A5014605577- AI-based Problem Solving and Planning
- Bayesian Modeling and Causal Inference
- Multi-Agent Systems and Negotiation
- Semantic Web and Ontologies
- Opinion Dynamics and Social Influence
- Game Theory and Applications
- Logic, Reasoning, and Knowledge
- Artificial Intelligence in Law
- Evolutionary Game Theory and Cooperation
- Constraint Satisfaction and Optimization
- Rough Sets and Fuzzy Logic
- Complex Network Analysis Techniques
- Mental Health and Patient Involvement
- Biomedical Text Mining and Ontologies
- Topic Modeling
- Mental Health Treatment and Access
- Distributed systems and fault tolerance
- Digital Mental Health Interventions
- Schizophrenia research and treatment
- Peer-to-Peer Network Technologies
- Data Quality and Management
- Mental Health Research Topics
- Caching and Content Delivery
- Business Process Modeling and Analysis
- Auction Theory and Applications
King's College London
2013-2024
University of Bath
2024
The London College
2024
University of Otago
2024
University of Oxford
2024
Medway School of Pharmacy
2024
University of Nottingham
2024
Delft University of Technology
2014
Imperial College London
2014
Michigan State University
2014
Narratives describing first‐hand experiences of recovery from mental health problems are widely available. Emerging evidence suggests that engaging with narratives can benefit people experiencing problems, but no randomized controlled trial has been conducted as yet. We developed the Narrative Experiences Online (NEON) Intervention, a web application providing self‐guided and recommender systems access to collection recorded (n=659). investigated whether NEON Intervention benefited adults...
Abstract Background Mental health recovery narratives have been defined as first-person lived experience accounts of from mental problems which refer to events or actions over a period time and include elements adversity struggle, also self-defined strengths, successes survival. They are readily available in invariant recorded form, including text, audio video. Previous studies provided evidence that receiving can provide benefits recipients. This protocol describes three pragmatic trials...
A key challenge of effective teaching is assessing and monitoring the extent to which students have assimilated material they were taught. Concept mapping a methodology designed model what learned. In effect, it seeks produce graphical representations (called concept maps) concepts that are important given domain how related, according students. recent decades various methods emerged evaluate maps, each measuring different features maps. New approaches still being developed. Few guidelines...
Consideration of a wide range plausible crime scenarios during any investigation is important to seek convincing evidence and hence minimize the likelihood miscarriages justice. It equally for investigators be able employ effective efficient evidence-collection strategies that are likely produce most conclusive information under limited available resources. An intelligent decision support system can assist human by automatically constructing scenarios, reasoning with best investigating...
Background Paranoia is a highly debilitating mental health condition. One novel intervention for paranoia cognitive bias modification (CBM-pa). CBM-pa comes from class of interventions that focus on manipulating interpretation bias. Here, we aimed to develop and evaluate new therapy content later use in self-administered digital therapeutic called STOP (“Successful Treatment Paranoia”). Objective This study (1) take user-centered approach with input living experts, clinicians, academics...
Background Recommender systems help narrow down a large range of items to smaller, personalized set. NarraGive is first-in-field hybrid recommender system for mental health recovery narratives, recommending narratives based on their content and narrator characteristics (using content-based filtering) beneficially impacting other similar users collaborative filtering). integrated into the Narrative Experiences Online (NEON) intervention, web application providing access NEON Collection...
Many solutions to AI problems require the task be represented in one of a multitude rigorous mathematical formalisms. The construction such models forms difficult problem which is often left user problem-solver. This void between problem-solvers and their studied by eclectic field automated modelling. Within this field, compositional modelling, knowledge-based methodology for system-modelling, has established itself as leading approach. In general, modeller organises knowledge structure...
Robust decision support systems (DSSs) for crime investigation are difficult to construct because of the almost infinite variation plausible scenarios. Thus existing approaches avoid any explicit reasoning about They focus on problems such as intelligence analysis and profiling. This paper introduces a novel model based technique that enables DSSs automatically representations It achieves this by storing component events scenarios instead entire providing an algorithm can instantiate compose...
Bayesian networks are a predominant approach to analyse the findings of forensic scientists. In part, this is due way fits scientific method employed in practice. The design that accurately and comprehensively represent relationships between investigative hypotheses evidence remains difficult sometimes contentious, however. Recent research has shown argumentation can inform construction networks. But distinct evidential reasoning with its on representation formalisms. This issue could be...
An important challenge in the field of law is attribution responsibility and blame to individuals organisations for a given harm. Attributing legal often involves (but not limited to) assessing what extent certain parties have caused harm, or could prevented harm from occurring. This paper presents causal framework performing such assessments that particularly suitable analysis complex cases, where actions many had direct indirect effect on did occur. evaluated by means case study applies it...
Recent work in forensic statistics has shown how Bayesian Networks (BNs) can be used to infer the probability of defence and prosecution statements based on evidence. This is an important development as it helps quantify meaning expert testimony during court proceedings, for example, that there "strong support" or position. Due lack experimental data, inferred probabilities often rely subjective provided by experts. Because these are informed guesses, very difficult express them accurately...
A crucial aspect of evidential reasoning in crime investigation involves comparing the support that evidence provides for alternative hypotheses. Recent work forensic statistics has shown how Bayesian Networks (BNs) can be employed this purpose. However, specification BNs requires conditional probability tables describing uncertain processes under evaluation. When these are poorly understood, it is necessary to rely on subjective probabilities provided by experts. Accurate type normally hard...
Wigmore’s charts and Bayesian networks are used to represent graphically the construction of arguments evaluate them. KAOS is a goal oriented requirements analysis method that enables analysts capture through realization business goals. However, does not have inbuilt mechanism for evaluating these goals inferring process. This paper proposes models extension model with features networks.
The field of digital evidence must contend with an increasing number devices to be examined paralleled diversity. Examiners face a battle understand what artefacts may exist on these devices. Further, many current forensic tools look comprehensively examine sources which can generate large amounts of, often spurious, data no easy means correlation. This paper proposes the use ontology - Digital Evidence Semantic Ontology (DESO) that allows examiner quickly discover available device before...
<title>Abstract</title> Background The field of digital mental health has followed an exponential growth trajectory in recent years. While the evidence base increased significantly, its adoption within and care services been slowed by several challenges, including a lack knowledge from researchers regarding how to navigate pathway for mandatory regulatory approval. This paper details steps that team must take achieve required approvals carry out research study using novel intervention. We...