Abstract: Most of the current dietary assessment methods rely on the individual’s own record, such as 24 hrs recall, and which often led to subjective and inaccurate measurements. Although there are some objective and accurate measurement methods, such as the use of doubly labelled water, weighted food record etc., these are either very expensive or can only be conducted in a highly controlled environment. These methods often fail to reveal the actual nutrient intake in the population. Given the advances in smartphone technologies, new software tools and mobile applications have been introduced for users to log and record their food intakes. Although these tools ease the recording of information, such active approach relies mainly on the users’ input which could be subjective and may miss some crucial information for dietary assessments. To address the need for accurate objective dietary assessment, we have introduced the passive approach in dietary monitoring with low-cost wearable cameras. The wearable cameras are designed to be worn on the glasses or pinned on the chest, and they can continuously capture snapshots throughout the day. Hence, the cameras will be able to capture all the eating activities of the users and other daily activities. In addition, to quantify the dietary intake from the images captured, novel AI methods have been developed to recognise the food items, estimate portion sizes, and deduce the nutrient intakes of the participants. With the support from the Bill and Melinda Gates Foundation, large scale studies are being carried out to assess the feasibility and effectiveness of such passive dietary monitoring approach in both rural and urban areas in two African countries, namely Uganda and Ghana. In this talk, I will briefly introduce the concept of passive dietary monitoring approach, present some of our recent work developed, and discuss the challenges faced in collecting/analysing data for estimating the individual dietary intake in our field studies.

Bio: Dr Benny Lo, PhD is a Senior Lecturer of the Hamlyn Centre/Dept of Surgery and Cancer, Imperial College. His research mainly focuses on Body Sensor Networks, Pervasive Sensing, Biomedical Engineering, Micro-Electronics, Surgical Vision, and Machine Learning for healthcare, well-being and sports applications. He is one of the pioneers in pervasive sensing research and led a number of the translational projects on applying sensing technologies in clinical applications. His research work has been highly recognised by academic and industrial and led to numerous awards, such as the Best Paper award at BSN2021, the FAU’s Open Challenge, etc. He is an Associate Editor of the IEEE Journal of Biomedical and Health Informatics (J-BHI) and the Topics Editor of the International Journal of Distributed Sensor Networks (IJDSN). He was the Past Chair of the IEEE EMBS Wearable Biomedical Sensors and Systems (WBSS) Technical Committee 2018-19 and a Steering Committee member of the IEEE EMBS Standards Technical Committee.