Explainable Multi-Modal Data Analysis In Aiops: Enhancing Situational Awareness And Decision-Making
Journal of Software Engineering and Simulation · 2023
DOI: 10.35629/3795-09025054 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Software Engineering and Simulation, 2023. Verfasst von Shally Garg Shally Garg.
Abstract (Originalsprache)
As a crucial tool for IT management, artificial intelligence for IT operations (AIOps) uses vast amounts of data from several sources, including logs, metrics, and sensor data, to automate procedures, identify irregularities, and forecast system problems. AIOps systems' inherent complexity and lack of transparency, restrict their efficacy and credibility in decision-making. By producing comprehensible and interpretable explanations from diverse data sources, this study introduces a paradigm for explainable AI (XAI) in multimodal data analysis, with the goal of enhancing situational awareness and decision-making. In order to ensure transparency and consumer confidence in AI-driven forecasts, we suggest combining several data sources and applying XAI approaches like SHAP and LIME
Zitieren
APA
Garg, S. G. S. (2023). Explainable Multi-Modal Data Analysis In Aiops: Enhancing Situational Awareness And Decision-Making. Journal of Software Engineering and Simulation. https://doi.org/10.35629/3795-09025054
Vancouver
Garg SGS. Explainable Multi-Modal Data Analysis In Aiops: Enhancing Situational Awareness And Decision-Making. Journal of Software Engineering and Simulation. 2023. doi:10.35629/3795-09025054
BibTeX
@article{Garg2023,
author = {Garg, Shally Garg Shally},
title = {Explainable Multi-Modal Data Analysis In Aiops: Enhancing Situational Awareness And Decision-Making},
journal = {Journal of Software Engineering and Simulation},
year = {2023},
doi = {10.35629/3795-09025054}
}
EUVIMED