A5072034864- Chronic Obstructive Pulmonary Disease (COPD) Research
- Air Quality Monitoring and Forecasting
- Dementia and Cognitive Impairment Research
- Technology Use by Older Adults
- Air Quality and Health Impacts
- Cognitive Functions and Memory
- Biomedical Text Mining and Ontologies
- Allergic Rhinitis and Sensitization
- Natural Language Processing Techniques
- Topic Modeling
- Advanced Text Analysis Techniques
- Satellite Image Processing and Photogrammetry
- Electronic Health Records Systems
- Medical Imaging Techniques and Applications
- Business Process Modeling and Analysis
- Traumatic Brain Injury and Neurovascular Disturbances
- Odor and Emission Control Technologies
- Data Stream Mining Techniques
- Mental Health via Writing
- Digital Humanities and Scholarship
- Context-Aware Activity Recognition Systems
- Digital and Traditional Archives Management
- Parallel Computing and Optimization Techniques
- Atmospheric and Environmental Gas Dynamics
- Persona Design and Applications
University of Manchester
2015-2024
Manchester University
2021
Urban Institute
2020
To determine whether multiple computer use behaviours can distinguish between cognitively healthy older adults and those in the early stages of cognitive decline, to investigate these are associated with functional ability.Older impairment (n = 20) controls 24) completed assessments abilities a series semi-directed tasks. Computer were captured passively using bespoke software.The profile was significantly different impaired compared control participants including more frequent pauses,...
Semantic relatedness between words is important to many NLP tasks, and numerous measures exist which use a variety of resources. Thus far, such work confined measuring similarity two (or texts), only handful utilize the web as corpus. This paper introduces distributional measure uses internet search counts also extends calculating within word-groups. The evaluation results are encouraging: for word-pairs, correlations with human judgments comparable state-of-the-art web-search page-count...
Abstract In recent years, quantifying the impacts of detrimental air quality has become a global priority for researchers and policy makers. At present, systems methodologies supporting collection manipulation this data are difficult to access. To support studies interplay between common gaseous particulate pollutants with meteorology biological particles, paper presents comprehensive data-set containing daily readings from Automatic Urban Rural Network, pollen weather Met Office monitoring...
Hay fever affects people differently and can change over a lifetime, but data is lacking on how environmental factors may influence this. This study the first to combine atmospheric sensor with real-time, geo-positioned hay symptom reports examine relationship between severity air quality, weather land use. We 36145 submitted 5 years by 700 UK residents using mobile application. Scores were recorded for nose, eyes breathing. Symptom are labelled as urban or rural land-use from UK's Office...
This paper proposes a Bayesian association rule mining algorithm (BAR) which combines the Apriori with networks. Two interesting-ness measures of rules: confidence (BC) and lift (BL) measure conditional dependence independence relationships between items are defined based on joint probabilities represented by networks rules. BAR outputs best rules according to BC BL. is evaluated for its performance using two anonymized clinical phenotype datasets from UCI Repository: Thyroid disease...
We report experience in requirements elicitation of domain knowledge from experts clinical and cognitive neurosciences. The target was a causal model for early signs dementia indicated by changes user behaviour errors apparent logs computer activity. A Delphi-style process consisting workshops with followed questionnaire adopted. paper describes how the had to be adapted deal problems encountered terminology limited consensus among experts. In spite difficulties encountered, partial...
We present a desktop monitoring application that combines keyboard, mouse, and application-level activities. It has been developed to discover differences in cognitive functioning amongst older computer users indicative of mild impairment (MCI). Following requirements capture from clinical domain experts, the tool collects all Microsoft Windows events deemed potentially useful for detecting early indicators dementia, with view further analysis determine most pertinent. Further potential...
Objectives Computer-use behaviours can provide useful information about an individual's cognitive and functional abilities. However, little research has evaluated unaided non-directed home computer-use. In this proof of principle study, we explored whether computer-use recorded during routine i) could discriminate between individuals with subjective decline (SCD) mild impairment (MCI); ii) were associated scores; iii) changed over time.Methods Thirty-two participants SCD (n = 18) or MCI 14)...
Birth-related acute profound hypoxic-ischaemic brain injury has specific patterns of damage including the paracentral lobules.To test hypothesis that there is anatomically coherent regional volume loss corpus callosum as a result this hemispheric abnormality.Study subjects included 13 children with proven and developmental delay but no abnormalities. A computerised system divided into 100 segments, measuring each width. Principal component analysis grouped widths contiguous anatomical...
Smart city projects are making available numerous, diverse, potentially valuable data streams. However, it is cumbersome and laborious for domain experts to identify, analyse inter-relate such In this paper we describe a system that designed support these users obtain an understanding of key features individual streams, undertake variety analyses multiple Three case studies presented, showing the use process live car-park, weather, building energy consumption bicycle journey from CityVerve...
Existing approaches to characterise engagement in online learning focus on features of the interaction students with platform including number posts forums, downloads materials and time spent watching videos. However, little is known about what actually do within resources whether these activities are indicators outcomes. To bridge this gap, we associate low-level activity patterns particular student modes a connectivist MOOC (cMOOC) that ran for four weeks involved 224 students. Our...
Computer use is becoming ubiquitous among older adults. As computer depends on complex cognitive functions, measuring individuals’ computer-use behaviours over time may provide a way to detect changes in their functioning. However, it uncertain which behaviour are most likely be associated with declines of particular functions. To address this, we convened six experts from clinical and neurosciences take part two workshops follow-up survey gain consensus would the strongest indicators...
The use of topical features is abundant in Natural Language Processing (NLP), a major example being dictionary-based Word Sense Disambiguation (WSD). Yet previous research does not attempt to measure the level topic cohesion documents, despite assertions its effects. This paper introduces quantitative Topic Homogeneity using range NLP resources and requiring prior knowledge correct senses. Evaluation performed firstly by WordNet::Domains package create word-sets with varying levels...