Research Article
BibTex RIS Cite

Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects

Year 2024, Volume: 7 Issue: 5, 960 - 970, 15.09.2024
https://doi.org/10.34248/bsengineering.1517904

Abstract

In recent times, astronomy has entered a new era with rapidly growing data sources and advanced observation techniques. The construction of powerful telescopes has enabled the collection of spectral data from millions of celestial objects. However, the increasing number and variety of data have made it challenging to categorize these celestial objects. This study employs machine learning methods to address the fundamental problem of classifying stars, galaxies, and quasars in astronomy. The dataset underwent detailed preprocessing to identify effective features for classification. KNIME Analytics Platform was used for data analysis and visualization, facilitating rapid and efficient data analysis through its drag-and-drop interface. Among the machine learning methods used in our study—Decision Trees, Random Forest, and Naive Bayes—the highest accuracy rate of 97.86% was achieved with the Random Forest model. Notably, despite its lower overall performance compared to other models, the Naive Bayes classifier exhibited superior performance in distinguishing the STAR class, which is one of the study's interesting findings. Future studies aim to enhance model accuracy by using larger and more diverse datasets and exploring different machine learning algorithms. Additionally, the impact of deep learning methods on classification performance will be investigated.

References

  • Brice MJ. 2019. Classification of stars from redshifted stellar spectra utilizing machine learning. MSc Thesis, Central Washington University, Computational Science, Washington, US, pp: 73.
  • Chen YC. 2018. Lecture 6: Density Estimation: Histogram and Kernel Density Estimator. URL= http://faculty.washington.edu/yenchic/18W_425/Lec6_hist_KDE.pdf (accessed date: May 10, 2024)

Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects

Year 2024, Volume: 7 Issue: 5, 960 - 970, 15.09.2024
https://doi.org/10.34248/bsengineering.1517904

Abstract

Son dönemde astronomi, hızla büyüyen veri kaynakları ve gelişmiş gözlem teknikleriyle yeni bir döneme girmiştir. Güçlü teleskopların yapılandırılmasıyla milyonlarca gök cisminin spektral verileri toplanabilmektedir. Ancak veri sayısının ve çeşitliliğinin artmasıyla gök cisimlerini kategorize etmek de zorlaşmıştır. Bu çalışmada astronomide temel bir problem olan yıldız, galaksi ve kuasarları sınıflandırmak için makine öğrenmesi yöntemlerini kullanılmıştır. Veri seti, sınıflandırmada etkili öznitelikleri ortaya çıkarmak için ayrıntılı bir veri önişlemeden geçirilmiştir. Veri analizi ve görselleştirme için KNIME Analytics Platformu kullanılmış, sürükle-bırak arayüzü sayesinde verilerin hızlı ve etkin bir şekilde analiz edilmesi sağlanmıştır. Makine öğrenmesi yöntemlerinden Karar Ağaçları, Rastgele Orman ve Naive Bayes’in kullanıldığı çalışmamızda en yüksek doğruluk oranı %97,86 ile Rastgele Orman modelinden elde edilmiştir. Diğer modellere göre performansı daha düşük olan Naive Bayes sınıflandırıcısının ise STAR sınıfını ayırt etmedeki üstün performansı ise çalışmanın dikkat çekici sonuçlarından biridir. Gelecek çalışmalarda, daha büyük ve çeşitli veri setleri kullanılarak model doğruluğunun artırılması ve farklı makine öğrenmesi algoritmalarının denenmesi planlanmaktadır. Ayrıca, derin öğrenme yöntemlerinin sınıflandırma performansını nasıl etkilediği araştırılacaktır.

References

  • Brice MJ. 2019. Classification of stars from redshifted stellar spectra utilizing machine learning. MSc Thesis, Central Washington University, Computational Science, Washington, US, pp: 73.
  • Chen YC. 2018. Lecture 6: Density Estimation: Histogram and Kernel Density Estimator. URL= http://faculty.washington.edu/yenchic/18W_425/Lec6_hist_KDE.pdf (accessed date: May 10, 2024)
There are 2 citations in total.

Details

Primary Language English
Subjects Communications Engineering (Other)
Journal Section Research Articles
Authors

Maide Feyza Er 0000-0003-2580-1309

Turgay Tugay Bilgin 0000-0002-9245-5728

Early Pub Date September 4, 2024
Publication Date September 15, 2024
Submission Date July 18, 2024
Acceptance Date September 3, 2024
Published in Issue Year 2024 Volume: 7 Issue: 5

Cite

APA Er, M. F., & Bilgin, T. T. (2024). Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects. Black Sea Journal of Engineering and Science, 7(5), 960-970. https://doi.org/10.34248/bsengineering.1517904
AMA Er MF, Bilgin TT. Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects. BSJ Eng. Sci. September 2024;7(5):960-970. doi:10.34248/bsengineering.1517904
Chicago Er, Maide Feyza, and Turgay Tugay Bilgin. “Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects”. Black Sea Journal of Engineering and Science 7, no. 5 (September 2024): 960-70. https://doi.org/10.34248/bsengineering.1517904.
EndNote Er MF, Bilgin TT (September 1, 2024) Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects. Black Sea Journal of Engineering and Science 7 5 960–970.
IEEE M. F. Er and T. T. Bilgin, “Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects”, BSJ Eng. Sci., vol. 7, no. 5, pp. 960–970, 2024, doi: 10.34248/bsengineering.1517904.
ISNAD Er, Maide Feyza - Bilgin, Turgay Tugay. “Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects”. Black Sea Journal of Engineering and Science 7/5 (September 2024), 960-970. https://doi.org/10.34248/bsengineering.1517904.
JAMA Er MF, Bilgin TT. Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects. BSJ Eng. Sci. 2024;7:960–970.
MLA Er, Maide Feyza and Turgay Tugay Bilgin. “Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects”. Black Sea Journal of Engineering and Science, vol. 7, no. 5, 2024, pp. 960-7, doi:10.34248/bsengineering.1517904.
Vancouver Er MF, Bilgin TT. Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects. BSJ Eng. Sci. 2024;7(5):960-7.

                                                24890