EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Intelligent Decommissioning of Workstation From Network to Avoid Human Error, Prevent Data Theft and Data Protection

G. Priyadharshini

Journal of Intelligent Decision Making and Information Science · 23.09.2026 · 3 (14s) · 373-397

DOI: 10.17762/jidmis.v3.4096 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 23.09.2026. Verfasst von G. Priyadharshini. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Decommissioning workstations in a modern enterprise network is subject to human error, data leakage and cyber threat. In this study we introduce a hybrid deep learning framework, namely DBAC-DI (Deep Behavioural Adaptive Control for Decommissioning Intelligence), which is based on the TON_IoT network dataset for the secure retirement of workstations. The framework consists of data preprocessing, feature engineering, generation of temporal sequences, risk prediction, and automated enforcement. Raw telemetry data is pre-processed using missing value handling, label encoding, and RobustScaler normalization. These behavioural characteristics like CPU utilization, memory usage, network traffic etc. are extracted to model the activity of workstations. Sliding window segmentation produces temporal sequences to learn short- and long-term dependencies. This basic model integrates a Temporal Dependency Learning Module, a Local Behavioural Pattern Extractor, and a Latent Anomaly Reconstruction Unit for hierarchical risk detection. Using risk scores derived from the computation, network isolation and adaptive sanitization (logical wipe, overwrite, cryptographic erase). A secure audit logging provides traceability and compliance. Finally, a fusion strategy, which combines the hybrid deep learning and rule-based approaches, infers the final decision of decommissioning, which will enhance reliability, lessen operational risk, and lessen human intervention in secure workstation decommissioning. In the experimental evaluation, the proposed framework achieves an impressive accuracy of 98% for all three precision, recall, and F1-scores, reflecting its strength in the field of decommissioning workstations.

Zitieren

APA

Priyadharshini, G. (2026). Intelligent Decommissioning of Workstation From Network to Avoid Human Error, Prevent Data Theft and Data Protection. Journal of Intelligent Decision Making and Information Science, 3(14s), 373-397. https://doi.org/10.17762/jidmis.v3.4096

Vancouver

Priyadharshini G. Intelligent Decommissioning of Workstation From Network to Avoid Human Error, Prevent Data Theft and Data Protection. Journal of Intelligent Decision Making and Information Science. 2026;3(14s):373-397. doi:10.17762/jidmis.v3.4096

BibTeX
@article{Priyadharshini2026,
  author = {Priyadharshini, G.},
  title = {Intelligent Decommissioning of Workstation From Network to Avoid Human Error, Prevent Data Theft and Data Protection},
  journal = {Journal of Intelligent Decision Making and Information Science},
  year = {2026},
  volume = {3},
  number = {14s},
  pages = {373--397},
  doi = {10.17762/jidmis.v3.4096}
}
Kostenlos starten →