Hazar Gölü’ndeki Radyoaktif Seviyelerin Belirlenmesi için Uyarlamalı Sinirsel-Bulanık Çıkarım Sistemi (ANFIS) ile Modellenmesi

Bu çalışmada, bir Adaptif Sinirsel Bulanık Çıkarım Sistemi (ANFIS) modeli Hazar Gölü (Türkiye) sularının alfa radyoaktivitesinin belirlenmesi ve onun bilinmeyen değerlerinin öngörülmesi için önerilmiştir. Model parametreleri olarak pH, toplam sertlik (TH), derinlik, elektriksel iletkenlik (EC) ve göl suyunun toplam alfa radyoaktivitesi belirlenmiştir. ANFIS modeli beş tabakalı yapı için geri-yayılım algoritması kullanılarak gerçekleştirilmiştir. Teorik ve deneysel (ANFIS) tahmin sonuçları arasındaki ortalama rölatif hata 0.7043% dir. Test verileriyle radyoaktivite verileri arasındaki rölatif hata 0.06% ve 14% arasında değişmiştir. Ek olarak, ANFIS modelinin geçerliliği regresyon modeli ile de test edilmiştir. ANFIS modeli istatistiksel olarak regresyon modelinden daha güvenilir sonuçlar vermiştir.

An Adaptive Neuro-Fuzzy Inference System (ANFIS) of Radioactivity Levels in Hazar Lake

In this study, an Adaptive Neuro-Fuzzy Inference System (ANFIS) model is proposed for thedetermination of alpha radioactivity of Hazar Lake waters and for the prediction of its unknown values. Themodel parameters of the lake water are pH, total hardness (TH), depth, electrical conductivity (EC), and alpharadioactivity. ANFIS model is performed using the back-propagation algorithm, which has the five layers.Average relative error between measurements predicted by theoretical (ANFIS) and experimental data isapproximately 0.7043%. The relative error between the test data and the radioactivity data change between0.06% and 14%. Additionally, validity of the model is also tested with a regression model. The predictedresults with the ANFIS model is better as statistically than the regression model.

PDF

___

Kamışlıoğlu M. and Külahcı F., Chaotic Behavior of Soil Radon Gas and Applications, Acta Geophysica., 64(5) (2016) 1563-1592.
Mon YJ., Airbag controller designed by adaptive- network-based fuzzy inference system (ANFIS), Fuzzy Sets Syst., 158 (2007) 2706-2714.
Melin P. and Castillo O., Intelligent control of a steepping motor drive using an adaptive neuro- fuzzy inference system, Inform Sciences., 170 (2005) 133-151.
Takagi H, and Hayashi I., NN-driven fuzzy reasoning., Int J Approx Reason., 5 (1991) 91-212.
Takagi T., and Sugeno M., Fuzzy identification of systems and its applications to modeling and control. IEEE T Syst Man Cy., 15 (1985) 116-132.
Jang JSR., ANFIS: Adaptive-network-based fuzzy inference system, IEEE T Syst Man Cy., 23 (1993) 665-685.
Krieger LH., Interim radiochemical methodology from drinking water., EPA 600(4), 75-008, Cincinnati, Ohio,1975 pp 20-100.
Tokalioglu S. and Kartal S., Chemometrical interpretation of lake waters after their chemical analysis by using AAS flame photometry and titrimetric techniques, Int J Environ An Ch., 82 (2002) 291-305.
Marsequera M., Model identification by neuro-fuzzy techniques: predicting the water level in a steam generator of a PWR, Prog Nucl Energ., 44 (2004) 237-252.
Kulahci F. and Doğru M., Physical and chemical investigation of water and sediment of the Keban Dam Lake, Turkey: Part 2: Distribution of radioactivity, heavy metals and major elements, J. Radioanal.Nucl. Ch., 268 (2006b) 529–537.
Kulahci F. and Dogru M., The physical and chemical researches in water and sediment of Keban Dam Lake, Turkiye: part 1-radioactivity iso-curves., J Radioanal Nucl Ch., 268 (2006) 517-528.
Kulahci F. Özer AB. and Doğru M., Prediction of the radioactivity in Hazar Lake (Sivrice, Turkey) by artificial neural networks, J Radioanal Nucl Ch., 269 (2006) 63-68.
Kisi O. Shiri J. and Nikoofar B., Forecasting daily lake levels using artificial intelligence approaches, Comput Geosci., 41 (2012) 169-180.
Abed-Erndoust A. and Kerachian R., Wave height prediction using the rough set theory. Ocean Eng., 54 (2012) 244-250
Talebizadeh M. and Moridnejad A., Uncertainty analysis for the forecast of lake level fluctuations using ensembles of ANN and ANFIS models, Expert Syst. Appl., 38 (2011) 4126-4135
Gueldal V. and Tongal H., Comparison of recurrent neural network, adaptive neurofuzzy inference system and stochastic models in Egirdir Lake level forecasting. Water Resour Manag, 24 (2010) 105-128.
Külahcı F. İnceöz M. Doğru M. Aksoy E. and Baykara O., Artificial neural network model for earthquake prediction with radon monitoring. Appl Radiat. Isotopes., 67 (2009) 212–219.
Baylar A. Hanbay D. and Batan M., Application of least square support vector machines in the prediction of aeration performance of plunging overfall jets from weirs, Expert Syst. Appl., 36 (2009) 8368- 8374.
Dragovic S. and Antonije O., Classification of soil samples according to geographic origin using gamma-ray spectrometry and pattern recognition methods. Appl Radiat. Isotopes., 65 (2007) 218-224.