Anomaly Detection and Downtime Prediction in Server Logs Using Hybrid Machine Learning

View Sample PDF

Author(s): Swati Gandhi (Anantrao Pawar College of Engineering and Research, Pune, India), Sharda Yashwant Salunkhe (Sharad Institute of Technology, College of Engineering, Kolhapur, India), Dipa Dattatray Dharmadhikari (Maharashtra Institute of Technology, India), Ajit Patil (Bharati Vidyapeeth's College of Engineering, Pune, India), Yogesh Uttamrao Bodhe (Government Polytechnic, Pune, India), Sonali Bhoite (Vishwakarma Institute of Technology, Pune, India), Kuldeep Vayadande (Vishwakarma Institute of Technology, Pune, India)and Rahul Mirajkar (Bharati Vidyapeeth's College of Engineering, Kolhapur, India)
Copyright: 2026
Pages: 22
Source title: Cyber Forensic Frameworks for User-Centric Human Threat Intelligence Analysis
Source Author(s)/Editor(s): Seifedine Kadry (Lebanese American University, Lebanon), Mritunjay Rai (Shri Ramswaroop Memorial University, Barabanki, India)and Padmesh Tripathi (Delhi Technical Campus, Greater Noida, India)
DOI: 10.4018/979-8-3373-4898-8.ch011

Keywords: Cyber and Network Security / Information Science Reference / Intelligent Technologies / Knowledge Management and Library Science

Purchase

View Anomaly Detection and Downtime Prediction in Server Logs Using Hybrid Machine Learning on the publisher's website for pricing and purchasing information.

Abstract

In this paper, we propose a forensic framework that is able to forecast downtime errors at the server level based on anomaly detection to system logs, converted into features according to machine learning (ML) algorithms. We used hybrid of ML model, based on Isolation Forest and One-Class SVM algorithms for encoding normal patterns of behaviour systems to annotate deviations from the norm. Detailed log file parsing of any log files of interest, feature extraction, and weighted scoring in combining anomalies were among the actions included in my approach. The hybrid model achieved 99.54% accuracy on real-world live-server log validation data and 95.08% in recall, consistent with individual models, making it a not-so-common occurrence. It identified high-risk periods and scheduled the preventive maintenance. This shows the practical way to bring into predictive IT operations log analysis using ML techniques, which in turn answers a very direct critical need for improved reliability of infrastructure. Future work will be pointed toward this dimension in view of limitations related to dataset scope and sensitivity of models to changes in log format.

The IRMA Community

Research IRM

Anomaly Detection and Downtime Prediction in Server Logs Using Hybrid Machine Learning

Purchase

Abstract

Related Content

IRMA Sponsors