Research Article
BibTex RIS Cite

K-Means Kümeleme Algoritması Kullanılarak Oluşturulan Yapay Zekâ Modelleri ile Sediment Taşınımının Tespiti

Year 2020, Volume: 9 Issue: 1, 306 - 322, 13.03.2020
https://doi.org/10.17798/bitlisfen.558113

Abstract

Akarsulardaki kirlilik seviyelerinin tespiti,
kullanma ve içme sularının tedarik edilmesinde, hem baraj hem de bağlama gibi
su yapılarının proje aşamasında sediment yükünün doğru bir şekilde tespit
edilmesi çok önemlidir. Bu çalışmada, Fırat Havzası üzerinde bulunan üç akım
gözlem istasyonu (AGİ) için yapay zekâ yöntemlerinden uyarlamalı ağ tabanlı
bulanık çıkarım sistemi (ANFIS), yapay sinir ağları (YSA) ve çoklu doğrusal
regresyon (MLR) gibi yöntemler denenmiştir. Oluşturulan ANFİS modellerinin küme
sayılarının seçiminde ise K-means kümeleme algoritmasından yararlanılmıştır. Yapılan çalışmalarda her bir istasyona ait
sediment (Qs), yağış (P), debi(Q) ve sıcaklık (P) verileri
kullanılmıştır. Bu veriler kullanılarak her bir istasyon için sediment tahmin
modeli geliştirilmiştir. Oluşturulan modelde girdi değişkeni olarak yağışın
gerçekleştiği günkü değeri (P), yağışın gerçekleştiği günün bir gün öncesindeki
değeri (P-1), debi ve sıcaklık değerleri, çıktı değişkeni olarak ise
sediment konsantrasyonu kullanılmıştır. Oluşturulan bu model tüm istasyonlar
için hem eğitim hem de test aşamalarında sırasıyla regresyon katsayısı (R2)
ve ortalama yüzde hatası (OYH) bakımından karşılaştırılmıştır. Yapılan
analizler sonucunda, K-means kümeleme algoritması ile alt küme sayısı
belirlenerek oluşturulan ANFIS modelinin hem alt küme sayısı rastgele
oluşturulan ANFIS modellerine göre hem de YSA ve MLR modellerine göre daha
başarılı sonuçlar elde ettiği görülmüştür. Ayrıca, YSA ve ANFIS yöntemleri
modellerinin MLR yöntemi modeline göre gözlenen değerlere daha yakın sonuçlar
elde ettiği görülmüştür.

