Online public opinion prediction based on a novel conformable fractional discrete grey model DOI Creative Commons
Feng Feng, Xiaoxiao Ge, Stefania Tomasiello

et al.

Kybernetes, Journal Year: 2024, Volume and Issue: 53(13), P. 72 - 100

Published: Nov. 27, 2024

Purpose As social networks have developed to be a ubiquitous platform of public opinion spreading, it becomes more and crucial for maintaining security stability by accurately predicting various trends dissemination in networks. Considering the fact that online is dynamic process full uncertainty complexity, this study establishes novel conformable fractional discrete grey model with linear time-varying parameters, namely CFTDGM(1,1) model, accurate prediction trends. Design/methodology/approach First, accumulation difference operators are employed build enhancing traditional integer-order parameters. Then, improve forecasting accuracy, base value correction term introduced optimize iterative model. Next, differential evolution algorithm selected determine optimal order proposed through comparison whale optimization particle swarm algorithm. The least squares method utilized estimate parameter values In addition, effectiveness tested event about “IG team winning championship”. Finally, we conduct empirical analysis on two hot events regarding “Chengdu toddler mauled Rottweiler” “Mayday band suspected lip-syncing,” further assess ability applicability seven other existing models. Findings test case recent reveal outperforms most models terms performance. Therefore, chosen forecast development these events. results indicate attention both will decline slowly over next three days. Originality/value A help has higher accuracy feasibility trend prediction.

Language: Английский

Multi-step carbon emissions forecasting using an interpretable framework of new data preprocessing techniques and improved grey multivariable convolution model DOI
Song Ding, Juntao Ye, Zhijian Cai

et al.

Technological Forecasting and Social Change, Journal Year: 2024, Volume and Issue: 208, P. 123720 - 123720

Published: Sept. 4, 2024

Language: Английский

Citations

8
A residual learning-based grey system model and its applications in Electricity Transformer’s Seasonal oil temperature forecasting DOI
Yiwu Hao, Xin Ma, Lili Song

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 147, P. 110260 - 110260

Published: Feb. 25, 2025

Language: Английский

Citations

1
The Interplay of Browsing Behaviors, Social Identity, and Benign Envy in Shaping Impulse Buying on E-Commerce Platforms: Evidence from France DOI

Felicito Jabutay,

Andrianasolo Ravalisaona Dera Nirina,

Ambre-Elise Cetaire

et al.

Journal of Internet Commerce, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 32

Published: March 19, 2025

Language: Английский

Citations

1
Advancing credit risk modelling with Machine Learning: A comprehensive review of the state-of-the-art DOI

André Aoun Montevechi,

Rafael de Carvalho Miranda, André Luiz Medeiros

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 137, P. 109082 - 109082

Published: Aug. 3, 2024

Language: Английский

Citations

8
Review of Smart-Home Security Using the Internet of Things DOI Open Access

G. E. Vardakis,

George Hatzivasilis,

Eleftheria Koutsaki

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(16), P. 3343 - 3343

Published: Aug. 22, 2024

As the Internet of Things (IoT) continues to revolutionize way we interact with our living spaces, concept smart homes has become increasingly prevalent. However, along convenience and connectivity offered by IoT-enabled devices in comes a range security challenges. This paper explores landscape smart-home security. In contrast similar surveys, this study also examines particularities popular categories devices, like home assistants, TVs, AR/VR, locks, sensors, etc. It various threats vulnerabilities inherent ecosystems, including unauthorized access, data breaches, device tampering. Additionally, discusses existing mechanisms protocols designed mitigate these risks, such as encryption, authentication, intrusion-detection systems. Furthermore, it highlights importance user awareness education maintaining environments. Finally, proposes future research directions recommendations for enhancing IoT, development robust best practices standards, improved authentication methods, more effective techniques. By addressing challenges, potential enhance efficiency while ensuring privacy, security, cyber-resilience can be realized.

Language: Английский

Citations

5
A Secure Medical Information Storage and Sharing Method Based on Multiblockchain Architecture DOI
Jian Hu, Peng Zhu, Juanjuan Li

et al.

