Gordon Lightbody

Shuwen Yu, William P Marnane, Geraldine B. Boylan et al.

This paper presents the HRVConformer, a novel deep learning architecture for the classification of hypoxic-ischemic encephalopathy (HIE) using the instantaneous heart rate (HR) signal. Unlike conventional approaches that rely on handcrafted features, HRVConformer directly processes raw HR signals in an end-to-end manner, capturing both local and long-range dependencies through a hybrid Convolution-Transformer framework. By integrating convolutional layers for local feature extraction and Transformer-based attention mechanisms for global context modelling, the architecture effectively enhances signal representation and classification performance. The model was trained using supervised learning on a large HR dataset consisting of 1,573 one-hour epochs, including 259 one-hour expert-annotated epochs and a substantial set of weakly labelled data. A 314-hour validation set provided a robust performance estimation, while an independent 215-hour dataset with expert annotations was reserved for final testing. HR signals were extracted from electrocardiogram (ECG) recordings using an improved Pan-Tompkins algorithm, which significantly enhanced both signal quality and data availability. Experimental results demonstrate that the HRVConformer achieves an AUC of 83.23\% and accuracy of 74.56\% on the test set. These results surpass the performance of the Transformer, ResNet50 and fully convolutional networks baselines, highlighting the advantages of integrating convolutional and Transformer-based components for HR-based HIE classification. The proposed method provides a promising step toward a more accurate and automated assessment of HIE using HR signals. The code is available at: https://github.com/syu-kylin/HRVConformer.

John M O'Toole, Sean R Mathieson, Sumit A Raurale et al.

This report describes a set of neonatal electroencephalogram (EEG) recordings graded according to the severity of abnormalities in the background pattern. The dataset consists of 169 hours of multichannel EEG from 53 neonates recorded in a neonatal intensive care unit. All neonates received a diagnosis of hypoxic-ischaemic encephalopathy (HIE), the most common cause of brain injury in full term infants. For each neonate, multiple 1-hour epochs of good quality EEG were selected and then graded for background abnormalities. The grading system assesses EEG attributes such as amplitude and frequency, continuity, sleep--wake cycling, symmetry and synchrony, and abnormal waveforms. Background severity was then categorised into 4 grades: normal or mildly abnormal EEG, moderately abnormal EEG, severely abnormal EEG, and inactive EEG. The data can be used as a reference set of multi-channel EEG for neonates with HIE, for EEG training purposes, or for developing and evaluating automated grading algorithms.

Daniel O'Keeffe, Stefano Riverso, Laura Albiol-Tendillo et al.

Voltage stability is a critical feature of an efficiently operating power distribution system such as a DC islanded microgrid. Large-scale autonomous power systems can be defined by heterogeneous elements, uncertainty and changing conditions. This paper proposes a novel scalable decentralised control scheme at the primary level of the typical hierarchical control architecture of DC islanded microgrids with arbitrary topology. Local state-feedback $\mathcal{L}_1$ adaptive controllers are retrofitted to existing baseline voltage controllers of DC-DC boost converters, which interface distributed generation units with loads. The use of $\mathcal{L}_1$ adaptive controllers achieves fast and robust microgrid voltage stability in the presence of dynamic uncertainty and plug-and-play operations. Furthermore, local controller synthesis is modular as it only requires approximate information about the line parameters that couple neighbouring units. The performance of the proposed architecture is evaluated using a heterogeneous DC islanded-microgrid that consists of 6 DC-DC boost converters configured in a radial and meshed topology. The use of $\mathcal{L}_1$ adaptive controllers achieves fast and robust microgrid voltage stability in the presence of plug-and-play operations, unknown load and voltage reference changes, and unmodelled dynamics. Finally, sufficient conditions for global stability of the overall system are provided.

Daniel O'Keeffe, Stefano Riverso, Laura Albiol-Tendillo et al.