References

  • [1] Buyukyildiz, M., & Kumcu, S. 2017. An estimation of the suspended sediment load using adaptive network based fuzzy inference system, support vector machine and artificial neural network models. Water resources management,, 31(4), 1343-1359.
  • [2] Khan, M., Tian, F., Hasan, F., & Chakrapani, G. 2019. Artificial neural network simulation for prediction of suspended sediment concentration in the River Ramganga, Ganges Basin, India. International journal of sediment research,, 34(2), 95-107.
  • [3] Qasem, S., Ebtehaj, I., & Riahi Madavar, H. 2017. Optimizing ANFIS for sediment transport in open channels using different evolutionary algorithms. Journal of Applied Research in Water and Wastewater,, 4(1), 290-298.
  • [4] Riahi-Madvar, H., & Seifi, A. 2018. Uncertainty analysis in bed load transport prediction of gravel bed rivers by ANN and ANFIS. Arabian Journal of Geosciences,, 11(21), 688.
  • [5] Malik , A., & Kumar, A. 2015. Co-Actıve Neuro-Fuzzy Inference System (Canfıs) And Multıple Lınear Regressıon (Mlr) Based Suspended Sedıment Modellıng. Journal Of Indian Water Resources Society,, 35(2), 43-48.
  • [6] Nivesh, S., & Kumar, P. 2017. Modelling river suspended sediment load using artificial neural network and multiple linear regression:. Vamsadhara River Basin, India. IJCS,, 5(5), 337-344.
  • [7] Çeribaşı, G., & Doğan, E. 2016. Aşağı Sakarya Nehrindeki Askı Maddesi Miktarının Esnek Yöntemler ile Tahmini. Karaelmas Fen ve Mühendislik Dergisi,, 6(2), 351-358.
  • [8] Kitsikoudis, V., Sidiropoulos, E., & Hrissanthou, V. 2015. Assessment of sediment transport approaches for sand-bed rivers by means of machine learning. Hydrological sciences journal, 60(9), 1566-1586.
  • [9] Partovian, A., Nourani, V., & Alami, M. 2016. Hybrid denoising-jittering data processing approach to enhance sediment load prediction of muddy rivers. Journal of Mountain Science, 13(12), 2135-2146.
  • [10] Firat, M., Dikbaş, F., Koc, A., & Güngör, M. 2012. Classification of Annual Precipitations and Identification of Homogeneous Regions using K-Means Method. Teknik Dergi,, 23(115), 1609-1622.
  • [11] Kisi, O., & Zounemat-Kermani, M. 2016. Suspended sediment modeling using neuro-fuzzy embedded fuzzy c-means clustering technique. Water resources management,, 30(11), 3979-3994.
  • [12] Şen, Z. 2004. Principles of Artificial Neural Networks. Turkish Water Foundation Publication, in Turkish.
  • [13] Avcar, M., & Saplioglu, K. 2015. An artificial neural network application for estimation of natural frequencies of beams. International Journal of Advanced Computer Sciences and Applications, 6, 94-102.
  • [14] Başkan, Ö. 2004. İzole Sinyalize Kavşaklardaki Ortalama Taşıt Gecikmelerinin Yapay Sinir Ağları İle Modellenmesi, Yüksek Lisans Tezi,. Pamukkale Üniversitesi, Fen Bilimleri Enstitüsü, Denizli, 120.
  • [15] Jang, J. 1993. ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics.
  • [16] Seyedian, S., & Rouhani, H. 2016. Assessing ANFIS accuracy in estimation of suspended sediments. Građevinar, 67(12), 1165-1176.
  • [17] Mamdani, E., & Assilian, S. 1975. An experiment in linguistic synthesis with a fuzzy logic controller. International Journal of Man-Machine Studies, 7(1), 1-13.
  • [18] Tsukamoto, Y. 1979. An approach to fuzzy reasoning method. In:M.M. Gupta, R.K. Ragade, and R. Yager, eds. Advances in fuzzy set theory and applications. Amsterdam: Elsevier Science Ltd.,137-149.
  • [19] Jang, J.-S., & Sun, C.-T. 1993. Functional equivalence between radial basis function networks and fuzzy inference systems. IEEE Transactions on Neural Networks, 4(1), 156-159.
  • [20] MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, 1(14), 281-297.
  • [21] Al Kindhi, B., Sardjono, T., Purnomo, M., & Verkerke, G. 2019. Hybrid K-means, fuzzy C-means, and hierarchical clustering for DNA hepatitis C virus trend mutation analysis. Expert Systems with Applications,, 121, 373-381.
  • [22] Vriend, S., van Gaans, P., Middelburg, J., & De Nijs, A. 1988. The application of fuzzy c-means cluster analysis and non-linear mapping to geochemical datasets: examples from Portugal. Applied Geochemistry,, 3(2), 213-224.
  • [23] Burrough, P., van Gaans, P., & MacMillan, R. 2000. High-resolution landform classification using fuzzy k-means. Fuzzy sets and systems,, 113(1), 37-52.
  • [24] Lucieer, V., & Lucieer, A. 2009. Fuzzy clustering for seafloor classification. Marine Geology, 264(3-4), 230-241.
  • [25] Hartigan, J., & Wong, M. 1979. Algorithm AS 136: A k-means clustering algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics),, 28(1), 100-108.
  • [26] Zeraatpisheh, M., Ayoubi, S., Brungard, C., & Finke, P. 2019. Disaggregating and updating a legacy soil map using DSMART, fuzzy c-means and k-means clustering algorithms in Central Iran. Geoderma,, 340, 249-258.
  • [27] Saplioglu, K., & Kucukerdem, T. 2018. Estımatıon Of Mıssıng Streamflow Data Usıng Anfıs Models And Determınatıon Of The Number Of Datasets For Anfıs: The Case Of Yeşilırmak Rıver. Applıed Ecology And Envıronmental Research, 16(3), 3583-3594.
  • [28] Sun, W., & Trover, B. 2018. Multiple model combination methods for annual maximum water level prediction during river ice breakup. Hydrological Processes, 32(3), 421-435.
  • [29] Hair, J., Black, W., Babin, B., & Anderson, R. 2009. Multivariate Data Analysis. – Pearson.
Year 2020, Volume: 9 Issue: 1, 306 - 322, 13.03.2020
https://doi.org/10.17798/bitlisfen.558113

