X. Rosalind Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
X. Rosalind Wang has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
- Mikhail Prokopenko
The University of Sydney
11 shared publications - Joseph T. Lizier
The University of Sydney
8 shared publications - Oliver Obst
University of New South Wales (UNSW)
8 shared publications - Amalia Z. Berna
Department of Pediatrics, Children’s Hospital of Philadelphia
4 shared publications - Raymond P. Norris
Australia Telescope National Facility, CSIRO
4 shared publications - Florence G. Bravo
CSIRO Health and Biosecurity, Clunies-Ross Street, Acton ACT 2601, Australia
3 shared publications
Latest Publications
- Open Access
- 21 October 2025
- Published by IOS Press
- p. 1229-1236
Do Explanations Expose Bias? How Saliency Maps Affect Judgements of Biased Face-Recognition Models
Saliency-map explanations are intended to make computer-vision models more transparent, but it is unclear whether they help people recognise biased behaviour. We conducted a controlled on-line study with 40 participants who compared Layer-wise Relevance Propagation maps from convolutional face-recognition models. A fair model was trained on a balanced synthetic dataset; two biased models were trained on data in which either light- or dark-skinned faces appeared only in frontal pose. Each participant completed 32 comparison trials. When the fair model was paired with the dark-skinned-pose-biased model, selections were near chance (52.8% favouring the fair model, binomial p = .36). When the fair model was paired with the light-skinned-pose-biased model, participants chose the biased model significantly more often (58.1%, p = .005). Confidence ratings varied with condition and did not systematically track model fairness. These results indicate that pixel-level attribution alone does not reliably expose training bias and can, in some settings, mislead non-expert users.
- 21 October 2025
- Published by IOS Press
- p. 1229-1236
Open AccessDo Explanations Expose Bias? How Saliency Maps Affect Judgements of Biased Face-Recognition Models
Saliency-map explanations are intended to make computer-vision models more transparent, but it is unclear whether they help people recognise biased behaviour. We conducted a controlled on-line study with 40 participants who compared Layer-wise Relevance Propagation maps from convolutional face-recognition models. A fair model was trained on a balanced synthetic dataset; two biased models were trained on data in which either light- or dark-skinned faces appeared only in frontal pose. Each participant completed 32 comparison trials. When the fair model was paired with the dark-skinned-pose-biased model, selections were near chance (52.8% favouring the fair model, binomial p = .36). When the fair model was paired with the light-skinned-pose-biased model, participants chose the biased model significantly more often (58.1%, p = .005). Confidence ratings varied with condition and did not systematically track model fairness. These results indicate that pixel-level attribution alone does not reliably expose training bias and can, in some settings, mislead non-expert users.
- 19 October 2025
- Published by Springer Nature
- p. 209-216
Classification of Kinetic-Related Injury in Hospital Triage Data Using NLP
- 19 October 2025
- Published by Springer Nature
- p. 209-216
Classification of Kinetic-Related Injury in Hospital Triage Data Using NLP
- Open Access
- 26 June 2025
- Published by Cambridge University Press (CUP) in Publications of the Astronomical Society of Australia
- Vol. 42, 1-19
Discovery of odd radio circles and other peculiars in the first year of the EMU survey using object detection
We present a systematic search for Odd Radio Circles (ORCs) and other unusual radio morphologies using data from the first year of the Evolutionary Map of the Universe (EMU) survey. ORCs are rare, enigmatic objects characterised by edge-brightened rings of radio emission, often found in association with distant galaxies. To identify these objects, we employ a hybrid methodology combining supervised object detection techniques and visual inspection of radio source candidates. This approach leads to the discovery of five new ORCs and two additional candidate ORCs, expanding the known population of these objects. In addition to ORCs, we also identify 55 Galaxies with Large-scale Ambient Radio Emission (GLAREs), which feature irregular, rectangular, or circular shapes of diffuse radio emission mostly surrounding central host galaxies. These GLAREs may represent different evolutionary stages of ORCs and studying them could offer valuable insights into their evolutionary processes. We also highlight a subset of Starburst Radio Ring Galaxies, which are star-forming galaxies exhibiting edge-brightened radio rings surrounding their central star-forming regions. We emphasise the importance of multi-wavelength follow-up observations to better understand the physical properties, host galaxy characteristics, and evolutionary pathways of these radio sources.
