Deep Learning Technologies for Secure IoT Sensors

Deep Learning Technologies for Secure IoT Sensors

deep learning

This post is also available in: heעברית (Hebrew)

Computer scientists have developed tiny computers in attempt to make smarter, smaller sensors for medical devices and the Internet of Things – sensors that can do more with less energy. They used deep learning technologies for enhancing face and voice recognition capabilities.

Many of the microphones, cameras, and other sensors that make up the eyes and ears of smart devices are always on alert, and frequently beam personal data into the cloud because they can’t analyze it themselves.

David Blaauw and his colleague Dennis Sylvester, both IEEE Fellows and computer scientists at the University of Michigan have developed the “micromote” computers. By developing tiny, energy-efficient computing sensors that can do analysis on board, they  hope to make these devices more secure, while also saving energy.

The micromote designs use only a few nanowatts of power to perform tasks such as distinguishing the sound of a passing car and measuring temperature and light levels. They showed off at a conference a compact radio that can send data from the small computers to receivers 20 meters away.

They also described their work with TSMC (Taiwan Semiconductor Manufacturing Company) on embedding flash memory into the devices, and a project to bring on board dedicated, low-power hardware for running artificial intelligence algorithms called deep neural networks.

According to the IEEE website, the group worked with TSMC to bring flash memory on board because to record video and sound, the tiny computers need more memory. Now they can make tiny computers with 1 megabyte of storage.

Another micromote they presented at the conference incorporates a deep-learning processor that can operate a neural network while using just 288 microwatts. Neural networks are artificial intelligence algorithms that perform well at tasks such as face and voice recognition. They typically demand both large memory banks and intense processing power. The Michigan group brought down the power requirements by redesigning the chip architecture.

The idea is to bring neural networks to the Internet of Things. “A lot of motion detection cameras take pictures of branches moving in the wind—that’s not very helpful,” says Blaauw. Security cameras and other connected devices are not smart enough to tell the difference between a burglar and a tree, so they waste energy sending uninteresting footage to the cloud for analysis. Onboard deep-learning processors could make better decisions, but only if they don’t use too much power.

The Michigan group imagine that deep-learning processors could be integrated into many other Internet-connected things besides security systems. For example, an HVAC system could decide to turn the air-conditioning down if it sees multiple people putting on their coats.

The Michigan group hopes they will be ready for market in a few years. Blaauw and Sylvester say their startup company, CubeWorks, is currently prototyping devices and researching markets. The company was quietly incorporated in late 2013. Last October, Intel Capital announced they had invested an undisclosed amount in the tiny computer company.