Signal waveform detection with statistical automaton for internet and web service streaming

Area of Science:

• Computer Science
• Network Security
• Data Analysis

Background:

• Internet and web streaming detection is crucial for network management and security.
• Existing methods for streaming detection have limitations.
• The need for efficient and accurate streaming detection techniques is growing.

Purpose of the Study:

• To propose a novel approach for Internet and web streaming detection using statistical automatons.
• To develop and evaluate two versions of waveform automata: basic Aho-Corasick (AC) and advanced AC-histogram.
• To demonstrate the feasibility and suitability of the proposed method for practical deployment.

Main Methods:

• Recording network connections over time to generate signal waveforms.
• Computing suspicious characteristics from the signal waveforms.
• Classifying network streaming using waveform features with newly designed Aho-Corasick (AC) automatons.
• Developing and experimenting with basic AC and advanced AC-histogram waveform automata.

Main Results:

• The proposed approach successfully detects Internet and web streaming.
• The AC-histogram automaton shows enhanced performance in classifying streaming data.
• Comprehensive experimentation validates the effectiveness of the developed methods.
• The system demonstrates feasibility and suitability for deployment in real-world scenarios.

Conclusions:

• The novel statistical automaton approach provides an effective solution for Internet and web streaming detection.
• The developed AC and AC-histogram automata are capable of accurate network streaming classification.
• The findings support the practical applicability of this method in network monitoring and security.