Paul Watson

Privacy and personalisation: predicting Parkinson’s disease severity from real-world gait with federated learning

Chloe H. L. Hinchliffe, Hugo Hiden, Lisa Alcock, Rachael Ashleigh Lawson et autres

Introduction: Cloud-based artificial intelligence (AI) combined with smart-health technology presents a powerful tool to passively monitor disease severity. However, current methods raise privacy concerns as they require transmitting patient data to the cloud. A potential solution is Federated Learning (FL), which only …

us, au, gb (code pays fourni par la source)

Mobilising UK Data and AI for All with a National Grid of Civic Learning Systems

John Ainsworth, Claudio; id_orcid 0000-0002-3140-7909 Angione, Kate Ardern, Katie Atkinson et autres

This paper sets out an opportunity for the UK to develop a world-leading infrastructure for data-driven public service innovation that feeds, and is fed by, science and engineering at national and civic scales, sustainably and with public trust. The disruptive model is …

Data Efficient Transformers for Wearable Sensor Analysis in Centralized and Federated Environments

Jamie McQuire, Paul Watson, Hugo Hiden, Michael Catt

Transformers have rapidly become the dominant architecture for analyzing sequential data, utilizing their self-attention mechanism to effectively capture long-term temporal patterns, outperforming recurrent-based methods across various applications. In this paper, we explore the application of transformers to wearable sensor data, focusing on …

gb (code pays fourni par la source)

Integrating MIL-STD Requirements into SysML Projects: A Unified Approach

Paul Watson

In support of developing complex systems, integrating requirements from various source standards, such as the Military Standard (MIL-STD) series and others, presents a significant challenge. This paper explores the development of Model-Based System Engineering (MBSE) Systems Modeling Language (SysML) projects that incorporate …

From eScience to Impact on the Economy and Society

Paul Watson, Barry Hodgson

eScience has had a major impact on science, engineering, healthcare and (increasingly) the humanities. However, there is enormous, largely untapped, potential to use the skills and expertise of eScience researchers to have a major impact on the economy and society. All organisations …

gb (code pays fourni par la source)

A Data Efficient Vision Transformer for Robust Human Activity Recognition from the Spectrograms of Wearable Sensor Data

Jamie McQuire, Paul Watson, Hugo Hiden, Michael Catt

This study introduces the Data Efficient Separable Transformer (DeSepTr) architecture, a novel framework for Human Activity Recognition (HAR) that utilizes a light-weight computer vision model to train a Vision Transformer (ViT) on spectrograms generated from wearable sensor data. The proposed model achieves …

gb (code pays fourni par la source)

Logical Optimisation and Cost Modelling of Stream-Processing Programs Written in a Purely-Functional Framework

Jonathan Dowland, Paul Watson, Adam Cattermole

We present a vision for the automatic optimisation of distributed stream processing programs. StrIoT -a distributed stream-processing framework built using purely-functional programming – enables a set of validated logical optimisation rules to generate a set of possible deployment plans. A cost model …

gb (code pays fourni par la source)

The e-Science Central Study Data Platform

Paul Watson, Hugo Hiden

Presentation for IEEE e-Science 20202

gb (code pays fourni par la source)

A new approach to impact case study analytics

Jiajie Zhang, Paul Watson, Barry Hodgson

Abstract The 2014 Research Excellence Framework (REF) assessed the quality of university research in the UK. 20% of the assessment was allocated according to peer review of the impact of research, reflecting the growing importance of impact in UK government policy. Beyond …

gb (code pays fourni par la source)

Uneven and Irregular Surface Condition Prediction from Human Walking Data using both Centralized and Decentralized Machine Learning Approaches

Jamie McQuire, Paul Watson, Hugo Hiden, Michael Catt

Gait data collected using wearable sensors offers non-intrusive, affordable, real-time monitoring of human motion. Recognizing surface conditions from wearable sensor data has the potential to help systems discriminate between ‘poor quality’ walking data. This research investigates the predictive capabilities of machine learning …

gb (code pays fourni par la source)

Run-time adaptation of stream processing spanning the cloud and the edge

Adam Cattermole, Jonathan Dowland, Paul Watson

Applications that process streams of events generated by sensors are important in a wide range of domains. It is now common to distribute stream processing across edge devices and the cloud. This exploits processing power near the sensors, reducing the load on …

gb (code pays fourni par la source)

A New Approach to Impact Case Study Analytics

Jiajie Zhang, Paul Watson, Barry Hodgson

The 2014 Research Excellence Framework (REF) assessed the quality of university research in the UK. A fifth of the assessment was allocated according to peer review of the impact of research, reflecting the growing importance afforded to impact in UK government policy. …

gb (code pays fourni par la source)