Nathan Griffiths
YOU?
Author Swipe
View article: STX-Search: Explanation Search for Continuous Dynamic Spatio-Temporal Models
STX-Search: Explanation Search for Continuous Dynamic Spatio-Temporal Models Open
Recent improvements in the expressive power of spatio-temporal models have led to performance gains in many real-world applications, such as traffic forecasting and social network modelling. However, understanding the predictions from a mo…
View article: MASALA: Model-Agnostic Surrogate Explanations by Locality Adaptation
MASALA: Model-Agnostic Surrogate Explanations by Locality Adaptation Open
Existing local Explainable AI (XAI) methods, such as LIME, select a region of the input space in the vicinity of a given input instance, for which they approximate the behaviour of a model using a simpler and more interpretable surrogate m…
View article: CHILLI: A data context-aware perturbation method for XAI
CHILLI: A data context-aware perturbation method for XAI Open
The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. Many models are treated as a `black-box' where the reasoning or criteria for a final decision…
View article: An agent-based model of the spread of behavioural risk-factors for cardiovascular disease in city-scale populations
An agent-based model of the spread of behavioural risk-factors for cardiovascular disease in city-scale populations Open
Cardiovascular disease (CVD) is the leading cause of mortality globally, and is the second main cause of mortality in the UK. Four key modifiable behaviours are known to increase CVD risk, namely: tobacco use, unhealthy diet, physical inac…
View article: Generosity and the Emergence of Forgiveness in the Donation Game
Generosity and the Emergence of Forgiveness in the Donation Game Open
Research has shown that cooperative action struggles to emerge in the noisy variant of the donation game, a simple model of noisy multi-agent systems where indirect reciprocity is required to maximise utility. Such noise can arise when age…
View article: Using Trajectory Subclustering to Improve Destination Prediction
Using Trajectory Subclustering to Improve Destination Prediction Open
Destination prediction is an active area of research, especially in the context of intelligent transportation systems. Intelligent applications, such as battery management in electric vehicles and congestion avoidance, rely on the accurate…
View article: Feature Selection for Supervised Learning and Compression
Feature Selection for Supervised Learning and Compression Open
Supervised feature selection aims to find the signals that best predict a target variable. Typical approaches use measures of correlation or similarity, as seen in filter methods, or predictive power in learned models, as seen in wrapper m…
View article: Conceptually Diverse Base Model Selection for Meta-Learners in Concept Drifting Data Streams
Conceptually Diverse Base Model Selection for Meta-Learners in Concept Drifting Data Streams Open
Meta-learners and ensembles aim to combine a set of relevant yet diverse base models to improve predictive performance. However, determining an appropriate set of base models is challenging, especially in online environments where the unde…
View article: Impact of postoperative acute kidney injury in patients undergoing major gastrointestinal surgery on 1-year survival and renal outcomes: a national multicentre cohort study
Impact of postoperative acute kidney injury in patients undergoing major gastrointestinal surgery on 1-year survival and renal outcomes: a national multicentre cohort study Open
Background The intermediate-term impact of acute kidney injury (AKI) in patients after major gastrointestinal and liver surgery has not been well characterized. This study aimed to evaluate the 1-year mortality rate and renal outcomes asso…
View article: Towards an integrated moisture-safe retrofit process for traditional buildings in policy and industry
Towards an integrated moisture-safe retrofit process for traditional buildings in policy and industry Open
Improving the energy efficiency of traditional buildings, which represent a large proportion of the building stock in the UK, is necessary to meet national targets on greenhouse gas emissions and alleviate fuel poverty. Traditional dwellin…
View article: Classifying Vehicle Activity to Improve Point of Interest Extraction
Classifying Vehicle Activity to Improve Point of Interest Extraction Open
Knowledge of drivers’ mobility patterns is useful for enabling context-aware intelligent vehicle functionality, such as route suggestions, cabin preconditioning, and power management for electric vehicles. Such patterns are often described…
View article: P77 Modelling the spread of behavioural risk factors for cardiovascular disease in a UK community using an agent-based model
P77 Modelling the spread of behavioural risk factors for cardiovascular disease in a UK community using an agent-based model Open
Background Tobacco use, unhealthy diet, physical inactivity, and harmful use of alcohol are key behavioural risk factors for non-communicable diseases, including cardiovascular disease. Individuals' behaviours and attitudes are affected by…
View article: <i>k</i> D-STR: A Method for Spatio-Temporal Data Reduction and Modelling
<i>k</i> D-STR: A Method for Spatio-Temporal Data Reduction and Modelling Open
Analysing and learning from spatio-temporal datasets is an important process in many domains, including transportation, healthcare and meteorology. In particular, data collected by sensors in the environment allows us to understand and mod…
View article: Bi-directional online transfer learning: a framework
Bi-directional online transfer learning: a framework Open
Transfer learning uses knowledge learnt in source domains to aid predictions in a target domain. When source and target domains are online, they are susceptible to concept drift, which may alter the mapping of knowledge between them. Drift…
View article: kD-STR: A Method for Spatio-Temporal Data Reduction and Modelling
kD-STR: A Method for Spatio-Temporal Data Reduction and Modelling Open
Analysing and learning from spatio-temporal datasets is an important process in many domains, including transportation, healthcare and meteorology. In particular, data collected by sensors in the environment allows us to understand and mod…
View article: Privacy Challenges With Protecting Live Vehicular Location Context
Privacy Challenges With Protecting Live Vehicular Location Context Open
Future Intelligent Transport Systems (ITS) will require that vehicles are equipped with Dedicated Short Range Communications (DSRC). With these DSRC capabilities, new privacy threats are emerging that can be taken advantage of by threat ac…
View article: Data mining and compression : where to apply it and what are the effects?
