- Heart Rate Variability and Autonomic Control
- Non-Invasive Vital Sign Monitoring
- Cardiovascular and exercise physiology
- ECG Monitoring and Analysis
- Context-Aware Activity Recognition Systems
- Cardiac electrophysiology and arrhythmias
- Telemedicine and Telehealth Implementation
- Advanced Control Systems Optimization
- Hemodynamic Monitoring and Therapy
- Balance, Gait, and Falls Prevention
- Fault Detection and Control Systems
- Stability and Control of Uncertain Systems
- Muscle activation and electromyography studies
- Gait Recognition and Analysis
- Mobile Health and mHealth Applications
- Neuroscience and Neural Engineering
- Blood Pressure and Hypertension Studies
- Cardiovascular Health and Disease Prevention
- Anomaly Detection Techniques and Applications
- Chronic Disease Management Strategies
- EEG and Brain-Computer Interfaces
- Control Systems and Identification
- Blind Source Separation Techniques
- Time Series Analysis and Forecasting
- Neural dynamics and brain function
UNSW Sydney
2016-2025
GTx (United States)
2024
Commonwealth Scientific and Industrial Research Organisation
2012-2021
Australian e-Health Research Centre
2021
CSIRO Health and Biosecurity
2017-2018
University of Technology Sydney
2005-2018
Health Sciences and Nutrition
2018
Information and Communication Technologies Centre
2013-2017
Western Sydney University
2010-2013
Data61
2007-2013
The real-time monitoring of human movement can provide valuable information regarding an individual's degree functional ability and general level activity. This paper presents the implementation a classification system for types associated with data acquired from single, waist-mounted triaxial accelerometer unit. major advance proposed by is to perform vast majority signal processing onboard wearable unit using embedded intelligence. In this way, distinguishes between periods activity rest,...
In this paper, an output position feedback control of the electro-hydraulic system (EHS) is proposed based on extended-state-observer (ESO) with backstepping. On basis augmented state model EHS, ESO designed to handle unknown load disturbance and uncertain nonlinearity. Then, observer bandwidth constraint derived compromise between dynamic performance maximal capability EHS. The effectiveness for suppression largely disturbances has been demonstrated by comparative experimental study, which...
Accelerometry shows promise in providing an inexpensive but effective means of long-term ambulatory monitoring elderly patients. The accurate classification everyday movements should allow such a system to exhibit greater 'intelligence', improving its ability detect and predict falls by forming more specific picture the activities person thereby allowing tracking health parameters associated with those activities. With this mind, study aims develop robust methods for postures motions from...
This paper presents an adaptive neural network (NN) control of a two-degree-of-freedom manipulator driven by electrohydraulic actuator. To restrict the system output in prescribed performance constraint, weighted function is designed to guarantee dynamic and steady tracking errors joint angle required accuracy. Then, radial-basis-function NN constructed train unknown model dynamics traditional backstepping (TBC) obtain preliminary estimated model, which can replace preknown iteration....
We assessed the feasibility of using a waist-mounted, wireless triaxial accelerometer (TA) to monitor human movements in an unsupervised home setting detect changes functional status. A pilot study was carried out with six healthy subjects aged 80-86 years. The wore TA unit every day for two three months. Each morning they short routine directed that included standing, sitting, lying and walking. Important movement variables were measured. During rest day, monitored falls, such as metabolic...
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper proposes a novel integrated approach for the identification and control of Hammerstein systems to achieve desired heart rate profile tracking performance an automated treadmill system. For systems, pseudorandom binary sequence input is employed decouple dynamic linear part from nonlinearity. The powerful $\epsilon$ -insensitivity support vector regression method adopted obtain sparse...
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> The first objective of this paper is to introduce a nonlinear system model the heart rate (HR) response during and after treadmill walking exercise. feedback interconnected that has components describe central peripheral local responses exercise their interactions. parameters were experimentally identified from subjects on at different speeds. stability obtained was mathematically proven....
Advances in technology have made possible new and innovative methods of health care delivery. Home telecare, which the patient's is monitored remotely at home, one such method. This paper discusses use a triaxial accelerometer within home telecare system for monitoring physiological functional parameters daily living. A novel described objectively continuously movement, suitable patients with chronic diseases including congestive heart failure obstructive pulmonary disease. The key design...
In this work, 33 dimensional time-frequency domain features were developed and evaluated to detect five different human walking patterns from data acquired using a triaxial accelerometer attached at the waist above iliac spine. 52 subjects asked walk on flat surface along corridor, up down flight of stairway constant gradient slope, in an unsupervised manner. Time-frequency acceleration anterior-posterior (AP), medio-lateral (ML) vertical (VT) direction developed. The signal each was...
Falls among the elderly population are a major cause of morbidity and injury-particularly over 65 years age group. Validated clinical tests associated models, built upon assessment functional ability, have been devised to estimate an individual's risk falling in near future. Those identified as at-risk may be targeted for interventative treatment. The migration these models estimating falls surrogate technique, use unsupervised environment, might broaden reach falls-risk screening beyond...
Falls can cause trauma, disability and death among older people. Ambulatory accelerometer devices are currently capable of detecting falls in a controlled environment. However, research suggests that most current approaches tend to have insufficient sensitivity specificity non-laboratory environments, part because impacts be experienced as ordinary daily living activities.We used waist-worn wireless tri-axial combined with digital signal processing, clustering neural network classifiers. The...
The telemonitoring of vital signs from the home is an essential element telehealth services for management patients with chronic conditions, such as congestive heart failure (CHF), obstructive pulmonary disease (COPD), diabetes, or poorly controlled hypertension. Telehealth now being deployed widely in both rural and urban settings, this paper, we discuss contribution made by biomedical instrumentation, user interfaces, automated risk stratification algorithms developing a clinical...
Home telecare, in which the health status of patients at home is monitored remotely, has potential to improve care and reduce costs. Its widespread implementation would require fundamental changes healthcare system.
The suppression of disturbances under parametric uncertainties is one the most common control problems in electrohydraulic systems, as both and often significantly degrade tracking performance bias load pressure actuator (EHA). This brief presents a state-constrained single-rod EHA to restrict position error prescribed accuracy guarantee maximal power boundary. Furthermore, dynamic surface designed avoid explosion complexity due repeatedly calculated differentiations virtual variables...