INFANT Research Centre - Conference Items
Permanent URI for this collection
Browse
Browsing INFANT Research Centre - Conference Items by Title
Now showing 1 - 20 of 30
Results Per Page
Sort Options
- ItemApplying design thinking(2016-06-30) O'Raghallaigh, Paidi
- ItemCNNs for heart rate estimation and human activity recognition in wrist worn sensing applications(Institute of Electrical and Electronics Engineers (IEEE), 2020-03) Brophy, Eoin; Muehlhausen, Willie; Smeaton, Alan F.; Ward, Tomás E.; Science Foundation IrelandWrist-worn smart devices are providing increased insights into human health, behaviour and performance through sophisticated analytics. However, battery life, device cost and sensor performance in the face of movement-related artefact present challenges which must be further addressed to see effective applications and wider adoption through commoditisation of the technology. We address these challenges by demonstrating, through using a simple optical measurement, photoplethysmography (PPG) used conventionally for heart rate detection in wrist-worn sensors, that we can provide improved heart rate and human activity recognition (HAR) simultaneously at low sample rates, without an inertial measurement unit. This simplifies hardware design and reduces costs and power budgets. We apply two deep learning pipelines, one for human activity recognition and one for heart rate estimation. HAR is achieved through the application of a visual classification approach, capable of robust performance at low sample rates. Here, transfer learning is leveraged to retrain a convolutional neural network (CNN) to distinguish characteristics of the PPG during different human activities. For heart rate estimation we use a CNN adopted for regression which maps noisy optical signals to heart rate estimates. In both cases, comparisons are made with leading conventional approaches. Our results demonstrate a low sampling frequency can achieve good performance without significant degradation of accuracy. 5 Hz and 10 Hz were shown to have 80.2% and 83.0% classification accuracy for HAR respectively. These same sampling frequencies also yielded a robust heart rate estimation which was comparative with that achieved at the more energy-intensive rate of 256 Hz.
- ItemDesign messiness: Impact by design(2017-09-26) O'Raghallaigh, Paidi; Sammon, David
- ItemDesign thinking: Leveraging customer empathy to identify hidden needs(2016-06-30) O'Raghallaigh, Paidi
- ItemDesigning effective theory for research impact(2016-01-15) O'Raghallaigh, Paidi
- ItemExploring the nuances of 'Wickedness' in information systems development(University of Hawai'i at Manoa, 2018-01) McCarthy, Stephen; O'Raghallaigh, Paidi; Fitzgerald, Ciara; Adam, Frédéric; Science Foundation IrelandInformation Systems Development (ISD) practice is an inherently challenging undertaking, as exemplified by the high rate of ISD project failures. The scale of the challenge is often heightened in distributed environments where ISD practitioners can face considerable complexity, uncertainty, and contention. The concept of -˜wickedness’ epitomizes such challenges. However, ISD literature has yet to fully explore the nuances of wickedness found in ISD practices within distributed environments. To address this gap, we use a theoretical framework to analyze case study findings from an interdisciplinary connected health project. In particular, we break open the social aspects of wickedness and explore their impact on shared understanding and shared commitment in ISD projects. The paper highlights the implications that these nuances have for group decision-making in distributed ISD project teams.
- ItemFour steps to designing initiatives with real impact(2016-03-03) O'Raghallaigh, Paidi
- ItemFour steps to designing research with real impact(2016-10-07) O'Raghallaigh, Paidi
- ItemFour steps towards ‘selling’ the value of any innovation initiative(2016-05-25) O'Raghallaigh, Paidi
- ItemHeart rate variability during periods of low blood pressure as a predictor of short-term outcome in preterms(Institute of Electrical and Electronics Engineers (IEEE), 2018-10-29) Semenova, Oksana; Carra, Giorgia; Lightbody, Gordon; Boylan, Geraldine B.; Dempsey, Eugene M.; Temko, Andriy; Science Foundation IrelandEfficient management of low blood pressure (BP) in preterm neonates remains challenging with a considerable variability in clinical practice. The ability to assess preterm wellbeing during episodes of low BP will help to decide when and whether hypotension treatment should be initiated. This work aims to investigate the relationship between heart rate variability (HRV), BP and the short-term neurological outcome in preterm infants less than 32 weeks gestational age (GA). The predictive power of common HRV features with respect to the outcome is assessed and shown to improve when HRV is observed during episodes of low mean arterial pressure (MAP) - with a single best feature leading to an AUC of 0.87. Combining multiple features with a boosted decision tree classifier achieves an AUC of 0.97. The work presents a promising step towards the use of multimodal data in building an objective decision support tool for clinical prediction of short-term outcome in preterms who suffer episodes of low BP.