- 26 June 2025
- Published by Cambridge University Press (CUP) in Publications of the Astronomical Society of Australia
- Vol. 42, 1-19
Open AccessDiscovery of odd radio circles and other peculiars in the first year of the EMU survey using object detection
We present a systematic search for Odd Radio Circles (ORCs) and other unusual radio morphologies using data from the first year of the Evolutionary Map of the Universe (EMU) survey. ORCs are rare, enigmatic objects characterised by edge-brightened rings of radio emission, often found in association with distant galaxies. To identify these objects, we employ a hybrid methodology combining supervised object detection techniques and visual inspection of radio source candidates. This approach leads to the discovery of five new ORCs and two additional candidate ORCs, expanding the known population of these objects. In addition to ORCs, we also identify 55 Galaxies with Large-scale Ambient Radio Emission (GLAREs), which feature irregular, rectangular, or circular shapes of diffuse radio emission mostly surrounding central host galaxies. These GLAREs may represent different evolutionary stages of ORCs and studying them could offer valuable insights into their evolutionary processes. We also highlight a subset of Starburst Radio Ring Galaxies, which are star-forming galaxies exhibiting edge-brightened radio rings surrounding their central star-forming regions. We emphasise the importance of multi-wavelength follow-up observations to better understand the physical properties, host galaxy characteristics, and evolutionary pathways of these radio sources.
- 17 June 2024
- Published by Oxford University Press (OUP) in The Journal of Infectious Diseases
- Vol. 230 (4) , 1013-1022
Breath Biomarkers of Pediatric Malaria: Reproducibility and Response to Antimalarial Therapy
Many insect-borne pathogens appear to manipulate the odors of their hosts in ways that influence vector behaviors. In our prior work, we identified characteristic changes in volatile emissions of cultured Plasmodium falciparum parasites in vitro and during natural human falciparum malaria. In the current study, we prospectively evaluate the reproducibility of these findings in an independent cohort of children in Blantyre, Malawi. We enrolled febrile children under evaluation for malaria and collected breath from children with and without malaria, as well as healthy controls. Using gas-chromatography/mass spectrometry, we characterized breath volatiles associated with malaria. By repeated sampling of children with malaria before and after antimalarial use, we determined how breath profiles respond to treatment. In addition, we investigated the stage-specificity of biomarkers through correlation with asexual and sexual stage parasitemia. Our data provide robust evidence that P. falciparum infection leads to specific, reproducible changes in breath compounds. While no individual compound served as adequate classifier in isolation, selected volatiles together yielded high sensitivity for diagnosis of malaria. Overall, the results of our predictive models suggest the presence of volatile signatures that reproducibly predict malaria infection status and determine response to therapy, even in cases of low parasitemia.
- 17 June 2024
- Published by Oxford University Press (OUP) in The Journal of Infectious Diseases
- Vol. 230 (4) , 1013-1022
Breath Biomarkers of Pediatric Malaria: Reproducibility and Response to Antimalarial Therapy
Many insect-borne pathogens appear to manipulate the odors of their hosts in ways that influence vector behaviors. In our prior work, we identified characteristic changes in volatile emissions of cultured Plasmodium falciparum parasites in vitro and during natural human falciparum malaria. In the current study, we prospectively evaluate the reproducibility of these findings in an independent cohort of children in Blantyre, Malawi. We enrolled febrile children under evaluation for malaria and collected breath from children with and without malaria, as well as healthy controls. Using gas-chromatography/mass spectrometry, we characterized breath volatiles associated with malaria. By repeated sampling of children with malaria before and after antimalarial use, we determined how breath profiles respond to treatment. In addition, we investigated the stage-specificity of biomarkers through correlation with asexual and sexual stage parasitemia. Our data provide robust evidence that P. falciparum infection leads to specific, reproducible changes in breath compounds. While no individual compound served as adequate classifier in isolation, selected volatiles together yielded high sensitivity for diagnosis of malaria. Overall, the results of our predictive models suggest the presence of volatile signatures that reproducibly predict malaria infection status and determine response to therapy, even in cases of low parasitemia.
