278177 research outputs found
Sort by
Personalised Stroke Rehabilitation:An AI Pipeline for Exercise Programmes Using a Co-Designed Decision Support Tablet Application
No full textStroke rehabilitation requires personalised and continuously adapted exercise programmes, resulting in significant therapist involvement and is often impractical for patients recovering at home in community settings. This motivates the need for assistive tools and decision support systems to enhance efficiency and rehabilitation progress. This position paper presents an integrated pipeline combining a therapist-informed tablet application with artificial intelligence (AI) models to support therapists in decision-making. Co-designed with stroke therapists, human-computer interaction (HCI) researchers, AI experts, and persons with stroke (PwS), the application captures baseline and weekly reassessment data, including BBS, TUG, pain, perceived difficulty, and FITT prescriptions, across 4–6 week cycles to determine whether to progress, sustain, or regress exercises. To facilitate early model development, we created a clinically informed synthetic dataset (n = 336 sessions across 5 PwS profiles over 12 weeks) that simulates functional progression and therapist decision-making patterns. This dataset reflects key features identified through workshops with clinicians and PwS, capturing essential assessment metrics such as stroke characteristics, functional scores, therapist goals, patient feedback, exercise difficulty, repetitions, duration, body area, FITT parameters, and exercise recommendations. We trained and evaluated models to predict weekly progression decisions. Logistic regression achieved a weighted F1-score of 51.6%, while a multilayer perceptron reached 79.3\% and a decision tree 90.2%. Clinical data will be collected in the next stage of the project (5–8 PwS, 4–6 weeks) and integrated with the synthetic dataset using real–synthetic fusion. This work advocates AI-augmented tools for scalable, patient-centred community stroke rehabilitation, with future efforts exploring generative AI and clinical validation
“It has a lot of pressure”:the impossible everyday labours of sex worker community paralegal volunteers in Nairobi
No full textThis article explores everyday pressures, as experienced by sex worker community paralegals in Nairobi. Community paralegals are important in national HIV response efforts, as they help to reduce the pressures on state structures by reducing the number of cases that go to courts, and alleviating the pressure on health services. However, the design of this volunteer role contains limitations that produces multiple individual pressures and exposes role holders to gendered harms. Focusing on social reproduction this article explores community social reproduction work that community paralegal role entails, alongside women’s income generating and familiar labours to demonstrate their intertwined nature and the set of numerous demands that they create on women’s time, energy, emotions and financial resources. Using the Space, Time, Violence framework, the article reveals the spatial and temporal dimensions of gendered harms that constitute the everyday lives of community paralegals in Nairobi. These harms are not fully recognised in the formal role design, and thus support to replenish community paralegals’ resources is very limited, so contributing to their struggles. Community paralegals’ attempts to bring justice to their communities is lived then as a daily expose to harms which causes them pressures and depletes them
Incorporating Memory into Bounded Confidence Models of Probabilistic Social Learning
No full textIn social learning models, truth-seeking agents learn both individually from direct evidence and socially by pooling beliefs with others. That learning can be undermined by two types of unreliable agents: zealots, who do not learn and promote the same fixed opinion and free riders, who lack access to evidence yet still influence others. In this paper, we explore how learning rules that incorporate memory can mitigate the effects of unreliable agents. To do so, we construct an agent-based model of social learning in which agents apply a probabilistic bounded confidence (BC) model that evaluates the similarity between themselves and others based on samples of recent beliefs rather than current beliefs only. When compared to a memoryless BC benchmark, BC with memory proves significantly less sensitive to the choice of similarity threshold governing agent interactions, to the extent that a fixed threshold is effective for avoiding all types of zealots. It is also less susceptible to high levels of distrust in evidence. The BC with memory model is then extended to social learning about multiple hypotheses, and we show that the robustness results generalize to the case in which beliefs are multi-dimensional probability distributions
Freedom Isn't Free:Resource Limits On Person-Centred Best Interests Decisions Under The Mental Capacity Act
No full textBest interests under the Mental Capacity Act 2005 has been cast as an empowering, person-centred process that protects a person’s rights and freedom of action. In practice this laudable goal is constrained by monetary and temporal resources. Drawing on a qualitative study which encompassed the views of patients, carers, healthcare professionals and lawyers, we observe that, where resources are inadequate, the quality of decision-making declines and the options on offer are restricted. While austerity has disproportionately disadvantaged people with disabilities and additional needs in numerous ways, in mental capacity law the impact of this is evident in the gap between the protection of procedural and substantive rights offered by the law. While the courts deal robustly with challenges to ‘faulty’ procedure, challenging substantive issues is difficult and has limited prospects of improving outcomes, even if the decision is clearly inadequate in any sensible interpretation of the court’s aspiration to person-centredness. Tracing these differences back to the different logics of the European Convention on Human Rights and the United Nations Convention on the Rights of Persons with Disabilities, we argue that, as things currently stand, the law cannot resolve these issues, dooming the aspiration to person-centredness to remain constrained and provisional
Digital assets, personal property and categorisation: the Property (Digital Assets etc) Act 2025
No full text[No abstract
A Combinatorial Structure for Many Hierarchically Hyperbolic Spaces
Get PDFThe combinatorial hierarchical hyperbolicity criterion is a very useful way of constructing new hierarchically hyperbolic spaces (HHSs). We show that, conversely, HHSs satisfying natural assumptions (satisfied, for example, by mapping class groups) admit a combinatorial HHS structure. This can be useful in constructions of new HHSs, and also our construction clarifies how to apply the combinatorial HHS criterion to suspected examples. We also uncover connections between HHS notions and lattice theory notions
Taking the Red Pill:Conspiracy Theories, Gender, and the ‘elusive epistemologies’ of the Manosphere
No full textIn this article we analyse the gender politics of the anti-feminist “red pill” or Matrix conspiracy theory. Extending the work of Jaron Harambam and Stef Aupers on how conspiracy theorists legitimise their truth claims in part through ‘futuristic imaginaries’, we draw attention to the role of popular culture and of intertextuality for generating the ‘commonsense’ of these beliefs. More specifically, based on a discourse analysis of a representative sample of “red pill” community YouTube videos we find that the conspiracy theory draws deliberately on the potent ‘image bank’ of the landmark science fiction film The Matrix (1999) in ways that are more extensive and important for legitimising violence than currently understood. Beyond pill metaphors, The Matrix conspiracy theory serves to entrench hierarchical differentiations between masculinities, reproduce narratives of aggrieved sexual entitlement against ‘feminist oppression’, and advocates for a violent ‘return’ to a more ‘traditional’ gender, race and sexual order
