Abordagem Híbrida FuzzyNetClass: Uma Contribuição à Classificação do Tráfego de Streaming de Vídeo Integrando Lógica Fuzzy Valorada Intervalarmente e Aprendizagem de Máquina
Year: 2023
Type: dissertation
Abstract: mong the challenges for classifying network traffic, the maintenance of user pri vacy stands out based on cryptography and traffic obfuscation techniques. This chal lenge, associated with the dynamics and similarity between the protocols used by the \ndifferent services, as well as the typical oscillations in the operational conditions of the \nnetworks, which impact the analysis of the captured data, has made the use of clas sical methods for classification unfeasible. Considering this, the general goal of this \nThesis is the conception of a hybrid approach for network traffic classification, called \nFuzzyNetClass, directed to the current profile of use of computer networks and thus \nconsidering the uncertainties generated by fluctuations in the network resources of the \ninfrastructures shared, which are non-deterministic. More specifically, this work aims \nto contribute to the traffic classification related to video streaming, exploring the inte gration of inference systems based on interval-valued fuzzy logic and machine learning \nalgorithms. In this perspective, the FuzzyNetClass approach extends the related work \nby exploring learning algorithms that contribute to the classification of the proposed \nfuzzy control system, preserving aspects related to its interpretability for the involved \nspecialists. Among the FuzzyNetClass approach contributions, the following stand out: \n(i) classification based on the specialist’s knowledge and the exploration of multivalued \nfuzzy logic; (ii) hybrid classification, which has the potential to provide more reliable \nand more realistic results; and, (iii) the design of optimization mechanisms that come \nfrom the integration between machine learning techniques and inference based on \nmultivalued logic. Three case studies were discussed to evaluate the FuzzyNetClass \napproach’s contributions, considering datasets conceived from real network traffic cap tures. The results were promising and pointed to continuing study and research efforts.
Author: Monks, Eduardo Maroñas
Institution: Universidade Federal de Pelotas
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7035561543
