Search or filter publications

Search publications Search

Filter by type:

Filter by publication type

• Book
• Book chapter
• Conference paper
• Journal article
• Patent
• Report
• Software

Filter by year:

Filter from 20222021202020192018 to Filter to 20222021202020192018

---

Search results

• Conference paper
  De Marcellis A, Di Patrizio Stanchieri G, Palange E, Faccio M, Constandinou TGet al., 2018,

  An ultra-wideband-inspired system-on-chip for an optical bidirectional transcutaneous biotelemetry

  , IEEE Biomedical Circuits and Systems (BioCAS) Conference 2018, Publisher: IEEE, Pages: 351-354

  This paper describes an integrated communicationsystem, implementing a UWB-inspired pulsed coding technique,for an optical transcutaneous biotelemetry. The system consistsof both a transmitter and a receiver facilitating a bidirectionallink. The transmitter includes a digital data coding circuit and iscapable of generating sub-nanosecond current pulses and directlydriving an off-chip semiconductor laser diode including all biasand drive circuits. The receiver includes an integrated compactPN-junction photodiode together with signal conditioning, de-tection and digital data decoding circuits to enable a high bitrate, energy efficient communication. The proposed solution hasbeen implemented in a commercially available 0.35μm CMOStechnology provided by AMS. The circuit core occupies a compactsilicon footprint of less than 0.13 mm2(only 113 transistors and1 resistor). Post-layout simulations have validated the overallsystem operation demonstrating the ability to operate at bit ratesup to 500 Mbps with pulse widths of 300 ps with a total powerefficiency (transmitter + receiver) lower than 74 pJ/bit. Thismakes the system ideally suited for demanding applications thatrequire high bit rates at extremely low energy levels. One suchapplication is implantable brain machine interfaces requiringhigh uplink bitrates to transmit recorded data externally througha transcutaneous communication channel.

  • Abstract
  • Publisher Web Link
  • Open Access Link
  • Cite
• Journal article
  Li H, Rezvani R, Kolanko MA, Sharp DJ, Wairagkar M, Vaidyanathan R, Nilforooshan R, Barnaghi Pet al.,

  An attention model to analyse the risk of agitation and urinary tract infections in people with dementia

  Behavioural symptoms and urinary tract infections (UTI) are among the mostcommon problems faced by people with dementia. One of the key challenges in themanagement of these conditions is early detection and timely intervention inorder to reduce distress and avoid unplanned hospital admissions. Using in-homesensing technologies and machine learning models for sensor data integrationand analysis provides opportunities to detect and predict clinicallysignificant events and changes in health status. We have developed anintegrated platform to collect in-home sensor data and performed anobservational study to apply machine learning models for agitation and UTI riskanalysis. We collected a large dataset from 88 participants with a mean age of82 and a standard deviation of 6.5 (47 females and 41 males) to evaluate a newdeep learning model that utilises attention and rational mechanism. Theproposed solution can process a large volume of data over a period of time andextract significant patterns in a time-series data (i.e. attention) and use theextracted features and patterns to train risk analysis models (i.e. rational).The proposed model can explain the predictions by indicating which time-stepsand features are used in a long series of time-series data. The model providesa recall of 91\% and precision of 83\% in detecting the risk of agitation andUTIs. This model can be used for early detection of conditions such as UTIs andmanaging of neuropsychiatric symptoms such as agitation in association withinitial treatment and early intervention approaches. In our study we havedeveloped a set of clinical pathways for early interventions using the alertsgenerated by the proposed model and a clinical monitoring team has been set upto use the platform and respond to the alerts according to the createdintervention plans.

  • Abstract
  • Author Web Link
  • Cite
• Journal article
  Palermo F, Li H, Capstick A, Fletcher-Lloyd N, Zhao Y, Kouchaki S, Nilforooshan R, Sharp D, Barnaghi Pet al.,

  Designing A Clinically Applicable Deep Recurrent Model to Identify Neuropsychiatric Symptoms in People Living with Dementia Using In-Home Monitoring Data

  Agitation is one of the neuropsychiatric symptoms with high prevalence indementia which can negatively impact the Activities of Daily Living (ADL) andthe independence of individuals. Detecting agitation episodes can assist inproviding People Living with Dementia (PLWD) with early and timelyinterventions. Analysing agitation episodes will also help identify modifiablefactors such as ambient temperature and sleep as possible components causingagitation in an individual. This preliminary study presents a supervisedlearning model to analyse the risk of agitation in PLWD using in-homemonitoring data. The in-home monitoring data includes motion sensors,physiological measurements, and the use of kitchen appliances from 46 homes ofPLWD between April 2019-June 2021. We apply a recurrent deep learning model toidentify agitation episodes validated and recorded by a clinical monitoringteam. We present the experiments to assess the efficacy of the proposed model.The proposed model achieves an average of 79.78% recall, 27.66% precision and37.64% F1 scores when employing the optimal parameters, suggesting a goodability to recognise agitation events. We also discuss using machine learningmodels for analysing the behavioural patterns using continuous monitoring dataand explore clinical applicability and the choices between sensitivity andspecificity in-home monitoring applications.

  • Abstract
  • Author Web Link
  • Cite
• Journal article
  Rezvani R, Kouchaki S, Nilforooshan R, Sharp DJ, Barnaghi Pet al.,

  Semi-supervised Learning for Identifying the Likelihood of Agitation in People with Dementia

  Interpreting the environmental, behavioural and psychological data fromin-home sensory observations and measurements can provide valuable insightsinto the health and well-being of individuals. Presents of neuropsychiatric andpsychological symptoms in people with dementia have a significant impact ontheir well-being and disease prognosis. Agitation in people with dementia canbe due to many reasons such as pain or discomfort, medical reasons such as sideeffects of a medicine, communication problems and environment. This paperdiscusses a model for analysing the risk of agitation in people with dementiaand how in-home monitoring data can support them. We proposed a semi-supervisedmodel which combines a self-supervised learning model and a Bayesian ensembleclassification. We train and test the proposed model on a dataset from aclinical study. The dataset was collected from sensors deployed in 96 homes ofpatients with dementia. The proposed model outperforms the state-of-the-artmodels in recall and f1-score values by 20%. The model also indicates bettergeneralisability compared to the baseline models.

  • Abstract
  • Author Web Link
  • Cite

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.