Computer Networks
Flow classification by Machine Learning • End-to-End QoS • Multimedia Streaming

About

This page presents my research in computer networks, including machine learning for traffic classification, adaptive streaming architectures, quality of service (QoS) mechanisms, and realistic performance evaluations. My recent focus is on high-performance data plane architectures and network resource management.

Publications

Journal Articles

  1. M. Soysal and E. G. Schmidt, "Machine Learning Algorithms for Accurate Flow-based Network Traffic Classification: Evaluation and Comparison," Performance Evaluation, Elsevier, vol. 67, no. 6, pp. 451–467, 2010.

Conference Papers

  1. T. Ç. Acar and E. G. Schmidt, "CBIBRS: Client-Side Best Initial Bitrate Selection for HTTP Adaptive Streaming," in 33rd Signal Processing and Communications Applications Conference (SIU), IEEE, 2025.
  2. M. F. Çemen and E. G. Schmidt, "Quality of Service Support for a 5G Network UPF Module: Software Implementation and Realistic Evaluation," in 32nd Signal Processing and Communications Applications Conference (SIU), IEEE, 2024.
  3. A. Öge and E. G. Schmidt, "Verimli Uyarlanabilir Akış (EFAST): Algoritma, Gerçekleştirim, Değerlendirme — EFficient Adaptive STreaming (EFAST): Algorithm, Implementation and Evaluation," in 26th Signal Processing and Communications Applications Conference (SIU), IEEE, 2018.
  4. M. Ozkardes and E. G. Schmidt, "CALMTV: A Cluster-Based Application Layer Multicast Architecture for IPTV," in IEEE Global Communications Conference (GLOBECOM), 2013.
  5. M. Soysal and E. G. Schmidt, "An Accurate Evaluation of Machine Learning Algorithms for Flow-based P2P Traffic Detection," in IEEE International Symposium on Computer and Information Sciences (ISCIS), 2007.
  6. S. E. (Guran) Schmidt and M. Soysal, "An Intrusion Detection-Based Approach for the Scalable Detection of P2P Traffic in the National Academic Network Backbone," in IEEE International Symposium on Computer Networks (ISCN), 2006.

Theses

  1. A UPF Module for 5G Networks with Quality of Service Support: Software Implementation and Realistic Evaluation, Mustafa Fatih Çemen, M.Sc. Thesis, Defense date: September 2023.
  2. A Link Delay Computation Method for the Quality of Service Support in Software Defined Networks, Efe Balo, M.Sc. Thesis, Defense date: September 2019.
  3. Efficient and Fair Adaptive Streaming: Algorithm, Implementation and Evaluation, Ahmet Öge, M.Sc. Thesis, Defense date: June 2017.
  4. TZAR – Time Zone Based Approximation To Ring: An Autonomous Protection Switching Algorithm for Globally Resilient Optical Transport Networks, Fatih Düzgün, M.Sc. Thesis, Defense date: February 2016.
  5. Simulation-based VoIP Performance Evaluation under Different Traffic and Codec Conditions, Berk Ünlü, M.Sc. Thesis, Defense date: September 2013.
  6. HTTP Adaptive Streaming Architectures for Video on Demand and Live TV Services, Yiğit Özcan, M.Sc. Thesis, Defense date: August 2013.
  7. A New Service Architecture for IPTV over Internet, Merve Özkardeş, M.Sc. Thesis, Defense date: January 2013.
  8. A Faster Intrusion Detection Method for High-Speed Computer Networks, Mehmet Cem Tarım, M.Sc. Thesis, Defense date: May 2011.
  9. A New Feedback-Based Contention Avoidance Algorithm for Optical Burst Switching Networks, Hadi Alper Toku, M.Sc. Thesis, Defense date: December 2008.
  10. A New Approach for the Scalable Intrusion Detection in High-Speed Networks, Ümit Burak Şahin, M.Sc. Thesis, Defense date: December 2007.
  11. A Novel Method for the Detection of P2P Traffic in the Network Backbone Inspired by Intrusion Detection Systems, Murat Soysal, M.Sc. Thesis, Defense date: June 2006.

Projects

  1. METU Research Project: “METU-STARS: A Novel and High-performance Systematic Software Defined Network–SDN Management Method”, Project end date: May 2019.
  2. METU Research Project: “METU-HAS: A Novel and High-performance Systematic HTTP Adaptive Streaming (HAS) Method”, Project end date: December 2017.