ORCID Profile
0000-0001-7232-7967
Current Organisation
UNSW Sydney
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Evolutionary computation | Planning and decision making | Artificial intelligence |
Publisher: IOP Publishing
Date: 19-04-2017
Abstract: Inspired by the lateral line of aquatic vertebrates, an artificial lateral line (ALL) system can localize and track an underwater moving object by analyzing the ambient flow caused by its motion. There are several studies on object detection, localization and tracking by ALL systems, but only a few have investigated the optimal design of the ALL system, the one that on average provides the highest characterization accuracy. Design optimization is particularly important because the uncertainties in the employed flow model and in sensor measurements deteriorate the reliability of sensing. This study investigates the optimal design of the ALL system in three-dimensional (3D) space for dipole source characterization. It highlights some challenges specific to the 3D setting and demonstrates the shortcomings of the designs in which all sensors and their sensing directions are in the same plane. As an alternative, it proposes two design concepts, called 'Offset Strategy' and 'Angle Strategy' to overcome these shortcomings. It investigates potentials of having a swarm of cooperative ALLs as well. It performs design optimization in the presence of sensor and model uncertainties and analyzes the trade-off between the number of sensors and characterization accuracy. The obtained solutions are analyzed to reveal their strategies in solving the problem efficiently. The dependency of the optimized solutions on the uncertainties is also demonstrated.
Publisher: Elsevier BV
Date: 02-2021
Publisher: Springer International Publishing
Date: 14-11-2022
Publisher: Elsevier BV
Date: 09-2010
Publisher: Elsevier BV
Date: 02-2016
Publisher: Elsevier BV
Date: 10-2023
Publisher: Informa UK Limited
Date: 16-10-2013
Publisher: Springer International Publishing
Date: 2021
Publisher: IEEE
Date: 28-06-2021
Publisher: Informa UK Limited
Date: 29-04-2020
Publisher: IEEE
Date: 06-2017
Publisher: IEEE
Date: 12-2020
Publisher: IEEE
Date: 06-2019
Publisher: Informa UK Limited
Date: 20-08-2014
Publisher: Elsevier BV
Date: 07-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2021
Publisher: Springer Science and Business Media LLC
Date: 07-08-2015
Publisher: The Sax Institute
Date: 28-01-2016
DOI: 10.17061/PHRP2611607
Abstract: It is important for consumers, clinicians and health service planners to know the risk of recurrence of primary breast cancer after initial treatment. At present, none of Australia's state or territory cancer registries routinely report this information. We aimed to determine the incidence of recurrence in New South Wales (NSW) clinical practice for the period 18 months to 6 years after diagnosis of primary breast cancer. Retrospective cohort study using population-based linked health data. We identified 2416 women in the 45 and Up Study who were diagnosed with primary invasive breast cancer between 2003 and 2008 in NSW, and who had not had a recurrence 18 months after diagnosis. Unit-level hospital, pharmacy and outpatient medical claims were used to identify treatment for recurrence. Incidence of recurrence was calculated using in idual person-time at risk (18 months to 6 years postdiagnosis), with follow-up censored for death or end of study period (median follow-up 3 years). Time to recurrence was calculated, and Cox proportional regression was used to identify women's baseline and active treatment characteristics that were predictive of recurrence up to 6 years postdiagnosis. 217 women (9%) had a hospital, pharmacy or outpatient claim indicating breast cancer recurrence. Overall annual incidence of recurrence was 3.3%. Recurrence rates were significantly higher for women with node-positive (4.8% vs 2.5% annually hazard ratio [HR] = 1.7 95% confidence interval [95% CI] 1.3, 2.3) or hormone receptor-negative tumours (3.8% vs 3.1% annually HR = 1.3 95% CI 1.0, 1.7). Women with tumours >2 cm at diagnosis were more likely to experience recurrence than women with smaller/unknown tumours (4.8% vs 2.7% annually HR = 1.5 95% CI 1.1, 2.0). A combination of routinely collected administrative health datasets can be used to determine recurrence rates, allowing future assessment of population-level changes over time and investigations of the real-world impact of specific treatments on outcomes.
Publisher: No publisher found
Date: 2016
Publisher: IEEE
Date: 05-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Publisher: Springer Science and Business Media LLC
Date: 04-03-2010
Publisher: Elsevier BV
Date: 2010
Publisher: Informa UK Limited
Date: 13-04-2016
Publisher: Elsevier BV
Date: 04-2009
Publisher: Springer Science and Business Media LLC
Date: 30-06-2012
Publisher: MIT Press - Journals
Date: 09-2017
DOI: 10.1162/EVCO_A_00182
Abstract: During the recent decades, many niching methods have been proposed and empirically verified on some available test problems. They often rely on some particular assumptions associated with the distribution, shape, and size of the basins, which can seldom be made in practical optimization problems. This study utilizes several existing concepts and techniques, such as taboo points, normalized Mahalanobis distance, and the Ursem’s hill-valley function in order to develop a new tool for multimodal optimization, which does not make any of these assumptions. In the proposed method, several subpopulations explore the search space in parallel. Offspring of a subpopulation are forced to maintain a sufficient distance to the center of fitter subpopulations and the previously identified basins, which are marked as taboo points. The taboo points repel the subpopulation to prevent convergence to the same basin. A strategy to update the repelling power of the taboo points is proposed to address the challenge of basins of dissimilar size. The local shape of a basin is also approximated by the distribution of the subpopulation members converging to that basin. The proposed niching strategy is incorporated into the covariance matrix self-adaptation evolution strategy (CMSA-ES), a potent global optimization method. The resultant method, called the covariance matrix self-adaptation with repelling subpopulations (RS-CMSA), is assessed and compared to several state-of-the-art niching methods on a standard test suite for multimodal optimization. An organized procedure for parameter setting is followed which assumes a rough estimation of the desired/expected number of minima available. Performance sensitivity to the accuracy of this estimation is also studied by introducing the concept of robust mean peak ratio. Based on the numerical results using the available and the introduced performance measures, RS-CMSA emerges as the most successful method when robustness and efficiency are considered at the same time.
Publisher: Elsevier BV
Date: 2022
Publisher: Informa UK Limited
Date: 09-09-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2022
Publisher: Elsevier BV
Date: 03-2021
Publisher: Elsevier BV
Date: 08-2021
Start Date: 08-2023
End Date: 08-2026
Amount: $329,278.00
Funder: Australian Research Council
View Funded Activity