Abstract

References

  • [1] Buyukyildiz, M., & Kumcu, S. 2017. An estimation of the suspended sediment load using adaptive network based fuzzy inference system, support vector machine and artificial neural network models. Water resources management,, 31(4), 1343-1359.
  • [2] Khan, M., Tian, F., Hasan, F., & Chakrapani, G. 2019. Artificial neural network simulation for prediction of suspended sediment concentration in the River Ramganga, Ganges Basin, India. International journal of sediment research,, 34(2), 95-107.
  • [3] Qasem, S., Ebtehaj, I., & Riahi Madavar, H. 2017. Optimizing ANFIS for sediment transport in open channels using different evolutionary algorithms. Journal of Applied Research in Water and Wastewater,, 4(1), 290-298.
  • [4] Riahi-Madvar, H., & Seifi, A. 2018. Uncertainty analysis in bed load transport prediction of gravel bed rivers by ANN and ANFIS. Arabian Journal of Geosciences,, 11(21), 688.
  • [5] Malik , A., & Kumar, A. 2015. Co-Actıve Neuro-Fuzzy Inference System (Canfıs) And Multıple Lınear Regressıon (Mlr) Based Suspended Sedıment Modellıng. Journal Of Indian Water Resources Society,, 35(2), 43-48.
  • [6] Nivesh, S., & Kumar, P. 2017. Modelling river suspended sediment load using artificial neural network and multiple linear regression:. Vamsadhara River Basin, India. IJCS,, 5(5), 337-344.
  • [7] Çeribaşı, G., & Doğan, E. 2016. Aşağı Sakarya Nehrindeki Askı Maddesi Miktarının Esnek Yöntemler ile Tahmini. Karaelmas Fen ve Mühendislik Dergisi,, 6(2), 351-358.
  • [8] Kitsikoudis, V., Sidiropoulos, E., & Hrissanthou, V. 2015. Assessment of sediment transport approaches for sand-bed rivers by means of machine learning. Hydrological sciences journal, 60(9), 1566-1586.
  • [9] Partovian, A., Nourani, V., & Alami, M. 2016. Hybrid denoising-jittering data processing approach to enhance sediment load prediction of muddy rivers. Journal of Mountain Science, 13(12), 2135-2146.
  • [10] Firat, M., Dikbaş, F., Koc, A., & Güngör, M. 2012. Classification of Annual Precipitations and Identification of Homogeneous Regions using K-Means Method. Teknik Dergi,, 23(115), 1609-1622.
  • [11] Kisi, O., & Zounemat-Kermani, M. 2016. Suspended sediment modeling using neuro-fuzzy embedded fuzzy c-means clustering technique. Water resources management,, 30(11), 3979-3994.
  • [12] Şen, Z. 2004. Principles of Artificial Neural Networks. Turkish Water Foundation Publication, in Turkish.
  • [13] Avcar, M., & Saplioglu, K. 2015. An artificial neural network application for estimation of natural frequencies of beams. International Journal of Advanced Computer Sciences and Applications, 6, 94-102.
  • [14] Başkan, Ö. 2004. İzole Sinyalize Kavşaklardaki Ortalama Taşıt Gecikmelerinin Yapay Sinir Ağları İle Modellenmesi, Yüksek Lisans Tezi,. Pamukkale Üniversitesi, Fen Bilimleri Enstitüsü, Denizli, 120.
  • [15] Jang, J. 1993. ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics.
  • [16] Seyedian, S., & Rouhani, H. 2016. Assessing ANFIS accuracy in estimation of suspended sediments. Građevinar, 67(12), 1165-1176.
