How do you feel about this article? Help us to provide better content for you.
Thank you! Your feedback has been received.
There was a problem submitting your feedback, please try again later.
What do you think of this article?
Edge AI is a relatively new option whereby the processing for artificial intelligence applications occurs close to the device’s location rather than getting sent elsewhere. Often, the information processing happens locally. Here are some of the specific benefits people can get by deploying these edge artificial intelligence solutions.
1. Increased Visibility for Better Decision-Making
Using edge computing for artificial intelligence applications significantly reduces the latency that can happen if data goes to an off-site facility for processing. That improved quickness is particularly valuable when a company’s leaders want to take action without delays.
In one recent example, Toyota Motor North America partnered with Invisible AI – an artificial intelligence (AI) startup – to employ edge devices at all of its factories. More specifically, it will install AI “eyes” to monitor nearly everything happening in a facility. Then, leaders can identify process bottlenecks and see what’s working well.
The complete system includes 500 edge AI devices with built-in chipsets and a high-resolution 3D camera that tracks what’s happening on the factory floor. Speaking of the setup, Eric Danzinger, Invisible AI’s founder and CEO, said, “[It] allows us to do a ton of processing at the camera, on the device in real-time, all the time.”
He continued, “What we have is an AI computer vision model that’s running and that’s constantly processing all the video that’s coming in. What that means is we can give you real-time information, real-time insights, [and] we can process that data incredibly efficiently. If you want to see a shift report, you can see that almost as soon as the shift ends.”
During the tech rollout’s early stages, the company will focus on using AI to monitor vehicle assembly. However, leaders are also interested in exploring other applications, including those related to safety and ergonomics.
2. Enhanced Flexibility and Ease of Deployment
Edge AI also gives people more options regarding how, when, and where they use artificial intelligence applications. Those benefits are particularly valuable when relying on AI in areas that may have limited infrastructure, such as construction sites.
One way that AI can help in such cases is by keeping worksites safer. Statistics indicate that falls are the top cause of construction fatalities. If a company uses cameras with AI processing at a site, the technology could screen for excessively risky situations and alert managers to intervene, whether the issues relate to instances where workers might fall, occasions where they are not wearing personal protective equipment, or something else.
CONXAI is one company aiming to improve construction site safety with artificial intelligence. That organization offers a modular, no-code AI platform for job site imaging. It uses a solution called the Veea Edge Platform to make information processing happen locally. However, this combination of edge computing and AI has additional benefits, too.
William Hurley, the chief revenue officer at Veea, said, “The upside opportunity for real estate developers and the construction companies they hire is limitless, especially as nearly every asset can be instrumented with increasingly low-cost sensors and camera systems.”
He continued, “With Veea’s edge computing platform and mesh networking, we can collect and analyze data locally while supporting automated systems and providing data in real-time to job site managers that can improve safety and productivity. We can also ship data to multiple clouds, feed existing enterprise systems, and enable remote management, which is extremely valuable, to large, distributed construction companies.”
3. Improved Data Processing Capabilities
Some cloud computing applications require half a second to send a query and receive a response. That sounds like a short time span, but it’s still too long for some types of AI, such as the kind installed on self-driving cars.
Matt Ranney is the chief systems architect at Uber. He spoke of how the Volvo XC90 automobiles used in the company’s self-driving fleet require edge computing because of all the real-time data the vehicles must ingest and process to function properly.
“This system has to make all of its decisions locally. It can't rely on any systems off-board to make any decisions about how to drive the car. It's got to use the sensors. All of the software that needs to make that decision has to be on-board. All we get from the outside world of data is where people want to be picked up,” he explained.
That edge artificial intelligence application appears to have paid off. Uber announced a 2022 launch of driverless food deliveries for the California market.
Some people familiar with autonomous cars even call them mobile data centres due to the sheer amount of processing handled locally. They assert that, due to the data consumed on-board the car and how much that information controls the automobile, companies specializing in self-driving cars need to invest more resources into protecting them from cyberattacks.
4. Expanded Use Cases
The progress associated with edge AI also creates more opportunities for people to use artificial intelligence in new, exciting ways. As those advancements continue, it’ll become more likely that individuals see artificial intelligence and edge computing as a smart pairing.
Consider a development from a research team at the University of Massachusetts Amherst. It’s an edge computing device that uses machine learning to analyze the size of a crowd and the prevalence of coughing. The team hopes that solution will help them track COVID-19 and seasonal illnesses, such as influenza.
During tests from December 2018 to July 2019, the system gathered more than 21 million non-speech audio samples and 350,000 thermal images from public waiting areas. When the researchers examined the data, they found it contained signals that helped identify daily flu case rates.
In another case, two companies partnered to deploy edge AI devices to monitor, examine, and prevent the adverse effects caused by extreme weather, including natural disasters. Some of the first pilot projects emerging from this collaboration will emphasize deploying AI on existing edge devices, such as railway and highway cameras.
Company representatives hope to utilize one camera every three to five kilometres and use them to monitor things like rainfall and snow amounts. They also believe their technology could reduce wildfire damage by analyzing smoke.
Will You Use Edge AI?
These examples show some of what’s possible when people pursue edge artificial intelligence solutions. If you’re thinking about doing the same, consider working with a tech provider that works with edge AI frequently and understands the feasible use cases. That way, you can approach them with your expectations and concerns and learn more about whether the technology is a good fit for your needs.