Ryan McConville

Harry Emerson, Matthew Guy, Ryan McConville

The widespread adoption of effective hybrid closed loop systems would represent an important milestone of care for people living with type 1 diabetes (T1D). These devices typically utilise simple control algorithms to select the optimal insulin dose for maintaining blood glucose levels within a healthy range. Online reinforcement learning (RL) has been utilised as a method for further enhancing glucose control in these devices. Previous approaches have been shown to reduce patient risk and improve time spent in the target range when compared to classical control algorithms, but are prone to instability in the learning process, often resulting in the selection of unsafe actions. This work presents an evaluation of offline RL for developing effective dosing policies without the need for potentially dangerous patient interaction during training. This paper examines the utility of BCQ, CQL and TD3-BC in managing the blood glucose of the 30 virtual patients available within the FDA-approved UVA/Padova glucose dynamics simulator. When trained on less than a tenth of the total training samples required by online RL to achieve stable performance, this work shows that offline RL can significantly increase time in the healthy blood glucose range from 61.6 +\- 0.3% to 65.3 +/- 0.5% when compared to the strongest state-of-art baseline (p < 0.001). This is achieved without any associated increase in low blood glucose events. Offline RL is also shown to be able to correct for common and challenging control scenarios such as incorrect bolus dosing, irregular meal timings and compression errors.

Armand K. Koupai, Mohammud J. Bocus, Raul Santos-Rodriguez et al.

The pervasiveness of Wi-Fi signals provides significant opportunities for human sensing and activity recognition in fields such as healthcare. The sensors most commonly used for passive Wi-Fi sensing are based on passive Wi-Fi radar (PWR) and channel state information (CSI) data, however current systems do not effectively exploit the information acquired through multiple sensors to recognise the different activities. In this paper, we explore new properties of the Transformer architecture for multimodal sensor fusion. We study different signal processing techniques to extract multiple image-based features from PWR and CSI data such as spectrograms, scalograms and Markov transition field (MTF). We first propose the Fusion Transformer, an attention-based model for multimodal and multi-sensor fusion. Experimental results show that our Fusion Transformer approach can achieve competitive results compared to a ResNet architecture but with much fewer resources. To further improve our model, we propose a simple and effective framework for multimodal and multi-sensor self-supervised learning (SSL). The self-supervised Fusion Transformer outperforms the baselines, achieving a F1-score of 95.9%. Finally, we show how this approach significantly outperforms the others when trained with as little as 1% (2 minutes) of labelled training data to 20% (40 minutes) of labelled training data.

Ferdian Jovan, Catherine Morgan, Ryan McConville et al.

Parkinson's disease (PD) is a slowly progressive, debilitating neurodegenerative disease which causes motor symptoms including gait dysfunction. Motor fluctuations are alterations between periods with a positive response to levodopa therapy ("on") and periods marked by re-emergency of PD symptoms ("off") as the response to medication wears off. These fluctuations often affect gait speed and they increase in their disabling impact as PD progresses. To improve the effectiveness of current indoor localisation methods, a transformer-based approach utilising dual modalities which provide complementary views of movement, Received Signal Strength Indicator (RSSI) and accelerometer data from wearable devices, is proposed. A sub-objective aims to evaluate whether indoor localisation, including its in-home gait speed features (i.e. the time taken to walk between rooms), could be used to evaluate motor fluctuations by detecting whether the person with PD is taking levodopa medications or withholding them. To properly evaluate our proposed method, we use a free-living dataset where the movements and mobility are greatly varied and unstructured as expected in real-world conditions. 24 participants lived in pairs (consisting of one person with PD, one control) for five days in a smart home with various sensors. Our evaluation on the resulting dataset demonstrates that our proposed network outperforms other methods for indoor localisation. The sub-objective evaluation shows that precise room-level localisation predictions, transformed into in-home gait speed features, produce accurate predictions on whether the PD participant is taking or withholding their medications.

Ferdian Jovan, Ryan McConville, Catherine Morgan et al.

