A5039139275- Context-Aware Activity Recognition Systems
- IoT and Edge/Fog Computing
- Innovative Human-Technology Interaction
- IoT-based Smart Home Systems
- Web Application Security Vulnerabilities
- Energy Efficient Wireless Sensor Networks
- Security and Verification in Computing
- Mobile Crowdsensing and Crowdsourcing
- Service-Oriented Architecture and Web Services
- Access Control and Trust
- Data Management and Algorithms
- Technology Use by Older Adults
- Mobile Health and mHealth Applications
- Video Surveillance and Tracking Methods
- Data Quality and Management
- Persona Design and Applications
- Semantic Web and Ontologies
- Personal Information Management and User Behavior
- Network Time Synchronization Technologies
- Genetic Syndromes and Imprinting
- Anomaly Detection Techniques and Applications
- Usability and User Interface Design
- Human Pose and Action Recognition
- Mobile Agent-Based Network Management
- Asthma and respiratory diseases
University of Bristol
2015-2018
Sciences, Philosophie, Histoire
2018
Ambient Assisted Living (AAL) systems based on sensor technologies are seen as key enablers to an ageing society. However, most approaches in this space do not provide a truly generic ambient - one that is only capable of assisting people with diverse medical conditions, but can also recognise the habits healthy habitants, well those developing conditions. The recognition Activities Daily (ADL) understanding and provisioning appropriate efficient care. ADL particularly difficult achieve...
Healthcare professionals currently lack the means to gather unbiased and quantitative multi-modal data about long-term behaviors of patients in their home environments. SPHERE is a platform non-medical sensors for behavior monitoring residential environments that aims overcome this major limitation healthcare provision by using inherently cost-efficient scalable technologies Internet Things (IoT). One SPHERE's key tasks help bring next-generation low-power wireless networking sensing from...
This paper outlines the Sensor Platform for HEalthcare in Residential Environment (SPHERE) project and details SPHERE challenge that will take place conjunction with European Conference on Machine Learning Principles Practice of Knowledge Discov- ery (ECML-PKDD) between March July 2016. The chal- lenge is an activity recognition competition where predictions are made from video, accelerometer environmental sensors. Monitory prizes be awarded to top three entrants, e1,000 being winner, e600...
Human Activity Recognition (AR) is an area of great importance for health and well-being applications including Ambient Intelligent (AmI) spaces, Assisted Living (AAL) environments, wearable healthcare systems.Such intelligent systems reason over large amounts sensor-derived data in order to recognise users' actions.The design AR algorithms relies on ground-truth sufficient quality quantity enable rigorous training validation.Ground-truth often acquired using video recordings which can...
Ubiquitous eHealth systems based on sensor technologies are seen as key enablers in the effort to reduce financial impact of an ageing society. At heart such sit activity recognition algorithms, which need data reason over, and a ground truth adequate quality used for training validation purposes. The large set up costs research projects their complexity limit rapid developments this area. Therefore, information sharing reuse, especially context collected datasets, is overcoming these...
Delivering effortless interactions and appropriate interventions through pervasive systems requires making sense of multiple streams sensor data. This is particularly challenging when these concern people’s natural behaviours in the real world. paper takes a multidisciplinary perspective annotation draws on an exploratory study 12 people, who were encouraged to use multi-modal app while living prototype smart home. Analysis usage data semi-structured interviews with participants revealed...
SPHERE is a large multidisciplinary project to research and develop sensor network facilitate home healthcare by activity monitoring, specifically towards activities of daily living. It aims use the latest technologies in low powered sensors, internet things, machine learning automated decision making provide benefits patients clinicians. This dataset comprises data collected from deployment during set experiments conducted 'SPHERE House' Bristol, UK, 2016, including video tracking,...
Labelling user data is a central part of the design and evaluation pervasive systems that aim to support through situation-aware reasoning. It essential both in designing training system recognise reason about situation, either definition suitable situation model knowledge-driven applications, or preparation for learning tasks data-driven models. Hence, quality annotations can have significant impact on performance derived systems. also vital validating quantifying applications. In...
Pervasive computing and, specifically, the Internet of Things aspire to deliver smart services and effortless interactions for their users. Achieving this requires making sense multiple streams sensor data, which becomes particularly challenging when these concern people's activities in real world. In paper we describe exploration different approaches that allow users self-annotate near real-time, turn can be used as ground-truth develop algorithms automated accurate activity recognition. We...
Current applications of Internet Things (IoT) often require nodes to implement logical decision-making on aggregated data, which involves more processing and wider interactions amongst network peers, resulting in higher energy consumption shorter node lifetime. This paper presents a game theoretic approach used Sensomax, an agent-based WSN middleware that facilitates seamless integration mathematical functions large-scale wireless sensor networks. In this context, we investigate...
AAL platforms for health and care purposes are designed to be used by diverse stakeholders, such as household residents, carers healthcare professionals, with equally needs. Reducing the latency of systems is key achieving a positive user experience, well enabling appropriate responses critical incidents. This paper introduces distributed middleware solution that can improve data-acquisition, run computational algorithms locally seamlessly deliver notifications various subscribers. The...
Maintaining good hydration is crucial for adequate physical and mental performance all human beings. In this paper we present SPLASH, an Android app that enables users to set daily goals keep track of their liquid intake through a combination smart-phone NFC technology NFC-tagged cups. We conducted several experiments verify the robustness technology, which indicated selected tags had acceptable robustness, operational distance penetration ability meet intended requirements monitoring...
An abstract is not available for this content. As you have access to content, full HTML content provided on page. A PDF of also in through the ‘Save PDF’ action button.
Ubiquitous eHealth systems based on sensor technologies are seen as key enablers in the effort to reduce financial impact of an ageing society. At heart such sit activity recognition algorithms, which need data reason over and a `ground truth' adequate quality - used for training validation purposes. The large set up costs research projects their complexity limit rapid developments this area. Therefore, information sharing reuse, especially context collected datasets, is overcoming these...
The Semantic Web (SW) is a significant advancement in the field of Internet technologies and an uncharted territory as far security concerned. In this paper, we investigate assess impact known attacks SPARQL/SPARUL injections on applications developed PHP. We highlight future challenges developing robust using Our results demonstrate quantify impacts Confidentiality, Integrity Availability (CIA) breaches data applications. recommendations are targeted to PHP developers, encourage them...
Reliably discerning human activity from sensor data is a nontrivial task in ubiquitous computing, which central to enabling smart environments. Ground-truth acquisition techniques for such environments can be broadly divided into observational and self-reporting approaches. In this paper we explore one approach, using speech-enabled logging generate ground-truth data. We report the results of user study participants (N=12) used both smart-watch smart-phone app record their activities daily...
Background: Vasopressin promotes cyst growth in Autosomal Dominant Polycystic Kidney Disease (ADPKD). receptor antagonists slow disease progression, but their use is limited by side effects and cost. High water intake suppresses vasopressin production may provide a viable alternative to pharmacological blockade. We aimed assess the feasibility of definitive randomised high trial ADPKD.Methods: conducted phase 2, single-centre open-label controlled (NCT02933268). Adults aged 16 years older...
This paper outlines the Sensor Platform for HEalthcare in Residential Environment (SPHERE) project and details SPHERE challenge that will take place conjunction with European Conference on Machine Learning Principles Practice of Knowledge Discovery (ECML-PKDD) between March July 2016. The is an activity recognition competition where predictions are made from video, accelerometer environmental sensors. Monetary prizes be awarded to top three entrants, Euro 1,000 being winner, 600 first runner...