Back to Top Mobile Nav

The Era of Edgeless Computing - Part 5

Welcome to the fifth of a series of articles to introduce some of the most cutting edge thinking about new computing and network architectures, bringing new forms of machine intelligence to where both digital and biological events occur.

Needle in a haystack

By Peter van Manen, EVP Research & Development of Living PlanIT

“If you torture the data long enough, it will confess to anything” – Ronald H. Coase

Making sense of a large amount of data is like finding a needle in a haystack. And the more and varied the data, the harder it is to tease out reliable meaning, when meaning is indeed there to be found.

I got involved in a project at Birmingham Children's Hospital back in 2011 and that was all about detecting deterioration in acutely ill children. (There is a TED talk about it below for additional context.) The consultants and nurses had already established a paper-based system of early warning, which had saved many lives, but they wanted to do more. Monitoring a child’s heart rate and blood oxygen level seemed the right starting point, but making sense of the data in a population of individuals with very different physiology was the challenge. Well, one of the challenges. Just collecting reliable data from a small baby wriggling around on a hospital bed is far from trivial.

The approach that we took was to process the data continuously, discriminating between real and instrumentation-related anomalies, establishing what was normal for each child, and then looking for change. The result was the potential to detect and hence prevent cardiac arrest and respiratory failure a few hours before they happened: enough time to avoid a life-threatening event. The doctors and nurses still decide which and when interventions are made, but the data provides early cues that trouble is brewing.

“ the physicians say it happens in hectic fever, that in the beginning of the malady it is easy to cure but difficult to detect, but in the course of time, not having been either detected or treated in the beginning, it becomes easy to detect but difficult to cure...” – Machiavelli

When looking for meaning in data, it is worth remembering the following:

In and around the city, much of daily life is routine. People commute to and from work at regular times, children are taken to and picked up from school, sunshine and rain follow the seasons, and so on. Once you have the data that expresses life in the city, and wrestle it into shape, mathematics can be very good at finding patterns. And patterns reveal both the normal and extraordinary.

Normal patterns of behavior are useful because they help us to plan how we best use the available space, energy and water in the city. Matching supply and demand can be done in a more thoughtful way, reducing waste and maintaining efficient systems. We can use patterns to forecast what might be expected to happen in the next little while, provided of course there are no sudden shocks. And when there are shocks or other departures from normality, we can see them early enough to take mitigating action. This is the key to finding that darn needle: characterizing what is normal for the haystack, and watching how and where it reacts when the needle is dropped. To be effective, you need to be watching the haystack most the time. Sensors and software are good at doing so.

As an example, consider what might be achieved in a busy airport, just by looking at the movement of people. You can use video cameras and passengers’ smart phones to expose this information. The normal flow at different times of the day will become known, permitting better planning and productivity from airport personnel. Deviations from normal flow patterns will allow congestion to be anticipated before it fully develops. Hence, more staff on the check-in counters, additional security personnel, extra serving staff in the food court and other interventions can be considered to prevent passenger frustration and delay. This information, captured in real-time, can also be used to influence and adapt the control of lighting and heating, ventilation and air conditioning (HVAC) systems. Unusual behavior of individuals, such as moving against the normal flow or lingering suspiciously in areas of the airport, will also be exposed quickly, enabling targeted security. And even when the flow of people appears normal, mathematical inconsistencies will provide a second level of defence against potential disruption and harm. The “wolf in sheep’s clothing” can be found even in situations where a casual look at data or security camera images shows no obvious suspicious activity.

This all leads to:

The PlanIT Urban Operating System™ (UOS) from Living PlanIT provides the live stream of data that underpins this rich functionality. The UOS has the hooks, via published APIs and web-sockets, for the analytics that find and act upon the patterns in the data. It also has the means, via its real-time control (RTC) layer, to adapt system performance directly.

Back in the hospital, faster and more effective detection of deterioration reduces the number of false alarms that currently plague acute care wards in hospitals. Nurses and doctors are helped by early warnings of deterioration. This can be the difference between a full recovery and a lifetime of care, or death. It also enables more targeted deployment of nursing care, the biggest single expense in most hospitals. Reducing waste, while improving productivity, resilience and safety, are the prizes for finding the needles in a haystack.

The same prizes are up for grabs in cities.

See related TED talk video here

See more of this series of articles here...
Part 1 – Turtles all the way down
Part 2 – Living in real-time
Part 3 – Back to the future
Part 4 – Elephant in the room
Part 5 – Needle in a haystack
Part 6 – Tale of two cities
Part 7 – Need to know
Part 8 – Gut feeling
Part 9 – Welcoming strangers

About Living PlanIT

Living PlanIT is a technology company that created the world’s first Urban Operating System (UOS) which, in combination with the products it supports, unlocks the full potential of data to make cities better, safer and more vibrant places to live.

Living PlanIT has built an extensive partner network around the concept of a shared, unified approach to smart urban technology architecture in which machine intelligence moves ever closer to originating sources of data and control. We call this architecture PlanIT Edgeless Computing™ and it is implemented throughout the PlanIT Urban Operating System™, providing a framework for resilient and secure computer and systems architecture for digital and biological sensing, control, analytics, machine learning, applications and visualization techniques.

Living PlanIT asserts its rights to the following Trademarks: Living PlanIT™, PlanIT Edgeless Computing™, Edgeless Computing™, PlanIT Urban Operating System™, PlanIT UOS™, PlanIT OS™, PlanIT Crumbs™, PlanIT PlaceApps™, PlanIT Valley™, PlanIT Assurance™, PlanIT Labs™, PlanIT Retail™, PlanIT Life™. Any reference to these names in this content shall be considered as an assertion of these Trademarks. or follow us on Twitter @Living_PlanIT