Parkinson's disease (PD) is a slowly progressive debilitating neurodegenerative disease which is prominently characterised by motor symptoms. Indoor localisation, including number and speed of room to room transitions, provides a proxy outcome which represents mobility and could be used as a digital biomarker to quantify how mobility changes as this disease progresses. We use data collected from 10 people with Parkinson's, and 10 controls, each of whom lived for five days in a smart home with various sensors. In order to more effectively localise them indoors, we propose a transformer-based approach utilizing two data modalities, Received Signal Strength Indicator (RSSI) and accelerometer data from wearable devices, which provide complementary views of movement. Our approach makes asymmetric and dynamic correlations by a) learning temporal correlations at different scales and levels, and b) utilizing various gating mechanisms to select relevant features within modality and suppress unnecessary modalities. On a dataset with real patients, we demonstrate that our proposed method gives an average accuracy of 89.9%, outperforming competitors. We also show that our model is able to better predict in-home mobility for people with Parkinson's with an average offset of 1.13 seconds to ground truth.

Andrés Domínguez Hernández, Richard Owen, Dan Saattrup Nielsen et al.

Machine learning (ML) enabled classification models are becoming increasingly popular for tackling the sheer volume and speed of online misinformation and other content that could be identified as harmful. In building these models, data scientists need to take a stance on the legitimacy, authoritativeness and objectivity of the sources of ``truth" used for model training and testing. This has political, ethical and epistemic implications which are rarely addressed in technical papers. Despite (and due to) their reported high accuracy and performance, ML-driven moderation systems have the potential to shape online public debate and create downstream negative impacts such as undue censorship and the reinforcing of false beliefs. Using collaborative ethnography and theoretical insights from social studies of science and expertise, we offer a critical analysis of the process of building ML models for (mis)information classification: we identify a series of algorithmic contingencies--key moments during model development that could lead to different future outcomes, uncertainty and harmful effects as these tools are deployed by social media platforms. We conclude by offering a tentative path toward reflexive and responsible development of ML tools for moderating misinformation and other harmful content online.

Ryan McConville, Raul Santos-Rodriguez, Robert J Piechocki et al.

Deep clustering has increasingly been demonstrating superiority over conventional shallow clustering algorithms. Deep clustering algorithms usually combine representation learning with deep neural networks to achieve this performance, typically optimizing a clustering and non-clustering loss. In such cases, an autoencoder is typically connected with a clustering network, and the final clustering is jointly learned by both the autoencoder and clustering network. Instead, we propose to learn an autoencoded embedding and then search this further for the underlying manifold. For simplicity, we then cluster this with a shallow clustering algorithm, rather than a deeper network. We study a number of local and global manifold learning methods on both the raw data and autoencoded embedding, concluding that UMAP in our framework is best able to find the most clusterable manifold in the embedding, suggesting local manifold learning on an autoencoded embedding is effective for discovering higher quality discovering clusters. We quantitatively show across a range of image and time-series datasets that our method has competitive performance against the latest deep clustering algorithms, including out-performing current state-of-the-art on several. We postulate that these results show a promising research direction for deep clustering. The code can be found at https://github.com/rymc/n2d

Harry Emerson, Ryan McConville, Matthew Guy

Blood glucose simulation allows the effectiveness of type 1 diabetes (T1D) management strategies to be evaluated without patient harm. Deep learning algorithms provide a promising avenue for extending simulator capabilities; however, these algorithms are limited in that they do not necessarily learn physiologically correct glucose dynamics and can learn incorrect and potentially dangerous relationships from confounders in training data. This is likely to be more important in real-world scenarios, as data is not collected under strict research protocol. This work explores the implications of using deep learning algorithms trained on real-world data to model glucose dynamics. Free-living data was processed from the OpenAPS Data Commons and supplemented with patient-reported tags of challenging diabetes events, constituting one of the most detailed real-world T1D datasets. This dataset was used to train and evaluate state-of-the-art glucose simulators, comparing their prediction error across safety critical scenarios and assessing the physiological appropriateness of the learned dynamics using Shapley Additive Explanations (SHAP). While deep learning prediction accuracy surpassed the widely-used mathematical simulator approach, the model deteriorated in safety critical scenarios and struggled to leverage self-reported meal and exercise information. SHAP value analysis also indicated the model had fundamentally confused the roles of insulin and carbohydrates, which is one of the most basic T1D management principles. This work highlights the importance of considering physiological appropriateness when using deep learning to model real-world systems in T1D and healthcare more broadly, and provides recommendations for building models that are robust to real-world data constraints.

