A5090992193- Technology Use by Older Adults
- Digital Mental Health Interventions
- Genetic Neurodegenerative Diseases
- Innovative Human-Technology Interaction
- Context-Aware Activity Recognition Systems
- Dementia and Cognitive Impairment Research
- Cardiac Imaging and Diagnostics
- Cardiovascular Function and Risk Factors
- Face and Expression Recognition
- Health disparities and outcomes
- Neurological disorders and treatments
- Impact of Technology on Adolescents
- Parkinson's Disease Mechanisms and Treatments
- Knee injuries and reconstruction techniques
- Neurological Disease Mechanisms and Treatments
- Muscle activation and electromyography studies
- Cardiovascular Disease and Adiposity
- IoT and Edge/Fog Computing
- Fibromyalgia and Chronic Fatigue Syndrome Research
- Digital Accessibility for Disabilities
- Generative Adversarial Networks and Image Synthesis
- Machine Learning and Data Classification
- Sports injuries and prevention
- Image Retrieval and Classification Techniques
- Autism Spectrum Disorder Research
The Open University
2018-2023
Cardiff University
2013-2016
Feature selection is used in many application areas relevant to expert and intelligent systems, such as data mining machine learning, image processing, anomaly detection, bioinformatics natural language processing. based on information theory a popular approach due its computational efficiency, scalability terms of the dataset dimensionality, independence from classifier. Common drawbacks this are lack about interaction between features classifier, redundant irrelevant features. The latter...
Quantitative assessment of movement impairment in Huntington's disease (HD) is essential to monitoring progression. This paper aimed develop and validate a novel low cost, objective automated system for the evaluation upper limb HD order eliminate inconsistency assessor offer more sensitive, continuous scale. Patients with genetically confirmed healthy controls were recruited this observational study. Demographic data, including age (years), gender, unified rating scale total motor score...
Activity recognition using wearable sensors has become essential for a variety of applications. Tri-axial accelerometers are the most widely used sensor activity recognition. Although various features have been to capture patterns and classify accelerometer signals recognise activities, there is no consensus on best choose. Reducing number can reduce computational cost complexity enhance performance classifiers. This paper identifies signal that significant discriminative power between...
Huntington's disease (HD) is a progressive inherited neurodegenerative disorder, causing involuntary movement and cognitive problems, severely affecting the quality of life. Controlling upper limb function core feature daily activity can prove problematic for people with HD. The Money Box Test (MBT) has been developed purpose quantifying frequently seen in In this research, wearable highly sensitive accelerometers are used to collect acceleration hands chest during performance MBT. Using...
Dementia is a syndrome caused by chronic or progressive disease of the brain, which affects memory, orientation, thinking, calculation, learning ability and language. The Clock Drawing Test (CDT) Mini Mental State Examination (MMSE) are well-known cognitive assessment tests. A known obstacle to wider usage CDT assessments scoring interpretation results. This paper introduces novel cascade classifier, can help in diagnosis three stages dementia. data used this research 604 clock drawings...
The global population is ageing, leading to shifts in healthcare needs. Home monitoring systems currently focus on physical health, but there an increasing recognition that psychological wellbeing also needs support. This raises the question of how design devices older adults can interact with log their feelings. We designed three tangible prototypes, based existing paper-based scales affect. report findings from a lab study which participants used prototypes emotion standardised emotional...
Loneliness is a significant well-being issue that affects older adults. Existing, commonly used social connection platforms do not contain facilities to break the cognitive cycle of loneliness, and loneliness interventions implemented without due processes could have detrimental effects on well-being. There also lack digital technology designed with adults.We aimed iteratively design user-centered smartphone app can address in The aim this study was investigate loneliness-related...
Background Movement analysis in a clinical setting is frequently restricted to observational methods inform decision making, which has limited accuracy. Fixed-site, optical, expensive movement laboratories provide gold standard kinematic measurements; however, they are rarely accessed for routine use. Wearable inertial measurement units (IMUs) have been demonstrated as comparable, inexpensive, and portable toolkits. MoJoXlab therefore developed work with generic wearable IMUs. However,...
The Clock Drawing Test is one of the most widely used screening tools for cognitive impairment and dementia. Since its introduction, more than fifteen scoring systems have been developed to assess clock drawings. However, very little research has conducted study significance elements (features) drawings correct diagnosis This paper employs a feature selection method called Feature Interaction Maximization (FIM) identify significant visual features test, which can be associated with proposed...
The world is facing an ageing population phenomenon, coupled with health and social problems, which affect older people's ability to live independently. This situation challenges the viability of services. Smart home technology can play a significant role in easing pressure on caregivers, as well reduce financial costs Activity Daily Living (ADL) recognition essential step translate sensor data into activities at high semantic levels. Supervised Machine Learning (ML) algorithms are most...
Older adults at home frequently rely on 'circles of support' which range from relatives and neighbours, to the voluntary sector, social workers, paid carers, medical professionals. Creating, maintaining, coordinating these circles support has often been done manually in an ad hoc manner. We argue that a socio-technical system assists creating, is key enabler community healthcare for older adults.
The COVID-19 pandemic is worsening loneliness for many older people through the challenges it poses in engaging with their social worlds. Digital technology has been offered as a potential aid, however, popular digital tools have not designed to address needs of adults during times limited contact. We propose that Social Identity Model Change (SIMIC) could be foundation interventions. While SIMIC well-established approach maintaining wellbeing life transitions, rigorously applied There are...
Stress echocardiography is a well-established diagnostic tool for suspected coronary artery disease (CAD). Cardiovascular risk factors are used in the assessment of probability CAD. The link between outcome stress and patients' variables including factors, current medication, anthropometric has not been widely investigated.This study aimed to use machine learning predict significant CAD defined by positive results patients with chest pain based on anthropometrics, cardiovascular medication...
Background The global population is aging, leading to shifts in health care needs. In addition developing technology support physical health, there an increasing recognition of the need consider how can emotional health. This raises question design devices that older adults interact with log their emotions. Objective We designed and developed 2 novel tangible devices, inspired by existing paper-based scales findings from a field trial these are reported. Methods Using interviews, deployment,...
Abstract Background The Clinch Token Transfer Test (C3t) is a bi-manual coin transfer task that incorporates cognitive tasks to add complexity. This study explored the concurrent and convergent validity of C3t as simple, objective assessment impairment reflective disease severity in Huntington’s, not reliant on clinical expertise for administration. Methods One-hundred-and-five participants presenting with pre-manifest ( n = 16) or manifest (TFC-Stage-1 39; TFC-Stage-2 43; TFC-Stage-3 7)...
<h3>Background</h3> Stress echocardiography is a well-established diagnostic prognostic modality with good predictive power in patient suspected coronary artery disease (CAD). Cardiovascular risk factors are used the assessment of probability CAD. The link between outcome stress and patients' variables has not been widely investigated. <h3>Objective</h3> aim this study to understand whether new algorithm can be developed using machine learning principle predict result patients CAD based on...