Purple Transform, a start-up working with the University of Lancaster and data giants Cisco presented its suicide prevention tool for the railways to the UK Government’s tech and business innovation conference in Manchester, explaining how “deep learning” and data modelling can help real people.
Alan O’Reilly, chief information officer at Purple Transform spoke at the event celebrating Innovate UK funding for its Project SAIVE.
Go deeper with GlobalData
The project is already working with Govia Thameslink and has a single test site. But O’Reilly announced Project SAIVE is now looking for further test sites.
“We had one pilot site that we deployed to, and what we’re looking to do at the moment is expand that out… having one location is not enough to prove definitively if it works or not,” he explained.
Along with the clear human effects of suicide, on or off the railway, O’Reilly highlighted the cost and reputational damage that suicide on the railways can cause.
There are approximately 250 suicides on UK railways each year, and every one has a knock-on effect of approximately £1.8-£2m ($2.5m) on the UK economy.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Thank you!
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form
By GlobalData“In purely economic terms we have what’s called the VSL, the value of a statistical life… that varies from country to country,” O’Reilly explained.
“But the actual cost of this, if you take into account all the delays, the lost productivity, the true cost of life, you’re actually talking about much more value than this.”
This is calculated by assessing the effect on staff (including train drivers) and the network delays (including passenger perception) that affect wider productivity.
The tech start-up worked with the University of Lancaster to develop (“teach”) its Deep Learning modules to recognise potentially worrying behavioural patterns near stations or rail lines. Existing CCTV is used to build risk metrics and eventually predict when a passenger or member of the public requires help.
The “SiYtE” platform that SAIVE uses will then alert station staff to the incident or person in need, and direct them to the best course of action.
“What we want to do is put at the fingertips of the person we’re alerting the right things to say, and the right resources to speak to,” the CIO told Manchester’s Bridgewater Hall.
Although O’Reilly said the tech ran into GDPR issues, he said the project is “now in a position where we want to take it out and spread it across the UK”.
