A5086829042- Dementia and Cognitive Impairment Research
- Time Series Analysis and Forecasting
- Data Quality and Management
- Data Management and Algorithms
- Music and Audio Processing
- Advanced Causal Inference Techniques
- Statistical Methods in Clinical Trials
- Advanced Database Systems and Queries
- Machine Learning in Healthcare
- Context-Aware Activity Recognition Systems
- Computational and Text Analysis Methods
- Artificial Intelligence in Healthcare and Education
- Ethics in Clinical Research
- Semantic Web and Ontologies
- Health Systems, Economic Evaluations, Quality of Life
- Statistical Methods and Inference
- Complex Systems and Time Series Analysis
- Web Data Mining and Analysis
- Anomaly Detection Techniques and Applications
- Big Data and Business Intelligence
- Health and Medical Research Impacts
- Geriatric Care and Nursing Homes
University of Surrey
2019-2021
Signal Processing (United States)
2019
UK Dementia Research Institute
2019
With the proliferation of sensors and IoT technologies, stream data are increasingly stored analyzed, but rarely combined, due to heterogeneity sources technologies. Semantics used share sensory data, not so much for annotating data. Semantic models annotation scarce, as generally semantics heavy process ideal Internet things (IoT) environments, where frequently updated. We present a light model semantically annotate streams, IoT-Stream. It takes advantage common knowledge sharing semantics,...
The rapid growth of Internet Things (IoT) and sensing technologies has led to an increasing interest in time-series data analysis. In many domains, detecting patterns IoT interpreting these are challenging issues. There several methods analysis that deal with issues such as volume velocity streams. However, analysing the content streams extracting insights from dynamic is still a task. this paper, we propose pattern representation method which represents frames vectors by first applying...
Due to the rapid development of Internet Things (IoT) and consequently, availability more IoT data sources, mechanisms for searching integrating sources become essential leverage all relevant improving processes services. This paper presents search framework IoTCrawler. The IoTCrawler is not only another framework, it a system systems which connects existing solutions offer interoperability overcome fragmentation. In addition its domain-independent design, features layered approach, offering...
In recent years, the development and deployment of Internet Things (IoT) devices has led to generation large volumes real world data. Analytical models can be used extract meaningful insights from this However, most IoT data is not fully utilised, which mainly due interoperability issues difficulties analyse collected by heterogeneous resources. To overcome heterogeneity, semantic technologies are create common share various originated sources. semantics add further overhead delivery,...
Edge computing can improve the scalability and efficiency of IoT systems by performing some analysis operations on nodes or intermediary edge devices. This will reduce energy consumption, data transmission load latency shifting processes to In this paper, we introduce a pattern extraction method which uses both Lagrangian Multiplier Principal Component Analysis (PCA) create patterns from raw sensory data. We have evaluated our applying clustering constructed patterns. The results show that...
Interpreting the environmental, behavioural and psychological data from in-home sensory observations measurements can provide valuable insights into health well-being of individuals. Presents neuropsychiatric symptoms in people with dementia have a significant impact on their disease prognosis. Agitation be due to many reasons such as pain or discomfort, medical side effects medicine, communication problems environment. This paper discusses model for analysing risk agitation how monitoring...
The rapid growth in collecting and sharing sensory observation form the urban environments provides opportunities to plan manage services cities better allows citizens also observe understand changes their surrounding a way. new data creates for further application service development by creative industries start-ups. However, as size diversity of this increase, finding accessing right set timely manner is becoming more challenging. This paper describes search engine designed indexing,...
Randomised controlled trials (RCTs) are regarded as the gold standard for estimating causal treatment effects on health outcomes. However, RCTs not always feasible, because of time, budget or ethical constraints. Observational data such those from electronic records (EHRs) offer an alternative way to estimate treatments. Recently, `target trial emulation' framework was proposed by Hernan and Robins (2016) provide a formal structure observational data. To promote more widespread...
Behavioural symptoms and urinary tract infections (UTI) are among the most common problems faced by people with dementia. One of key challenges in management these conditions is early detection timely intervention order to reduce distress avoid unplanned hospital admissions. Using in-home sensing technologies machine learning models for sensor data integration analysis provides opportunities detect predict clinically significant events changes health status. We have developed an integrated...
Behavioural changes and neuropsychiatric symptoms such as agitation are common in people with dementia. These impact the quality of life dementia can increase stress on caregivers. This study aims to identify likelihood having affected by (i.e., patients carers) using routinely collected data from in-home monitoring technologies. We have used a digital platform analytical methods, developed our previous study, generate alerts when occur markers sensing technologies vital signs, environmental...