Thanaphon Suwannaphong, Ferdian Jovan, Ian Craddock et al.

This paper proposes small and efficient machine learning models (TinyML) for resource-constrained edge devices, specifically for on-device indoor localisation. Typical approaches for indoor localisation rely on centralised remote processing of data transmitted from lower powered devices such as wearables. However, there are several benefits for moving this to the edge device itself, including increased battery life, enhanced privacy, reduced latency and lowered operational costs, all of which are key for common applications such as health monitoring. The work focuses on model compression techniques, including quantization and knowledge distillation, to significantly reduce the model size while maintaining high predictive performance. We base our work on a large state-of-the-art transformer-based model and seek to deploy it within low-power MCUs. We also propose a state-space-based architecture using Mamba as a more compact alternative to the transformer. Our results show that the quantized transformer model performs well within a 64 KB RAM constraint, achieving an effective balance between model size and localisation precision. Additionally, the compact Mamba model has strong performance under even tighter constraints, such as a 32 KB of RAM, without the need for model compression, making it a viable option for more resource-limited environments. We demonstrate that, through our framework, it is feasible to deploy advanced indoor localisation models onto low-power MCUs with restricted memory limitations. The application of these TinyML models in healthcare has the potential to revolutionize patient monitoring by providing accurate, real-time location data while minimizing power consumption, increasing data privacy, improving latency and reducing infrastructure costs.

William Leeney, Ryan McConville

(1) The enhanced capability of Graph Neural Networks (GNNs) in unsupervised community detection of clustered nodes is attributed to their capacity to encode both the connectivity and feature information spaces of graphs. The identification of latent communities holds practical significance in various domains, from social networks to genomics. Current real-world performance benchmarks are perplexing due to the multitude of decisions influencing GNN evaluations for this task. (2) Three metrics are compared to assess the consistency of algorithm rankings in the presence of randomness. The consistency and quality of performance between the results under a hyperparameter optimisation with the default hyperparameters is evaluated. (3) The results compare hyperparameter optimisation with default hyperparameters, revealing a significant performance loss when neglecting hyperparameter investigation. A comparison of metrics indicates that ties in ranks can substantially alter the quantification of randomness. (4) Ensuring adherence to the same evaluation criteria may result in notable differences in the reported performance of methods for this task. The $W$ Randomness coefficient, based on the Wasserstein distance, is identified as providing the most robust assessment of randomness.

William Leeney, Ryan McConville

Federated Learning is machine learning in the context of a network of clients whilst maintaining data residency and/or privacy constraints. Community detection is the unsupervised discovery of clusters of nodes within graph-structured data. The intersection of these two fields uncovers much opportunity, but also challenge. For example, it adds complexity due to missing connectivity information between privately held graphs. In this work, we explore the potential of federated community detection by conducting initial experiments across a range of existing datasets that showcase the gap in performance introduced by the distributed data. We demonstrate that isolated models would benefit from collaboration establishing a framework for investigating challenges within this domain. The intricacies of these research frontiers are discussed alongside proposed solutions to these issues.

Harry Emerson, Sam Gordon James, Matthew Guy et al.

Reinforcement learning (RL) has demonstrated success in automating insulin dosing in simulated type 1 diabetes (T1D) patients but is currently unable to incorporate patient expertise and preference. This work introduces PAINT (Preference Adaptation for INsulin control in T1D), an original RL framework for learning flexible insulin dosing policies from patient records. PAINT employs a sketch-based approach for reward learning, where past data is annotated with a continuous reward signal to reflect patient's desired outcomes. Labelled data trains a reward model, informing the actions of a novel safety-constrained offline RL algorithm, designed to restrict actions to a safe strategy and enable preference tuning via a sliding scale. In-silico evaluation shows PAINT achieves common glucose goals through simple labelling of desired states, reducing glycaemic risk by 15% over a commercial benchmark. Action labelling can also be used to incorporate patient expertise, demonstrating an ability to pre-empt meals (+10% time-in-range post-meal) and address certain device errors (-1.6% variance post-error) with patient guidance. These results hold under realistic conditions, including limited samples, labelling errors, and intra-patient variability. This work illustrates PAINT's potential in real-world T1D management and more broadly any tasks requiring rapid and precise preference learning under safety constraints.