- ItemIn-depth performance analysis of an EEG based neonatal seizure detection algorithm(Elsevier, 2016-02-21) Mathieson, Sean; Rennie, Janet; Livingstone, Vicki; Temko, Andriy; Low, Evonne; Pressler, R. M.; Boylan, Geraldine B.; Wellcome Trust; Science Foundation IrelandObjective: To describe a novel neurophysiology based performance analysis of automated seizure detection algorithms for neonatal EEG to characterize features of detected and non-detected seizures and causes of false detections to identify areas for algorithmic improvement. Methods: EEGs of 20 term neonates were recorded (10 seizure, 10 non-seizure). Seizures were annotated by an expert and characterized using a novel set of 10 criteria. ANSeR seizure detection algorithm (SDA) seizure annotations were compared to the expert to derive detected and non-detected seizures at three SDA sensitivity thresholds. Differences in seizure characteristics between groups were compared using univariate and multivariate analysis. False detections were characterized. Results: The expert detected 421 seizures. The SDA at thresholds 0.4, 0.5, 0.6 detected 60%, 54% and 45% of seizures. At all thresholds, multivariate analyses demonstrated that the odds of detecting seizure increased with 4 criteria: seizure amplitude, duration, rhythmicity and number of EEG channels involved at seizure peak. Major causes of false detections included respiration and sweat artefacts or a highly rhythmic background, often during intermediate sleep. Conclusion: This rigorous analysis allows estimation of how key seizure features are exploited by SDAs. Significance: This study resulted in a beta version of ANSeR with significantly improved performance.
- ItemInnovation in practice: Lessons learned(2017-06-28) O'Raghallaigh, Paidi
- ItemInnovative thinking. Moving from ‘playing not to lose’ to ‘playing to win’(2017-02-14) O'Raghallaigh, Paidi
- ItemInteractions between vitamin D status, calcium intake and parathyroid hormone concentrations in healthy pregnant women(Cambridge University Press (CUP) on behalf of the Nutrition Society, 2018-06) Hemmingway, Andrea; O'Callaghan, Karen M.; Hennessy, Áine; Kiely, Mairead E.Emerging evidence highlights the potential of the vitamin D and calcium metabolic system to impact pregnancy outcomes and adverse effects of vitamin D-parathyroid hormone (PTH) interactions on perinatal health have been reported(1,2). PTH concentrations reflect homeostasis in the calcium metabolic system, and can be impacted by calcium intake as well as circulating 25-hydroxyvitamin D [25(OH)D] concentrations, reflecting vitamin D status. Little explored in pregnancy, we aimed to examine the relative importance of vitamin D status and calcium intake on PTH concentrations among healthy pregnant women. This was a cross-sectional analysis of 142 white-skinned participants of mean (SD) 14 (2) weeks’ gestation at baseline of a dose-response randomised controlled trial of vitamin D [NCT02506439](3). Serum 25(OH)D was measured by a CDC-accredited LC-MS/MS method and calcium intakes were estimated using a validated quantitative food frequency questionnaire(4). Serum albumin-corrected calcium and intact PTH were measured by colorimetric assay (Randox Laboratories Ltd.) and ELISA (MD Biosciences Inc.), respectively. Serum 25(OH)D was stratified at 50 nmol/L and calcium intakes by < 800, 800–1000 and ≥ 1000 mg/day according to the Institute of Medicine(5). After log transformation of PTH, we used Pearson’s correlations and two-way ANOVA to explore effects of calcium intakes and 25(OH)D on PTH. Geometric mean (95% CI) PTH concentration was 9·24 (8·37, 10·19) pg/mL. Mean (SD) 25(OH)D and calcium intake were 54·9 (22·6) nmol/L and 1182·5 (485·8) mg/day, respectively. 44% of participants had a 25(OH)D < 50 nmol/L and calcium intake was < 800 and ≥ 1000 mg/day in 22% and 63%, respectively. PTH was inversely correlated with vitamin D status (r = −0·311, P < 0·01), but not calcium intake (r = −0·087) or serum calcium (r = 0·057). There was no evidence of an interaction between calcium intake and 25(OH)D on PTH concentration (P = 0·941). There was a statistically significant main effect of serum 25(OH)D (P = 0·025) but not calcium intake (P = 0·822) on PTH. To conclude, in this group of healthy pregnant women with largely sufficient calcium intake, vitamin D status, but not calcium intake was important for maintaining calcium homeostasis.
