Syed, Waseem (2025) Revolutionizing mobile platform engineering: AI-driven event logging for enhanced performance and cost efficiency. International Journal of Science and Research Archive, 14 (1). pp. 1221-1231. ISSN 2582-8185
![IJSRA-2025-0152.pdf [thumbnail of IJSRA-2025-0152.pdf]](https://eprint.scholarsrepository.com/style/images/fileicons/text.png)
IJSRA-2025-0152.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial Share Alike.
Abstract
Mobile platform engineering faces unique challenges that impact performance and operational costs. This article explores the revolutionary potential of AI-driven event-logging systems in addressing these issues. By transitioning from traditional to AI-enhanced logging techniques, we significantly enhance performance through machine learning-based log prioritization, generative AI for root cause analysis, and efficient local event chain caching. This study provides a comparative analysis of conventional methods versus AI-driven systems, highlighting substantial improvements in error detection, system reliability, and cost efficiency. Real-world implementations and theoretical frameworks demonstrate how these advanced logging systems meet mobile-specific requirements such as protocol-agnostic logging, network state management, and battery optimization. The findings suggest that AI-driven logging not only transforms mobile platform engineering through enhanced operational performance but also provides scalable solutions that can adapt to evolving technological landscapes.
Item Type: | Article |
---|---|
Official URL: | https://doi.org/10.30574/ijsra.2025.14.1.0152 |
Uncontrolled Keywords: | Mobile Logging Systems; AI-Driven Event Logging; Protocol-Agnostic Logging; Resource Optimization; Error Detection Systems; Machine Learning Optimization; Event Chain Analysis; AI in System Reliability Enhancement; Intelligent Error Logging; AI-Driven Analytics |
Depositing User: | Editor IJSRA |
Date Deposited: | 15 Jul 2025 15:20 |
Related URLs: | |
URI: | https://eprint.scholarsrepository.com/id/eprint/734 |