Cloud Computing

Of Big Brains and Tiny Devices: Here Comes the Internet of the Body

Share this post:

How does a gifted student in Switzerland in the 1980s apply his talents? On precision mechanics and watchmaking, of course.

Before becoming the multifaceted scientist he is today, Bruno Michel started out as a watchmaking apprentice. But at the time the watch industry was facing a challenging period and its four-century dominance was coming to an end as digital began taking over. This triggered Michel to switch his field from mechanics and electronics to biochemistry where he eventually carried out a PhD at the University of Zurich.

He would come to realize that his previously acquired knowhow wasn’t time wasted as he developed smart robots to reach even more accurate results on a much wider library of genetically engineered enzymes he was studying — completely unheard of at the time.

Thankfully for IBM and for the engineering community, these two experiences triggered his fascination with integrating all kinds of functionality into smaller and smaller highly efficient devices.

Thirty-plus years later Michel, a National Academy of Engineering inductee, now leads an IBM Research team in developing tiny, powerful computing devices – some so small they can eventually be fixed in the ear canal or worn as a sub-millimeter thin patch no more intrusive than a Band-Aid.

These devices are part of an initiative known as the Internet of the Body, which is part of the IBM Frontiers Institute, a collaborative effort bringing together IBM scientists with clients to work side by side on forward thinking science with implications for business and society.

The Cognitive Hypervisor sits near a patient’s bed at home and collects data from various wearable devices

Cognitive Hypervisor

The combination of exploding compute power, extreme miniaturization, IoT and the rise of big data and cognitive analytics holds huge breakthrough potentials. Think about how communications will change with tiny computers attached to our bodies.

“Our goal is a health companion and we call it the cognitive hypervisor,” Michel says on a visit to his lab in Zurich where a collection of early generation wearables sit in heaps alongside prototypes in various stages of design. “We want to enable patients to leave the hospital sooner, so they can recover from the comfort of their own home, while still receiving care remotely from trained medical staff.”

Wearing two smart watches and a smart ring, which monitors his pulse, Michel is convinced that tiny computers will unobtrusively collect and analyze vast data flows from all over our bodies – key vital and emotional signs – to become trusted personal healthcare advisors.

“They record clinical-quality patient data and have the power to transform the patient-doctor experience,” he says. “Recovering at home will significantly lower healthcare costs while increasing patient satisfaction – if we are successful the hospital of the future will look very different.”

The cognitive hypervisor is a versatile platform that shows an end to end integration from multiple wearable sensors in an edge computing device that interacts with the IBM Cloud to provide seamless access to IBM Watson API’s already commercially available, such as speech to text, to drive a powerful user interaction. If a vital sign begins to go beyond normal ranges, like blood pressure, doctors and emergency services can be notified — welcome news particularly for an aging population above 60, which will reach 22 percent by 2050.

With the elderly numbers skyrocketing, in addition to remote monitoring, the cognitive hypervisor can also provide augmented healthcare services such as reminding patients when to take their pills, when to take a rest or sit down, and in an emergency, call an ambulance. Using Watson’s APIs, patients can also ask it questions, such as “Can I take aspirin with my current medication?”

For patients with debilitating diseases such as Alzheimer’s, dementia and Parkinson’s Disease, the cognitive hypervisor can also monitor patients via their speech patterns to recognize advancements of the disease based on audible changes.

In addition to helping patients, Michel sees other applications for the technology particularly in workplace safety.

He adds, “To demonstrate the viability of the technology we are monitoring physiological and psychological stress and potential other problems during “smoke diver” trainings which are part of a fireman’s overall education.”

The Cognitive Hypervisor dashboard shows real-time data from various wearables can can be viewed by doctors and caretakers while the patients are recovering at home. (Click for larger view)

Design Thinking

When your goal is to create the internet of the body or an entire IoT system, it’s important to design with the body in mind. One of Michel’s favorite design strategies is known as biomimicry or bionics, which, simply put, is copying the body’s functionality into an inorganic device.

For example, he used the concept of combined power delivery and cooling using hierarchically branched transport systems, the second most important biological concept after the genetic code, to build much more efficient cloud and edge computers using first server and then smartphone technology. Edge computing occurs when data is analyzed at the source  where it is collected and not in the cloud.

This experience will undoubtedly contribute to Michel’s ultimate vision of packaging the capabilities of the palm-sized cognitive hypervisor into a device which can sit comfortably in your ear within the next five years.

He adds, “This is the starting point of a roadmap towards powerful miniaturized sensors that make use of the latest sensing, secure communication and computation technologies. It’s now time for the next grand challenge of building an efficient wearable IoT system with brains, sensors, communications, and actuators very much like our own bodies.”

Michel has spent nearly three decades at IBM Research pushing the boundaries of computer design, but he hasn’t forgotten the contributions that generations of mechanical artisans have brought to the field.

“We must not forget that the first wearables were in fact wrist watches,” he says. “The functionality may have been somewhat limited, but they paved the path for a future of powerful miniature efficient machines that will improve our life.”

Follow the progress of the research @BmiBruno

More stories

Dark Matter Matters: AI Makes DNA Dark Matter Useful

What is the minimal description that captures a space? Asking a mathematician’s basic question of a  biological dataset reveals interesting answers about biology itself. This summarizes our underlying approach to subtyping hematological cancer. Disease subtyping is a central tenet of precision medicine, and is the challenging task of identifying and classifying patients with similar presentations […]

Continue reading

Helping to Untangle Cancer Drug Resistance with Data

Why do targeted cancer therapies often fail? We have acquired so much more understanding about cancer in the last fifty years than in the last five thousand years. Approaches to patient treatments have dramatically changed, and statistics show significant improvement in patient response and outcomes to therapy in the last half a century [1]. Yet […]

Continue reading

World’s smallest DRAM cell promises low-power memory in future mobile devices

In a new paper published in Nature Electronics, IBM researchers demonstrate the smallest ever built DRAM memory cell, fifty years after its invention. The new DRAM cells feature potentially low power consumption and an unprecedented small footprint. They could be therefore particularly appealing for implementation in mobile devices or as cache memory.

Continue reading