 |
 |
 |
 |
 |
 |
Sains Malaysiana 54(7)(2025): 1785-1796
Meneroka Keberkesanan Diskriminan Fisher dalam Pengelasan
Morfologi Galaksi
(Exploring the
Viability of Fisher Discriminants in Galaxy Morphology Classification)
SAZATUL NADHILAH
ZAKARIA, SANTTOSH MUNIYANDY & JOHN Y.H. SOO*
School of
Physics, Universiti Sains Malaysia, 11800 USM, Pulau Pinang, Malaysia
Diserahkan: 17 Mac 2025/Diterima: 19 Mei 2025
Abstrak
Salah satu cabaran terbesar dalam astronomi
adalah pengelasan galaksi dengan tepat, terutamanya dalam membezakan antara
jenis galaksi yang berbeza. Terdapat pelbagai algoritma kompleks yang telah
menunjukkan prestasi tinggi dalam menjalankan tugas pengelasan, namun kerumitan
algoritma ini kebiasaannya mengambil masa pemprosesan yang lebih lama dan sukar
untuk difahami. Kajian kami menangani isu ini dengan meneroka keberkesanan diskriminan
Fisher, suatu algoritma yang jauh lebih mudah dalam menjalankan pengelasan
morfologi galaksi. Kami menguji empat algoritma pembelajaran mesin: diskriminan
Fisher, Rangkaian Neural Buatan (ANN), Pokok Keputusan Tergalak (BDT) dan k-jiran
terdekat (kNN) untuk mengelaskan galaksi berdasarkan bentuk bonjol
pusat. Dengan menggunakan data dari Tinjauan Langit Digital Sloan (SDSS), kami
menguji lima transformasi pemboleh ubah pra-pemprosesan: penormalan,
nyahkorelasi, analisis komponen utama (PCA), penyeragaman dan Gaussanisasi,
serta mengelaskan bentuk bonjol pusat galaksi kepada bentuk bulat atau tiada
bonjol, berdasarkan Pokok Keputusan Galaxy
Zoo. Apabila dibandingkan dengan label daripada Galaxy Zoo 2 (GZ2),
diskriminan Fisher dengan transformasi penyeragaman memperoleh skor kejituan
tertinggi iaitu 0.9310, melebihi ANN, BDT dan kNN masing-masing setinggi
1.93%, 0.42% dan 3.08%.
Kata kunci: Diskriminan Fisher; morfologi galaksi; pembelajaran mesin pengelasan
galaksi; rangkaian neural buatan
Abstract
One of the major
challenges in astronomy involves accurately classifying galaxies, particularly
distinguishing between different galaxy types. While many complex algorithms
have shown strong performance in classification tasks, their complexity often
results in longer processing times and increased difficulty in understanding.
This study addresses this issue by exploring the viability of Fisher
discriminants, a much simpler algorithm, in performing galaxy morphology
classification. We tested four machine learning algorithms: the Fisher
discriminant, Artificial Neural Networks (ANNs), Boosted Decision Trees (BDTs),
and k-Nearest Neighbours (kNNs) to classify galaxies by the shape
of their central bulges. Using data from the Sloan Digital Sky Survey (SDSS),
we utilised five pre-processing transformations: normalisation, decorrelation,
principal component analysis (PCA), uniformisation, and Gaussanisation, and
classified the shape of central bulge into either rounded or no-bulge, based on
the Galaxy Zoo Decision Tree. When compared to the Galaxy Zoo 2 (GZ2) labels,
the Fisher discriminant with uniformisation obtained the highest accuracy score
of 0.9310, outperforming ANN, BDT, and kNN by 1.93%, 0.42%, and 3.08%,
respectively.
Keywords: Artificial
Neural Networks; fisher discriminants; galaxy classification; galaxy morphology; machine learning
RUJUKAN
Almeida, A., Anderson, S.F., Argudo-Fernández, M.,
Badenes, C., Barger, K., Barrera-Ballesteros, J.K. et al. 2023. The eighteenth
data release of the sloan digital sky surveys: Targeting and first spectra from
SDSS-V. The Astrophysical Journal Supplement Series 267(2): 44.