- ItemInvestigating the impact of CNN depth on neonatal seizure detection performance(Institute of Electrical and Electronics Engineers (IEEE), 2018-10-29) O'Shea, Alison; Lightbody, Gordon; Boylan, Geraldine B.; Temko, Andriy; Wellcome Trust; Science Foundation IrelandThis study presents a novel, deep, fully convolutional architecture which is optimized for the task of EEG-based neonatal seizure detection. Architectures of different depths were designed and tested; varying network depth impacts convolutional receptive fields and the corresponding learned feature complexity. Two deep convolutional networks are compared with a shallow SVMbased neonatal seizure detector, which relies on the extraction of hand-crafted features. On a large clinical dataset, of over 800 hours of multichannel unedited EEG, containing 1389 seizure events, the deep 11-layer architecture significantly outperforms the shallower architectures, improving the AUC90 from 82.6% to 86.8%. Combining the end-to-end deep architecture with the feature-based shallow SVM further improves the AUC90 to 87.6%. The fusion of classifiers of different depths gives greatly improved performance and reduced variability, making the combined classifier more clinically reliable.
- ItemInvestigation of lung volume measurements in neonates using gas in scattering media absorption spectroscopy(Optica Publishing Group, 2022-04) Pacheco, Andrea; Jayet, Bapiste; Grygoryev, Konstantin; Messina, Walter; Dehghani, Hamid; Krite Svanberh, Emilie; Dempsey, Eugene M.; Andersson-Engels, Stefan; Science Foundation IrelandWe perform phantom and numerical studies of the changes in molecular oxygen and water vapor spectroscopic signals, showing the potential of measuring pulmonary volume changes with GASMAS technique in neonates.
- ItemLessons from trying to innovate in the age of digital disruption(2017-05-31) O'Raghallaigh, Paidi
- ItemNear infrared light propagation modeling of infant lung with light source placed inside intubated airway(OSA Publishing, 2018-04-03) Pacheco, Andrea; Svanberg, Emilie Krite; Dempsey, Eugene M.; Andersson-Engels, Stefan; Science Foundation IrelandWe simulate light propagation in 3D numerical model of infant thorax at 761 nm with light source placed inside the trachea and detectors over the skin between axilla and sternum.
- ItemNon-invasive lung oxygen monitoring in term infants: a pilot trial(Optica Publishing Group, 2022-04) Panaviene, Jurate; Grygoryev, Konstantin; Pacheco, Andrea; Dempsey, Eugene M.; Andersson-Engels, Stefan; Science Foundation IrelandEmploying non-invasive GASMAS based system, lung oxygen measurements were performed on 25 healthy term infants on various chest positions. Oxygen and water vapor absorption signal was detected on most occasions.
- ItemPericonceptional and antenatal nutritional supplement use in Irish women: data from the IMPROvED Study(Nutrition Society, 2021-12) Kelliher, Lisa; Hennessy, Áine; McCarthy, Fergus P.; Kiely, Mairead E.