Digital Life: What modular chips could mean for the internet of things

Researchers from Carnegie Mellon University are arguing for a shortcut for building the so-called internet of things — where embedded electronics tie together sensors from multiple devices, collecting and spreading data on everything from the milk supply in your refrigerator to the humidity level in your basement.

So far, industry has developed the internet of things, or IoT, one appliance at a time, such as a connected thermostat, like Nest, or the Amazon Echo that listens to voice commands for music requests or internet searches.

But the Carnegie Mellon team on Wednesday unveiled the idea of “Synthetic Sensors, a sensing abstraction project that allows everyday environments to become smart environments, without the use of cameras.”

They’re exploring a universal sensor that could be added to existing appliances, or stationed in various places in a kitchen or warehouse to detect a range of inputs with the ability to standardize the data and share it.

That “general purpose sensing” could speed the IoT revolution and make it more powerful because it would standardize the chips and the way they collect, record and share data. Your washing machine could, effectively, more easily talk to the dishwasher and the hot water heater, or the garage door opener could communicate with your doorbell and security system. It would be easier to share and coordinate the sensing if all the sensors in a room, or on the market, acted in the same way.

“Traditional approaches rely on direct or distributed sensing, most often by measuring one particular aspect of an environment with special-purpose sensors,” researchers Gierad Laput, Yang Zhang and Chris Harrison of the Human-Computer Interaction Institute wrote in a paper presented at the Conference on Human Factors in Computing Systems on Wednesday. “In this work, we explore the notion of general-purpose sensing, wherein a single, highly capable sensor can indirectly monitor a large context, without direct instrumentation of objects.”

They’ve built a prototype with 19 separate sensor channels, including those that can pick up sound, vibration, motion, color, light intensity, speed and direction.

The sensor can plug into an electrical wall outlet, eliminating a need for battery power. Instead of having a new dishwasher with IoT technology built in, the all-purpose sensors would detect the vibration or heat of one in use. Over time, the sensors could be “trained” to recognize different inputs associated with what’s happening in a room.

“It’s like a little” artificial intelligence, Harrison said in an article published by the university. “It only knows about the things we’ve trained it on. Every time we give it something new, it gives a best guess based on the data we’ve given it.” The researchers hope a modular sensor would be a cheaper way to build “smart” environments.

“We’ve been promised these smart buildings of the future — offices, homes, hospitals. But even the smartest environment is actually pretty dumb,” he said in the article. “People don’t want to spend thousands of dollars to upgrade their homes. The idea is to do this in a way where you don’t have to upgrade your entire home or business.”

This story was originally published May 11, 2017 at 8:58 AM with the headline "Digital Life: What modular chips could mean for the internet of things."