A Systematic Approach for Temporal Traffic Selection Across Various Applications

Abstract

The paper presents a framework that analyzes temporal traffic in applications, with a focus on statistical analysis and traffic classification. The framework utilizes time-based sampling and traffic flow selection to identify the characteristics of idle time, continuous traffic and burst threshold. It also includes time-based feature selection to improve the accuracy and efficiency of predictive models by removing irrelevant or redundant features. Our study involves exploratory data analysis and machine learning-based classification, and we found that our method improves application analysis in both statistical analysis and the precision of encrypted application traffic. We compared our approach to various state-of-the-art methods and consistently outperformed them in terms of performance. By focusing on traffic classification, our framework can benefit various domains such as Quality of Service (QoS) and security. For example, it can help network administrators identify and analyze various application characteristics, which can lead to better security measures. Overall, our approach offers a promising solution for improving temporal traffic analysis.