Personalised lifestyle analytics has always been of interest to researchers in domains such as healthcare, where researchers may be interested in understanding whether diabetes can be prevented by providing intervention. In the retail domain, researchers are interested in understanding factors that lead to changes in buying patterns. Our technologies dramatically reduce the human effort in which such data capture and analytics require, by relying on automated, smart sensing carried out by personal devices (such as smartphones and smartwatches). In particular, we utilise the inertial sensors and the embedded camera of a smartwatch to capture an individual’s eating behaviour and diet choices unobtrusively. Similarly, we utilise the inertial and Radio Frequency (RF) sensors on a shopper’s smartphone and/or smartwatch to capture their in-store interactions with different products and build deeper profiles for each individual shopper. Current approaches involve either significantly higher manual effort or more extensive infrastructure deployment. For example, for eating analytics, existing approaches require individuals to manually upload pictures of their diet or enter their eating activities into digital journals. For retail, alternative approaches involve the use of in-store cameras and videos, which have privacy concerns and cannot attach an observed shopping profile to a specific customer.
The technology comprises customised applications that run on commercially available personal mobile and wearable devices. The device applications are trained to identify various aspects of the targeted activities (currently eating and shopping) by using machine learning. Software applications, which contain the relevant machine learning components, run on these wearable devices and analyse the data from the various embedded sensors and determine the various aspects of the individual’s activities. The technology also includes backend systems where the inferred behavioural data (e.g., pictures of food items consumed) are stored and displayed for visual inspection. To date, various controlled and on-the-ground studies have been conducted with real-world participants to ensure that the systems are robust and usable.
Various industries can take advantage of this system.
(A) Shopper Analytics: This technology is useful to various companies in the retail industry ecosystem, including store operators, advertisers and multi-channel retail analytics software providers. Such shopper activity may also be of relevance to companies in the consumer healthcare industry sectors.
(B) Food/Eating Analytics: The primary industry is consumer healthcare and wellness. An obvious application is in monitoring food intake. It can be used in elderly health monitoring to ensure that the elderly consume their medicine, or in allergy monitoring (to identify the food consumed in the case of an allergic reaction). This technology can also be used by public sector health and wellness organisations to provide personal feedback and intervention to individuals, which can help foster healthy eating and lifestyle choices.
Since the adoption of smartwatches and the penetration of smartphones is on the rise, a simple deployment on the devices makes our technology available to the end customer. At present, the addressable market is for the more affluent individuals who have the means to purchase consumer smartwatch devices.
· Unobtrusive and automatic monitoring of eating and shopping
· Identification of multiple activities and behaviour by the same system
· Smart analytics