Beck, M.R., Scarlata, C., Fortson, L.F., Lintott,
C.J., Simmons, B.D., Galloway, M.A., Willett, K.W., Dickinson, H., Masters,
K.L., Marshall, P.J. & Wright, D. 2018. Integrating human and machine
intelligence in galaxy morphology classification tasks. Monthly Notices of the
Royal Astronomical Society 476(4): 5516-5534.
Bertin, E. & Arnouts, S. 1996. SExtractor:
Software for source extraction. Astronomy and Astrophysics Supplement Series 117(2): 393-404.
Brun, R. & Rademakers, F. 1997. ROOT - An object
oriented data analysis framework. Nuclear
Instruments and Methods in Physics Research, Section A: Accelerators,
Spectrometers, Detectors and Associated Equipment 389(1): 81-86.
Burkert, A. & Naab, T. 2003. Major mergers and the
origin of elliptical galaxies. Dlm. Galaxies
and Chaos, Lecture Notes in Physics
626, disunting oleh Contopoulos, G. & Voglis, N. Springer,
Berlin, Heidelberg.
Buta, R.J. 2011. Galaxy morphology. arXiv preprint.
arXiv:1102.0550.
Chen, T. & Guestrin, C. 2016. XGBoost: A scalable
tree boosting system. 22nd ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining (KDD ‘16). hlm.
785-794.
Dey, A., Schlegel, D.J., Lang, D., Blum, R., Burleigh,
K., Fan, X., Findlay, J.R., Finkbeiner, D., Herrera, D., Juneau, S. et al.
2019. Overview of the DESI legacy imaging surveys. Astronomical Journal 157(5): 168.
De Diego, M.I., Redondo, A.R., Fernández, R.R.,
Navarro, J. & Moguerza, J.M. 2022. General performance score for
classification problems. Applied Intelligence 52: 12049-12063.
Dickinson, H., Fortson, L., Lintott, C., Scarlata, C.,
Willett, K., Bamford, S., Beck, M., Cardamone, C., Galloway, M., Simmons, B.,
Keel, W., Kruk, S., Masters, K., Vogelsberger, M., Torrey, P. & Snyder,
G.F. 2018. Galaxy zoo: Morphological classification of galaxy images from the
illustris simulation. The Astrophysical Journal 853(2): 194.
Doi, M., Tanaka, M., Fukugita, M., Gunn, J.E., Yasuda,
N., Ivezić, Ž., Brinkmann, J., de Haars, E., Kleinman, S.J., Krzesinski,
J. & Leger, R.F. 2010. Photometric response functions of the sloan digital
sky survey imager. The Astronomical Journal 139(4):
1628-1648.
Fisher, R.A. 1936. Annals
Eugenics 7: 179.
Fraix-Burnet, D. 2023. Machine learning and galaxy
morphology: For what purpose? Monthly
Notices of the Royal Astronomical Society 523(3): 3974-3990.
Fukugita, M., Ichikawa, T., Gunn, J.E., Doi, M.,
Shimasaku, K. & Schneider, D.P. 1996. The sloan digital sky survey
photometric system. Astronomical Journal 111(4): 1748.
Gunn, J.E., Siegmund, W.A., Mannery, E.J., Owen, R.E.,
Hull, C.L., French Leger, R., Carey, L.N., et al. 2006. The 2.5 m telescope of
the sloan digital sky survey. Astronomical Journal 131(4): 2332-2359.
Gunn, J.E., Carr, M., Rockosi, C., Sekiguchi, M.,
Berry, K., Elms, B., de Haas, E. et al. 1998. The sloan digital sky survey
photometric camera. Astronomical Journal 116(6): 3040-3081.
Hoecker, A.,
Speckmayer, P., Stelzer, J., Therhaag, J., von Toerne, E.,
Voss, H., Backes, M., Carli, T., Cohen, O.,
Christov, A., Dannheim, D., Danielowski, K.,
Henrot-Versille, S., Jachowski, M., Kraszewski, K.,
Krasznahorkay Jr. A., Kruk, M., Mahalalel, Y.,
Ospanov, R., Prudent, X., Robert, A., Schouten, D.,
Tegenfeldt, F., Voigt, A., Voss, K., Wolter, M. &
Zemla, A. 2007. TMVA-toolkit for multivariate data analysis. arXiv preprint physics/0703039.
Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D.,
Wang, W., Weyand, T., Andreetto, M. & Adam, H. 2017. MobileNets: Efficient convolutional
neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.
Huang, G., Liu, Z., Van Der Maaten, L. &
Weinberger K.Q. 2017. Densely connected convolutional networks. 2017
IEEE Conference on Computer Vision and Pattern Recognition (CVPR). hlm. 2261-2269.
Hubble, E.P. 1926. Extragalactic Nebulae. Astrophysical
Journal 64: 321-369.
Le, T.T., Fu, W. & Moore, J.H. 2020. Scaling tree-based
automated machine learning to biomedical big data with a feature set selector. Bioinformatics 36(1): 250-256.
Lintott, C.J., Schawinski, K., Slosar, A., Land, K.,
Bamford, S., Thomas, D., Raddick, M.J., Nichol, R.C., Szalay, A., Andreescu,
D., Murray, P. & Vandenberg, J. 2008. Galaxy zoo: Morphologies derived from
visual inspection of galaxies from the Sloan digital sky survey. Monthly
Notices of the Royal Astronomical Society 389(3): 1179-1189.
López-Sanjuan, C.,
Vázquez Ramió, H., Varela, J., Spinoso, D., Angulo, R.E., Muniesa, D.,
Viironen, K., , , , , , , , , , , , , , , , , , , , , , , , & 2019. J-PLUS: morphological star/galaxy classification
by PDF analysis. Astronomy and Astrophysics 622: A177.
Mahmud Pathi, I., Soo,
J.Y.H., Wee, M.J., Zakaria, S.N., Ismail, N.A., Baugh, C.M., Manzoni, G.,
Gaztanaga, E., Castander, F.J., Eriksen, M., Carretero, J.,
Fernandez, E., Garcia-Bellido, J., Miquel, R., Padilla, C.,
Renard, P., Sanchez, E., Sevilla-Noarbe, I. &
Tallada-Crespí, P. 2025. ANNz+: an enhanced photometric redshift
estimation algorithm with applications on the PAU survey. Journal of
Cosmology and Astroparticle Physics 2025: 097.
Paterson, K. 2017. MeerLICHT: MeerKAT’s Optical Eye. Proceedings
of the International Astronomical Union 14(S339): 203.
Raichoor, A., Comparat,
J., Delubac, T., Kneib, J.-P., Yèche, C., Zou, H., Abdalla, F.B., Dawson, K.,
de la Macorra, A., Fan, X., Fan, Z., Jiang, Z.,
Jing, Y., Jouvel, S., Lang, D., Lesser, M., Li, C.,
Ma, J., Newman, J.A., Nie, J., Palanque-Delabrouille, N.,
Percival, W.J., Prada, F., Shen, S., Wang, J., Wu, Z.,
Zhang, T., Zhou, X. & Zhou, Z. 2015. The SDSS-IV
extended Baryon Oscillation Spectroscopic Survey: Selecting emission line
galaxies using the Fisher discriminant. Astronomy
and Astrophysics 585: A50.
Reza, M. 2021. Galaxy morphology classification using
automated machine learning. Astronomy and Computing 37: 100492.
Sadeh, I., Abdalla, F.B. & Lahav, O. 2016. ANNZ2:
Photometric redshift and probability distribution function estimation using
machine learning. Astronomical Society of the Pacific 128(968): 104502.
Simmons, B.D., Lintott, C., Willett, K.W., Masters,
K.L., Kartaltepe, J.S., Häußler, B., Kaviraj, S. et al. 2016. Galaxy Zoo:
Quantitative Visual Morphological Classifications for 48,000 Galaxies from
CANDELS. Monthly Notices of the Royal Astronomical Society 464(4):
4420-4447.
