College of Maine researchers invented a tool that might function a launchpad for brand new know-how to ease each day monitoring of meals and beverage consumption for seniors and folks with persistent well being circumstances. 

SipBit, created by Nimesha Ranasinghe, an assistant professor of spatial computing, and Chamath Amarasinghe, a Ph.D. pupil of spatial info science and engineering, can pinpoint beverage sort, quantity and sugar content material as soon as submerged in liquid. The gadget, skilled to acknowledge these traits by way of a collection of deep studying algorithms, can determine them by utilizing electrical impedance measurements over a spread of frequencies of a drink.  

Electrical impedance is the opposition supplied to the electrical present — transferring charged particles like electrons— by an object. A given set of measurements of {an electrical} impedance correlates with a specific beverage trait, corresponding to whether or not it’s tea, espresso or soda. 

SipBit applies a recognized electrical pulse throughout 1000’s of frequencies after which measures the impedances by way of the drink, a technique referred to as electrical impedance spectroscopy. After amassing a number of units of measurements, SipBit analyzes them to determine the bodily and chemical properties of a beverage, notably what sort of drink it’s and its quantity and sugar content material. 

Many seniors and folks with strict diets, together with those that have most cancers, coronary heart and kidney ailments, diabetes and different circumstances, should manually file each day what they eat and drink intimately to assist protect their well being, which Ranasinghe says could be tedious, time consuming and open to miscalculation. He and Amarasighe hope to boost the know-how in SipBit to determine much more traits, corresponding to sodium (i.e., salt), carbohydrates, protein, and spice content material, and file it on units like computer systems and smartphones to alleviate their burden. They then hope to develop cutlery and drinkware which might be geared up with SipBit. 

Watch the video about SipBit produced by the Multisensory Interactive Media Lab to be taught extra. 

“We’re ranging from this basis,” Ranasinghe says. “Our subsequent step is to discover completely different purposes and create a wise cup or tumbler the place individuals can mechanically file their calorie consumption intimately and actual time.” 

SipBit differs from different know-how designed to determine numerous features of meals and drinks by utilizing electrical impedance spectroscopy as a substitute of analyzing photos of what individuals eat and drink earlier than and after meals.

Amarasinghe and Ranasinghe say different units have issues precisely distinguishing drinks of the identical coloration and figuring out their quantity and different inside attributes. For instance, they might battle to find out whether or not a espresso was a darkish or medium roast or how a lot is the sugar content material of the drink. 

“Via electrical impedance, we will acknowledge completely different beverage varieties and traits primarily based on completely different signatures; for instance, a cup of Pepsi versus a cup of Coca Cola,” Amarasinghe says. 

Ranasinghe’s analysis primarily focuses on replicating culinary experiences by simulating tastes, smells and different senses by way of multisensory augmented actuality and different applied sciences. His innovations have earned awards and nationwide acclaim. A few of his standard units embody the Digital Cocktail, or Vocktail, Digital Lollipop and Digital Lemonade. 

Ranasinghe says SipBit builds on his earlier analysis as a result of having sensory know-how that may detect and acquire information on completely different meals or beverage traits will assist invent new units to simulate these experiences. He says he finally hopes to develop a digital area the place individuals can share simulated meals and drinks world wide. 

“We will present new alternatives for human-food interactions,” Ranasinghe says. “One drive I’ve is determining how we will add these unexplored senses — scent and style — into our applied sciences. SipBit is a part of an even bigger puzzle of future human-food digital interactions as a result of if you wish to incorporate new senses, it’s a must to invent know-how that may simulate them, sense them and acquire information on them.”  

Contact: Marcus Wolf, 207.581.3721; marcus.wolf@maine.edu