If there’s one thing Rory Armes wants audiences at Buildex Calgary to understand, it’s the idea that even a small investment in big data and predictive artificial intelligence (AI) can provide actionable insights and pay solid dividends.
Armes is CEO of Eight Solutions Inc., a company built on the idea that any business, large or small, can benefit from big data analytics and predictive AI. Its proprietary solution is Cumul8, a cloud-based Internet of Things platform that accepts a wide range of data from any type of monitoring device, then teases valuable conclusions from that data.
“People are sometimes left with the notion that they either go all-in on costly predictive AI systems, or stay out of it altogether,” says Armes. “Those unrealistic polar choices leaves them comatose.”
He aims to demystify the concepts around big data in a construction context, explain predictive AI and show how it can quickly demonstrate value.
“For many people, their concept of AI is based on a combination of science fiction and the horrible experiences they’ve had with IT,” he says. “Predictive AI is not about science fiction. It’s more about economics and putting insights in front of humans so that they can make decisions, while assuring them that they are in control of the data.”
Armes suggests construction companies might begin by targeting the top five problem areas in building operation and see if predictive AI can provide insights into them.
An AI system in its current form might tell you that it looks like an HVAC component could fail within the next two weeks
— Rory Armes
Eight Solutions Inc.
“If you can improve the efficiency of these systems by 10 per cent, it represents a massive return on investment,” he says.
For Eight Solutions, the process in a building application begins with collection of raw data from a variety of sources, ranging from motion sensors to heating and cooling valves.
“We take the data and throw it up into a cloud database,” says Armes. “Inside the cloud, we’re running auto-AI to look at unusual variances outside of normal operating range. If we can read the sensor of a valve in an air conditioning unit, we can predict when that valve is underperforming or failing.
“You could also use deeper AI code to combine data, such as the movement of people through a building with the heating and cooling of each room, to draw insights from that.”
He notes the most effective AI systems drill down through vast amounts of data to provide humans with information that allows them to use their own judgment about what to do next.
“An AI system in its current form might tell you that it looks like an HVAC component could fail within the next two weeks, based on records of the past,” Armes says. “It would be up to you to decide how to respond.”
AI systems can also be wrong, again underlining the importance of human insight. The system may need to be taught what’s important.
Armes reckons that even Amazon’s Stage 3 AI only suggests products that people might actually want about 15 per cent of the time.
“When Amazon gets to Stage 7 AI, they’ll be shipping you products that you’ve never asked for,” he says. “And you’ll want them. Buildings will also be pushing back, using AI to tell operators what they ought to be doing.”
Armes says he wants to leave his audience at the Buildex session with some idea of what they can already do with the data they currently have — without spending a cent.
“Even if it’s hand-entered on an Excel spreadsheet, they can use that data to gain insights,” he says. “Those insights often lead people to further explore the possibilities of big data.”
Big Data and the Built Environment is scheduled for Wednesday, Nov. 7 at 9:45 to 10:45 a.m. on the PerformEX Stage on the Tradeshow Floor.
Recent Comments
comments for this post are closed