Least Squares Support Vector Machine Classifiers
Neural Processing Letters
Computer Vision and Fuzzy-Neural Systems
Computer Vision and Fuzzy-Neural Systems
An expert system for predicting aeration performance of weirs by using ANFIS
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Prediction of aeration efficiency on stepped cascades by using least square support vector machines
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Predicting flow conditions over stepped chutes based on ANFIS
Soft Computing - A Fusion of Foundations, Methodologies and Applications
Using intelligent methods to predict air-demand ratio in venturi weirs
Advances in Engineering Software
A versatile software tool making best use of sparse data for closed loop process control
Advances in Engineering Software
Hi-index | 0.00 |
Oxygen transfer is the process which oxygen is transferred from the gaseous to the liquid phase. The oxygen transfer efficiency depends almost entirely on the amount of surface contact between the air and water. This surface contact can be increased by conduit flow that involves air-water mixture flow. In reality, the physical structure of the air-water interface is complex and still awaits clarification. In the past few years, many artificial intelligence methods have been successfully applied to the solution of complex problems. In this study, models based on Adaptive Network based Fuzzy Inference Systems and Least Squares Support Vector Machines methods were developed to predict oxygen transfer efficiency in free flowing gated closed conduits. Experimental results were compared with the results of these artificial intelligence methods. The best performance was obtained with the Least Squares Support Vector Machine model. Average correlation coefficient (R^2) and average root mean square error (RMSE) in the Least Squares Support Vector Machine model were achieved equal to 0.9927 and 0.0073, respectively. Extremely good agreement between the predicted and measured values proves the validity of the Least Squares Support Vector Machine model.