- Open Access
- 19 July 2023
- Published by Cambridge University Press (CUP) in Publications of the Astronomical Society of Australia
- Vol. 40, 1-29
Measuring photometric redshifts for high-redshift radio source surveys
With the advent of deep, all-sky radio surveys, the need for ancillary data to make the most of the new, high-quality radio data from surveys like the Evolutionary Map of the Universe (EMU), GaLactic and Extragalactic All-sky MurchisonWidefield Array survey eXtended, Very Large Array Sky Survey and LOFAR Two-metre Sky Survey is growing rapidly. Radio surveys produce significant numbers of Active Galactic Nuclei (AGNs), and have a significantly higher average redshift when compared with optical and infrared all-sky surveys. Thus, traditional methods of estimating redshift are challenged, with spectroscopic surveys not reaching the redshift depth of radio surveys, and AGNs making it difficult for template fitting methods to accurately model the source. Machine Learning (ML) methods have been used, but efforts have typically been directed towards optically selected samples, or samples at significantly lower redshift than expected from upcoming radio surveys. This work compiles and homogenises a radio-selected dataset from both the northern hemisphere (making use of Sloan Digital Sky Survey optical photometry), and southern hemisphere (making use of Dark Energy Survey optical photometry). We then test commonly used ML algorithms such as k-Nearest Neighbours (kNN), Random Forest, ANNz and GPz on this monolithic radio-selected sample. We show that kNN has the lowest percentage of catastrophic outliers, providing the best match for the majority of science cases in the EMU survey. We note that the wider redshift range of the combined dataset used allows for estimation of sources up to z = 3 before random scatter begins to dominate. When binning the data into redshift bins and treating the problem as a classification problem, we are able to correctly identify ≈76% of the highest redshift sources — sources at redshift z > 2.51 — as being in either the highest bin (z > 2.51), or second highest (z = 2.25).
- 19 July 2023
- Published by Cambridge University Press (CUP) in Publications of the Astronomical Society of Australia
- Vol. 40, 1-29
Open AccessMeasuring photometric redshifts for high-redshift radio source surveys
With the advent of deep, all-sky radio surveys, the need for ancillary data to make the most of the new, high-quality radio data from surveys like the Evolutionary Map of the Universe (EMU), GaLactic and Extragalactic All-sky MurchisonWidefield Array survey eXtended, Very Large Array Sky Survey and LOFAR Two-metre Sky Survey is growing rapidly. Radio surveys produce significant numbers of Active Galactic Nuclei (AGNs), and have a significantly higher average redshift when compared with optical and infrared all-sky surveys. Thus, traditional methods of estimating redshift are challenged, with spectroscopic surveys not reaching the redshift depth of radio surveys, and AGNs making it difficult for template fitting methods to accurately model the source. Machine Learning (ML) methods have been used, but efforts have typically been directed towards optically selected samples, or samples at significantly lower redshift than expected from upcoming radio surveys. This work compiles and homogenises a radio-selected dataset from both the northern hemisphere (making use of Sloan Digital Sky Survey optical photometry), and southern hemisphere (making use of Dark Energy Survey optical photometry). We then test commonly used ML algorithms such as k-Nearest Neighbours (kNN), Random Forest, ANNz and GPz on this monolithic radio-selected sample. We show that kNN has the lowest percentage of catastrophic outliers, providing the best match for the majority of science cases in the EMU survey. We note that the wider redshift range of the combined dataset used allows for estimation of sources up to z = 3 before random scatter begins to dominate. When binning the data into redshift bins and treating the problem as a classification problem, we are able to correctly identify ≈76% of the highest redshift sources — sources at redshift z > 2.51 — as being in either the highest bin (z > 2.51), or second highest (z = 2.25).
