A primary motivation of our research is the monitoring of physical, physiological, and biochemical parameters - in any environment and without activity restriction and behaviour modification - through using miniaturised, wireless Body Sensor Networks (BSN). Key research issues that are currently being addressed include novel sensor designs, ultra-low power microprocessor and wireless platforms, energy scavenging, biocompatibility, system integration and miniaturisation, processing-on-node technologies combined with novel ASIC design, autonomic sensor networks and light-weight communication protocols. Our research is aimed at addressing the future needs of life-long health, wellbeing and healthcare, particularly those related to demographic changes associated with an ageing population and patients with chronic illnesses. This research theme is therefore closely aligned with the IGHI’s vision of providing safe, effective and accessible technologies for both developed and developing countries.

Some of our latest works were exhibited at the 2015 Royal Society Summer Science Exhibition.

Search or filter publications

Filter by type:

Filter by publication type

Filter by year:



  • Showing results for:
  • Reset all filters

Search results

  • Conference paper
    Qiu J, Lo FPW, Sun Y, Wang S, Lo Bet al., 2019,

    Mining discriminative food regions for accurate food recognition

    , BMVC 2019, Publisher: British Machine Vision Association

    Automatic food recognition is the very first step towards passive dietary monitoring. In this paper, we address the problem of food recognition by mining discriminative food regions. Taking inspiration from Adversarial Erasing, a strategy that progressively discovers discriminative object regions for weakly supervised semantic segmentation, we propose a novel network architecture in which a primary network maintains the base accuracy of classifying an input image, an auxiliary network adversarially mines discriminative food regions, and a region network classifies the resulting mined regions. The global (the original input image) and the local (the mined regions) representations are then integrated for the final prediction. The proposed architecture denoted as PAR-Net is end-to-end trainable, and highlights discriminative regions in an online fashion. In addition, we introduce a new fine-grained food dataset named as Sushi-50, which consists of 50 different sushi categories. Extensive experiments have been conducted to evaluate the proposed approach. On three food datasets chosen (Food-101, Vireo-172, andSushi-50), our approach performs consistently and achieves state-of-the-art results (top-1 testing accuracy of 90:4%, 90:2%, 92:0%, respectively) compared with other existing approaches.

  • Journal article
    Deligianni F, Guo Y, Yang G-Z, 2019,

    From emotions to mood disorders: A survey on gait analysis methodology

    , IEEE Journal of Biomedical and Health Informatics, Vol: 23, Pages: 2302-2316, ISSN: 2168-2194

    Mood disorders affect more than 300 million peopleworldwide and can cause devastating consequences. Elderlypeople and patients with neurological conditions are particularlysusceptible to depression. Gait and body movements can beaffected by mood disorders, and thus they can be used as asurrogate sign, as well as an objective index for pervasivemonitoring of emotion and mood disorders in daily life. Here wereview evidence that demonstrates the relationship between gait,emotions and mood disorders, highlighting the potential of amultimodal approach that couples gait data with physiologicalsignals and home-based monitoring for early detection andmanagement of mood disorders. This could enhance selfawareness, enable the development of objective biomarkers thatidentify high risk subjects and promote subject-specific treatment.

  • Journal article
    Chabloz N, Wenzel M, Perry H, Yoon I, Molisso S, Stasiuk G, Elson D, Cass A, Wilton-Ely Jet al., 2019,

    Polyfunctionalised nanoparticles bearing robust gadolinium surface units for high relaxivity performance in MRI

    , Chemistry - A European Journal, Vol: 25, Pages: 10895-10906, ISSN: 0947-6539

    The first example of an octadentate gadolinium unit based on DO3A (hydration number q = 1) with a dithiocarbamate tether has been designed and attached to the surface of gold nanoparticles (around 4.4 nm in diameter). In addition to the superior robustness of this attachment, the restricted rotation of the Gd complex on the nanoparticle surface leads to a dramatic increase in relaxivity (r1) from 4.0 mM‐1 s‐1 in unbound form to 34.3 mM‐1 s‐1 (at 10 MHz, 37 °C) and 22 ± 2 mM‐1s‐1 (at 63.87 MHz, 25 °C) when immobilised on the surface. The ‘one‐pot’ synthetic route provides a straightforward and versatile way of preparing a range of multifunctional gold nanoparticles. The incorporation of additional surface units improving biocompatibility (PEG and thioglucose units) and targeting (folic acid) lead to little detrimental effect on the high relaxivity observed for these non‐toxic multifunctional materials. In addition to the passive targeting attributed to gold nanoparticles, the inclusion of a unit capable of targeting the folate receptors overexpressed by cancer cells, such as HeLa cells, illustrates the potential of these assemblies.

