Photometric redshift-aided classification using ensemble learning

Cunha, P. A. C.; Humphrey, A.

doi:10.1051/0004-6361/202243135

Cited by 19 publications

(10 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison to similar studies, our classification approach demonstrates better performance. Cunha & Humphrey (2022) obtained an average F1 98.13 per cent using XGBoost, LightGBM, and CatBoost classifiers and Chaini et al (2022) used a combination of photometric information and images from SDSS to achieve the best averaged F1-score of 93.3 per cent through the use of artificial neural networks (ANN) and conventional neural networks (CNN).…”

Section: Discussionmentioning

confidence: 99%

“…A majority of the literature on these two surveys in the case of photometric classification using machine learning, beginning from Suchkov et al (2005), have focused on broad classifications or specific subtypes of astronomical objects. For instance, some studies have examined separating stars from galaxies (Ball et al 2006;Vasconcellos et al 2011;Kovacs & Szapudi 2015), distinguishing star/galaxy/QSO (Krakowski et al 2016;Kurcz et al 2016;Nakoneczny et al 2019Nakoneczny et al , 2021Clarke et al 2020;Cunha & Humphrey 2022;Chaini et al 2022), examining ELGs (AGN/non-AGN, Seyfert I/Sefert II) (Cavuoti et al 2014), as well as classifying AGNs (X-ray AGNs, IRAGNs, radio-selected AGNs) (Chang et al 2021). Despite significant progress in the field, a gap remains in the literature regarding the detailed classification of all astronomical objects using solely photometric data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning-based photometric classification of galaxies, quasars, emission-line galaxies, and stars

Zeraatgari,

Hafezianzadeh,

Zhang

et al. 2023

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

This paper explores the application of machine learning methods for classifying astronomical sources using photometric data, including normal and emission line galaxies (ELGs; starforming, starburst, AGN, broad line), quasars, and stars. We utilized samples from Sloan Digital Sky Survey (SDSS) Data Release 17 (DR17) and the ALLWISE catalog, which contain spectroscopically labeled sources from SDSS. Our methodology comprises two parts. First, we conducted experiments, including three-class, four-class, and seven-class classifications, employing the Random Forest (RF) algorithm. This phase aimed to achieve optimal performance with balanced datasets. In the second part, we trained various machine learning methods, such as k-nearest neighbors (KNN), RF, XGBoost (XGB), voting, and artificial neural network (ANN), using all available data based on promising results from the first phase. Our results highlight the effectiveness of combining optical and infrared features, yielding the best performance across all classifiers. Specifically, in the three-class experiment, RF and XGB algorithms achieved identical average F1 scores of 98.93 per cent on both balanced and unbalanced datasets. In the seven-class experiment, our average F1 score was 73.57 per cent. Using the XGB method in the four-class experiment, we achieved F1 scores of 87.9 per cent for normal galaxies (NGs), 81.5 per cent for ELGs, 99.1 per cent for stars, and 98.5 per cent for quasars (QSOs). Unlike classical methods based on time-consuming spectroscopy, our experiments demonstrate the feasibility of using automated algorithms on carefully classified photometric data. With more data and ample training samples, detailed photometric classification becomes possible, aiding in the selection of follow-up observation candidates.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning-based photometric classification of galaxies, quasars, emission-line galaxies, and stars

Zeraatgari,

Hafezianzadeh,

Zhang

et al. 2023

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

show abstract

“…This workflow has potential far beyond neuropathology. Indeed we believe it can provide utility in the various pathology subfields, such as cancer and nephrology, and even fields as far flung as Astronomy, which similarly processes exceptionally large and complex imaging data [ 67 , 68 ]. Though even just within neuropathology, this work is likely only the beginning, and we hope the dataset generated and discussed herein, which has been made public, will be the foundation from which many workflows may be created.…”

Section: Discussionmentioning

confidence: 99%

Toward a generalizable machine learning workflow for neurodegenerative disease staging with focus on neurofibrillary tangles