This paper proposes a new distributed control architecture for distributed generation units in heterogeneous DC islanded microgrids. Each unit is equipped with state-feedback baseline and augmenting $\mathcal{L}_1$ adaptive voltage controllers at the primary level of the microgrid control hierarchy. Local controller synthesis is scalable as it only requires information about corresponding units, couplings, and at most, the addition of state-predictor measurements of neighbouring controllers. Global asymptotic stability of the microgrid is guaranteed in a plug-and-play fashion by exploiting Lyapunov functions and algebraic Riccati equations. The performance of the proposed architecture is evaluated using a heterogeneous DC islanded microgrid that consists of 6 DC-DC boost converters configured in a radial and meshed topology. The use of $\mathcal{L}_1$ adaptive controllers achieves fast and robust microgrid voltage stability in the presence of plug-and-play operations, topology changes and unknown load changes. Finally, the distributed architecture is tested on a bus-connected islanded-microgrid consisting of linear resistive load and non-linear DC motor.

Daniel O'Keeffe, Stefano Riverso, Laura Albiol-Tendillo et al.

Constant-power loads are notoriously known to destabilise power systems, such as DC microgrids, due to their negative incremental impedance. This paper equips distributed generation units with decentralised L1 adaptive controllers at the primary level of the microgrid control hierarchy. Necessary and sufficient conditions are provided to local controllers for overall microgrid stability when constant-power loads are connected. The advantages of the architecture over conventional heuristic approaches are: (i) scalable design, (ii) plug-and-play functionality, (iii) well defined performance and robustness guarantees in a heterogeneous and uncertain system, and (iv) avoids the need for online measurements to obtain non-a priori system impedance information. The proposed primary control architecture is evaluated with distributed consensus-based secondary level controls using a bus-connected DC microgrid, which consists of DC-DC buck and boost converters, linear and non-linear loads. Stability of the overall hierarchical control system is proven using a unit-gain approximation of the primary level.

Alison O'Shea, Gordon Lightbody, Geraldine Boylan et al.

A deep learning classifier for detecting seizures in neonates is proposed. This architecture is designed to detect seizure events from raw electroencephalogram (EEG) signals as opposed to the state-of-the-art hand engineered feature-based representation employed in traditional machine learning based solutions. The seizure detection system utilises only convolutional layers in order to process the multichannel time domain signal and is designed to exploit the large amount of weakly labelled data in the training stage. The system performance is assessed on a large database of continuous EEG recordings of 834h in duration; this is further validated on a held-out publicly available dataset and compared with two baseline SVM based systems. The developed system achieves a 56% relative improvement with respect to a feature-based state-of-the art baseline, reaching an AUC of 98.5%; this also compares favourably both in terms of performance and run-time. The effect of varying architectural parameters is thoroughly studied. The performance improvement is achieved through novel architecture design which allows more efficient usage of available training data and end-to-end optimisation from the front-end feature extraction to the back-end classification. The proposed architecture opens new avenues for the application of deep learning to neonatal EEG, where the performance becomes a function of the amount of training data with less dependency on the availability of precise clinical labels.

Alison OShea, Rehan Ahmed, Gordon Lightbody et al.

EEG is the gold standard for seizure detection in the newborn infant, but EEG interpretation in the preterm group is particularly challenging; trained experts are scarce and the task of interpreting EEG in real-time is arduous. Preterm infants are reported to have a higher incidence of seizures compared to term infants. Preterm EEG morphology differs from that of term infants, which implies that seizure detection algorithms trained on term EEG may not be appropriate. The task of developing preterm specific algorithms becomes extra-challenging given the limited amount of annotated preterm EEG data available. This paper explores novel deep learning (DL) architectures for the task of neonatal seizure detection in preterm infants. The study tests and compares several approaches to address the problem: training on data from full-term infants; training on data from preterm infants; training on age-specific preterm data and transfer learning. The system performance is assessed on a large database of continuous EEG recordings of 575h in duration. It is shown that the accuracy of a validated term-trained EEG seizure detection algorithm, based on a support vector machine classifier, when tested on preterm infants falls well short of the performance achieved for full-term infants. An AUC of 88.3% was obtained when tested on preterm EEG as compared to 96.6% obtained when tested on term EEG. When re-trained on preterm EEG, the performance marginally increases to 89.7%. An alternative DL approach shows a more stable trend when tested on the preterm cohort, starting with an AUC of 93.3% for the term-trained algorithm and reaching 95.0% by transfer learning from the term model using available preterm data.

