IMPLEMENTING SVM AND ISOLATION FOREST IN DETECTING AND RESOLVING SIP TRUNK ISSUES

The rise of Session Initiation Protocol (SIP) trunks has significantly enhanced voice communications in contact centers, offering benefits such as cost efficiency and scalability. However, these advancements also introduce technical challenges like call drops and network disruptions. Traditional manual detection methods delay issue resolution, resulting in prolonged downtimes and reduced service quality. This study identifies a critical gap: the need for proactive, real-time monitoring tools to detect and resolve SIP trunk issues before they impact users. To address this gap, the Automated SIP Trunk Guardian (ASTG) was developed, integrating machine learning algorithms such as Isolation Forest and One-Class Support Vector Machines (SVM) along with natural language processing (NLP) to automate detection and visualization of anomalies. The system was evaluated using 160 SIP incident samples and expert feedback guided by ISO/IEC 25010. Results demonstrated significant improvements over manual detection, including reduced mean time to detect (MTTD) and mean time to resolve (MTTR), increased precision, recall, and F-measure. This study contributes a practical, operationally validated framework for SIP trunk anomaly detection in contact centers, offering measurable improvements in service reliability and efficiency.

• Publication year

  2025

• Venue

  Journal of Artificial Intelligence

• Publication date

  2025-12-30

• Fields of study

  Not labeled

• Identifiers
  DOI 10.29121/shodhai.v2.i2.2025.60
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• AirNet: predictive machine learning model for air quality forecasting using web interface

  2024cited by this paper
• Future prospects: AI and machine learning in cloud-based SIP trunking

  2024cited by this paper
• An Efficient Support Vector Machine Algorithm Based Network Outlier Detection System

  2024cited by this paper
• Combating alert fatigue with AlertPro: Context-aware alert prioritization using reinforcement learning for multi-step attack detection

  2023cited by this paper
• Automatic Parsing and Utilization of System Log Features in Log Analysis: A Survey

  2023cited by this paper
• Anomaly Detection in Log Files Using Selected Natural Language Processing Methods

  2022cited by this paper
• Evaluation of the firewall influence on the session initiation by the SIP multimedia protocol

  2021cited by this paper
• Generalized isolation forest for anomaly detection

  2021cited by this paper
• Improving security using SVM-based anomaly detection: issues and challenges

  2020cited by this paper
• Detection

  2020cited by this paper
• Self-Supervised Log Parsing

  2020cited by this paper
• COMPREHENSIVE STUDY OF

  2018cited by this paper
• Review

  1998cited by this paper
• Challenges

  1991cited by this paper

• No citing papers are available for this paper.