Browsing by Subject "Artificial intelligence methods"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    River flow estimation from upstream flow records by artificial intelligence methods
    (2009) Turan M.E.; Yurdusev M.A.
    Water resources management has become more and more crucial by the depletion of available water resources to use as opposed to the increase of the water consumption. An effective management relies on accurate and complete information about the river on which a project will be constructed. Artificial intelligence techniques are often and successfully used to complete the unmeasured data. In this study, feed forward back propagation neural networks, generalized regression neural network, fuzzy logic are used to estimate unmeasured data using the data of the four runoff gauge station on the Birs River in Switzerland. The performances of these models are measured by the mean square error, determination coefficients and efficiency coefficients to choose the best fit model. © 2009 Elsevier B.V. All rights reserved.
  • No Thumbnail Available
    Item
    Developing cation exchange capacity and soil index properties relationships using a neuro-fuzzy approach
    (Springer Verlag, 2014) Pulat H.F.; Tayfur G.; Yukselen-Aksoy Y.
    Artificial intelligence methods are employed to predict cation exchange capacity (CEC) from five different soil index properties, namely specific surface area (SSA), liquid limit, plasticity index, activity (ACT), and clay fraction (CF). Artificial neural networks (ANNs) analyses were first employed to determine the most related index parameters with cation exchange capacity. For this purpose, 40 datasets were employed to train the network and 10 datasets were used to test it. The ANN analyses were conducted with 15 different input vector combinations using same datasets. As a result of this investigation, the ANN analyses revealed that SSA and ACT are the most effective parameters on the CEC. Next, based upon these most effective input parameters, the fuzzy logic (FL) model was developed for the CEC. In the developed FL model, triangular membership functions were employed for both the input (SSA and ACT) variables and the output variable (CEC). A total of nine Mamdani fuzzy rules were deduced from the datasets, used for the training of the ANN model. Minimization (min) inferencing, maximum (max) composition, and centroid defuzzification methods are employed for the constructed FL model. The developed FL model was then tested against the remaining datasets, which were also used for testing the ANN model. The prediction results are satisfactory with a determination coefficient, R2 = 0.94 and mean absolute error, (MAE) = 7.1. © 2014, Springer-Verlag Berlin Heidelberg.
  • No Thumbnail Available
    Item
    Estimating Breathing Levels of Asthma Patients with Artificial Intelligence Methods
    (Springer, 2021) Yüksel A.S.; Tan F.G.
    Pollen contains highly allergic proteins. One of the major causes of allergic diseases is the pollen in the air we breathe. Asthma patients are known to show allergic reaction to pollens. Therefore, they need to be more careful and avoid the factors that trigger asthma. In this study, the first step was taken to develop an artificial-intelligence-based decision support system to improve the quality of life of asthma patients. Finding the ratio of pollen in nature is a long process, and it is measured by using different instruments and hours of calculations in laboratories. In this study, Adaptive Network-Based Fuzzy Extraction System (ANFIS) and normalization methods were applied to meteorological data to estimate the breathing levels of asthma patients according to the amount of pollen in the air. The data were tested via the Artificial Neural Networks method, and it was found that the model produced better results that are very close to real values when compared to the results in ANFIS. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.