- 17 February 2022
- Published by Elsevier in Astronomy and Computing
- Vol. 39, 100557
Estimating galaxy redshift in radio-selected datasets using machine learning
- 17 February 2022
- Published by Elsevier in Astronomy and Computing
- Vol. 39, 100557
Estimating galaxy redshift in radio-selected datasets using machine learning
- 9 December 2021
- Published by Springer Nature
- p. 121-135
Chameleon: A Python Workflow Toolkit for Feature Selection
- 9 December 2021
- Published by Springer Nature
- p. 121-135
Chameleon: A Python Workflow Toolkit for Feature Selection
- 2 July 2020
- Published by Oxford University Press (OUP) in Monthly Notices of the Royal Astronomical Society
- Vol. 497 (3) , 2730-2758
Cataloguing the radio-sky with unsupervised machine learning: a new approach for the SKA era
We develop a new analysis approach towards identifying related radio components and their corresponding infrared host galaxy based on unsupervised machine learning methods. By exploiting PINK, a self-organising map algorithm, we are able to associate radio and infrared sources without the a priori requirement of training labels. We present an example of this method using 894,415 images from the FIRST and WISE surveys centred towards positions described by the FIRST catalogue. We produce a set of catalogues that complement FIRST and describe 802,646 objects, including their radio components and their corresponding AllWISE infrared host galaxy. Using these data products we (i) demonstrate the ability to identify objects with rare and unique radio morphologies (e.g. ‘X’-shaped galaxies, hybrid FR-I/FR-II morphologies), (ii) can identify the potentially resolved radio components that are associated with a single infrared host and (iii) introduce a “curliness” statistic to search for bent and disturbed radio morphologies, and (iv) extract a set of 17 giant radio galaxies between 700 − 1100 kpc. As we require no training labels, our method can be applied to any radio-continuum survey, provided a sufficiently representative SOM can be trained.
- 2 July 2020
- Published by Oxford University Press (OUP) in Monthly Notices of the Royal Astronomical Society
- Vol. 497 (3) , 2730-2758
Cataloguing the radio-sky with unsupervised machine learning: a new approach for the SKA era
We develop a new analysis approach towards identifying related radio components and their corresponding infrared host galaxy based on unsupervised machine learning methods. By exploiting PINK, a self-organising map algorithm, we are able to associate radio and infrared sources without the a priori requirement of training labels. We present an example of this method using 894,415 images from the FIRST and WISE surveys centred towards positions described by the FIRST catalogue. We produce a set of catalogues that complement FIRST and describe 802,646 objects, including their radio components and their corresponding AllWISE infrared host galaxy. Using these data products we (i) demonstrate the ability to identify objects with rare and unique radio morphologies (e.g. ‘X’-shaped galaxies, hybrid FR-I/FR-II morphologies), (ii) can identify the potentially resolved radio components that are associated with a single infrared host and (iii) introduce a “curliness” statistic to search for bent and disturbed radio morphologies, and (iv) extract a set of 17 giant radio galaxies between 700 − 1100 kpc. As we require no training labels, our method can be applied to any radio-continuum survey, provided a sufficiently representative SOM can be trained.
- Open Access
Projected ICU and Mortuary load due to COVID-19 in Sydney
The spread of COVID-19 is expected to put a large strain on many hospital resources, including ICU bed space, and mortuary capacity. In this report we study the possible demands on ICU and mortuary capacity in Sydney, Australia, using an adapted SEIR epidemiological model.
Open AccessProjected ICU and Mortuary load due to COVID-19 in Sydney
The spread of COVID-19 is expected to put a large strain on many hospital resources, including ICU bed space, and mortuary capacity. In this report we study the possible demands on ICU and mortuary capacity in Sydney, Australia, using an adapted SEIR epidemiological model.
- 1 October 2019
- Published by Elsevier in Journal of Chromatography A
- Vol. 1604, 460476
Peak alignment of gas chromatography–mass spectrometry data with deep learning
- 1 October 2019
- Published by Elsevier in Journal of Chromatography A
- Vol. 1604, 460476
Peak alignment of gas chromatography–mass spectrometry data with deep learning