A5002563560- Context-Aware Activity Recognition Systems
- Non-Invasive Vital Sign Monitoring
- Energy Efficient Wireless Sensor Networks
- Nuclear and radioactivity studies
- Wireless Body Area Networks
- Mobile Ad Hoc Networks
- IoT and Edge/Fog Computing
- Bluetooth and Wireless Communication Technologies
- Anomaly Detection Techniques and Applications
- Heart Rate Variability and Autonomic Control
- Corrosion Behavior and Inhibition
- Electron and X-Ray Spectroscopy Techniques
- Air Quality Monitoring and Forecasting
- Energy Harvesting in Wireless Networks
- Network Security and Intrusion Detection
- Software System Performance and Reliability
- Caching and Content Delivery
- Indoor and Outdoor Localization Technologies
- Advanced Malware Detection Techniques
- EEG and Brain-Computer Interfaces
- Data Stream Mining Techniques
- Software-Defined Networks and 5G
- ECG Monitoring and Analysis
- Underwater Vehicles and Communication Systems
- Advanced Graph Neural Networks
University of Bristol
1970-2025
Bristol Robotics Laboratory
2024
University of North Alabama
2020-2021
University of Montevallo
2019-2020
Stephens College
2020
George Mason University
2010-2016
Cardiovascular diseases are the leading cause of death in U.K., motivating use long term wearable devices to monitor heart out-of-the-clinic settings. While a wide number rate measuring now available, they principally based upon photoplethysmography rather than electrocardiogram (ECG) and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">stand-alone</i> integrated with Internet-of-Things infrastructures which collect combine information from...
Smart health home systems and assisted living architectures rely on severely energy-constrained sensing devices, such as wearable sensors, for the generation of data their reliable wireless communication to a central location. However, need recharging battery regularly constitutes maintenance burden that hinders long-term cost-effectiveness these systems, especially health-oriented applications target people in need, elderly or chronically ill. These generate raw is processed into knowledge...
Wearable technologies are valuable tools that can encourage people to monitor their own well-being and facilitate timely health interventions. In this paper, we present SPW-2; a low-profile versatile wearable sensor employs two ultra low power accelerometers an optional gyroscope. Designed
The upcoming Internet of Things (IoT) applications include real-time human activity monitoring with wearable sensors. Compared to the traditional environmental sensing low-power wireless nodes, these new generate a constant stream much higher rate. Nevertheless, devices remain battery powered and therefore restricted standards such as IEEE 802.15.4 or Bluetooth Low Energy (BLE). Our work tackles problem building reliable autonomous schedule for forwarding this kind dynamic data in TSCH...
This paper presents Vesta, a digital health platform composed of smart home in box for data collection and machine learning based analytic system deriving indicators using activity recognition, sleep analysis indoor localization. has been deployed the homes 40 patients undergoing heart valve intervention United Kingdom (UK) as part EurValve project, measuring well-being before after their operation. In this work cohort 20 are analyzed, 2 analyzed detail example case studies. A quantitative...
Abstract In this paper, a portfolio optimization model on the basis of risk measure lower partial moment first order is discussed. Two meta‐heuristic methods particle swarm and genetic algorithm performances are applied compared from different aspects to derive stocks portfolios efficient frontier. The data belongs monthly returns 20 randomly selected approved in New York Stock Exchange for financial period 2005–2011. results prove that both algorithms quite solving mean‐lower with being superior.
Data integrity becomes paramount as the number of Internet Things (ioT) sensor deployments increases. Sensor data can be altered by benign causes or malicious actions. Mechanisms that detect drifts and irregularities prevent disruptions bias in state an IoT application. This paper presents LE3D, ensemble framework drift estimators capable detecting abnormal behaviours. Working collaboratively with surrounding ioT devices, type (natural/abnormal) also identified reported to end-user. The...
