Portfolio

Below are a few recent Research Projects, Collaboration Projects, Publications and Technical / Business Portfolio. See the Portfolio Nav menu for links to client projects and YT channel for recent videos (see footer for links and contact details).

ReSEARCH & Development

‘Build a Lightstage’ Project (2015-).(latest Update)

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 my first 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:

  • 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. (Dedicated website details here).
  • Building the Spherical Lightstage Structure and triggered image capture platform, see details on Dr. Dee’s post.


‘Self-Healing Architectures Against Malware’ PhD Project (2011-15)(Latest Update)

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 funded by EPSRC and Airbus Group Innovations 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.

This is an early proof-of-concept demo video of CARDINAL-E (2013) – one of the variants of the distributed self-healing system algorithm. In the video the software is parsing network packet inputs via the tshark parser (Wireshark), selecting and learning from high discrepancy features selected from KDDCup’99 dataset and sharing learnt signature profiles between the two instances on virtual machines and connected via the local loopback device.


Other COLLABORATION R&D Projects include:

  • 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 various others…

Publications:

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

portfolio:

For a portfolio of software (and in cases, hardware) development projects including the operational roles and the development stacks used, please see the Workflows and Stacks page.

If you are interested to work together or want to discuss a project, then ping me an email with your name and subject and I will get back to you.

Recent Posts

On Estimating Thailand’s Infection Fatality Ratio (IFR)

This post is to record the method used to create the estimate for Thailand’s IFR metric nationally and by province for death estimations and their distributions per province. This was sparked by Matt Greenfield and Dylan Jay’s discussion. Obviously, there’s too much to fit in a tweet. In the article, we show (1) how readers … Continue reading On Estimating Thailand’s Infection Fatality Ratio (IFR)

Extension of Python Dict .get() – Lookup with Similarity for Built-in Libraries

This is a prospective extension to Python dict .get() that solves a common problem in data applications. The bold proposal asks whether to include such an implementation in the core language or in a library, across languages used for data processing. See what you think.. Background & Why? These days we have more data-oriented code … Continue reading Extension of Python Dict .get() – Lookup with Similarity for Built-in Libraries

Thailand Province Border Adjacency Dataset/Code

A quick update post to help get my latest project’s new dataset more readily indexed on Google search, etc. (Feb 8th 2021) I’ve recently been working on risk assessment for COVID-19 in our 2nd wave. To create an email alert per province (taking account of local regional data) I needed to join provincial data together. … Continue reading Thailand Province Border Adjacency Dataset/Code

More Posts