Veri Madenciliği Birliktelik Kuralları ile Binaların Risk Durumlarının Analizi: Kaynaşlı, Düzce Örneği

Çok çeşitli verinin analiziyle anlamlı sonuçlar elde edilmesine yönelik teknikler veri madenciliği kavramını ifade etmektedir. Birliktelik kuralları, veri madenciliğinin temel tekniklerinden birisidir. Genel olarak farklı olayların, birlikte gerçekleşebilme durumlarının tespit edilmesinde kullanılmaktadır. Analizi yapılan veri setinde bulunan verilerin birbirleri arasında bulunan birliktelik bağıntıları bulunabilmektedir.. Böylece bu bağıntılar arasında eğer bir yada daha fazla durum var ise, bu durumların sonucunda belli durumlar olabilir şeklinde çıkarımlar yapılabilmektedir. Bu çalışmada Kaynaşlı (Düzce) ilçesinde yer alan 2112 binaya ait deprem riski puanlama verileri kullanılmıştır. Bu verisetindeki sözel veriler; binalar ile ilgili kat yüksekliği, kullanım durumu, bina malzemesi, 1999 depremi öncesinde ya da sonrasında inşaa edilme durumu ve elde edilen risk puanlarından oluşmaktadır. Daha detaylı birliktelik analizi yapılması için coğrafi bilgi sistemleri kullanılarak kesişim analizi yapılmış ve veri setinin mekansal verileri elde edilmiştir. Bunlar binaların bulundukları konumlara bağlı olarak oluşturulan eğim, jeoloji, taşıma gücü, zemin titreşim, zemin sınıfı, zemin büyütme ve yer altı suyu verileridir. Elde edilen sonuçlara göre bir binanın yerel deprem puanı 93.5’den büyük ve zemin titreşimi 0.10-0.20 aralığında ise düşük riskli, bina 2 katlı ve düşük riskli ise yerel deprem puanı 93.5’den büyük ve meskendir gibi çıkarımlar yapılabilmektedir.

Analysis of Risk Situations of Buildings with Data Mining Association Rules: Kaynaşlı, Düzce Example

Techniques for obtaining meaningful results by analyzing a wide variety of data express the concept of data mining. Association rules are one of the basic techniques of data mining. It is generally used in determining the different events and their occurrence. The data in the analyzed dataset can have correlation relations between each other. Thus, if there are one or more situations between these relations, it can be inferred that there may be certain situations as a result of these situations.. In this study, earthquake risk scoring data of 2112 buildings in Kaynaşlı (Düzce) district were used. Verbal data of this dataset; Consists of floor height, usage status, building material, construction status before or after the 1999 earthquake and the obtained risk points. In order to perform more detailed association rules analysis, intersection analysis was performed using geographic information systems and spatial data of the data set were obtained. These are the slope, geology, bearing capacity, ground vibration, ground class, ground magnification and groundwater data created depending on the locations of the buildings. According to the results obtained, the local earthquake score of a building is greater than 93.5 and the ground vibration is in the range of 0.10-0.20, the result is low risk. If the building has 2 floors and low risk, it can be deduced that the local earthquake score is greater than 93.5 and residential.

