Basketbol Salonlarının Parıltısının Makina Öğrenme Yöntemleriyle Tahmini

Abstract

Kapalı spor salonları yapay aydınlatmaya ihtiyaç duyulan ve sağlıklı spor yapılabilmesi için aydınlatmanın kontrol altında tutulması gereken alanlardandır. Oyuncu performansları ve sağlıkları korumak için; TV’de maç izleyen seyircilerin görüş yeteneği ve konforu için önemlidir. Aydınlatma yapım aşamasından başlayarak planlı bir şekilde bakımları ve kontrolleri yapılmalıdır. Kapalı spor salonlarında noktasal ölçü aletleriyle yapılan ölçümler uzun zaman almaktadır. Bu çalışmada bu soruna çözüm bulmak için makine öğrenme teknikleri kullanılarak kapalı spor salonunun parıltı ölçümleri yapılmıştır. Veri setini oluşturmak için spor salonunda standartlarda olduğu gibi 91 tane referans noktası belirlenmiştir. Belirlenen bu noktaların parıltısı ölçülmüş ve çekilen fotoğrafı üzerinden bu noktaların piksel değerleri (R,G,B) hesaplanmıştır. 91 veri seti rastgele olarak %70 eğitim verisi, %30 test verisi olarak ayrılmıştır. Çalışmada makine öğrenme yöntemi olarak Olasılıksal Sinir Ağı (PNN) ve Destek Vektör Makinesi (SVM) teknikleri kullanılmıştır. Tekniklerin başarısını ölçmek için Ortalama Hata Karesi (MSE), Kök Ortalama Kare Hatası (RMSE), korelasyon katsayısı ve doğruluk oranı yöntemleri kullanılmıştır.

Keywords

• Spor salonları
• aydınlatma
• makine öğrenmesi
• parıltı

The Luminance Estimation of Basketball Halls Using Machine Learning Methods

Abstract

Indoor sports halls are places in which artificial lighting is needed and lighting should be monitored in order to provide a healthy sports environment. It is of utmost importance for maintaining player performances and their health and the visual ability and comfort of the spectator watching matches on TV. Lighting should be maintained and monitored in a planned manner starting from the construction period. It takes a long of period of time to perform measurements using point measuring tools in indoor sports halls. In this study, the luminance estimation of an indoor sports hall was made using machine learning techniques in order to find a solution to this problem. In order to form the data set, 91 reference points were identified according to the standards in the sports hall. The luminance of these points was measured and pixel values of these points (R, G, B) were identified on the photograph taken. 91 data sets were randomly categorized as training data (70%) and test data (30%). In the study, Probabilistic Neural Network (PNN) and Support Vector Machine (SVM) techniques were used as machine learning methods. The mean square error (MSE), the root mean square error (RMSE), the correlation coefficient and the accuracy rate methods were used in order to test the success rate of these techniques.

Keywords

• Sports halls
• lighting
• machine learning
• luminance

References

1. [1] K. W. Houser, M. Royer, and R. G. Mistrick, "Light loss factors for sports lighting,", The Journal of the Illuminating Engineering Society, vol. 6, no. 3, pp. 183-201, 2010.
2. [2] K. W. Houser, M. Wei, and M. P. Royer, "Illuminance uniformity of outdoor sports lighting,", The Journal of the Illuminating Engineering Society, vol. 7, no. 4, pp. 221-235, 2011.
3. [3] C. H. Hsu, "The Effects of Lighting Quality on Visual Perception at Sports Events: A Managerial Perspective," International Journal of Management, vol. 27, no. 3, pp. 693-703, 2010.
4. [4] L. Tao, Y. Mengming, and Y. Meng, "Study of glare evaluation system for indoor sports lighting,", Electrical Technology of Intelligent Buildings, vol. 2, no.1, pp. 19-23, 2008.
5. [5] T. Goodman, "Measurement and specification of lighting: A look at the future," Lighting Research & Technology, vol. 41, no. 3, pp. 229-243, 2009.
6. [6] H. Zhou, F. Pirinccioglu, and P. Hsu, "A new roadway lighting measurement system," Transportation Research Part C: Emerging Technologies, vol. 17, no. 3, pp. 274-284, 2009.
7. [7] R. A. Zimmer, "Mobile illumination evaluation system," Transportation Research Record, vol. 1172, pp. 68-73, 1988.
8. [8] A. Zatari, G. Dodds, K. McMenemy, and R. Robinson, "Glare, luminance, and illuminance measurements of road lighting using vehicle mounted CCD cameras," The Journal of the Illuminating Engineering Society, vol. 1, no. 2, pp. 85-106, 2005.

