Journal of Cloud Computing

References Fadhil ISM, Nizar NBM, Rostam RJ (2023) Security and privacy issues in cloud computing. Authorea Preprints Google Scholar Jimmy FNU (2024) Cyber security vulnerabilities and remediation through cloud security tools. J Educ Chang Artif Intel Gener Sci (JAIGS) ISSN: 3006–4023 2(1):129–171 Google Scholar Suhana S, Karthic S, Yuvaraj N (2023 January) Ensemble based dimensionality reduction for intrusion detection using random forest in wireless networks.

The device type can be identified during the initial network connection stage to set a reasonable control strategy. As previously mentioned, we focus on the fine-grained distinction of similar devices, so the experimental data should cover the utmost range of device types with an emphasis on incorporating devices with similar functions or from the same brand.

References Abrera J (2024) Data privacy and security in cloud computing: a comprehensive review. J Comput Sci Inform: 1–13. https://doi.org/10.61424/jcsit Accenture (2023) How cybersecurity boosts enterprise reinvention to drive business resilience 2023, pp. 1–39. Available at: https://www.accenture.com/content/dam/accenture/final/accenture-com/document/Accenture-State-Cybersecurity.pdf#zoom=40 Aissaoua H et al. (2024). Ingénierie des Systèmes d’Information. 29(5).

References Levitin G, Xing L, Xiang Y (2022) Co-residence data theft attacks on n-version programming-based cloud services with task cancelation. IEEE Trans Syst Man Cybern Syst 52(1):324–333. https://doi.org/10.1109/TSMC.2020.3002930 Saxena D, Gupta I, Gupta R, Singh AK, Wen X (2023) An ai-driven vm threat prediction model for multi-risks analysis-based cloud cybersecurity. IEEE Trans Syst Man Cybern Syst 53(11):6815–6827.

In this section, we review three key research areas that inform our work: (1) style-aware recommendation in art and visual domains, (2) compatibility modeling and group-based recommendation, and (3) graph-based methods for structured recommendation. Style plays a central role in how users perceive, interpret, and engage with visual content.

We conduct experiments on all smart contracts collected from the State of the DApps platform as well as the Etherscan platform, and the implementation of our vulnerability detection system is available at https://github.com/limiaoer/GaGATVulDet. In this section, we aim to answer the following research questions: RQ1: Does the method effectively detect vulnerabilities related to reentrancy, Tx.origin, callDepth, TOD, timestamp dependence and infinite loop?

The HTBP algorithm is proposed for partitioning periodic real-time tasks on a non-ideal DVFS multicore processor with shared resources. Dynamic-priority-based scheduling is considered for this research due to its higher utilization limit compared to fixed-priority approaches.

In this section, we introduce a hybrid POI recommendation model PRAS that combines ARIMA and SVD for effective user preference analysis and preference-aware POI prediction based on real-time and historical user data.

Traditional machine learning algorithms such as Support Vector Machines (SVM), Random Forests, and k-Nearest Neighbors (KNN) are widely used in wearable health analytics, for the public especially for the young student community, due to their efficiency in feature extraction and classification. Literature [44] proposed an SVM-based classification model for heart rate variability (HRV) analysis using wearable biosensors.

References Selvaraj S, Sundaravaradhan S (2020) Challenges and opportunities in IoT healthcare systems: a systematic review. SN Appl Sci 2:139 Google Scholar Abadi ZJK, Mansouri N, Khalouie M (2023) Task scheduling in fog environment-challenges, tools & methodologies: a review. Comput Sci Rev 48:100550 MathSciNet Google Scholar Murad SA, Muzahid AJM, Azmi ZRM et al (2022) A review on job scheduling technique in cloud computing and priority rule based intelligent framework.