Vizcarra,

Pearce,

Dugger

et al. 2023

acta neuropathol commun

View full text Add to dashboard Cite

Machine learning (ML) has increasingly been used to assist and expand current practices in neuropathology. However, generating large imaging datasets with quality labels is challenging in fields which demand high levels of expertise. Further complicating matters is the often seen disagreement between experts in neuropathology-related tasks, both at the case level and at a more granular level. Neurofibrillary tangles (NFTs) are a hallmark pathological feature of Alzheimer disease, and are associated with disease progression which warrants further investigation and granular quantification at a scale not currently accessible in routine human assessment. In this work, we first provide a baseline of annotator/rater agreement for the tasks of Braak NFT staging between experts and NFT detection using both experts and novices in neuropathology. We use a whole-slide-image (WSI) cohort of neuropathology cases from Emory University Hospital immunohistochemically stained for Tau. We develop a workflow for gathering annotations of the early stage formation of NFTs (Pre-NFTs) and mature intracellular (iNFTs) and show ML models can be trained to learn annotator nuances for the task of NFT detection in WSIs. We utilize a model-assisted-labeling approach and demonstrate ML models can be used to aid in labeling large datasets efficiently. We also show these models can be used to extract case-level features, which predict Braak NFT stages comparable to expert human raters, and do so at scale. This study provides a generalizable workflow for various pathology and related fields, and also provides a technique for accomplishing a high-level neuropathology task with limited human annotations.

show abstract

“…Some typical methods are Polynomial Function Fitting (Connolly et al, 1995), Bayesian model (Benítez, 2000), Support Vector Machine (Wadadekar, 2005), K-Nearest Neighbor (Beck et al, 2016), Kernel Regression (Wang et al, 2008), Random Forest (Carrasco and Brunner, 2013), Active Learning (Han et al, 2015), Artificial Neural Network (Firth et al, 2003) and so on. The latest methods are Ensemble Learning (Cunha and Humphrey, 2022), Deep Capsule Network (Dey et al, 2022) and so on.…”

Section: Machine Learningmentioning

confidence: 99%

Measurement methods for gamma-ray bursts redshifts

Kang

et al. 2023

Front. Astron. Space Sci.

View full text Add to dashboard Cite

In the era of multi-messenger astronomy, gamma-ray bursts (GRBs) with known redshifts, especially high-redshift GRBs, are a powerful tool for studying the structure and evolution of the early Universe. We review the background, the history, and the application of measurement methods of GRB redshifts in astronomy. Based on different observation targets, two measurement methods are mainly introduced. One is on GRB afterglow, the other is on GRB host galaxy. There are various processing methods belonging to measurement methods based on afterglow, including spectral measurement method of afterglow and afterglow spectral energy distribution fitting method with improved methods. There are also numerous measurement methods based on host galaxy, such as spectral measurement method of host galaxy, template matching method of host galaxy, some automatic spectroscopic redshift measurement methods, and machine learning methods. We subsequently introduce the principles, effects, and performance of these methods. We enumerate several detection and measurement instruments, which have been used in observation. The characteristics, advantages, disadvantages, and applicability of the GRB redshift measurement methods are summarized and analyzed. Furthermore, we provide a data set of 611 GRBs with measured redshift. The data set has been collected since 1997. Analysis and statistics are presented based on this data set. We summarize the characteristics of GRBs such as location, time, and accuracy. Finally, we introduce Space-based multi-band astronomical Variable Objects Monitor (SVOM) mission dedicated to searching high redshift GRBs. We also introduce the application prospect of various redshift measurement methods in SVOM mission.

show abstract

Photometric redshift-aided classification using ensemble learning

Cited by 19 publications

References 51 publications

Machine learning-based photometric classification of galaxies, quasars, emission-line galaxies, and stars

Machine learning-based photometric classification of galaxies, quasars, emission-line galaxies, and stars

Toward a generalizable machine learning workflow for neurodegenerative disease staging with focus on neurofibrillary tangles

Measurement methods for gamma-ray bursts redshifts

Contact Info

Product

Resources

About