Friday, 20 October 2017

Working it out in Logs

Long time no blog - but have been busy on top secret stuff. Here is a glimpse into some of the things I've been up to.

Railway safety management is a complex subject that involves a significant amount of manual intervention in the assessment, analysis and control of risk. Supporting documentation is, usually, worked on by multiple parties, with differences in system viewpoints and writing styles. Maintaining quality safety documentation is therefore an interesting challenge for the industry.
Hazard logs, for example, play a central role in both system engineering and risk assessment activity. The role of the log is to contain a representation of the risks related to the system under consideration. The content of the hazard log relies upon input from a variety of sources and collaborative activities involving teams with varying expertise and knowledge. From past experience we have found that the quality of this information can vary greatly both within and between projects. This is particularly so for larger projects where problems can arise when the amount of textual data that has to be processed increases. The volume and variety of the data and the need for collaboration creates the significant challenge of managing the content, keeping up the textual readability, format and consistency.
What we are currently working on is a tool that automatically assesses the ‘quality’ of a risk log. The intention is that the tool can be used to monitor the quality of a hazard log in ‘real’ time or at least at regular intervals during a project or for checking the output from critical risk workshop sessions. The tool uses Natural Language Processing and machine learning to assess the quality of a hazard log, based solely on the textual content in the log. The method includes text classification and term frequency-inversion to identify important keywords on different textual elements to represent quality indicators.
The intention is not to replace a human expert, but rather to support assessments by providing an early indication of the textual data in the log. This involves checking for signs of imprecise and unclear writing and identifying issues that may make it hard for readers to fully interpret accident sequences.  The tool has been built around the CENELEC standards to aid compliance with both the standards and risk management best practice in general.
A preliminary study in collaboration with Lancaster University has been undertaken to prove the method. Results from this study have demonstrated the power of using textural analysis in this arena.  We have identified a number of hazard log quality indicators and developed demonstrator software which performed well against a manual evaluation of a sample data set. In general, the tool can help the users by saving time and effort by helping in the review of entries in the log. It can also help clarify thinking around accident sequences by highlighting ambiguous or multi-content entries.
The results of this study will be presented at the Transport Research Arena conference in April 2018 in Vienna.
(post reproduced from

Thursday, 24 March 2016

ELBowTie - use of big data in safety analysis

The first of 3 papers has hit the streets!

Definition of big data for use in safety assessments utilising - ELBowTie for managing real time safety analysis.

Thursday, 28 January 2016

Minecraft training

Today's the day for attending a Minecraft training day at the University of Manchester!

Fact finding session thoughts begin.

Before going in my thoughts are:

1 I've seen my lads playing this game and it looks pretty simple. It seems to be a bit like Lego on steroids.

2 So you can construct great structures. I can see how this could be used to aid some sort of design process. Something akin to VR but  using blocks?

3 What I want to find out is can it be used for non construction training. Say for example safety engineering training, risk assessments and the like?

Okay here we go:

What a brilliant day! Got much more out of it than anticipated. Especially when the Internet connection dropped out giving more time to bombard the organisers with questions.

In answer to Q3  above the answer is yes. We had ideas of building for example a level crossing and injecting in guidance on design standards to aid knowledge based learning. Another idea was to inject failure rates into parts of the design to aid appreciation on safety and reliability effects.

The big idea was however to look to get youngsters involved in the railway arena through the design of their local station. Then to look for improvements and risks associated with the design. Needs a bit of through on exactly how to make this entertaining but we all though that it would be doable through the primary school tech programmes.

All in all - very impressed - off to learn how to programme in Python!

Sunday, 3 January 2016

2015 start of a new era

Well 2015 all in all was a bit of a blast. Not only did it herald in the start of my new business NTTX Advisory and winning a couple of sizeable contract it also saw me getting back to a bit of research.

The business is now up and running with things moving a lot faster that I originally intended. Which hasn't done much for my early semi-retirement plan but has been great fun and given me a reboot on a number of fronts.

The research and development has resulted in 2 papers both to be presented this year. One in Sardinia and the other in Brussels. Both on the use of 'big data' in risk assessment. On the back of this work we are developing a software product called ELBowTie which will implement the approach by integrating enterprise data into a living risk management tool. All very exciting! Well done to the Dev team of Alex, Richardsthe and Ray in getting this off the ground while not being paid for any of it! It is a bootstrap startup after all!

A lot of code designing went on last year - which is a step in the right direction with respect to the revival plan.


Friday, 20 November 2015

Hackathons - the rise!

Corporate led hackathons are what I'm mulling over.

Hackathon or Exploitathon - that's all I have to say.

Sunday, 8 November 2015

The Potential for Using Big Data Analytics to Predict Safety Risks by Analysing Rail Accidents

Railways 2016
The Third International Conference on
Railway Technology:
Research, Development and Maintenance
Cagliari, Sardinia, Italy
5-8 April 2016

My first research paper in over 25 years will be presented at the above conference! 

Big Data what does it mean for safety management. 

The Potential for Using Big Data Analytics to Predict Safety Risks by Analysing Rail Accidents.
Dr Howard Parkinson CEng FIMechE MIRSE
Rail System Engineering Limited
Dr Gary Bamford FBCS, CEng, CITP
NTTX Advisory Limited

Plus we have 'invented' a new safety product, plus the conference is in Sardinia - can't wait. It's all top-secret until next April of course.

Now working on the follow on paper ..... onward and upward!

Thursday, 2 July 2015

Big Data accidents

I am getting to hate the term but appear to be being dragged into the 'Big Data' foray. Everyone seems to be rabbiting on about it so though I may as well have a go too.

I'm running the risk of letting the cat out of the bag here as myself and a colleague Howard Parkinson (contact site are in the process of writing a couple of papers on the subject. Both papers have a focus on its use in the management of safety within the rail industry.

The idea is to investigate how 'Big Data' and it's sidekick 'Analytics' can be used to help prevent accidents.

One thorny issue which has come up right at the start relates to the collection of personal data. We have generated a safety data taxonomy - business, operational, asset, social, personal etc, as part of the study. Of course safety management has a focus on the people and a large fraction of accidents are caused by - people. So, our study may be a short one if the data that matters for the 'analytics bit' is driven by staff related information. Not sure the rail industry is ready for that one with all its security and privacy issues.

We shall see - more later ......