PDF

___

[1] S. Daw, “Machine Learning Applications Using Waikato Environment for Knowledge Analysis,” in Proc. of the 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC), 11-13 March 2020, Erode, India [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/ abstract/document/9076531
[2] R. Amornchewin and W. Kreesuradej, “Probability-based incremental association rule discovery algorithm,” in Proc. of the International Symposium on Computer Science and Its Applications (CSA), 13-15 Oct. 2008, Hobart, ACT, Australia [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/ document/4654088. [Accessed: July, 15, 2019].
[3] J. K. Chahal, “Finding Association Rules in Medical Datasets,” International Journal of Scientific Research in Science and Technology, vol. 2, no. 3, pp. 167-170, April 2019. Doi: http://doi.org/10.32628 /IJSRST
[4] Y. Shen, J. Liu, and J. Shen, “The further development of Weka base on positive and negative association rules,” in Proc. of the 2010 International Conference on Intelligent Computation Technology and Automation (ICICTA), 11-12 May 2010, Changsha, China [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/document/5523114. [Accessed: July, 15, 2019].
[5] K. Rameshkumar, M. Sambath, and S. Ravi, “Relevant association rule mining from medical dataset using new irrelevant rule elimination technique,” in Proc. of the 2013 International Conference on Information Communication and Embedded Systems (ICICES), 21-22 Feb. 2013, Chennai, India [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/document/6508351. [Accessed: July, 15, 2019].
[6] R. Agrawal, T. Imieliński, and A. Swami, “Mining association rules between sets of items in large databases,” in ACM SIGMOD Record, vol. 22, no. 2, pp. 207–216, Jun. 1993. Doi: https://doi.org/10.1145/170036.170072
[7] Y. Zhong and Y. Liao, “Research of mining effective and weighted association rules based on dual confidence,” in Proc. of the 4th International Conference on Computational and Information Sciences (ICCIS), 17-19 Aug. 2012, Chongqing, China [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/document/6301339. [Accessed: July, 15, 2019].
[8] J. Feng, Q. Zeng, and Z. Zhang, “A method of mining the meta-association rules for dynamic association rule based on the model of AR-markov,” in Proc. of the 2nd International Conference on Networks Security, Wireless Communications and Trusted Computing (NSWCTC), 24-25 Apr. 2010, Wuhan, Hubei, China [Online]. Available: IEEE Xplore,https://ieeexplore.ieee.org/document/5480826. [Accessed: July, 15, 2019].
[9] S. Naredi and R. A. Deshmukh, “Improved extraction of quantitative rules using Best M Positive Negative Association Rules Algorithm,” in Proc. of the 2015 IEEE International Conference on Electronics, Computing and Communication Technologies, (CONECCT), 10-11 July 2016, Bangalore, India [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/document/7383857. [Accessed: July, 15, 2019].
[10] X. Piao, Z. Wang, and G. Liu, “Research on mining positive and negative association rules based on dual confidence,” in Proc. of the 5th International Conference on Internet Computing for Science and Engineering, (ICICSE), 1-2 Nov. 2010, Heilongjiang, China [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/document/6076550. [Accessed: July, 15, 2019].
[11] W. Ouyang and Q. Huang, “Mining direct and indirect weighted fuzzy association rules in large transaction databases,” in Proc. of the 6th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD, 14-16 Aug. 2009, Tianjin, China [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/document/5358916. [Accessed: July, 15, 2019].
[12] X. S. Xiong, L. Fan, and Z. Lei, “Ontology-Based Association Rule Quality Evaluation Using Information Theory,” in Proc. of the 2010 International Conference on Computational and Information Sciences, 17-19 Dec. 2010, Chengdu, China [Online]. Available: IEEE Xplore, https://ieeexplore.ieee.org/document/5708913. [Accessed: July, 15, 2019].
[13] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten, “The WEKA data mining software,” in ACM SIGKDD Explorations Newsletter, vol. 11, no. 1, p. 10, Nov. 2009. Doi: https://doi.org/10.1145/1656274.1656278
[14] J. Demšar et al., “Orange: Data Mining Toolbox in Python,” Journal of Machine Learning Research, vol. 14, no. 1, pp. 2349–2353, Jan. 2013. Doi: https://dl.acm.org/doi/abs/10.5555/2567709.2567736
[15] H. Bayraktar, “CBS ve Sokak Taraması Yöntemleri Kullanılarak Düzce- Kaynaşlı İlçesinin Afet Riski Yönünden Yerleşim Durumunun Belirlenmesi ve Yerel Afet Risk Yönetimi,” Ph.D. dissertation, Gazi Üniversitesi, Ankara, Türkiye, 2014.
[16] “QGIS.” [Online]. Available: https://www.qgis.org/en/site/about. [Accessed: July, 15, 2019].
[17] İ. B. Aydilek, “Veri Kümelerindeki Eksik Değerlerin Yeni Yaklaşımlar Kullanılarak Hesaplanması,” Ph.D. dissertation, Selçuk Üniversitesi, Konya, Türkiye, 2013.
[18] D. Sağaltıcı, F. D. Alay, C. Efil, and N. İlhan, “Veri Madenciliği Yöntemleri İle Meteorolojik Verilerden Kayıp Güneş Işınım Değerlerinin Tahmini,” Harran Üniversitesi Mühendislik Dergisi, vol. 03, no. 2, pp. 49–53, Oct. 2018.
[19] Imran, S. Ahmad, and D. H. Kim, “Quantum GIS Based Descriptive and Predictive Data Analysis for Effective Planning of Waste Management,” IEEE Access, vol. 8, pp. 46193–46205, March 2020. Doi: 10.1109/ACCESS.2020.2979015
[20] Q. Cai, “Cause Analysis of Traffic Accidents on Urban Roads Based on an Improved Association Rule Mining Algorithm,” IEEE Access, vol. PP, p. 1, April 2020. Doi: 10.1109/ACCESS.2020.2988288
[21] F. C. Özçakir and A. Y. Çamurcu, “Birliktelik Kuralı Yöntemi İçin Bir Veri Madenciliği Yazılımı Tasarımı Ve Uygulaması,” İstanbul Ticaret Üniversitesi Fen Bilimleri Dergisi, vol. 6, no. 12, pp. 21–37, Güz 2007/2.
[22] A. C. Gülce, “Veri Madenciliğinde Apriori Algoritması ve Apriori Algoritmasının Farklı Veri Kümelerinde Uygulanması,” M.Sc. dissertation Trakya Üniversitesi, Edirne, Türkiye, 2010.
[23] H. Sever and B. Oğuz, “Veritabanlarında Bilgi Keşfine Formal bir Yaklaşım, Kısım 1: Eşleştirme Sorguları ve Algoritmalar,” Bilgi Dünyası, vol. 3, no. 2, pp. 173-204, Jan. 2002.
[24] M. Hahsler, “A Probabilistic Comparison of Commonly Used Interest Measures for Association Rules.” [Online]. Available: https://michael.hahsler.net/research/association_rules /measures.html. [Accessed: July, 15, 2019].
[25] “Validation and Testing accuracy widely different.” [Online]. Available: https://stackoverflow.com/questions/48718663/valida tion-and-testing-accuracy-widely-different. [Accessed: July, 15, 2019].