Life is like a box of chocolates, you never know what you’re gonna get
— Forrest Gump

Md Tariqul Islam

PhD Student

tariqsaj [at] dca.fee.unicamp.br| mtarislam [at] gmail.com


About Me

I am currently enrolled in the PhD program under the supervision of Prof. Dr. Christian Esteve Rothenberg in the Department of Computer Engineering and Industrial Automation (DCA), School of Electrical and Computer Engineering (FEEC) at the University of Campinas (UNICAMP), Brazil. I am also part of the INTRIG as a graduate research assistant.
I received MSc in Computer Engineering from FEEC/UNICAMP, Brazil, in 2021 and BSc in Information and Communication Technology from Mawlana Bhashani Science and Technology University, Bangladesh, in 2018.

Research

My main research interest is centered around enhancing network performance and Quality of Experience (QoE) for emerging eXtended Reality (XR) services by incorporating 5G and Beyond (5GB) networks, Edge Computing, and Machine Learning (ML) techniques. I am engaged in exploring 360-degree VR streaming use cases, investigating ML-based network-level measurement correlation and analysis with user QoE, and assessing the feasibility of such correlation and analysis in the 5GB network context. Additionally, I am interested in exploring QoE and Quality of Service (QoS) aspects for beyond omnidirectional 360-degree VR, such as holographic video streaming. Currently, I am also engaged in developing a traffic generator to emulate mobile application traffic, with a focus on virtual reality app traffic. My past work includes predicting traditional DASH video QoE metrics at the network edge using ML models for performance optimization.

Recent News

  • I have been participated in the 42nd SBRC event to represent the SMARTNESS 2023 research project, Brazil (2024). [PDF]
  • I spent three days at Ericsson Research in San Jose for technical discussions with our research collaborators, USA (2023).
  • I have been participated IEEE ComSoc School Series Atlanta and also selected for Travel Grant, sponsored by IEEE ComSoc, USA (2023). [PDF]

Research Projects

  • SMARTNESS 2030: SMART Networks and Services for 2030, Research Lab: INTRIG, External Collaborators: FAPESP and Ericsson, 2023 – Present.
  • 5G Services in Programmable Networks with Machine Learning Capabilities, Research Lab: INTRIG, External Collaborators: Ericsson, 2022.
  • CLAML: Control Loop Architecture with Adaptive Policy and Machine Learning Capabilities, Research Lab: INTRIG, External Collaborators: Ericsson, 2019-2021.
  • NECOS: Novel Enablers for Cloud Slicing, Research Lab: INTRIG, 2018-2019.

Publications

Journal
  • Machine Learning-Assisted Closed-Control Loops for Automated Healing in Multi-Domain Zero-Touch Networks. Nathan Saraiva, Md Tariqul Islam, Raza Ul Mustafa, Danny Lachos Perez, Christian Esteve Rothenberg, Pedro Henrique Gomes. In Journal of Network and Systems Management, 2022. [PDF]
Conference
  • Predicting XR Services QoE with ML: Insights from In-band Encrypted QoS Features in 360-VR. Md Tariqul Islam, Christian Esteve Rothenberg, Pedro Henrique Gomes. To Appear In NetSoft, Technical Session, 2023. [PDF]
  • EFFECTOR: DASH QoE and QoS Evaluation Framework For EnCrypTed videO tRaffic. Raza Ul Mustafa, Md Tariqul Islam, Christian Esteve Rothenberg, Pedro Henrique Gomes. To Appear In NOMS, Technical Session, 2023. [PDF]
Workshop
  • DASH QoE Performance Evaluation Framework with 5G Datasets. Raza Ul Mustafa, Md Tariqul Islam, Christian Esteve Rothenberg, Simone Ferlin, Darijo Raca, Jason J. Quinlan. In CNSM, Workshop, 2020. [PDF] [Video] [GitHub]
  • HAS Based Empirical QoE Study over TCP and QUIC on Diverse Networks. Md Tariqul Islam, Christian Esteve Rothenberg. In VII Pre-IETF, Workshop, 2020. [Slides] [Video]
Demo
  • Intent-based Control Loop for DASH Video Service Assurance using ML-based Edge QoE Estimation. Christian Esteve Rothenberg, Danny Lachos Perez, Nathan Saraiva, Raphael Rosa, Raza Ul Mustafa, Md Tariqul Islam, Pedro Henrique Gomes. In NetSoft, Demo Session, 2020. [PDF] [Video]
Poster
  • QoE Estimation by Virtual Probe at Edge Computing Facilities. Md Tariqul Islam, Christian Esteve Rothenberg. In XII EADCA Poster Session, 2019.

Thesis

  • (MSc) A predictive DASH QoE approach based on machine learning at multi-access edge computing: Uma abordagem preditiva de DASH QoE baseada em aprendizado de máquina em multi-access edge computing.Md Tariqul Islam. 1 recurso online (108 p.) Dissertação (mestrado) – Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação, Campinas, SP. Disponível em: https://hdl.handle.net/20.500.12733/1641360, Acesso em: 10 nov. 2022. [Slides]