Quantum Imaging for Monitoring of Wellbeing & Disease in Communities

Lead Research Organisation: University of Glasgow
Department Name: School of Engineering

Abstract

We have identified the home as the place where future transformational healthcare changes will occur with the greatest impact potential. Our vision is that the home of the future will be an environment that has the ability to follow our everyday movements, behaviour and wellness. In this sense, it will become an extension of our physical bodies, providing us with feedback, advice and alerts in the presence of anomalies in the data streams collected by new-generation sensors. The analysis of the data-streams from the sensors will be based on clinically approved models, thus effectively bringing highly trained expertise directly to the living environment.

Remote detection and monitoring of parameters such as gait, macro and micro-movements, blood flow, heart rate and potentially even brain function, when combined with data-driven models, will allow to both monitor health and the onset of non-communicable diseases (NCDs) but also recovery from NCDs or surgery with personalised and continuously updated re-habilitation programmes.
This therefore takes the concept of precision medicine and extends it to our overall physical and mental well-being, with the vision of enabling "precision healthcare" delivered to the home.

The sensors we are proposing are based on new-generation quantum-inspired cameras. These cameras can detect extremely low levels of light, thus rendering their presence in the home completely unobtrusive. The cameras can also detect the arrival time of light at the sensor with very high precision and at very high frame rates. The combination of these features enables the measurement of both macro-movement (in a similar fashion to more common cameras) and micro-movement (not currently possible with current, low-cost or low form-factor cameras). Micro-movement detection is sufficiently precise to capture nanometric variations in skin/body shape and thus directly detect blood flow, monitoring the precise shape and variations of heart beat. Future, very ambitious plans, include extending this capability to the brain. Our cameras can also be combined with RF technology to provide richer data, e.g. Doppler signals directly related to speed of movement.

All these indicators will be fed into machine learning models that monitor, learn and are updated over time and, most importantly, adapt to the individuals inhabiting the home environment. Thus, the systems will quickly adapt and evolve for bespoke individuals, providing precision healthcare monitoring and feedback.

Alongside the engineers and computer scientists working on the sensors and data analysis, our programme involves clinicians who will provide the interpretation models for our data and also partners who will give us access to new-generation intelligent homes inhabited by users who are already beta-testing sensors monitoring for example gross movement.

Planned Impact

Currently, Non-Communicable Diseases (NCDs) pose a major public health challenge, affecting more than 42% of the population. These individuals require significant resource across primary, secondary and community care. Coronary heart disease remains the leading public health problem in the UK in terms of its economic burden in community care with costs outside of clinical treatment that are approaching £8B. Other NCDs are becoming increasingly important with estimates now suggesting that stroke consumes more than 7% of spending in community healthcare. These figures continue to increase as demographic changes accelerate towards an ageing population.

Economic and demographic trends are likely to impact significantly on community healthcare systems over the coming decades, with increasingly dependent, unwell individuals either living alone or within other community care settings. The capacity for sensing and intelligent feedback in such future homes has the potential to enable residents to initiate programmes of professionally validated therapies for a variety of health and wellness issues.

Bringing precision healthcare to the home environment is therefore the main impact expected from our research programme with all the consequences that this will bring associated to improved life expectancy, improved quality of life, reduced pressure on the NHS and consequent improvement of service quality with the redeployment of the financial resources.

Our technology has the ability to assess not only physical health of an individual but also to measure proxies for mental health, social health and happiness/wellness. It will transform rehabilitation strategies and fitness monitoring, either at home or in community settings. If fully realized, the technology may also have a broad applicability within hospital environments. In all of these cases this research programme has the potential to mitigate the increasing health, social care and wellness costs of an ageing population, with growing prevalence of NCDs, not only within the immediate term but also as we approach 2050 and beyond.

Beyond the long-term impact described above, the following impacts are expected from this project in the short term, namely:

1. Advances in scientific knowledge and understanding that maintain the UK leadership position in the development and exploitation of novel engineering and data science solutions to assess health and wellness;

2. Partnerships with healthcare providers to develop cutting edge technology targeted to accelerate translation and enhance health and wellness of patients and individuals.

3. Contributions to the economic competitiveness of the United Kingdom, through the translation and commercialization of scientific knowledge into new technologies, services and products.

4. Trained researchers with a set of multidisciplinary skills in engineering, healthcare technologists and computing science for both academic and non-academic professions.

