The MXC Blog

The MXC Foundation has made a remarkable entry into the nascent multi-billion dollar AI smart device market. With the exponential growth of its network across the globe, the Foundation is thrilled to introduce more aspects to its network usage, allowing its mining community to utilize the data republic and see the network in action. The proprietary MXProtocol, together with scalable and secure aspects of device provisioning that connect with sensor technology, has proven successful and brings us a step closer to realizing truly smart cities. One such use case, which the MXC Foundation recently tested in a controlled environment, was the Edge X AI Camera. Read on to find out more about all the great functionalities packed into one small device.

What is the Edge X AI camera?

The Edge X AI camera is a smart camera with numerous incredible functions. It can be trained on any type of dataset, in accordance with whatever you are interested in tracking or gathering more data on. The camera can detect all sorts of things, from raccoons and foxes that run through your backyard at night, to how many people pass by your storefront every day. Sometimes, cameras trained to distinguish between croissants and bear claws end up detecting cancer cells. Countless curious patterns can be found if you look close enough.

The AI cameras can be trained with any sort of data set and continuously transmit detected patterns as data packets. These data packets are collected in compliance with all relevant regulations and then transmitted within the LPWAN network built by the mining community, using MatchX’s M2 Pro, the world’s first multi-token miner. The MXProtocol enables machine-to-machine transactions, empowering the mining community to create a scalable and sustainable network, and in return, incentivizing each transaction with mining rewards. Additionally, the MXProtocol ensures the security and encryption of data packets and thus protects all transmitted data.

You can train it (more on that later) to look for the things you are interested in and discover unknown unknowns. Improve your business with more accurate data, simplify your life by knowing what’s happening around your house, or just gain some peace of mind because you will always get a push notification whenever something comes up.

The AI camera uses LPWAN (low-power wide-area network), which ensures that the sensors connecting to the network can do so using only a small amount of energy and are secure and decentralized. Should there ever be an outage with the nearest LPWAN transmitter, the connection will instantly be resumed with the next nearest LPWAN gateway. This is the beauty of operating on a truly decentralized network. Given that the camera itself is equipped with a solar panel, it can work for up to 24 hours without being connected to another power source.

If you are interested in some more technical details, this is the article for you! If you want to purchase a dev kit to see what you can do yourself, you can do so here.

What can the camera do?

This AI camera can detect all sorts of different items or animals that you train it to. For example:

1. The camera can be trained to detect parking spaces and help ameliorate tense parking situations in cities. The anonymous data collected can then be used for further research to aid in future city planning. You can read more about this type of AI-based solution here.
2. You can train it to detect small animals, such as raccoons, skunks, chipmunks, or whatever other animals are local to wherever you have set up the camera.
3. The camera can be taught to differentiate between types of refuse on the street, to then be able to determine which company was the originator of the most prevalent types of litter. Here is a link to read more about how the camera was successfully able to identify and count how many cigarette butts were in a given area, as well as determining other types of trash.

4. Another use case for the camera is counting people who, for instance, pass by a particular storefront. When determining the value of the property, one metric of interest could be how many people passed by the window display and how long they spent in front of the shop. This data set could be further segmented into people the AI camera identifies as male and female, thus informing decisions about what kind of products would sell best at this location.

5. Municipal entities can collect data on how much their infrastructure and facilities are being used and how to optimize further given these parameters. Individuals could use this information to know where parking spots are available, for example, and optimize their commute to and from work. Here is a more in-depth article that explains how this system works.

6. Operators of toll booths or other paid private roads can use these cameras to count how many cars are passing through their roads at which time. Further, they could use this information for most effective preventative maintenance, based on which lanes are used most frequently, for instance. This predictive maintenance saves time and money, as quicker, more cost-effective fixes can be made before there are ever overt outward signs of excessive wear and tear.

7. The camera can also be employed to conduct temperature checks to keep people safe when traveling or in other crowded areas. You can watch a video on this here.

The camera is convenient and energy-efficient, coming equipped with a solar panel to charge during the day. Of course, it is also possible to connect the camera with a cable as well, to ensure an uninterrupted and stable connection.

The 4K camera captures clear images and is even able to identify objects moving at very fast speeds across its field of view.

Why is the Edge X AI Camera beneficial?

The camera is highly capable, as illustrated by the varied use cases listed above. Additionally, you can opt in to receive push notifications via the DataDash app when the camera sees something or a specific event occurs.

Given that you have an M2 Pro miner in the vicinity (40 km radius) that provides the coverage for data transmission, you can send data through the miner to a supernode. People owning M2 Pros receive payments for downlinks, which is, of course, beneficial for the miner.

How do you train the camera?

Similar to any other machine learning system, this AI camera can be trained by giving it a data set to learn from. You can find more technical information on how that is done here.

In short, the Edge X AI Camera is fed a data set that corresponds to whatever it is you are interested in tracking or identifying. From there, machine learning enables the camera to learn the relevant attributes quickly and refine itself from there, with minimal input on your part.

How is the camera secured?

The Edge X AI camera comes as an end-to-end encrypted device out of the box. The innovative device provisioning implemented by the MXC Foundation ensures that all cameras are secured and function as a safe plug-and-play model.

“Privacy is a major concern for citizens and therefore smart city projects around the globe,” said MatchX Co-Founder and CEO Sheen Xin Hu. “By ensuring that no data is stored on the device and only the results of the AI analysis are transmitted to the cloud, we provide companies with a headstart on privacy, especially when building GDPR-compliant solutions.”

Because data is never stored on the device, and only anonymized metadata is ever sent to the cloud, the AI camera is powerful yet still in line with all privacy parameters.

There are countless ways you can use the Edge X AI Camera to improve processes or understand more about your surroundings. We are excited to see all the innovative ways you use this technology and can’t wait to hear your feedback!

‍