IEEE Transactions on Computational Social Systems, Journal Year: 2024, Volume and Issue: 11(5), P. 6392 - 6406

Published: April 16, 2024

With the increasing application of technology in healthcare industry, it has become imperative to establish a robust medical information ecosystem for effective management secure storage and sharing. This article proposes healthier collaboration with main consortium chain data side chain, using multiblockchain architecture. In implementation methods this ecosystem, we store JavaScript Object Notation (JSON) format within different structures. Additionally, introduce an improved Practical Byzantine Fault Tolerant (PBFT) consensus mechanism based on point nomination system dynamic RBAC access mechanism. By simulating blockchain environment multiple nodes, analyze efficiency method terms record retrieval, mechanism, execution time. The results demonstrate that compared single structure, proposed achieves substantial 30% improvement query time efficiency. Moreover, PBFT outperforms traditional algorithm without dishonest nodes. Medical records stored JSON require shorter text records. research contributes toward enhancing security sharing among subject systems, thereby fostering alliance ecosystem.

Language: Английский

Citations

4
Forecasting personal heat strain under extremely hot environments: Utilizing feature importance in machine learning DOI Creative Commons
Seungwon Seo, Yujin Choi, Choongwan Koo

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108507 - 108507

Published: May 6, 2024

Since the frequency and intensity of heatwaves are expected to increase due global warming, it is crucial establish a simplified approach preventing personal heat-related illnesses as occupational hazard under extremely hot environments, by taking into account individual differences in heat strain. In light this, this study proposed forecast model for strain environments utilizing feature importance machine learning, focused on enhancing its field applicability. Using 1417 records gathered from experiments conditions, was developed four types learning algorithms (i.e., random forest, extreme gradient boosting, support vector regression, multi-layer perceptron). As result, models with principal features dry-bulb temperature, radiant relative humidity, percentage body fat) were found be most reliable, resulting small difference 0.047 °C compared reference model. biometric can easily measured simple low-cost composition test (but not physical measurement core temperature) before they put field, will aid providing more systematic efficient management system proactively illnesses. Furthermore, that applicability continuously enhanced accumulated big data field-based living-lab projects over lengthy period.

Language: Английский

Citations

4
Security Evaluation of Provably Secure ECC-Based Anonymous Authentication and Key Agreement Scheme for IoT DOI Creative Commons
Kisung Park, Myeonghyun Kim, Youngho Park

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(1), P. 237 - 237

Published: Jan. 3, 2025

The proliferation of the Internet Things (IoT) has worsened challenge maintaining data and user privacy. IoT end devices, often deployed in unsupervised environments connected to open networks, are susceptible physical tampering various other security attacks. Thus, robust, efficient authentication key agreement (AKA) protocols essential protect privacy during exchanges between devices servers. previous work “Provably Secure ECC-Based Anonymous Authentication Key Agreement for IoT” proposed a novel AKA scheme secure environments. They claimed their protocol offers comprehensive features, guarding against numerous potential flaws while achieving session security. However, this paper demonstrates through logical mathematical analyses that is vulnerable We conducted analysis using extended Canetti Krawczyk (eCK) model, which widely employed evaluations. This model considers scenarios where an attacker complete control over network, including ability intercept, modify, delete messages, also accounting exposure ephemeral private keys. Furthermore, we show fails meet critical requirements relies on flawed assumptions. prove our findings automated validation internet applications, recognized formal verification tool. To strengthen attack resilience, propose several recommendations advancement more robust specifically designed

Language: Английский

Citations

0
Novel disctete grey Bernoulli seasonal model with a time powter term for predicting monthly carbon dioxide emissions in the United States DOI Creative Commons
Jianming Jiang,

Yandong Ban,

Nong Sheng

et al.

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 3, 2025

This study proposes a more efficient discrete grey prediction model to describe the seasonalvariation trends of carbon dioxide emissions. The setting bernoulli parameter and time powerterm in new ensures that can capture trend nonlinear changesin sequence. At same time, inclusion dummy variables allows for direct simulationof seasonal fluctuations emissions without need additional treatment theseasonality optimal search model’s hyperparameters is achieved using MPA algorithm. constructed applied monthly U.S. datafrom January 2003 December 2022, total 240 months. trained on 216 months 2020, data from 2021 2022 usedfor prediction, which then compared with actual values. results show proposed modelexhibits higher forecasting performance SARIMA other models. Therefore, this methodcan effectively simulate variation emissions, providing valuablereference information relevant departments formulate effective policies.

Language: Английский

Citations

0
A contracted container-based code component collaboration model with reusable but invisible right management DOI
Wei Wang, Zhenping Xie

Information Processing & Management, Journal Year: 2025, Volume and Issue: 62(3), P. 104057 - 104057

Published: Jan. 8, 2025

Language: Английский

Citations

0