Sumit A. Raurale, Geraldine B. Boylan, Gordon Lightbody et al.

Electroencephalography (EEG) is a valuable clinical tool for grading injury caused by lack of blood and oxygen to the brain during birth. This study presents a novel end-to-end architecture, using a deep convolutional neural network, that learns hierarchical representations within raw EEG data. The system classifies 4 grades of hypoxic-ischemic encephalopathy and is evaluated on a multi-channel EEG dataset of 63 hours from 54 newborns. The proposed method achieves a testing accuracy of 79.6% with one-step voting and 81.5% with two-step voting. These results show how a feature-free approach can be used to classify different grades of injury in newborn EEG with comparable accuracy to existing feature-based systems. Automated grading of newborn background EEG could help with the early identification of those infants in need of interventional therapies such as hypothermia.

Sumit A. Raurale, Geraldine B. Boylan, Gordon Lightbody et al.

Electroencephalography (EEG) is an important clinical tool for reviewing sleep-wake cycling in neonates in intensive care. Trace alternant (TA)-a characteristic pattern of EEG activity during quiet sleep in term neonates-is defined by alternating periods of short-duration, high-voltage activity (bursts) separated by lower-voltage activity (inter-bursts). This study presents a novel approach for detecting TA activity by first detecting the inter-bursts and then processing the temporal map of the bursts and inter-bursts. EEG recordings from 72 healthy term neonates were used to develop and evaluate performance of 1) an inter-burst detection method which is then used for 2) detection of TA activity. First, multiple amplitude and spectral features were combined using a support vector machine (SVM) to classify bursts from inter-bursts within TA activity, resulting in a median area under the operating characteristic curve (AUC) of 0.95 (95% confidence interval, CI: 0.93 to 0.98). Second, post-processing of the continuous SVM output, the confidence score, was used to produce a TA envelope. This envelope was used to detect TA activity within the continuous EEG with a median AUC of 0.84 (95% CI: 0.80 to 0.88). These results validate how an inter-burst detection approach combined with post processing can be used to classify TA activity. Detecting the presence or absence of TA will help quantify disruption of the clinically important sleep-wake cycle.

Sumit A. Raurale, Saif Nalband, Geraldine B. Boylan et al.

Electroencephalography (EEG) is an important clinical tool for grading injury caused by lack of oxygen or blood to the brain during birth. Characteristics of low-voltage waveforms, known as inter-bursts, are related to different grades of injury. This study assesses the suitability of an existing inter-burst detection method, developed from preterm infants born <30 weeks of gestational age, to detect inter-bursts in term infants. Different features from the temporal organisation of the inter-bursts are combined using a multi-layer perceptron (MLP) machine learning algorithm to classify four grades of injury in the EEG. We find that the best performing feature, percentage of inter-bursts, has an accuracy of 59.3%. Combining this with the maximum duration of inter-bursts in the MLP produces a testing accuracy of 77.8%, with similar performance to existing multi-feature methods. These results validate the use of the preterm detection method in term EEG and show how simple measures of the inter-burst interval can be used to classify different grades of injury.

Alison O'Shea, Gordon Lightbody, Geraldine Boylan et al.

This 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 SVM-based 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.

Alison O'Shea, Gordon Lightbody, Geraldine Boylan et al.

This study presents a novel end-to-end architecture that learns hierarchical representations from raw EEG data using fully convolutional deep neural networks for the task of neonatal seizure detection. The deep neural network acts as both feature extractor and classifier, allowing for end-to-end optimization of the seizure detector. The designed system is evaluated on a large dataset of continuous unedited multi-channel neonatal EEG totaling 835 hours and comprising of 1389 seizures. The proposed deep architecture, with sample-level filters, achieves an accuracy that is comparable to the state-of-the-art SVM-based neonatal seizure detector, which operates on a set of carefully designed hand-crafted features. The fully convolutional architecture allows for the localization of EEG waveforms and patterns that result in high seizure probabilities for further clinical examination.