Thanaphon Suwannaphong, Ryan McConville, Ian Craddock

With the growing demand for health monitoring systems, in-home localisation is essential for tracking patient conditions. The unique spatial characteristics of each house required annotated data for Bluetooth Low Energy (BLE) Received Signal Strength Indicator (RSSI)-based monitoring system. However, collecting annotated training data is time-consuming, particularly for patients with limited health conditions. To address this, we propose Conditional Generative Adversarial Networks (ConGAN)-based augmentation, combined with our transfer learning framework (T-ConGAN), to enable the transfer of generic RSSI information between different homes, even when data is collected using different experimental protocols. This enhances the performance and scalability of such intelligent systems by reducing the need for annotation in each home. We are the first to demonstrate that BLE RSSI data can be shared across different homes, and that shared information can improve the indoor localisation performance. Our T-ConGAN enhances the macro F1 score of room-level indoor localisation by up to 12.2%, with a remarkable 51% improvement in challenging areas such as stairways or outside spaces. This state-of-the-art RSSI augmentation model significantly enhances the robustness of in-home health monitoring systems.

William Leeney, Ryan McConville

Graph Neural Networks (GNNs) can be trained to detect communities within a graph by learning from the duality of feature and connectivity information. Currently, the common approach for optimisation of GNNs is to use comparisons to ground-truth for hyperparameter tuning and model selection. In this work, we show that nodes can be clustered into communities with GNNs by solely optimising for modularity, without any comparison to ground-truth. Although modularity is a graph partitioning quality metric, we show that this can be used to optimise GNNs that also encode features without a drop in performance. We take it a step further and also study whether the unsupervised metric performance can predict ground-truth performance. To investigate why modularity can be used to optimise GNNs, we design synthetic experiments that show the limitations of this approach. The synthetic graphs are created to highlight current capabilities in distinct, random and zero information space partitions in attributed graphs. We conclude that modularity can be used for hyperparameter optimisation and model selection on real-world datasets as well as being a suitable proxy for predicting ground-truth performance, however, GNNs fail to balance the information duality when the spaces contain conflicting signals.

Alex Iacob, Pedro P. B. Gusmão, Nicholas D. Lane et al.

Human Activity Recognition (HAR) training data is often privacy-sensitive or held by non-cooperative entities. Federated Learning (FL) addresses such concerns by training ML models on edge clients. This work studies the impact of privacy in federated HAR at a user, environment, and sensor level. We show that the performance of FL for HAR depends on the assumed privacy level of the FL system and primarily upon the colocation of data from different sensors. By avoiding data sharing and assuming privacy at the human or environment level, as prior works have done, the accuracy decreases by 5-7%. However, extending this to the modality level and strictly separating sensor data between multiple clients may decrease the accuracy by 19-42%. As this form of privacy is necessary for the ethical utilisation of passive sensing methods in HAR, we implement a system where clients mutually train both a general FL model and a group-level one per modality. Our evaluation shows that this method leads to only a 7-13% decrease in accuracy, making it possible to build HAR systems with diverse hardware.

William Leeney, Ryan McConville

Graph Neural Networks (GNNs) have improved unsupervised community detection of clustered nodes due to their ability to encode the dual dimensionality of the connectivity and feature information spaces of graphs. Identifying the latent communities has many practical applications from social networks to genomics. Current benchmarks of real world performance are confusing due to the variety of decisions influencing the evaluation of GNNs at this task. To address this, we propose a framework to establish a common evaluation protocol. We motivate and justify it by demonstrating the differences with and without the protocol. The W Randomness Coefficient is a metric proposed for assessing the consistency of algorithm rankings to quantify the reliability of results under the presence of randomness. We find that by ensuring the same evaluation criteria is followed, there may be significant differences from the reported performance of methods at this task, but a more complete evaluation and comparison of methods is possible.

