Journal of Retailing and Consumer Services, Год журнала: 2024, Номер 82, С. 104110 - 104110
Опубликована: Окт. 4, 2024
Язык: Английский
Journal of Retailing and Consumer Services, Год журнала: 2024, Номер 82, С. 104110 - 104110
Опубликована: Окт. 4, 2024
Язык: Английский
Journal of Retailing and Consumer Services, Год журнала: 2023, Номер 73, С. 103363 - 103363
Опубликована: Апрель 26, 2023
Язык: Английский
Процитировано
60IEEE Access, Год журнала: 2024, Номер 12, С. 51630 - 51649
Опубликована: Янв. 1, 2024
Software Defined Networks (SDN) offer dynamic reconfigurability and scalability, revolutionizing traditional networking. However, countering Distributed Denial of Service (DDoS) attacks remains a formidable challenge for both SDN-based networks. The integration Machine Learning (ML) into SDN holds promise addressing these threats. While recent research demonstrates ML's accuracy in distinguishing legitimate from malicious traffic, it faces difficulties handling emerging, low-rate, zero-day DDoS due to limited feature scope training. ever-evolving landscape, driven by new protocols, necessitates continuous ML model retraining. In response challenges, we propose an ensemble online machine-learning designed enhance detection mitigation. This approach utilizes learning adapt the with expected attack patterns. is trained evaluated using simulation (Mininet Ryu). Its selection capability overcomes conventional limitations, resulting improved across diverse types. Experimental results demonstrate remarkable 99.2% rate, outperforming comparable models on our custom dataset as well various benchmark datasets, including CICDDoS2019, InSDN, slow-read-DDoS. Moreover, proposed undergoes comparison industry-standard commercial solutions. work establishes strong foundation proactive threat identification mitigation environments, reinforcing network security against evolving cyber risks.
Язык: Английский
Процитировано
19Journal of Retailing and Consumer Services, Год журнала: 2024, Номер 81, С. 103967 - 103967
Опубликована: Июнь 27, 2024
Язык: Английский
Процитировано
18Complex & Intelligent Systems, Год журнала: 2021, Номер 8(2), С. 1781 - 1801
Опубликована: Авг. 28, 2021
Topical treatments with structural equation modelling (SEM) and an artificial neural network (ANN), including a wide range of concepts, benefits, challenges anxieties, have emerged in various fields are becoming increasingly important. Although SEM can determine relationships amongst unobserved constructs (i.e. independent, mediator, moderator, control dependent variables), it is insufficient for providing non-compensatory constructs. In contrast previous studies, newly proposed methodology that involves dual-stage analysis ANN was performed to provide linear Consequently, numerous distinct types studies diverse sectors conducted hybrid SEM-ANN analysis. Accordingly, the current work supplements academic literature systematic review includes all major techniques used 11 industries published past 6 years. This study presents state-of-the-art classification taxonomy based on compares effort domains classification. To achieve this objective, we examined Web Science, ScienceDirect, Scopus IEEE Xplore® databases retrieve 239 articles from 2016 2021. The obtained were filtered basis inclusion criteria, 60 selected classified under categories. multi-field uncovered new research possibilities, motivations, challenges, limitations recommendations must be addressed synergistic integration multidisciplinary studies. It contributed two points potential future resulting developed taxonomy. First, importance determinants play, musical art therapy adoption autistic children within healthcare sector most important consideration investigations. context, second use barriers adopting sensing-enhanced satisfy provided by sector. indicates manufacturing technology number investigations, whereas construction small- medium-sized enterprise least. will helpful reference academics practitioners guidance insightful knowledge
Язык: Английский
Процитировано
80Journal of Business Research, Год журнала: 2023, Номер 173, С. 114453 - 114453
Опубликована: Дек. 28, 2023
We propose a routine for combining partial least squares-structural equation modeling (PLS-SEM) with selected machine learning (ML) algorithms to exploit the two method's causal-predictive and causal-exploratory capabilities. Triangulating these methods can improve predictive accuracy of research models, enhance understanding relationships, assist in identifying new relationships therewith contribute theorizing. demonstrate advantages challenges triangulating on an illustrative example along four-step-routine: (1) Develop PLS-SEM baseline conceptual model use its standards assess measurement quality generate latent variables scores. (2) Apply specific ML extracted data validate identify (linear) that may go beyond initial hypotheses; similarly, advancements form nonlinearities interaction effects. (3) Evaluate theoretical plausibility alternative models. (4) Integrate models compare using recently proposed prediction-oriented test procedure PLS-SEM.
Язык: Английский
Процитировано
30International Journal of Information Management, Год журнала: 2023, Номер 72, С. 102662 - 102662
Опубликована: Май 13, 2023
Язык: Английский
Процитировано
26Electronic Commerce Research, Год журнала: 2025, Номер unknown
Опубликована: Фев. 12, 2025
Язык: Английский
Процитировано
1Chaos Solitons & Fractals, Год журнала: 2021, Номер 153, С. 111445 - 111445
Опубликована: Ноя. 14, 2021
Язык: Английский
Процитировано
56Arabian Journal for Science and Engineering, Год журнала: 2022, Номер 48(2), С. 1693 - 1714
Опубликована: Июнь 21, 2022
Язык: Английский
Процитировано
26Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 124, С. 106643 - 106643
Опубликована: Июнь 26, 2023
Язык: Английский
Процитировано
14