9. [9] J. He, Z. Zhu, F. Wang, and J. Li, "Illumination Control of Intelligent Street Lamps Based on Fuzzy Decision,", International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), Changsha, China, 513-516, (2019).
10. [10] T. Muhammad, Y. Guo, Y. Wu, W. Yao, and A. Zeeshan, "CCD Camera-Based Ball Balancer System with Fuzzy PD Control in Varying Light Conditions,", IEEE 16th International Conference on Networking, Sensing and Control (ICNSC), Banff, Canada, 305-310, (2019).
11. [11] P. Mohandas, J. S. A. Dhanaraj, and X.-Z. Gao, "Artificial Neural Network based Smart and Energy Efficient Street Lighting System: A Case Study for Residential area in Hosur," Sustainable Cities and Society, vol. 48, no. 101499, pp. 1-13, 2019.
12. [12] M. Kayakuş and I. Üncü, "Research note: the measurement of road lighting with developed artificial intelligence software," Lighting Research & Technology, vol. 51, no. 6, pp. 969-977, 2019.
13. [13] M. Şahin, Y. Oğuz, and F. Büyüktümtürk, "ANN-based estimation of time-dependent energy loss in lighting systems," Energy and Buildings, vol. 116, pp. 455-467, 2016.
14. [14] T. Kazanasmaz, M. Günaydin, and S. Binol, "Artificial neural networks to predict daylight illuminance in office buildings," Building and Environment, vol. 44, no. 8, pp. 1751-1757, 2009.
15. [15] R. W. da Fonseca, E. L. Didoné, and F. O. R. Pereira, "Using artificial neural networks to predict the impact of daylighting on building final electric energy requirements," Energy and Buildings, vol. 61, pp. 31-38, 2013.
16. [16] de Basketball, Fédération Internationale. "Official Basketball Rules." (2000).
17. [17] B. Mohebali, A. Tahmassebi, A. Meyer-Baese, and A. H. Gandomi, "Probabilistic neural networks: a brief overview of theory, implementation, and application," in Handbook of Probabilistic Models: Elsevier, 2020, pp. 347-367.
18. [18] D. F. Specht, "Probabilistic neural networks," Neural networks, vol. 3, no. 1, pp. 109-118, 1990.
19. [19] N. Nariman-Zadeh, A. Darvizeh, M. Darvizeh, and H. Gharababaei, "Modelling of explosive cutting process of plates using GMDH-type neural network and singular value decomposition," Journal of Materials Processing Technology, vol. 128, no. 1-3, pp. 80-87, 2002.
20. [20] M.-W. Cho, G.-H. Kim, T.-I. Seo, Y.-C. Hong, and H. H. Cheng, "Integrated machining error compensation method using OMM data and modified PNN algorithm," International Journal of Machine Tools and Manufacture, vol. 46, no. 12-13, pp. 1417-1427, 2006.
21. [21] G. Kumaşoğlu and B. Bolat, "Yapay sinir ağlarıyla müzikal tür tanıma,", Elektrik-Elektronik Bilgisayar Sempozyumu (FEEB), Elazığ, Turkey, 5-7, (2011).
22. [22] S. Ayhan and Ş. Erdoğmuş, "Destek vektör makineleriyle sınıflandırma problemlerinin çözümü için çekirdek fonksiyonu seçimi," Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilimler Dergisi, vol. 9, no. 1, pp. 175-201, 2014.
23. [23] J. A. Suykens and J. Vandewalle, "Least squares support vector machine classifiers," Neural processing letters, vol. 9, no. 3, pp. 293-300, 1999.
24. [24] L. Zhang, W. Zhou, and L. Jiao, "Wavelet support vector machine," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 34, no. 1, pp. 34-39, 2004.
25. [25] S. K. Shevade, S. S. Keerthi, C. Bhattacharyya, and K. R. K. Murthy, "Improvements to the SMO algorithm for SVM regression," IEEE Transactions on Neural Networks, vol. 11, no. 5, pp. 1188-1193, 2000.
26. [26] A. Fillbrunn, C. Dietz, J. Pfeuffer, R. Rahn, G. A. Landrum, and M. R. Berthold, "KNIME for reproducible cross-domain analysis of life science data," Journal of Biotechnology, vol. 261, pp. 149-156, 2017.
27. [27] Berthold, M. R., Cebron, N., Dill, F., Gabriel, T. R., Kötter, T., Meinl, T., Ohl, P., Thiel, K., Wiswedel, B., "KNIME-the Konstanz Information Miner: Version 2.0 and Beyond," AcM SIGKDD Explorations Newsletter, vol. 11, no. 1, pp. 26-31, 2009.
28. [28] C. Dietz and M. R. Berthold, "KNIME for open-source bioimage analysis: a tutorial,", Focus on Bio-Image Informatics: Springer, 2016.
29. [29] S. Yu, D. Zhao, W. Chen, and H. Hou, "Oil-immersed power transformer internal fault diagnosis research based on probabilistic neural network," Procedia Computer Science, vol. 83, pp. 1327-1331, 2016.