Data mining and compression : where to apply it and what are the effects? Open
In data mining it is important for any transforms made to training
\ndata to be replicated on evaluation or deployment data. If they
\nis not, the model may perform poorly or be unable to accept the
\ninput. Lossy data compression has othe…
View article: Addressing class imbalance in trust and stereotype assessment
Addressing class imbalance in trust and stereotype assessment Open
Trust, reputation and stereotypes enable agents to identify reliable interaction partners based on past interactions. However, such methods can cause agents to choose the same known partners instead of unknown, but potentially better, alte…
View article: A vision for socially incentivised recommendations
A vision for socially incentivised recommendations Open
Typically, recommender systems focus solely on individual preferences of users or small groups of users, but recommendations can have effects on the wider social structure. Social considerations are there- fore necessary in recommendation …
View article: 2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling
2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling Open
Spatio-temporal data generated by sensors in the environment, such as traffic data, is widely used in the
transportation domain. However, learning from and analysing such data is increasingly problematic as the
volume of data grows. Ther…
View article: CANdata.zip
CANdata.zip Open
Funded by Jaguar Land Rover and EPSRC grant.1221 signals times by 72 files of anonymised time series vehicle data. rescaledDataAll.csv contains all data from the other files, it is a copy of them in the same format, just pasted together.
View article: Selection of compressible signals from telemetry data
Selection of compressible signals from telemetry data Open
Sensors are deployed in all aspects of modern city infrastructure and generate vast amounts of data. Only subsets of this data, however, are relevant to individual organisations. For example, a local council may collect suspension movement…
View article: Addressing Concept Drift in Reputation Assessment
Addressing Concept Drift in Reputation Assessment Open
In this paper, we address the limitations of existing methods to select representative data for trust assessment when agent behaviours can change at varying speeds and times across a system. We propose a method that uses concept drift dete…
View article: Manipulating concept spread using concept relationships
Manipulating concept spread using concept relationships Open
The propagation of concepts in a population of agents is a form of influence spread, which can be modelled as a cascade from a set of initially activated individuals. The study of such influence cascades, in particular the identification o…
View article: Issue Information
Issue Information Open
No abstract is available for this article.
View article: Toward personalized and adaptive QoS assessments via context awareness
Toward personalized and adaptive QoS assessments via context awareness Open
Quality of Service (QoS) properties play an important role in distinguishing between functionally equivalent services and accommodating the different expectations of users. However, the subjective nature of some properties and the dynamic …
View article: Investigating the Feasibility of Vehicle Telemetry Data as a Means of Predicting Driver Workload
Investigating the Feasibility of Vehicle Telemetry Data as a Means of Predicting Driver Workload Open
Driving is a safety critical task that requires a high level of attention from the driver. Although drivers have limited attentional resources, they often perform secondary tasks such as eating or using a mobile phone. When performing mult…
View article: Establishing norms with metanorms over interaction topologies
Establishing norms with metanorms over interaction topologies Open
Norms are a valuable means of establishing coherent cooperative behaviour in decentralised systems in which there is no central authority. Axelrod’s seminal model of norm establishment in populations of self-interested individuals provides…