Frangipani
Regular
"The system is constantly learning.." And there-in lies the spin.
We are meant to think that the chip learns. But of course it's connected to a server and needs to be trained, so no Akida.
In fact, it's just an example of a niche we missed out on.
That’s your interpretation only. The way I see it, we are not led to believe that the chip itself is capable of learning - in fact, on-chip learning is simply not required for these solar-powered devices that can send and receive data via the LoRaWAN network, the leading standard for long-range IoT.
I already posted about these wildfire sensors a couple of weeks ago (https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-305877), and this is what the company manufacturing them states on their website:
How can these sensors detect the fire? How can they know it’s a real fire but not just a burning cigarette?
The built-in artificial intelligence (AI) of the sensors is continually trained for the specific ‘smell’ of the target forest on fire. Our customers collect samples from the forest floor and send them to Germany so that we can train our AI in the lab. Over time, we will collect more and more samples from typical forests in the different parts of the world and will eventually no longer have to train the AI for new deployments as there is only a finite amount of forest types. We expect this to be the case within the first two years of operation.Doing so allows our Silvanet system to be continuously evolving and improving and greatly minimizes any risks of false positives within the platform.
———————————————————————————————————
What the Bosch article does say is:
“With the help of artificial intelligence, this sensor also analyzes the data it collects right there on the spot. If it detects a fire, it immediately sounds the alarm, sending a signal to the cloud and notifying emergency services.
(…)
The tiny “nose” that sniffs out forest fires measures just three by three millimeters. The Bosch environmental sensor installed in this forest-fire detection system is the world’s first gas sensor to feature artificial intelligence and the first to be deployed as an early wildfire warning tool. It can detect various gases, including fire gases such as hydrogen, carbon monoxide, and most hydrocarbons. The system is constantly learning and improving. Data collected from all installed sensors serves to continuously train the environmental sensors using artificial intelligence so they can detect and analyze gases with even greater accuracy. The BME AI-Studio Server software was developed specifically for this purpose.”
———————————————————————————————————-
These kind of Edge AI devices would be a perfect use case for Akida, even without utilising its on-chip learning function, especially since the Bosch sensors are collecting other environmental data as well such as temperature, humidity and air pressure, and the company is also looking at future applications, e.g. involving sensors that can detect chainsaw noise to help prevent illegal logging.
Dryad explicitly state on their website they are open-minded about collaborations: “Open for integration of 3rd party sensors and applications, no single-vendor lock-in.”
So maybe we haven’t entirely missed out on that niche just yet?
Is Dryad involved solely in wildfire detection?
While our initial focus at Dryad is wildfire detection, the Bosch BME688 sensors used in Silvanet sensor devices also collect environmental data such as temperature, humidity and air pressure which is periodically sent to the Silvanet Cloud, allowing forest owners to better understand the microclimate of the forest and its influence and development of the forest heath over time.Further planned use-cases involve sensors that can detect chainsaw noise to help prevent illegal logging.
It’s not just about forests either, our technology can also be applied to other ecosystems including lakes, rivers and oceans. At Dryad, we have ambitious plans to connect the natural world and protect our planet.
Last edited: