Makine öğrenmesi algoritmalarıyla astronomik gözlem kalitesi tahminine yönelik karar destek sistemi geliştirilmesi ve uygulanması

Yıl 2022, Cilt: 36 Sayı: 3, 289 - 303, 15.07.2022

Ömer Çağrı Yavuz , Ersin Karaman , Cahit Yeşilyaprak

Öz

Kurulumunun tamamlanmasıyla birlikte araştırmacıların kullanımına sunulması planlanan Doğu Anadolu Gözlemevi (DAG) teleskobunun etkin ve verimli kullanımı önem arz etmektedir. Bu çalışma kapsamında araştırmacılar tarafından sunulan projelerin, gözlemevinin bulunduğu bölgenin yerel özellikleri dikkate alınarak gözlem türüyle eşleştirilmesi, değerlendirilmesi ve en uygun güne atanmasına yönelik karar destek sistemi geliştirilmesi amaçlanmaktadır. Bu amaç doğrultusunda öncelikle Naive Bayes, K En Yakın Komşu, Karar Ağacı ve Rastgele Orman algoritması kullanılarak dört farklı algoritmanın performansları değerlendirilmiş, yeniden örnekleme yöntemleri uygulanmış ve öz niteliklerin sonuca etkisi incelenmiştir. Sonrasında MAUT yönteminden esinlenilerek her bir proje için yarar fonksiyonu formülünü barındıran fayda değerlerinin hesaplanmasına dayalı karar destek modeli geliştirilmiştir. Fayda değerleri projeler için başarı puanını temsil etmektedir. Projeler, gözlem türüne göre sınıflandırılarak başarı puanına göre büyükten küçüğe sıralanmıştır. Sonrasında önceden tahmin edilen gözlem türleri doğrultusunda projeler önceliklendirilerek ilgili günlere atanmıştır. Geliştirilen karar destek modeli ile teleskobun etkin ve verimli kullanımıyla birlikte değerlendirme sürecinin otomatikleştirilmesi amaçlanmaktadır.

Anahtar Kelimeler

Astronomik gözlem kalitesi, Doğu Anadolu Gözlemevi, tahmin, karar destek sistemleri, makine öğrenmesi

Developing and implementing a decision support system for astronomical observation quality estimation with machine learning algorithms

Öz

Anahtar Kelimeler

Astronomival observation quality, decision support systems, Eastern Anatolia Observatory, estimation, machine learning

Kaynakça

• Agarwal, M., Rao, K. K., Vaidya, K., & Bhattacharya, S. (2021). ML-MOC: Machine Learning (kNN and GMM) based Membership determination for Open Clusters. Monthly Notices of the Royal Astronomical Society, 502(2), 2582-2599.
• Agarwal, M., Rao, K. K., Vaidya, K., & Bhattacharya, S. (2021). ML-MOC: Machine Learning (kNN and GMM) based Membership determination for Open Clusters. Monthly Notices of the Royal Astronomical Society, 502(2), 2582-2599.
• Ahmadzadeh, A., Aydin, B., Georgoulis, M. K., Kempton, D. J., Mahajan, S. S., & Angryk, R. A. (2021). How to Train Your Flare Prediction Model: Revisiting Robust Sampling of Rare Events. The Astrophysical Journal Supplement Series, 254(2), 23.
• Albayrak, A. S., & Yilmaz, S. K. (2009). Veri Madenciliği: Karar Ağacı Algoritmaları Ve İmkb Verileri Üzerine Bir Uygulama. Süleyman Demirel University Journal of Faculty of Economics & Administrative Sciences, 14(1), 31-52.
• Alinezhad, A., & Khalili, J. (2019). New methods and applications in multiple attribute decision making (MADM) (Vol. 277). Cham: Springer.
• Arsioli, B., & Dedin, P. (2020). Machine learning applied to multifrequency data in astrophysics: blazar classification. Monthly Notices of the Royal Astronomical Society, 498(2), 1750-1764.
• Ballica, Y. (2020). Savunma Sanayi Projelerinin Analitik Hiyerarşi Süreci Yöntemi Kullanilarak Önceliklendirilmesi. Yüksek Lisans Tezi. Sosyal Bilimler Enstitüsü, Hacettepe Üniversitesi.
• Barchi, P. H., da Costa, F. G., Sautter, R., Moura, T. C., Stalder, D. H., Rosa, R. R., & de Carvalho, R. R. (2017). Improving galaxy morphology with machine learning. arXiv preprint arXiv:1705.06818.
• Beitia-Antero, L., Yáñez, J., & de Castro, A. I. G. (2018). On the use of logistic regression for stellar classification. Experimental Astronomy, 45(3), 379-395.
• Bellinger, E. P., Angelou, G. C., Hekker, S., Basu, S., Ball, W. H., & Guggenberger, E. (2016). Fundamental parameters of main-sequence stars in an instant with machine learning. The Astrophysical Journal, 830(1), 31.
• Bellinger, E. P., Kanbur, S. M., Bhardwaj, A., & Marconi, M. (2020). When a period is not a full stop: Light-curve structure reveals fundamental parameters of Cepheid and RR Lyrae stars. Monthly Notices of the Royal Astronomical Society, 491(4), 4752-4767.
• Bluck, A. F., Maiolino, R., Sánchez, S. F., Ellison, S. L., Thorp, M. D., Piotrowska, J. M., ... & Bundy, K. A. (2020). Are galactic star formation and quenching governed by local, global, or environmental phenomena?. Monthly Notices of the Royal Astronomical Society, 492(1), 96-139.
• Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
• Breton, S. N., Bugnet, L., Santos, A. R. G., Saux, A. L., Mathur, S., Palle, P. L., & Garcia, R. A. (2019). Determining surface rotation periods of solar-like stars observed by the Kepler mission using machine learning techniques. arXiv preprint arXiv:1906.09609.
• Broos, P. S., Getman, K. V., Povich, M. S., Townsley, L. K., Feigelson, E. D., & Garmire, G. P. (2011). A naive Bayes source classifier for X-ray sources. The Astrophysical Journal Supplement Series, 194(1), 4.
• Chan, M. C., & Stott, J. P. (2021). Z-Sequence: photometric redshift predictions for galaxy clusters with sequential random k-nearest neighbours. Monthly Notices of the Royal Astronomical Society, 503(4), 6078-6097.
• Chastenay, P., & Riopel, M. (2019). A Logistic Regression Model Comparing Astronomy and Non-Astronomy Teachers in Québec's Elementary Schools. Journal of Astronomy & Earth Sciences Education, 6(1), 1-16.
• Cheng, Q. B., Feng, C. J., Zhai, X. H., & Li, X. Z. (2021). Artificial neural network spectral light curve template for type Ia supernovae and its cosmological constraints. Modern Physics Letters A, 36(21), 2150149.
• Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27.
• Curran, S. J., Moss, J. P., & Perrott, Y. C. (2021). QSO photometric redshifts using machine learning and neural networks. Monthly Notices of the Royal Astronomical Society, 503(2), 2639-2650.
• Daşdemir, İ.(2012). Orman mühendisliği için planlama ve proje değerlendirme. Bartın Üniversitesi.
• Dillon, J. L., & Perry, C. (1977). Multiattribute utility theory, multiple objectives and uncertainty in ex ante project evaluation. Review of Marketing and Agricultural Economics, 45(430-2016-30709), 3-27.
• Du Buisson, L., Sivanandam, N., Bassett, B. A., & Smith, M. (2015). Machine learning classification of SDSS transient survey images. Monthly Notices of the Royal Astronomical Society, 454(2), 2026-2038.
• Elyiv, A. A., Melnyk, O. V., Vavilova, I. B., Dobrycheva, D. V., & Karachentseva, V. E. (2020). Machine-learning computation of distance modulus for local galaxies. Astronomy & Astrophysics, 635, A124.
• Ercire M. (2019). Kısa Süreli Güç Kalitesi Bozulmalarının Dalgacık Analizi ve Rastgele Orman Yöntemi ile Sınıflandırılması. Yüksek Lisans Tezi. Fen Bilimleri Enstitüsü, Kütahya Dumlupınar Üniversitesi, Türkiye.
• Gao, X. H. (2016). An application of the k-th nearest neighbor method to open cluster membership determination. Research in Astronomy and Astrophysics, 16(12), 184.
• Garton, T. M., Jackman, C. M., Smith, A. W., Yeakel, K. L., Maloney, S. A., & Vandegriff, J. (2021). Machine Learning Applications to Kronian Magnetospheric Reconnection Classification. arXiv preprint arXiv:2104.00496.
• Golob, A., Sawicki, M., Goulding, A. D., & Coupon, J. (2021). Classifying stars, galaxies, and AGNs in CLAUDS+ HSC-SSP using gradient boosted decision trees. Monthly Notices of the Royal Astronomical Society, 503(3), 4136-4146.
• Goy G, Gezer C, Gungor VC. (2019). Credit Card Fraud Detection with Machine Learning Methods. In 2019 4th International Conference on Computer Science and Engineering (UBMK), 350-354. IEEE.
• Hamurcu, M., & Eren, T. (2018). Kamu kurumunda bulanık TOPSIS yaklaşımı ile proje seçimi için bir grup karar verme uygulaması. Transist 11. Uluslararası Ulaşım Teknolojileri Sempozyumu ve Fuarı, 11-20.
• Hartley, P., Flamary, R., Jackson, N., Tagore, A. S., & Metcalf, R. B. (2017). Support vector machine classification of strong gravitational lenses. Monthly Notices of the Royal Astronomical Society, 471(3), 3378-3397.
• Huang, C., Ma, Y. H., Zhao, H. B., & Lu, X. P. (2016). Spectral Classification of Asteroids by Random Forest. Acta Astronomica Sinica, 57(5), 526-533.
• Huang, C., Ma, Y. H., Zhao, H. B., & Lu, X. P. (2016). Spectral Classification of Asteroids by Random Forest. Acta Astronomica Sinica, 57(5), 526-533.
• Jin-Meng, Y., & Xiao-Qing, W. (2021). The regression of effective temperatures in APOGEE and LAMOST. New Astronomy, 86, 101568.
• Korsós, M. B., Erdélyi, R., Liu, J., & Morgan, H. (2021). Testing and Validating Two Morphological Flare Predictors by Logistic Regression Machine Learning. Frontiers in Astronomy and Space Sciences, 7, 113.
• Kumar, S. S. (2004). AHP-based formal system for R&D project evaluation. Journal of Scientific and Industrial Research (JSIR), 63(11), 888-896.
• Kügler, S. D., Polsterer, K., & Hoecker, M. (2015). Determining spectroscopic redshifts by using k nearest neighbor regression-I. Description of method and analysis. Astronomy & Astrophysics, 576, A132.
• Liu, C., Deng, N., Wang, J. T., & Wang, H. (2017). Predicting solar flares using SDO/HMI vector magnetic data products and the random forest algorithm. The Astrophysical Journal, 843(2), 104.
• Lochner, M., McEwen, J. D., Peiris, H. V., Lahav, O., & Winter, M. K. (2016). Photometric supernova classification with machine learning. The Astrophysical Journal Supplement Series, 225(2), 31.
• Lochner, M., McEwen, J. D., Peiris, H. V., Lahav, O., & Winter, M. K. (2016). Photometric supernova classification with machine learning. The Astrophysical Journal Supplement Series, 225(2), 31.
• Lopes, Y. G., & de Almeida, A. T. (2015). Assessment of synergies for selecting a project portfolio in the petroleum industry based on a multi-attribute utility function. Journal of Petroleum Science and Engineering, 126, 131-140.
• Luken, K. J., Norris, R. P., & Park, L. A. (2019). Preliminary Results of Using k-nearest-neighbor Regression to Estimate the Redshift of Radio-selected Data Sets. Publications of the Astronomical Society of the Pacific, 131(1004), 108003.
• Marton, G., Tóth, L. V., Paladini, R., Kun, M., Zahorecz, S., McGehee, P., & Kiss, C. (2016). An all-sky support vector machine selection of WISE YSO candidates. Monthly Notices of the Royal Astronomical Society, 458(4), 3479-3488.
• Mucesh, S., Hartley, W. G., Palmese, A., Lahav, O., Whiteway, L., Bluck, A. F. L., ... & (DES Collaboration). (2021). A machine learning approach to galaxy properties: joint redshift–stellar mass probability distributions with Random Forest. Monthly Notices of the Royal Astronomical Society, 502(2), 2770-2786.
• Niederhausen, H. (2018). Measurement of the high energy astrophysical neutrino flux using electron and tau neutrinos observed in four years of icecube data (Doctoral dissertation, State University of New York at Stony Brook).
• Norris, R. P. (2017). Discovering the unexpected in astronomical survey data. Publications of the Astronomical Society of Australia, 34.
• Pawlak, M., Pejcha, O., Jakubčík, P., Jayasinghe, T., Kochanek, C. S., Stanek, K. Z., ... & Will, D. (2019). The ASAS-SN catalogue of variable stars–IV. Periodic variables in the APOGEE survey. Monthly Notices of the Royal Astronomical Society, 487(4), 5932-5945.
• Petrusevich, D. (2020). Investigation of Pulsar Stars Astronomical Dataset by Means of Machine Learning Algorithms. International Multidisciplinary Scientific GeoConference: SGEM, 20(2.1), 199-206.
• Saux, A. L., Bugnet, L., Mathur, S., Breton, S. N., & Garcia, R. A. (2019). Automatic classification of K2 pulsating stars using machine learning techniques. SF2A 2019, arXiv:1906.09611v1.
• Saux, A. L., Bugnet, L., Mathur, S., Breton, S. N., & Garcia, R. A. (2019). Automatic classification of K2 pulsating stars using machine learning techniques. arXiv preprint arXiv:1906.09611.
• Sharma, K., Singh, H. P., Gupta, R., Kembhavi, A., Vaghmare, K., Shi, J., ... & Wu, Y. (2020). Stellar spectral interpolation using machine learning. Monthly Notices of the Royal Astronomical Society, 496(4), 5002-5016.
• Smal, K. A. (1998). Project evaluation. The University of California Transportation Center.
• Teimoorinia, H., Jalilkhany, M., Scudder, J. M., Jensen, J., & Ellison, S. L. (2021). A reassessment of strong line metallicity conversions in the machine learning era. Monthly Notices of the Royal Astronomical Society, 503(1), 1082-1095.
• 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 & Astrophysics, 648, A122.
• 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 & Astrophysics, 648, A122.
• Wang, Z., Zhang, S., & Kuang, J. (2010, June). A dynamic MAUT decision model for R&D project selection. In 2010 International Conference on Computing, Control and Industrial Engineering. IEEE. 1, 423-427.
• Yavuz, Ö. Ç., & Karaman, E. (2021) Astronomik Gözlem Kalitesi Tahmininde Makine Öğrenmesi Algoritmalarının Kullanımı. Uluslararası Yönetim Bilişim Sistemleri ve Bilgisayar Bilimleri Dergisi, 5(1), 12-19.
• Yavuz, Ö. Ç., Karaman, E., & Yeşilyaprak, C. (2021). Doğu Anadolu Gözlemevi Teleskobu için Astronomik Gözlem Türü Belirlenmesi. 8th International Management Information Systems Conference (IMISC2021), İstanbul, Türkiye, 20 - 22 Ekim 2021.
• Yesuf, H. M., Faber, S. M., Koo, D. C., Woo, J., Primack, J. R., & Luo, Y. (2020). The Activation of Galactic Nuclei and Their Accretion Rates Are Linked to the Star Formation Rates and Bulge-types of Their Host Galaxies. The Astrophysical Journal, 889(1), 14.
• Yılmaz, Z. (1980). "Proje değerlendirme yöntemleri," Bursa Üniversitesi İktisadi ve Sosyal Bilimler Fakültesi Dergisi, 1(2), 51-62