Invited Speakers

Benny Lo

Dr Benny Lo, PhD is a Senior Lecturer of the Hamlyn Centre/Dept of Surgery and Cancer, Imperial College. His research mainly focuses on 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 BSN2019, the FAU’s Open Challenge, etc. He is an Associate Editor of the IEEE Journal of Biomedical and Health Informatics (J-BHI) and a member of the Editorial board of the International Journal of Distributed Sensor Networks (IJDSN). He is the Past Chair of the IEEE EMBS Wearable Biomedical Sensors and Systems (WBSS) Technical Committee and the Steering Committee member of the IEEE EMBS Standards Technical Committee.

An innovative passive dietary monitoring system
There is currently no accurate measurement of dietary intake. All current methodologies of assessing food intake have inaccuracy rates of 30-70%. Yet accurate assessment of nutritional intake is a prerequisite to define the nutritional status, nutritional needs of a population and to monitor the effectiveness of public health interventions to maintain nutritional health. To this end, it is necessary to develop tools that facilitate accurate assessment of nutritional intake in populations without affecting their normal routines. Existing dietary methods are labour-intensive, expensive, and do not report nutritional intake accurately or social hierarchy of food intake. To address this gap in dietetics, the Bill and Melinda Gates Foundation funded project “An Innovative passive dietary monitoring system” aims to develop a passive dietary monitoring system for people living in Low-or-Middle Income Countries (LMICs) which does not rely on individual participation to record intake. This project focuses on both urban and rural areas in two African countries, Uganda and Ghana. To capture individual dietary intake, wearable camera technologies and fixed cameras are integrated into the system for capturing food preparation and eating activities in kitchens and dining areas. Extensive studies and field trials are being carried out in home settings in Uganda and Ghana.
In this talk, I will give you an overview of this project and introduce some of the innovative approaches we have developed for addressing the challenges faced in collecting/analysing data and estimating the individual dietary intake from the data acquired in field studies in Africa.

Anastasios Delopoulos

Dr. Anastasios Delopoulos was born in Athens, Greece, in 1964. He graduated from the Department of Electrical Engineering of the National Technical University of Athens (NTUA) in 1987, received the M.Sc. from the University of Virginia in 1990 and the Ph.D. degree from NTUA in 1993. From 1995 till 2001 he was a senior researcher in the Institute of Communication and Computer Systems of NTUA. Since 2001 he is with the Electrical and Computer Engineering Department of the Aristotle University of Thessaloniki where he serves as an associate professor and as the director of the Information Processing Laboratory of the same department. His research interests lie in the areas of machine learning, signal and multimedia processing and computer vision. On the applied domain he works in the areas of multimedia retrieval, biomedical engineering and behavioural informatics. He is the (co)author of more than 120 journal and conference scientific papers. He has participated in 22 European and National R&D projects related to application of his research to entertainment, culture, education and health sectors. He was the coordinator of “SPLENDID: Personalised Guide for Eating and Activity Behaviour for the Prevention of Obesity and Eating Disorders” (EU-FP7, 2013-16) and he currently coordinates “BigO: Big Data against Childhood Obesity” (EU H2020, 2016-20) and “REBECCA: REsearch on BrEast Cancer induced chronic conditions supported by Causal Analysis of multi-source data” (EU H2020, 2021-25). Dr. Delopoulos is a member of the Technical Chamber of Greece and the IEEE.

BigO: Big Behavioural data against childhood obesity
In 2013, over 42 million children were considered overweight or obese, and approximately 70 million children will be overweight or obese by 2025. In Europe, the prevalence of overweight and obese children varies across countries, peaking at just over 40%. In general obesity increases the risk of many severe health problems, such as type II diabetes, stroke and coronary heart disease and, even in children and adolescents, overweight and obesity are associated with significant earlier morbidity and mortality. Also, childhood obesity is regarded a chronic condition, and the affected children are regarded as the obese adults of the future.
EU has adopted the Action Plan on Childhood Obesity 2014-2020 which enumerates a collection of possible interventions that should be taken by different agents towards childhood obesity reduction. This is a useful collection of policies and policy change suggestions, however without evidence based prioritization, identification of locally targeted causes, pre-assessment and monitoring of the effects, we believe that it will never succeed in its objectives. This is where BigO, an EU funded H2020 project, enters the picture. BigO intends to (i) Support Public Health Authorities to design local counter obesity interventions on the basis of collected evidence, (ii) Support Clinicians in obesity clinics to obtain a clear and objective view of how their patients, children with obesity and overweight, behave in between visits. To implement these functionalities, BigO relies on the use of novel signal processing, machine learning and causal inference technologies in order to
– Measure obesity related behaviour of individual children and aggregated indicators of the population (eating habits, physical activity, sleep) in a massive, objective and privacy preserving way.
– Measure the environment parameters that have causal influence on the above behaviours
– Support detailed visualization of the spatial distribution of behaviours and environment parameters
– Identify the main factors of the environment that are responsible for the obesogenic behaviours for each region
– Predict the effect of designed interventions
This presentation will briefly explain the most interesting aspects of this approach and will demonstrate indicative results of the big behavioural data analysis and causal modeling.