Yu Guan

Yu.Guan@ncl.ac.uk | Faculty

Yu Guan

I am a lecturer in data science and I lead the Machine Learning Group in Open Lab. My research interests are machine learning and its various applications such as behaviour analysis, wearables, ubiquitous computing, computer vision and biometrics, etc. Before joining Newcastle University, I received my PhD degree at the Department of Computer Science, University of Warwick in 2015.


  • Associate Editor, ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT/UbiComp Core A*) 2017-Now
  • Session Chair, ACM UbiComp (Core A*), 2017
  • TPC Members, IEEE Int'l Symposium on Wearable Computers (ISWC, Core A*), 2017, IEEE Int'l Workshop on Biometrics and Forensics (IWBF), 2017, IEEE Int'l Conf. Multimedia and Expo (ICME), 2014
  • Regular Reviewers, IEEE Trans. Pattern Analysis and Machine Intelligence (T-PAMI, Core A*), IEEE Trans. Information Forensics and Security (T-IFS), IEEE Trans. Circuits and Systems for Video Technology (T-CSVT), IEEE Trans. Cybernetics (T-CYB), IEEE Signal Processing Letters (SPL), ACM Multimedia (ACM-MM, Core A*), IEEE ISWC (Core A*), ACM UbiComp (Core A*), Pattern Recognition Letters (PRL), Image and Vision Computing (IVC), IET Biometrics, etc.

Teaching and Tutoring:

  • Module Organiser, CSC8111 "Machine Learning", School of Computing, Newcastle University, 2017-2018
  • Guest Lecturer, "Deep Learning for Human Activity Recognition", for MSc Module "Introduction to Deep Learning", Department of Computer Science, UCL, London, Oct. 2017
  • Tutorial Lecturer, "Deep Learning For Ubiquitous Computing", ACM UbiComp (Core A*), (Co-hosting with T. Ploetz, Georgia Tech, N. Lane, Oxford University&Bell Labs, and S. Bhattacharya, Bell Labs), Maui, Hawaii, US. Sept. 2017.
  • Guest Lecturer, "Deep Neural Networks", for MSc Module "Machine Learning", School of Computing Science, Newcastle University, Dec. 2016
  • Tutorial Lecturer, "Deep Learning and its Mobile Applications", the 8th Int'l Conference on Mobile Computing, Application and Services (MobiCASE), (Co-hosting with T. Ploetz, Georgia Tech, N. Lane, UCL&Bell Labs, and S. Bhattacharya, Bell Labs), Cambridge, Nov. 2016.
  • Guest Lecturer, "Machine Learning for Biometric Applications", for BSc Module "Machine Learning", Department of Computer Science, University of Warwick, Dec. 2014
  • Guest Lecturer, "An Introduction to Gait Recognition", for MSc Module "Multimedia Processing Communications and Storage", Department of Computer Science, University of  Warwick, Nov. 2012

Selected Publications (google scholar citations):

  • Y. Guan and T. Ploetz, "Ensembles of Deep LSTM Learners for Activity Recognition using Wearables ",  ACM IMWUT/UbiComp (Core A*), 2017
  • R. Li, C.-T. Li, and Y. Guan,  "Inference of a Compact Representation of Sensor Fingerprint for Source Camera Identification", Pattern Recognition (PR, Core A*), 2017
  • Y. Guan, C.-T. Li, and F. Roli, "On Reducing the Effect of Covariate Factors in Gait Recognition: a Classifier Ensemble Method",  IEEE T-PAMI (Core A*), 2015


About Machine Learning Group

Our research agenda is to develop state-of-the-art machine learning algorithms for real-world applications. One of our major research directions is computational behaviour analysis in different scenarios (e.g., identification/activity recognition/anomaly detection) based on various data sources (e.g., from videos/wearable sensors). In terms of methodologies, we are very interested in deep learning, zero-shot learning, and multimodal fusion. Our group members have substantial experience in publishing papers at top-tier (applied) machine learning venues such as IEEE T-PAMI, CVPR, AAAI, IJCAI, ACM-MM, IMWUT/UbiComp, PR, CVIU, etc.  Please contact me if you want to collaborate with us in such exciting fields!

Recent News:

  • Yang's Paper "Towards Affordable Semantic Searching: Zero-shot Retrieval via Dominant Attributes" has been accepted by AAAI 2018 (Core A*)! Well Done!
  • Yu gave a guest lecture on "Deep Learning for Human Activity Recognition" at UCL!
  • Yang's Paper "Zero-shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation" has been accepted by IEEE T-PAMI (Core A*)!  Congrats!

 Group Members:

  • Yu Guan (Faculty, Deep Learning, Behaviour Analysis, Wearables, Computer Vision and Biometrics)
  • Yang Long (PostDoc, Deep Learning, Zero-shot Learning, Computer Vision, Wearables)
  • Rob Thompson (PhD, Wearables, Animal Behaviour Analysis)
  • Shane Halloran (PhD, Wearables, Stroke Assessment by Behaviour Analysis)
  • Bing Zhai (MRes, Wearables, Sleep Quality Assessment)

BSc/MSc Student Projects:

  • Joss Cousins (Automated Archery Skill Assessment using Wearables)
  • Guillermo Chibas Puente (Stock Market Prediction using Machine Learning Techniques)
  • Robert Nixon (Behaviour Analysis for Tennis Players using Wearables)
  • Cameron Smith (Image Analysis using Machine Learning Algorithms)

Visiting Researchers:

  • Ruoshui Liu (PhD, Hanwei Ltd & Cambridge University), Nov. 2017
  • Tom White (PhD, Cambridge University), Feb. 2017


Inference of a compact representation of sensor fingerprint for source camera identification
Li R, Li C-T, Guan Y, Pattern Recognition556-567


Ensembles of deep LSTM Learners for Activity Recognition using Wearables
Guan Y, Ploetz T, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies


Enhanced SVD for Collaborative Filtering
Guan X, Li CT, Guan Y, Advances in Knowledge Discovery and Data Mining (PAKDD 2016)503-514


On Reducing the effect of Covariate Factors in Gait Recognition: A Classifier Ensemble Method
Guan Y, Li C-T, Roli F, IEEE Transactions on Pattern Analysis and Machine Intelligence1521-1528
Copyright 2015 Open Lab