Many countries are facing burdens on their health care systems due to ageing populations. A promising strategy address the problem is allow selected people remain in homes and be monitored using recent advances wearable devices, saving in-hospital resources. With respect heart monitoring, devices date have principally used optical techniques by shining light through skin. However, these severely hampered motion artifacts limited rate detection. Further, consume a large amount of power order...
The efficient and effective deployment of Internet Things (IoT) systems in real world scenarios remains a challenge, particularly applications such as indoor localisation. Various methods have been proposed recently to calibrate localisation systems, ranging from precise but time consuming processes those involving little explicit calibration based on crowdsourced collection data over time. However it is not clear how estimate compare the quality specific instance calibration. In this paper...
Non-invasive, environmental monitoring is being successfully utilised to improve health care outcomes for patients while allowing them more safely and comfortably live in their homes instead of facilities. This promises reduce costs ease the burden many countries globally. However, these systems are still early stages research only highly skilled researchers engineers can deploy them. The difficulty deploying prevents mass use potential cost savings motivating interest smart a box (SHiB). In...
Graph neural networks (GNNs) are powerful models capable of managing intricate connections in non-Euclidean data, such as social networks, physical systems, chemical structures, and communication networks. Despite their effectiveness, the large-scale complex nature graph data demand substantial computational resources high performance during both training inference stages, presenting significant challenges, particularly context embedded systems. Recent studies on GNNs have investigated...
An annotated dataset of measurements obtained using the EurValve Smart Home In a Box (SHIB) rehabilitation monitoring system is presented. The SHiB low cost and easily deployable kit designed to collect data from wrist-worn wearable in home environment. presented intended evaluate room level indoor localization methods. device registers tri-axial accelerometer which are sampled transmitted as payload Bluetooth Low Energy (BLE) packet. Four receiving gateways, each placed different throughout...
The Internet of Things promises to enable numerous future applications spanning many domains, including health care, and is comprised devices that are constrained in terms computational energy resources. A specific care application ascertain patients' activity daily living while at home using accelerometer data from non-invasive wearables. It often necessary store this on the device be retrieved later for analysis. However, typically far more than can transmitted with commonly used low power...
We are interested in hot and cold water flow detection domestic kitchen bathroom taps for smart home environments. Water monitoring is particularly valuable long-term behavioural systems health-related applications, as it enables the collection of data on hydration levels house residents, associated with several activities daily life, such cooking cleaning. This paper presents a sensing device that based vibrations pipe when flowing through them. The proposed solution noninvasive energy...
Efficient one-to-many broadcasting is an essential function in dense or large-scale wireless systems managed by a sink gateway. This paper describes HASTE, novel heuristic designed for broadcast tree production. Minimizing maximum hop count reduces worst case latency, while maximizing the number of leaf nodes transmitted messages. The algorithm to be used with current routing protocols that have capability push configurations into network. We evaluated HASTE against approximation and found...
Edge computing is rapidly changing the IoT-Cloud landscape. Various testbeds are now able to run multiple Docker-like containers developed and deployed by end-users on edge devices. However, this capability may allow an attacker deploy a malicious container host compromise it. This paper presents dataset based Linux Auditing System, which contains benign activity. We two scenarios, denial of service privilege escalation attack, where adversary uses device. Furthermore, we user in parallel...
Low-power wearable devices are becoming increasingly important for fitness and healthcare applications. However, existing protocols based on the IEEE 802.15.4 low-power wireless standard not optimized data collection from mobile devices. This paper presents Instant: a schedule TSCH protocol tailored this application. We evaluate speed, energy consumption, fairness of Instant, show that Instant achieves several times higher speed nodes compared with state-of-the-art Orchestra schedule.
One of the main shortcomings received signal strength‐based indoor localisation techniques is labour and time cost involved in acquiring labelled ‘ground‐truth’ training data. This data often obtained through fingerprinting, which involves visiting all prescribed locations to capture sensor observations throughout environment. In this work, authors present a helmet for optimisation (H4LO): low‐cost robotic system designed cut down on said by utilising an off‐the‐shelf light detection ranging...