MEMS, sensor steer mental health analysis

Article By : Peter Clarke

With hyperspectral imaging, it is possible to spot hidden dangers such as contaminated food or black ice and obstacles shrouded in fog.

AI, MEMS and sensors will play a major role on our lives within five years, based on IBM’s research. In IBM’s multimedia website under the label "IBM 5 in 5: five innovations that will help change our lives within five years," it expounds the possibilities the analog, MEMS and sensors bring. But digital electronics will also have its say in the form of big data and AI.

The full list covers AI, hyperspectral imaging, microfluidic lab-on-chips, networks of novel sensors and something IBM calls "macroscoping."

Mental health analysis

Amongst the developments IBM researchers are predicting–and a slightly disconcerting prediction at that–is that what we say and write could be monitored and used as indicators of our mental health and physical well-being. Patterns of speech and writing and how they change over time, analysed by cognitive systems, could provide tell-tale signs of early-stage developmental disorders, mental illness and degenerative neurological diseases.

However, IBM reports that the global cost of mental health is projected to hit ₹407.97 lakh crore by 2030 and early treatment may well be the best way to ameliorate that bill and keep people fitter and happier for longer.

The sort of conditions such cognitive analysis could highlight include Parkinson’s, Alzheimer’s, Huntington’s disease, Post-traumatic stress disorder (PTSD) or even neurodevelopmental conditions such as autism and Attention deficit hyperactivity disorder (ADHD).

Technical possibilities

Hyperspectral imaging is the sensing in multiple bands of the electromagnetic spectrum in a correlated way. By working with the visible spectrum and beyond it is possible to spot hidden dangers such as contaminated food or black ice and obstacles shrouded in fog. IBM researcher predict that in the next five years what is already technically possible will come down dramatically in size and price, making "superhero vision" part of everyday experience.

As to macroscoping: IBM predicts that in a similar way to hyperspectral imaging there are tremendous gains to be achieved by aligning, correlating and using the exabytes of data that are already captured for discrete purposes. At the moment, IBM states, most data collected is "unorganised." There are already more than six billion connected devices generating tens of exabytes of data per month, with a growth rate of more than 30% per year.

If multiple sources of data could be aggregating, organised and analysed it would be possible to find new optimal practises in such areas as water-efficient agriculture and in science from microscopes to telescopes.

First seen on EDN Europe

Leave a comment