Subscribe / Unsubscribe Enewsletters | Login | Register

Pencil Banner

Neura's novel approach: Baking intelligence into connected devices

Nancy Gohring | Aug. 15, 2014
Neura, a startup that has been accepted into Microsoft Ventures' accelerator program, has a novel approach to connecting devices.

Neura could also provide information to services so that, for example, a music service like Spotify can get a notification that a user only has 15 minutes left to her run so that the service can start playing music that might motivate her through the final stretch.

On the backend, Neura ingests the sensor data into its translation machine that it calls Harmony. It's an abstraction layer that normalizes the data that's coming from different sources. On top of that sits what Neura calls its Trac Event Machine which looks for patterns in user behavior. Its artificial intelligence layer makes sense of the data.

With all this data, Neura creates what it calls a physical graph for users. "The physical graph is how we see you. So it's all your devices and all your locations populated on a map, whether you input them or we infer them," Meiri said. Neura can infer the location of your home, for instance, based on it being the location you most often sleep. It can infer family members based on proximity to other user devices in the home and it can similarly figure out colleagues and running mates.

Of course, that might create what some people view as a privacy nightmare. Meiri thinks Neura will get past privacy concerns by being ultra transparent. "We are transparency geeks," he said. "My personal philosophy is that whatever I know about you, you should know as well."

In practice, that means Neura wants to let its users view this physical graph and decide exactly what they want to share. "We want to become your firewall," he said. For instance, the app would first ask a user if it can automatically make sure the front door is locked when the user is about to go to sleep at night. A user will be able to change such settings any time.

Meiri argues that its approach is better from a privacy perspective than some other approaches. If a company with a smart door lock wants to automatically lock the door when a user goes to sleep, it might have to collect data from a user's sleep sensor and phone.

"They have to take your entire sleep data, crunch it, and figure it out," he said. Apps on a smart light bulb, attached to the water heater, and the furnace would have to similarly collect and crunch that same data. Neura hopes to be a central clearinghouse that not only crunches all that data just once, but only delivers the relevant bits to individual apps, rather than requiring each app to collect far more data about users than they actually need.


Previous Page  1  2  3  Next Page 

Sign up for CIO Asia eNewsletters.