In summary we aim to generate impact by revolutionising health and care in the community for 2050 using novel, quantum-inspired, imaging methods, transforming homes and healthcare centres into smart-health environments through innovative machine learning and quantum sensor technology that is unobtrusive and data privacy-friendly.

Publications

10 25 50
 
Description Aegean airlines donation
Amount € 74,000 (EUR)
Organisation Aegean Conferences 
Sector Private
Country United States
Start 08/2023 
End 08/2028
 
Description Designing Interaction Freedom via Active Inference (DIFAI)
Amount £2,137,996 (GBP)
Funding ID EP/Y029178/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 01/2024 
End 12/2029
 
Description Google Soli donation
Amount $200,000 (USD)
Organisation Google 
Sector Private
Country United States
Start 12/2021 
 
Description Moodagent Closed-loop Search PhD Studentship
Amount £37,000 (GBP)
Organisation Moodagent 
Sector Private
Country Denmark
Start 03/2022 
End 09/2025
 
Title 5G-Enabled Contactless Multi-User Presence and Activity Detection for Independent Assisted Living 
Description The dataset represents a combination of activities captured through wireless channel state information, using two USRP X300/X310 devices, to serve a system that was designed to detect presence and activities amongst multiple subjects. The dataset was divided into 16 classes, each represents a particular number of subjects and activities. More details can be found in the readme file. 
Type Of Material Database/Collection of data 
Year Produced 2021 
Provided To Others? Yes  
URL http://researchdata.gla.ac.uk/id/eprint/1151
 
Title Intelligent Wireless Walls for Contactless In-Home Monitoring 
Description The dataset is about monitoring human activities in complex Non-line-of-sight (Non-LOS) environments. Radio frequency (RF) sensing was employed in particular to collect unique channel fluctuations induced by multiple activities. The data collection hardware consists of two USRP devices one used as a transmitter (Tx) and one as receiver (Rx). Both USRPs are placed in a position where Tx and Rx were not in LOS. One was corner scenario, and the other was multifloor scenario. In the corner scenario, Tx was in one corridor while the Rx was in the other corridor and reflecting intelligent surface (RIS) was placed at corner to steer the beam towards the subject. The activities were performed between Tx and RIS. In multifloor scenario, Tx was on 5th floor and Rx was 3rd floor along with RIS. Activities were performed between RIS and Rx. Two subjects participated in experiments where each activity was performed for 6 seconds. The considered activities were sitting, standing, walking and empty. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL http://researchdata.gla.ac.uk/id/eprint/1281
 
Title NodeNS Human Activity Dataset 
Description To date, numerous types of collection devices have been used in the recognition of human activities. However, due to the scarcity of training data, the task of 3D point cloud labelling has not yet made significant progress. To overcome this challenge, it is aimed to deduce this data requirements gap, allowing deep learning methods to reach their full potential in 3D point cloud tasks. The dataset used for this process is comprised of dense point clouds acquired with the static ground sensor by the NodeNs company supported MIMO radar (NodeNs ZERO 60 GHz IQ radar). It contains multiple types of human being data ranging from one to four individuals and encompasses a range of human action scenarios, including standing, sitting, picking up, falling, and walking. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL http://researchdata.gla.ac.uk/id/eprint/1354
 
Title Non-invasive Localization using Software-Defined Radios 
Description The dataset is about locating human activities in an office environment. Radio frequency (RF) sensing was employed in particular to collect unique channel fluctuations induced by multiple activities. The data collection hardware consists of two USRP devices that communicate with each other when activity takes place inside their coverage region. The USRPs are based on the National Instrument (NI) X310/X300 models, which are connected to two PCs by 1G Ethernet connections and have extended bandwidth daughterboard slots that cover DC-6 GHz and up to 120 MHz of baseband bandwidth. The two PCs were equipped with Intel(R) Core (TM) i7 7700.360 GHz processors, 16 GB RAM, and the Ubuntu 16.04 virtual operating system. For wireless communication, the USRPs were equipped with VERT2450 omnidirectional antennae. One participant performed in a room environment for the duration of the experiment, collecting 4300 samples for seven different activities in three zones and locations. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL http://researchdata.gla.ac.uk/id/eprint/1283
 
Title On the Reduction of Uplink Electromagnetic Field Exposure Using Reflecting Intelligent Surfaces: An Experimental Validation 
Description The dataset represents the measured values of power captured during uplink transmission by an E-field probe near a head phantom model to evaluate Specific Absorption Rate (SAR) in the presence of a Reconfigurable Intelligent Surface (RIS). A combination of different configurations (effective unit cells which are switched on) of RIS. The head phantom was marked with 120 different positions. For each RIS configuration, 120 measurements were recorded to measure sensed power at a head phantom model using an E-field probe. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL http://researchdata.gla.ac.uk/id/eprint/1335
 
