Research Projects

Project: Build a Lightstage

Keywords: Photometric Stereo; Physics Simulation; Geometry; Numerical Optimisation; OpenGL Visualisations; Agri-tech; 3d Reconstruction; Feeding the Future; Morphological Identification; Climate Change Resilience in Crops.

This is a post-doctoral research project at Aberystwyth University with funding from University’s Research Fund grant (URF) and supported by National Plant Phenomics Centre, UK. Principal Investigator is Dr. Hannah Dee. The project involved the following:

  • Developed Open Source Experimental Framework, for numerical optimisation using Computer Vision techniques and exporting results to the platform.
  • Designing numerical physics methodology to evaluate light and camera positioning for data capture, using less and improved data, for Photometric Stereo, Structure-from-Motion and 3d Reconstruction pipelines.
  • Building the Spherical Lightstage Structure and triggered image capture platform, see details on Dr. Dee’s post.

Project: Self-Healing Architectures Against Malware

Operation Aurora (2007) SCADA Security Researchers demonstrate Cyber Attack can cause a generator to self-destruct (CNN). Later followed Stuxnet (2009), Flame, Duqu and BlackEnergy (2015) each targeting Critical National Infrastructure of countries incl. US, Iran, Ukraine, etc.
CARDINAL-E (2013) – proof-of-concept decentralised self-healing system algorithm to recognise and respond to abnormal Network Traffic. This prototype parses network packet data via the tshark parser (Wireshark), selects and learns from high discrepancy traffic features selected from KDDCup’99 dataset and shares learnt signature profiles via independent routes to all devices.

Keywords: Self-Healing Systems; Cyber Security; Artificial Immune Systems; Distributed; Computer Network; Peer-to-Peer; Decentralised; Industrial Control Systems; Robotics; Manufacturing; Critical National Infrastructure.

This was my Doctoral (PhD) research project at Aberystwyth University (Wales) funded by EPSRC UK and Airbus Group Innovations (UK) and advised by Dr. Mark J. Neal, David E. Price and Dr. Jules Pagna Disso.

  • Researched Self-Healing Systems from Cyber Attacks on Critical Infrastructure and Manufacturing Automation devices, such as Industrial Control Systems and SCADA networks.
  • The PhD thesis experimentation focused on an intelligent Artificial Immune System framework called CARDINAL.
  • Designed Machine Learning Pipelines for Network Security datasets, including phases: feature selection, self-supervised Fuzzy-clustering, supervised C4.5 decision tree. Co-authored results in Cyberspace Safety and Security 2013 proceedings paper and Journal of Computers 2014 article.
  • Reformatted, maintained and host the CSIC 2010 HTTP Dataset in CSV Format for training Machine Learning models applied to web application security, a subcategory of Network Security problems.
  • Published theoretical proposal (2016) to address the related challenges in trust and in detection for these aspects of critical national infrastructure going forward.

A few Past Collaboration Projects

  • Cyber Security Robotic Testbed for SCADA Networks — Design, procure, build, write & test code for a programmable logic controller (PLC) attack testbed. Network dataset collection for Stuxnet/Flame style attacks. The hardware used was Siemens S7-312 series PLC with CP343-1 networking module, distributed communication processor CP343-2P over an actuator sensor interface (AS-I) bus to operate a robotic grabber and arm with seven degrees of freedom.
  • Cyber Security Dataset — Hosted, maintained & supported reformatted revisions of the CSIC 2010 HTTP web penetration and network attack dataset for the network security machine learning community.
  • Data Mining Publications on Network Security Datasets — Design, write & test the C4.5 decision tree with a modified mutual information feature selection (MMIFS) algorithm resulting in improved performance on KDDCup datasets. Collaboration with Dr. Jingping Song.
  • Data Mining on Biological Pathway Investigations — Combined >500 curated biomodels (from EBI) using SBML libraries with chemical protein interaction datasets (from STITCH) to explore chemical pathway patterns within the biological models.
  • plus many others…


For more publications and research activity, see find profiles on Google Scholar, DBLP, ResearchGate or Acadamia.edu.

Technical Summary

Find a technology summary of software and hardware used/developed during recent client projects. These include workflows and development stacks. For a specialised portfolio, get in touch.

If you are interested to work together, discuss a project or ask a question then ping me an email and let’s have a chat.