Sean Feng

Welcome to my page!

I am currently a Teaching Fellow in Computer Science at Royal Holloway, University of London.
I obtained my PhD in Computer Science from Royal Holloway, University of London, where my research focused on Machine Learning for WiFi technologies with applications in indoor positioning, under the supervision of Dr Khuong Nguyen and Prof Zhiyuan Luo.

I completed my BSc degree at Zhejiang University. I am also the holder of a Utility Model Patent for a sensor design, published during my junior year of undergraduate study.


Recent news:

• Feb 2026 -
  • Book chapter "Reliable Train Delay Forecasting with Conformal Prediction" of The Importance of Being Learnable published by Springer. 
• Jan 2026 –
  • 👑Selected as a finalist for the STEM for Britain 2026 competition to present research at the House of Commons in March before Members of Parliament.
  • Journal paper "Robust Indoor Positioning with Hybrid WiFi RTT-RSS Signals" published by Sensors journal (Impact Factor 3.5, CiteScore 8.2).
• Sept 2025 –
  • 🎓 Commenced supervision of two Ph.D students.
  • Programme Committee Member (Operations) for 14th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2025).
• June 2025 –
  • Journal paper "A Survey on Data Augmentation for WiFi Fingerprinting Indoor Positioning" published by IEEE Sensors Reviews.
• Feb 2025 –
  • 💼 Joined as a Teaching Fellow in Computer Science at Royal Holloway, University of London.
• Jan 2025 –
  • 🧑‍🎓 Successfully passed the Ph.D viva, subject to minor corrections, for the thesis ‘Machine Learning Approaches for WiFi Round Trip Time Indoor Positioning Systems’.
• Nov 2024 –
  • Journal paper "A Review of Open Access WiFi Fingerprinting Datasets for Indoor Positioning" published by IEEE Access (Impact factor 3.6, CiteScore 9.0).
• Sept 2024 –
  • 🧑‍🔬 Successfully completed the role of Machine Learning Scientist on the Innovate UK–funded project ‘DataSim: A Machine Learning-powered simulation tool for rail timetable optimisation’.
• June 2024 –
  • I re-published my 6 WiFi RSS RTT datasets on Zenodo, with open access to the research public, as a contribution to the IPIN community.
  • The WiFi indoor positioning datasets contain LOS condition labels in real-world complex indoor scenarios. Please download via these two links: release1 and release2. 
• May 2024 –
  • Hired as a research assistant in RHUL KTP Pump-Prime Project: Indoor positioning in crowded public spaces.
• April 2024 –
  • Journal paper "A Wi-Fi RSS-RTT Indoor Positioning Model Based on Dynamic Model Switching Algorithm" published by IEEE.
• Sept 2023 –
  • 🏅 My research paper, "A dynamic model switching algorithm for WiFi fingerprinting indoor positioning" was Top #10 at the IEEE IPIN 2023 conference.
  • 🏅 I achieved 4th place as a one-person team in 10th IPIN Competition onsite and offsite Indoor Localization.
• Aug 2023 –
  • Journal paper “WiFi round-trip time (RTT) fingerprinting: an analysis of the properties and the performance in non-line-of-sight environments” published by Taylors & Francis.
  • Won the Best Papers IEEE J-ISPIN Award organised by the IPIN committee, with submitted research paper being one of the top papers.
• Jul 2023 –
  • Research article “A dynamic model switching algorithm for WiFi fingerprinting indoor positioning” accepted by IPIN 2023, the biggest conference on indoor positioning and indoor navigation, as a regular paper and to be presented on 26th Sept, Nuremberg, Germany.
  • Successfully completed project conclusion and final report submission for Student Research Experience Scheme 2022-23.
• May 2023 –
  • Published three brand new publicly available WiFi datasets, collected on three new complicated scenarios to facilitate research within model selection and indoor localisation domains.
• Mar 2023 –
  • Published the proceedings paper "A Multi-Scale Feature Selection Framework for WiFi Access Points Line-of-sight Identification", presented at the WCNC 2023, a leading conference in Wireless Communications.
  • 💰Won Project Lead award (£1,000 grant) for Student Research Experience Scheme 2022-23, Funded by Santander Universities and Enhancing Research Culture Fund.
• Dec 2022 –
  • 💡Successfully completed project conclusion and final report submission for Brighton BRITE programme in collaboration with Naurt (UK).
• Nov 2022 –
  • Journal article "WiFi Access Points Line-of-Sight Detection for Indoor Positioning Using the Signal Round Trip Time", published on Remote Sensing (Impact Factor 5.0) by MDPI.
• Nov 2022 –
  • 🧑‍🔬Senior Research Support Assistant, developing performance analysis experiments to evaluate the outdoor-indoor tracking SDK in numerous challenging everyday scenarios. Part of the Brighton BRITE programme. In collaboration with Naurt (UK).
• Sept 2022 –
  • Published the proceedings paper "An analysis of the properties and the performance of WiFi RTT for indoor positioning in non-line-of-sight environments", presented at the LBS 2022.
• Mar 2022 –
  • Published three publicly available WiFi Round-Trip-Time and Received Signal Strength datasets, collected on three challenging, complex indoor environments, to facilitate research in WiFi-based indoor positioning and contribute to the broader body of knowledge.
• Aug 2022 –
  • Managed on-site operations and coordination at COPA 2022.
• Sept 2021 –
  • 📖 Journal paper “A survey of deep learning approaches for WiFi-based indoor positioning” based on more than 150 research papers published by Taylors & Francis, cited by 117 (by Jan 2026).

In an emergency, what if “Where am I?” and “Which way?” were questions your phone could answer instantly indoors?

I explore how to strengthen indoor positioning by integrating WiFi Round-Trip-Time with machine learning models that can handle noisy, dynamic environments. Traditional indoor methods often degrade due to multipath effects and interference, producing inconsistent accuracy when reliability matters most. By incorporating feature selection, my approach reduces computational cost and filters out less informative signal attributes, leading to more robust predictions. The broader aim is accurate, scalable indoor navigation using existing infrastructure—supporting faster, safer movement through complex indoor spaces.

I have had the pleasure to supervise the following 2 Ph.D students.

- Charles Gadd (2025 - present): researching Machine Learning for Smart Transport. co-supervised with Prof. Zhiyuan Luo and Dr. Khuong An Nguyen.

- Yinqi Zhang (2025 - present): researching Smart Earables for Indoor Navigation. co-supervised with Prof. Zhiyuan Luo and Dr. Khuong An Nguyen.