Title Pushing the Limits of Remote RF Sensing: Reading Lips Under Face Mask 
Description The dataset is about reading lips in a privacy preserving manner. In particular, radio frequency (RF) sensing was used to capture unique channel variation due to lip movements. USRP x300 was utilised equipped with the VERT2450 omnidirectional antenna and HyperLOG 7040 X used for reception and transmission respectively. Further, the same experiment was repeated with a Xethru UWB radar, where doppler frequency shifts due to lip movements are captured. We consider six classes for lip movements. Five vowels (a, e, i, o, u) and one empty class where lips were not moving. We are able to read lips even under face masks. Three subjects 1 male and 2 females participated in the experiments. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL http://researchdata.gla.ac.uk/id/eprint/1282
 
Title Recognizing British Sign Language using Deep Learning: A Contact-less and Privacy-Preserving Approach 
Description The dataset is about BSL in a privacy-preserving manner. In particular, radio frequency (RF) sensing was used to capture doppler frequency shifts due to Head and Hand movements. Xethru UWB Radar X4M03 was used for reception and transmission respectively. We consider fifteen classes for BSL movements. fifteen Signs such as drink, eat, help, stop, walk, confused, depressed, pleased, hate, sad, family, brother, father, mother, and sister were performed. Four subjects 1 male and 3 females participated in the experiments. 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL http://researchdata.gla.ac.uk/id/eprint/1350
 
Title Remote laser-speckle sensing of heart sounds for health assessment and biometric identification 
Description The paper describes a contactless, machine-learning assisted method for heart-sound identification and quantification based on the remote measurement of the reflected laser speckle from the human neck skin surface. For more details see Readme.rtf 
Type Of Material Database/Collection of data 
Year Produced 2022 
Provided To Others? Yes  
URL http://researchdata.gla.ac.uk/id/eprint/1238
 
Description NHS 
Organisation National Health Service
Country United Kingdom 
Sector Hospitals 
PI Contribution Ongoing discussions and collaborations on research projects.
Collaborator Contribution Ongoing discussions and collaborations on research projects.
Impact See joint publications.
Start Year 2021
 
Title Dispositif de caractérisation de l'actimétrie d'un sujet en temps réel 
Description L'invention présente un dispositif (1) pour caractériser en temps réel l'actimétrie d'un sujet, présentant : un radar (2) émettant et recevant des signaux radar et présentant une interface logicielle pour configurer la forme du signal émis ; des moyens de traitement et de calcul (3) couplés au radar (2), présentant un classifieur (3a) entrainé à l'aide d'une base de données, lesdits moyens de traitement et de calcul (3) étant configurés pour réaliser en temps réel: -une acquisition d'images micro-doppler (6) couleurs ayant plusieurs canaux de couleurs (R, V, B), présentant chacune des signatures micro-doppler (6a) avec des pixels couleurs dont la valeur est fonction d'une réflectivité et d'une vitesse du sujet; -un traitement des images micro-doppler (6) pour : calculer une image dite monochromatique ayant des pixels monochromatiques, ayant chacun une intensité monochromatique donnée, à partir des pixels couleurs de chaque image micro-doppler couleur ; transformation de l'image monochromatique en image binaire par segmentation, selon un seuil d'intensité, des pixels monochromatiques, réalisant des pixels binaires dont la valeur est dépendante de l'intensité chromatique du pixel monochromatique associé au pixel binaire, par rapport au seuil, Figure 1 
IP Reference EP19306308 
Protection Patent application published
Year Protection Granted 2021
Licensed No
Impact currently in progress. We do not know if this will be granted yet but the patent has been submitted. It is likely to be used to leverage for projects in the consortium we are forming. This has created opportunities to collaborate with France University Cergy-Pontoise, TU Deflt and the University of Glasgow who are now part of a consortium around asisted living to bid for projects in that area to leverage the IP (if it is granted).
 