  • [17] Mamdani, E., & Assilian, S. 1975. An experiment in linguistic synthesis with a fuzzy logic controller. International Journal of Man-Machine Studies, 7(1), 1-13.
  • [18] Tsukamoto, Y. 1979. An approach to fuzzy reasoning method. In:M.M. Gupta, R.K. Ragade, and R. Yager, eds. Advances in fuzzy set theory and applications. Amsterdam: Elsevier Science Ltd.,137-149.
  • [19] Jang, J.-S., & Sun, C.-T. 1993. Functional equivalence between radial basis function networks and fuzzy inference systems. IEEE Transactions on Neural Networks, 4(1), 156-159.
  • [20] MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, 1(14), 281-297.
  • [21] Al Kindhi, B., Sardjono, T., Purnomo, M., & Verkerke, G. 2019. Hybrid K-means, fuzzy C-means, and hierarchical clustering for DNA hepatitis C virus trend mutation analysis. Expert Systems with Applications,, 121, 373-381.
  • [22] Vriend, S., van Gaans, P., Middelburg, J., & De Nijs, A. 1988. The application of fuzzy c-means cluster analysis and non-linear mapping to geochemical datasets: examples from Portugal. Applied Geochemistry,, 3(2), 213-224.
  • [23] Burrough, P., van Gaans, P., & MacMillan, R. 2000. High-resolution landform classification using fuzzy k-means. Fuzzy sets and systems,, 113(1), 37-52.
  • [24] Lucieer, V., & Lucieer, A. 2009. Fuzzy clustering for seafloor classification. Marine Geology, 264(3-4), 230-241.
  • [25] Hartigan, J., & Wong, M. 1979. Algorithm AS 136: A k-means clustering algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics),, 28(1), 100-108.
  • [26] Zeraatpisheh, M., Ayoubi, S., Brungard, C., & Finke, P. 2019. Disaggregating and updating a legacy soil map using DSMART, fuzzy c-means and k-means clustering algorithms in Central Iran. Geoderma,, 340, 249-258.
  • [27] Saplioglu, K., & Kucukerdem, T. 2018. Estımatıon Of Mıssıng Streamflow Data Usıng Anfıs Models And Determınatıon Of The Number Of Datasets For Anfıs: The Case Of Yeşilırmak Rıver. Applıed Ecology And Envıronmental Research, 16(3), 3583-3594.
  • [28] Sun, W., & Trover, B. 2018. Multiple model combination methods for annual maximum water level prediction during river ice breakup. Hydrological Processes, 32(3), 421-435.
  • [29] Hair, J., Black, W., Babin, B., & Anderson, R. 2009. Multivariate Data Analysis. – Pearson.
There are 29 citations in total.

Details

Primary Language Turkish
Journal Section Araştırma Makalesi
Authors

Kemal Saplıoğlu 0000-0003-0016-8690

Ramazan Acar 0000-0001-5864-0076

Publication Date March 13, 2020
Submission Date April 26, 2019
Acceptance Date August 2, 2019
Published in Issue Year 2020 Volume: 9 Issue: 1

Cite

IEEE K. Saplıoğlu and R. Acar, “K-Means Kümeleme Algoritması Kullanılarak Oluşturulan Yapay Zekâ Modelleri ile Sediment Taşınımının Tespiti”, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 9, no. 1, pp. 306–322, 2020, doi: 10.17798/bitlisfen.558113.

Bitlis Eren University
Journal of Science Editor
Bitlis Eren University Graduate Institute
Bes Minare Mah. Ahmet Eren Bulvari, Merkez Kampus, 13000 BITLIS