• University College London Featured PhD Programmes
  • National University of Singapore Featured PhD Programmes
  • Northumbria University Featured PhD Programmes
  • University of East Anglia Featured PhD Programmes
  • University of Leeds Featured PhD Programmes
  • University of Glasgow Featured PhD Programmes

Postgrad LIVE! Study Fair


University of York Featured PhD Programmes
University of Dundee Featured PhD Programmes
Monash University Featured PhD Programmes
University of the West of England, Bristol Featured PhD Programmes
University of Reading Featured PhD Programmes

Adaptive anomaly detection with big data from non-stationary systems

  • Full or part time
  • Application Deadline
    Applications accepted all year round
  • Self-Funded PhD Students Only
    Self-Funded PhD Students Only

About This PhD Project

Project Description

Applications are invited for a fully-funded PhD studentship with a £14,553 per year tax free bursary to contribute to project in the area of data science, specifically anomaly detection.

Anomaly detection is a powerful technique that finds patterns in big data that do not conform to expected behaviour. It has played an increasingly important role in big data applications such as detecting abusive/bullying posts on social networks, identifying suicidal users on Facebook, discovering the presence of abnormal behaviour / terrorists in surveillance systems, detecting illegal traders in stock markets, and monitoring abnormal conditions of critical systems such as jet engines and nuclear power stations. Data collected from all such systems have a distinct feature that its statistic properties change over time, a.k.a. data drift, such systems are called non-stationary systems. For example, community (group of connected users) of Twitter changes over time when members join or leave the community or when a community splits and multiple communities merge.

This project aims to develop an adaptive method that achieves reliable anomaly detection by accurately dealing with data drift in non-stationary systems. It builds a detector using available data collected and knowledge captured from all known conditions. The detector is then used to monitor the target system. If the output of the detector is significantly different from that of known conditions, then it warns that an abnormal event has occurred in the system.

A reliable novelty detector should have a closed decision surface. Therefore, the project will focus on techniques that construct closed decision surface around data distribution. It builds on the supervisors’ state-of-the-art work on novelty detection and critical pattern selection. It will develop a method that extracts critical information by identifying extreme patterns surrounding the given pattern set. Factors that control detector performance will be optimised. The performance of the developed anomaly detector will be evaluated on real-world problems such as detection of bullying/abusive/terrorist activities on social networks, fraud detection in financial industry, and anomalous event detection of dynamic networks.


Candidates must be from the EU and will need a 1st class or high 2:1 honours degree in a relevant subject such computing, mathematics, engineering or a physical science. Candidates will have strong analytical and programming skills, be confident in mathematics/statistics. Knowledge/experience in machine learning and data mining is desirable.


Application where funding can be secured from other sources will be accepted at any time. For further information visit: http://www.salford.ac.uk/study/postgraduate/fees-and-funding/research-degree-fees-and-funding

Further information and applying

For further information, please contact Dr Yuhua Li at

For more information on research within the School of Computing Science & Engineering and to make an application please visit: http://www.salford.ac.uk/research/sirc/postgraduate-research

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

Cookie Policy    X