Title METHOD AND DEVICE FOR HUMAN ACTIVITY CLASSIFICATION USING RADAR MICRO DOPPLER AND PHASE 
Description The invention relates to the field of real-time detection and characterization of 5 the body motion of a subject. More particularly, the invention relates to a method and a device for real-time classification of human activity using micro-Doppler signatures. 
IP Reference EP21306742.4 
Protection Patent / Patent application
Year Protection Granted 2021
Licensed No
Impact METHOD AND DEVICE FOR HUMAN ACTIVITY CLASSIFICATION USING RADAR MICRO DOPPLER AND PHASE EP21306742.4 this has been flagged for a high growth spin out but we ran into technical difficulties which has delayed this endeavour.
 
Company Name LIGHT-HEARTED AI LIMITED 
Description Light Hearted AI (now registered as Light Hearted AI Healthcare) is a spin out from my research team that aims to commercialise technology to remotely monitor heart health. This work is based on the PhD project and PhD publication led by Lucrezia Cester, currently CE of Light Hearted AI. The technology is based on the use of an eye safe laser and a camera that collects the laser light that is back reflected from the neck of the person being monitored. Clinical trials indicate the ability to detect heart murmurs. VC capital has been raised and 4 people have been hired to work on various aspects related to commercialisation of the device. The company is also actively collaborating with the research team at University of Glasgow. 
Year Established 2022 
Impact The company has only recently attracted VC capital that has allowed it to hire new people. Preliminary clinical trials are still underway at the time of writing (February 2024). However, the company and the clinical trials have been the topic of a very positive article the Guardian (January 2024).
 
Description Demonstration of our QUEST activity to the CEO UKRI and STFC 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Policymakers/politicians
Results and Impact Demonstration of our QUEST activity to the CEO UKRI and STFC
Year(s) Of Engagement Activity 2023
 
Description Maintaining muscle function and sensing in assisted living - U3A Bearsden Milngavie 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Study participants or study members
Results and Impact We discussed the effect of Krill oil in maintaining muscle function with the university of the 3rd age members of Bearsden and Milngavie and how we monitor people in their own homes.
I was invited back to present to the Science special interest group and nominated for the national level talks as a speaker of interest.
Furthermore we recruited over 15 participants for 3 separate studies on krill oil for muscle function.
Year(s) Of Engagement Activity 2023
 
Description Maintaining muscle function and sensing in assisted living - U3A Newton Mearns 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Study participants or study members
Results and Impact We discussed how krill oil is used to maintain muscle function in elderly adults and how to monitor people in their own homes.
This allowed the recruitemt of 4 participants in the krill oil studies and 1 for the sensing studies as well as changes in attitudes.
Year(s) Of Engagement Activity 2023
 
Description radar in assisted living demonstration 
Form Of Engagement Activity Participation in an open day or visit at my research institution
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact University of Glasgow - engineering open day - radar in assisted living demonstration - high school students
Students inquired about the use of the sensors and if they would see this during their curriculum in Glasgow.
Year(s) Of Engagement Activity 2022
 
Description radar in assisted living: an overview 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Invited talk, radar in assisted living: an overview, IET international radar conference 2023, Chongqing, China
This has led to further participation being required for other events. No formal collaborations yet.
Year(s) Of Engagement Activity 2023
URL http://ietradar.org/page_show.asp?m_id=305
 
Description radar in assisted living: an overview 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Postgraduate students
Results and Impact Department seminar, radar in assisted living: an overview, Imperial College London.
Year(s) Of Engagement Activity 2023
URL http://ietradar.org/page_show.asp?m_id=305
 
Description radar in assisted living: an overview 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Invited talk, radar in assisted living: an overview, International workshop on Signal and Information Intelligent Learning and Processing SIILP2023, Xi'an, China.
This was done to a panel of experts. This has led to a new collaboration within my university and another invitation to present in China at the IET international radar conference 2023.
Year(s) Of Engagement Activity 2023
 
Description radar in assisted living: latest developments 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact over 70 particpants came to the presentation aimed at fostering enhanced collaborations between the university of Glasgow and UESTC. No outcome on this occasion as export control as slowed down efforts to collaborate with UESTC dramatically.
Year(s) Of Engagement Activity 2023
 
Description radar sensing civilian applications 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Undergraduate students
Results and Impact University of Glasgow, ENG4185 Radar and Electro-Optic Systems 4 - radar sensing civilian applications - 4th year students BEng/MEng
Year(s) Of Engagement Activity 2023
 
Description seminar BIOSAN - radar sensing in assisted living and veterinary science 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact This seminar had 11 participants from a master degree course on biomed - the seminar was to widen the horizon of students on the use of radar in biomedical engineering. Students have asked questions on the applications during and after the presentation.
Year(s) Of Engagement Activity 2021,2022,2023