Dan Saattrup Nielsen, Ryan McConville

Misinformation is becoming increasingly prevalent on social media and in news articles. It has become so widespread that we require algorithmic assistance utilising machine learning to detect such content. Training these machine learning models require datasets of sufficient scale, diversity and quality. However, datasets in the field of automatic misinformation detection are predominantly monolingual, include a limited amount of modalities and are not of sufficient scale and quality. Addressing this, we develop a data collection and linking system (MuMiN-trawl), to build a public misinformation graph dataset (MuMiN), containing rich social media data (tweets, replies, users, images, articles, hashtags) spanning 21 million tweets belonging to 26 thousand Twitter threads, each of which have been semantically linked to 13 thousand fact-checked claims across dozens of topics, events and domains, in 41 different languages, spanning more than a decade. The dataset is made available as a heterogeneous graph via a Python package (mumin). We provide baseline results for two node classification tasks related to the veracity of a claim involving social media, and demonstrate that these are challenging tasks, with the highest macro-average F1-score being 62.55% and 61.45% for the two tasks, respectively. The MuMiN ecosystem is available at https://mumin-dataset.github.io/, including the data, documentation, tutorials and leaderboards.

Taku Yamagata, Ryan McConville, Raul Santos-Rodriguez

A promising approach to improve the robustness and exploration in Reinforcement Learning is collecting human feedback and that way incorporating prior knowledge of the target environment. It is, however, often too expensive to obtain enough feedback of good quality. To mitigate the issue, we aim to rely on a group of multiple experts (and non-experts) with different skill levels to generate enough feedback. Such feedback can therefore be inconsistent and infrequent. In this paper, we build upon prior work -- Advise, a Bayesian approach attempting to maximise the information gained from human feedback -- extending the algorithm to accept feedback from this larger group of humans, the trainers, while also estimating each trainer's reliability. We show how aggregating feedback from multiple trainers improves the total feedback's accuracy and make the collection process easier in two ways. Firstly, this approach addresses the case of some of the trainers being adversarial. Secondly, having access to the information about each trainer reliability provides a second layer of robustness and offers valuable information for people managing the whole system to improve the overall trust in the system. It offers an actionable tool for improving the feedback collection process or modifying the reward function design if needed. We empirically show that our approach can accurately learn the reliability of each trainer correctly and use it to maximise the information gained from the multiple trainers' feedback, even if some of the sources are adversarial.

James Neve, Ryan McConville

Recommender Systems are algorithms that predict a user's preference for an item. Reciprocal Recommenders are a subset of recommender systems, where the items in question are people, and the objective is therefore to predict a bidirectional preference relation. They are used in settings such as online dating services and social networks. In particular, images provided by users are a crucial part of user preference, and one that is not exploited much in the literature. We present a novel method of interpreting user image preference history and using this to make recommendations. We train a recurrent neural network to learn a user's preferences and make predictions of reciprocal preference relations that can be used to make recommendations that satisfy both users. We show that our proposed system achieves an F1 score of 0.87 when using only photographs to produce reciprocal recommendations on a large real world online dating dataset. Our system significantly outperforms on the state of the art in both content-based and collaborative filtering systems.

Hok-Shing Lau, Ryan McConville, Mohammud J. Bocus et al.

Traditional approaches to activity recognition involve the use of wearable sensors or cameras in order to recognise human activities. In this work, we extract fine-grained physical layer information from WiFi devices for the purpose of passive activity recognition in indoor environments. While such data is ubiquitous, few approaches are designed to utilise large amounts of unlabelled WiFi data. We propose the use of self-supervised contrastive learning to improve activity recognition performance when using multiple views of the transmitted WiFi signal captured by different synchronised receivers. We conduct experiments where the transmitters and receivers are arranged in different physical layouts so as to cover both Line-of-Sight (LoS) and non LoS (NLoS) conditions. We compare the proposed contrastive learning system with non-contrastive systems and observe a 17.7% increase in macro averaged F1 score on the task of WiFi based activity recognition, as well as significant improvements in one- and few-shot learning scenarios.

Alexander Hepburn, Valero Laparra, Jesús Malo et al.

Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations. Inspiration was usually taken from the human visual perceptual system and how the system processes different perturbations in order to replicate to what extent it determines our ability to judge image quality. While recent works have presented deep neural networks trained to predict human perceptual quality, very few borrow any intuitions from the human visual system. To address this, we present PerceptNet, a convolutional neural network where the architecture has been chosen to reflect the structure and various stages in the human visual system. We evaluate PerceptNet on various traditional perception datasets and note strong performance on a number of them as compared with traditional image quality metrics. We also show that including a nonlinearity inspired by the human visual system in classical deep neural networks architectures can increase their ability to judge perceptual similarity. Compared to similar deep learning methods, the performance is similar, although our network has a number of parameters that is several orders of magnitude less.

Taku Yamagata, Raúl Santos-Rodríguez, Ryan McConville et al.

Recent advances in both machine learning and Internet-of-Things have attracted attention to automatic Activity Recognition, where users wear a device with sensors and their outputs are mapped to a predefined set of activities. However, few studies have considered the balance between wearable power consumption and activity recognition accuracy. This is particularly important when part of the computational load happens on the wearable device. In this paper, we present a new methodology to perform feature selection on the device based on Reinforcement Learning (RL) to find the optimum balance between power consumption and accuracy. To accelerate the learning speed, we extend the RL algorithm to address multiple sources of feedback, and use them to tailor the policy in conjunction with estimating the feedback accuracy. We evaluated our system on the SPHERE challenge dataset, a publicly available research dataset. The results show that our proposed method achieves a good trade-off between wearable power consumption and activity recognition accuracy.

Alexander Hepburn, Valero Laparra, Ryan McConville et al.

In recent years there has been a growing interest in image generation through deep learning. While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked. In this paper we propose an alternative perceptual regulariser for image-to-image translation using conditional generative adversarial networks (cGANs). To do so automatically (avoiding visual inspection), we use the Normalised Laplacian Pyramid Distance (NLPD) to measure the perceptual similarity between the generated image and the original image. The NLPD is based on the principle of normalising the value of coefficients with respect to a local estimate of mean energy at different scales and has already been successfully tested in different experiments involving human perception. We compare this regulariser with the originally proposed L1 distance and note that when using NLPD the generated images contain more realistic values for both local and global contrast. We found that using NLPD as a regulariser improves image segmentation accuracy on generated images as well as improving two no-reference image quality metrics.

Michal Kozlowski, Ryan McConville, Raul Santos-Rodriguez et al.

As sensor networks for health monitoring become more prevalent, so will the need to control their usage and consumption of energy. This paper presents a method which leverages the algorithm's performance and energy consumption. By utilising Reinforcement Learning (RL) techniques, we provide an adaptive framework, which continuously performs weak training in an energy-aware system. We motivate this using a realistic example of residential localisation based on Received Signal Strength (RSS). The method is cheap in terms of work-hours, calibration and energy usage. It achieves this by utilising other sensors available in the environment. These other sensors provide weak labels, which are then used to employ the State-Action-Reward-State-Action (SARSA) algorithm and train the model over time. Our approach is evaluated on a simulated localisation environment and validated on a widely available pervasive health dataset which facilitates realistic residential localisation using RSS. We show that our method is cheaper to implement and requires less effort, whilst at the same time providing a performance enhancement and energy savings over time.

Ryan McConville, Gareth Archer, Ian Craddock et al.

In this paper we study the prediction of heart rate from acceleration using a wrist worn wearable. Although existing photoplethysmography (PPG) heart rate sensors provide reliable measurements, they use considerably more energy than accelerometers and have a major impact on battery life of wearable devices. By using energy-efficient accelerometers to predict heart rate, significant energy savings can be made. Further, we are interested in understanding patient recovery after a heart rate intervention, where we expect a variation in heart rate over time. Therefore, we propose an online approach to tackle the concept as time passes. We evaluate the methods on approximately 4 weeks of free living data from three patients over a number of months. We show that our approach can achieve good predictive performance (e.g., 2.89 Mean Absolute Error) while using the PPG heart rate sensor infrequently (e.g., 20.25% of the samples).