dataset consisting of 450 uploaders of videos on diabetes and traditional Chinese medicine was constructed, five features of the fake video uploaders were proposed, and a Naive Bayesian model was built. Through experiments, the optimal feature combination was identified, and the proposed model reached a maximum accuracy of 70.7%.

scholarly journals Crash Risk Assessment of Off-Ramps, Based on the Gaussian Mixture Model Using Video Trajectories

2020 ◽  
Vol 12 (8) ◽  
pp. 3076
Author(s):  
Ting Xu ◽  
Yanjun Hao ◽  
Shichao Cui ◽  
Xingqi Wu ◽  
Zhishun Zhang ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Bayesian Model ◽  
Logistic Regression Model ◽  
Gaussian Mixture ◽  
Ordinal Logistic Regression ◽  
Crash Risk ◽  
Naive Bayesian ◽  
Naïve Bayesian ◽  
Ordinal Logistic Regression Model

The focus of this paper is the crash risk assessment of off-ramps in Xi’an. The time-to-collision (TTC) is used for the measurement and cross-comparison of the crash risk of each location. Five sites from the urban expressway in Xi’an were selected to explore the TTC distribution. An unmanned aerial vehicle and a camera were used to collect traffic flow data for 20 min at each site. The parameters, including speed, deceleration rate, truck percentage, traffic volume, and vehicle trajectories, were extracted from video images. The TTCs were calculated for each vehicle. The Gaussian mixture model (GMM) was proposed to predict the TTC probability density functions (PDFs) and cumulative density functions (CDFs) for five sites. The Kolmogorov–Smirnov (K-S) test indicated that the samples followed the estimated GMM distribution. The relationship between the crash risk level and influencing factors was studied by an ordinal logistic regression model and a naive Bayesian model. The results showed that the naive Bayesian model had an accuracy of 86.71%, while the ordinal logistic regression model had an accuracy of 84.81%. The naive Bayesian model outperformed the ordinal logistic regression model, and it could be applied to the real-time collision warning system.

scholarly journals A Zero-Proof Knowledge Based on NFC for Data Authentication/Protection using Blockchain for Mobile Edge Computing

2020 ◽  
Vol 8 (6) ◽  
pp. 2547-2552
Keyword(s):  
Web Application ◽  
Rapid Development ◽  
Edge Computing ◽  
The Internet ◽  
Mobile Edge Computing ◽  
Everyday Objects ◽  
Knowledge Based ◽  
Data Authentication ◽  
Proposed Model ◽  
The Internet Of Things

Mobile edge computing is a recent trend to complement the Internet of Things (IoT) ecosystem in the computing sector. IoT is the internet connected communications related to physical devices and everyday objects. The emergence of intelligent living spaces has been due to the rapid development of IoT technologies. Blockchain is one such technology that expands the list of information also referred to like records that are saved as blocks in the Blockchain which are connected using cryptographic algorithms. Within a Blockchain IoT environment, when data or device authentication information is stored in a Blockchain, authentication information can be displayed when verifying Block chain’s transactions, which are also referred to as proof of work. A principle of Zero-knowledge proof (ZKF) is implemented in this paper which is a way of proving that knowledge is known without exposing any data to the user. The proposed model uses a Mobile application where users can prove without revealing users' passwords. Blockchain stores client information that can prevent data from being manipulated. The results of applying the ZKF theory for data security are shown through a web application and NFC.

scholarly journals A Cross-Chain Solution to Integrating Multiple Blockchains for IoT Data Management

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2042 ◽  
Author(s):  
Yiming Jiang ◽  
Chenxu Wang ◽  
Yawei Wang ◽  
Lang Gao
Keyword(s):  
Data Management ◽  
Rapid Development ◽  
The Internet ◽  
Privacy And Security ◽  
Security Issues ◽  
High Resource ◽  
Proposed Model ◽  
Effectiveness And Efficiency ◽  
Iot Devices ◽  
The Internet Of Things

With the rapid development of the internet of things (IoT), traditional industries are setting off a massive wave of digitization. In the era of the Internet of Everything, millions of devices and links in IoT pose more significant challenges to data management. Most existing solutions employ centralized systems to control IoT devices, which brings about the privacy and security issues in IoT data management. Recently, blockchain has attracted much attention in the field of IoT due to its decentralization, traceability, and non-tamperability. However, it is non-trivial to apply the current blockchain techniques to IoT due to the lack of scalability and high resource costs. Different blockchain platforms have their particular advantages in the scenario of IoT data management. In this paper, we propose a cross-chain framework to integrate multiple blockchains for efficient and secure IoT data management. Our solution builds an interactive decentralized access model which employs a consortium blockchain as the control station. Other blockchain platforms customized for specific IoT scenarios run as the backbone of all IoT devices. It is equivalent to opening the off-chain channels on the consortium blockchain. Our model merges transactions in these channels for confirmation based on the notary mechanism. Finally, we implement a prototype of the proposed model based on hyperledge Fabric and IOTA Tangle. We evaluate the performance of our method through extensive experiments. The results demonstrate the effectiveness and efficiency of our framework.

scholarly journals Prediction of algal bloom occurrence based on the naive Bayesian model considering satellite image pixel differences

2021 ◽  
Vol 124 ◽  
pp. 107416
Author(s):  
Meng Mu ◽  
Yunmei Li ◽  
Shun Bi ◽  
Heng Lyu ◽  
Jie Xu ◽  
...  
Keyword(s):  
Bayesian Model ◽  
Algal Bloom ◽  
Satellite Image ◽  
Naive Bayesian ◽  
Naïve Bayesian
Sign in / Sign up

Export Citation Format

Share Document