Stoppa, F., Bhattacharyya, S., de Austri, R.,
Vreeswijk, P., Caron, S., Zaharijas, G., Bloemen, S., Principe, G., Malyshev,
D., Vodeb, V., Groot, P.J., Cator, E. & Nelemans, G. 2023.
AutoSourceID-Classifier: Star-galaxy classification using a convolutional
neural network with spatial information. Astronomy and Astrophysics 680: A109.
Stoughton, C., Lupton, R.H., Bernardi, M., Blanton,
M.R., Burles, S., Castander, F.J., Connolly, A.J., et al. 2002. Sloan Digital
Sky Survey: Early data release. The Astronomical Journal 123(1): 485-548.
Tan, M. & Le, Q.V. 2019. EfficientNet: Rethinking model
scaling for convolutional neural networks. Proceedings of the 36th International
Conference on Machine Learning. PMLR 97: 6105-6114.
Urechiatu, R. & Frincu, M. 2024. Improved galaxy
morphology classification with convolutional neural networks. Universe 10(6): 230.
Vavilova, I.B., Dobrycheva, D.V., Vasylenko, M.Y.,
Elyiv, A.A., Melnyk, O.V. & Khramtsov, V. 2021. Machine learning technique
for morphological classification of galaxies from the SDSS: I. Photometry-based
approach. Astronomy and Astrophysics 648: A122.
von Marttens, R.,
Marra, V., Quartin, M., Casarini, L., Baqui, P.O., Alvarez-Candal, A.,
Galindo-Guil, F.J., Fernández-Ontiveros, J.A., del Pino, A., Díaz-García, L.A., López-Sanjuan, C., Alcaniz, J., Angulo, R., Cenarro, A.J., Cristóbal-Hornillos, D., Dupke, R., Ederoclite, A., Hernández-Monteagudo, C., Marín-Franch, A., Moles, M., Sodré, L., Varela, J.
& Vázquez Ramió, H. 2023. J-PLUS: Galaxy-Star-Quasar classification for DR3. Monthly
Notices of the Royal Astronomical Society 527(2): 3347-3365.
Weglarczyk, S. 2018. Kernel density estimation and its
application. ITM web of conferences. EDP
Sciences 23: 00037.
Willett, K.W., Galloway, M.A., Bamford, S.P., Lintott,
C.J., Masters, K.L., Scarlata, C., Simmons, B.D., Beck, M., Cardamone, C.N.,
Cheung, E., Edmondson, E.M., Fortson, L.F., Griffith, R.L.,
Haeussler, B., Han, A., Hart, R., Melvin, T.,
Parrish, M., Schawinski, K., Smethurst, R.J. & Smith, A.M. 2016. Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in
HST Legacy Imaging. Monthly Notices of the Royal Astronomical
Society 464(4): 4176-4203.
Willett, K.W., Lintott,
C.J., Bamford, S.P., Masters, K.L., Simmons, B.D., Casteels, K.R.V., Edmondson,
E.M., Fortson, L.F., Kaviraj, S., Keel, W.C.,
Melvin, T., Nichol, R.C., Raddick, M.J.
Schawinski, K., Simpson, R.J., Skibba, R.A., Smith, A.M.
& Thomas, D. 2013. Galaxy zoo 2: Detailed morphological
classifications for 304 122 galaxies from the Sloan Digital Sky Survey. Monthly Notices of the Royal Astronomical
Society 435(4): 2835-2860.
Xie, Y., Byrd, R.H. & Nocedal, J. 2020. Analysis
of the BFGS method with errors. SIAM Journal on Optimization 30(1):
182-209.
York, D.G., Adelman, J., Anderson Jr., J.E., Anderson,
S.F., Annis, J., Bahcall, N.A., Bakken, J.A. et al. 2000. The Sloan Digital Sky
Survey: Technical summary. Astronomical Journal 120(3): 1579-1587.
Zhu, X-P., Dai, J-M., Bian, C-J., Chen, Y., Chen, S.
& Hu, C. 2019. Galaxy morphology classification with deep convolutional
neural networks. Astrophysics and Space Science 364(4): 55.
*Pengarang untuk surat-menyurat; email: johnsooyh@usm.my
|
|||
|
