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

DP-SGD-global-adapt-V2-S: Triad improvements of privacy, accuracy and fairness via step decay noise multiplier and step decay upper clipping threshold DOI
Sai Venkatesh Chilukoti, Md Imran Hossen, Liqun Shan

et al.

Electronic Commerce Research and Applications, Journal Year: 2025, Volume and Issue: unknown, P. 101476 - 101476

Published: Feb. 1, 2025

Language: Английский

Citations

0
A Fuzzy-Bayesian belief network approach to compute efficiency as a metric for IoT systems DOI

Rishabh Deo Pandey,

Itu Snigdh

Soft Computing, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 10, 2025

Language: Английский

Citations

0
Facilitation or Replacement: ICT Use in Leisure Constraints Negotiation During the Digital Transformation Era DOI Open Access

Sung-Bum Chun,

Jinsun Lim,

Hee-Yeob Kang

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(4), P. 1503 - 1503

Published: Feb. 12, 2025

This study explores how Information and Communications Technology (ICT) impacts active leisure activity participants in South Korea, focusing on constraints negotiation strategies. As ICT continues to transform experiences, this research examines whether serves as a facilitator or replacement for traditional leisure. Using survey data from 285 adult participants, the categorizes ICT’s influence based framework. Key findings reveal that while time management energy conservation strategies shape use replacement, fitness level adjustments are associated with facilitative role These insights highlight nuanced ways digital tools impact participation, especially among various demographic groups. The suggest dual either supporting substituting reflects broader trends transformation informs development of aimed at enhancing well-being through engagement.

Language: Английский

Citations

0
Professional demand analysis for teaching Chinese to speakers of other languages: a text mining approach on internet recruitment platforms DOI Creative Commons
Xingrong Guo, Xingjia Wang, Yiming Guo

et al.

Humanities and Social Sciences Communications, Journal Year: 2025, Volume and Issue: 12(1)

Published: March 5, 2025

The rapid development of international education in China highlights the growing importance employment analysis Teaching Chinese to Speakers Other Languages (TCSOL). This study explores enterprise demands for TCSOL professionals using text mining techniques analyze recruitment data collected from four major platforms: Boss Zhipin, Zhaopin.com, 51job.com, and Liepin.com. Combining descriptive statistics, LDA topic modeling, BERT-BiLSTM-CRF-based named entity recognition, co-occurrence network were used. Results show that there is a high demand professionals, especially small-scale enterprises located first-tier cities such as Beijing, Shanghai, Guangzhou, Shenzhen. Employers tend favor candidates with at least bachelor's degree 1–3 years work experience. model highlighted three central themes job descriptions, emphasizing shift toward more diverse skill set. Named recognition identified essential attributes "communication ability", "teaching experience", "bachelor's or above" "responsibility" core requirements. revealed "teaching" "priority" nodes. Time series showed seasonal fluctuations demand, peaking during spring graduation periods. A hierarchical talent proposed, integrating perspectives employers, seekers, educators, policymakers. provides valuable insights aspiring offering guidance better align training market needs improve prospects.

Language: Английский

Citations

0
Investigating the Influence of Augmented Reality Marketing Application on Consumer Purchase Intentions: A Study in the E-commerce Sector DOI Creative Commons
Thi Thuy An Ngo, Thanh Tu Tran, Gia Khuong An

et al.

Computers in Human Behavior Reports, Journal Year: 2025, Volume and Issue: unknown, P. 100648 - 100648

Published: March 1, 2025

Language: Английский

Citations

0
STID-Net: Optimizing Intrusion Detection in IoT with Gradient Descent DOI Creative Commons

H. James Deva Koresh,

D. Usha Nandini, Kalaichelvi Nallusamy

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(6), P. 1852 - 1852

Published: March 17, 2025

The rapid evolution of IoT environment in medical and industrial applications has led to an increase network vulnerabilities, making intrusion detection system a critical requirement. Existing methods often struggle capturing complex irregular patterns from dynamic data, them not suitable for different applications. To address these limitations, this work proposes STID-Net that integrated customized convolutional kernels spatial feature extraction LSTM layers temporal sequence modelling. Unlike traditional models, improved ability identify datasets. This is also equipped with attention mechanism enhancing the long-term dependencies patterns. experimented MBGD SGD optimizers, we are satisfied performance optimizer both IoMT IIoT optimized model provides faster convergence better weight adjustments handling noisy datasets, it robust scalable diverse experimental demonstrates accuracy 97.14% 97.85% while attained 98.58% 99.15% optimization, respectively. proposed methodology outperforms standalone CNN models incorporated result indicates robustness scalability

Language: Английский

Citations

0
The competition between human and AI streamers: live streaming strategies in a duopoly market considering consumer heterogeneity DOI
Dequan Zheng, Yuemei Ding, Shizhen Bai

et al.

Acta Psychologica, Journal Year: 2025, Volume and Issue: 256, P. 105040 - 105040

Published: May 2, 2025

Language: Английский

Citations

0
Semi-supervised segmentation for primary nasopharyngeal carcinoma tumors using local-region constraint and mixed feature-level consistency DOI
Bin Zheng, Junying Zeng, Xiuping Zhang

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108389 - 108389

Published: April 13, 2024

Language: Английский

Citations

2
Assessing the Impact of Artificial Intelligence Tools on Employee Productivity: Insights from a Comprehensive Survey Analysis DOI Open Access
Sabina-Cristiana Necula, Doina Fotache,

Emanuel Rieder

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(18), P. 3758 - 3758

Published: Sept. 21, 2024

This study provides a nuanced understanding of AI’s impact on productivity and employment using machine learning models Bayesian Network Analysis. Data from 233 employees across various industries were analyzed logistic regression, Random Forest, XGBoost, with 5-fold cross-validation. The findings reveal that high levels AI tool usage integration within organizational workflows significantly enhance productivity, particularly among younger employees. A significant interaction between tools (β = 0.4319, p < 0.001) further emphasizes the importance comprehensive adoption. Analysis highlights complex interdependencies usage, innovation, employee characteristics. confirms strategic integration, along targeted training programs ethical frameworks, is essential for maximizing economic potential.

Language: Английский

Citations

2
New discrete fractional accumulation Grey Gompertz model for predicting carbon dioxide emissions DOI Creative Commons
Jianming Jiang,

Yandong Ban,

Ming Zhang

et al.

Frontiers in Environmental Science, Journal Year: 2024, Volume and Issue: 12

Published: Aug. 28, 2024

Predicting carbon dioxide emissions is crucial for addressing climate change and achieving environmental sustainability. Accurate emission forecasts provide policymakers with a basis evaluating the effectiveness of policies, facilitating design implementation reduction strategies, helping businesses adjust their operations to adapt market changes. Various methods, such as statistical models, machine learning, grey prediction have been widely used in prediction. However, existing research often lacks comparative analysis other forecasting techniques. This paper constructs new Discrete Fractional Accumulation Grey Gompertz Model (DFAGGM(1,1) based on system theory provides detailed solution process. The Whale Optimization Algorithm (WOA) find hyperparameters model. By comparing it five benchmark DFAGGM(1,1) predicting data China United States validated.

Language: Английский

Citations

1