  • Conference paper
    Guo Y, Sun M, Lo FPW, Lo Bet al., 2019,

    Visual guidance and automatic control for robotic personalized stent graft manufacturing

    , 2019 International Conference on Robotics and Automation (ICRA), Publisher: IEEE, Pages: 8740-8746

    Personalized stent graft is designed to treat Abdominal Aortic Aneurysms (AAA). Due to the individual difference in arterial structures, stent graft has to be custom made for each AAA patient. Robotic platforms for autonomous personalized stent graft manufacturing have been proposed in recently which rely upon stereo vision systems for coordinating multiple robots for fabricating customized stent grafts. This paper proposes a novel hybrid vision system for real-time visual-sevoing for personalized stent-graft manufacturing. To coordinate the robotic arms, this system is based on projecting a dynamic stereo microscope coordinate system onto a static wide angle view stereo webcam coordinate system. The multiple stereo camera configuration enables accurate localization of the needle in 3D during the sewing process. The scale-invariant feature transform (SIFT) method and color filtering are implemented for stereo matching and feature identifications for object localization. To maintain the clear view of the sewing process, a visual-servoing system is developed for guiding the stereo microscopes for tracking the needle movements. The deep deterministic policy gradient (DDPG) reinforcement learning algorithm is developed for real-time intelligent robotic control. Experimental results have shown that the robotic arm can learn to reach the desired targets autonomously.

  • Journal article
    Modi HN, Singh H, Fiorentino F, Orihuela-Espina F, Athanasiou T, Yang G-Z, Darzi A, Leff DRet al., 2019,

    Association of residents' neural signatures with stress resilience during surgery

    , JAMA Surgery, Vol: 154, ISSN: 2168-6254

    Importance: Intraoperative stressors may compound cognitive load, prompting performance decline and threatening patient safety. However, not all surgeons cope equally well with stress, and the disparity between performance stability and decline under high cognitive demand may be characterized by differences in activation within brain areas associated with attention and concentration such as the prefrontal cortex (PFC). Objective: To compare PFC activation between surgeons demonstrating stable performance under temporal stress with those exhibiting stress-related performance decline. Design, Setting, and Participants: Cohort study conducted from July 2015 to September 2016 at the Imperial College Healthcare National Health Service Trust, England. One hundred two surgical residents (postgraduate year 1 and greater) were invited to participate, of which 33 agreed to partake. Exposures: Participants performed a laparoscopic suturing task under 2 conditions: self-paced (SP; without time-per-knot restrictions), and time pressure (TP; 2-minute per knot time restriction). Main Outcomes and Measures: A composite deterioration score was computed based on between-condition differences in task performance metrics (task progression score [arbitrary units], error score [millimeters], leak volume [milliliters], and knot tensile strength [newtons]). Based on the composite score, quartiles were computed reflecting performance stability (quartile 1 [Q1]) and decline (quartile 4 [Q4]). Changes in PFC oxygenated hemoglobin concentration (HbO2) measured at 24 different locations using functional near-infrared spectroscopy were compared between Q1 and Q4. Secondary outcomes included subjective workload (Surgical Task Load Index) and heart rate. Results: Of the 33 participants, the median age was 33 years, the range was 29 to 56 years, and 27 were men (82%). The Q1 residents demonstrated task-induced increases in HbO2 across the bilateral ventrolateral PFC (VLPFC) and right dorsolateral P

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-t4-html.jsp Request URI: /respub/WEB-INF/jsp/search-t4-html.jsp Query String: id=758&limit=5&page=5&respub-action=search.html Current Millis: 1597177007122 Current Time: Tue Aug 11 21:16:47 BST 2020