TAILIEUCHUNG - Comparing neural networks, linear and nonlinear regression techniques to model penetration resistance

Penetration resistance (PR) is an important property of soils, and can be expressed as cone index (CI). Because of high variability, there are no accurate and representative PR data in most cases. Variable PR is considerably affected by gravimetric soil water content (GWC) and bulk density (BD). | Turk J Agric For 32 (2008) 425-433 © TÜB‹TAK Comparing Neural Networks, Linear and Nonlinear Regression Techniques to Model Penetration Resistance Hossein BAYAT1,*, Mohammad Reza NEYSHABOURI1, Mohammad Ali HAJABBASI2, Ali Akbar MAHBOUBI3, Mohammad Reza MOSADDEGHI3 1 Department of Soil Science, Faculty of Agriculture, Tabriz University, Tabriz - IRAN 2 Department of Soil Science, Faculty of Agriculture, Isfahan University of Technology, Isfahan - IRAN 3 Department of Soil Science, Faculty of Agriculture, Bu-Ali Sina University, Hamadan 65174 - IRAN Received: Abstract: Penetration resistance (PR) is an important property of soils, and can be expressed as cone index (CI). Because of high variability, there are no accurate and representative PR data in most cases. Variable PR is considerably affected by gravimetric soil water content (GWC) and bulk density (BD). In this study, artificial neural networks (ANNs) were used to simulate relationship between BD, GWC, and CI. A data set of 381 samples was collected from 2 study sites, Hamadan and Maragheh. Pedotransfer functions (PTFs) were developed using ANNs and linear and nonlinear regression models to predict CI for the combined data set and each data set separately. For the combined and Hamadan data sets, ANNs produced a greater correlation coefficient (R = ) and lower root mean square error (RMSE) compared with the linear regression model (R = ). For the Maragheh data set, however, the regression model yielded better results. Introducing TP and relative saturation (θv/TP) into the models improved the prediction of CI. The results further showed that ANN models performed better than nonlinear regression models. Therefore, ANNs were recognized as powerful tools to predict CI by BD, GWC, TP, and θv/TP as the independent variables under the very diverse conditions of the soils and treatments employed. Key Words: Artificial neural networks, bulk density, cone index, regression models, water .

• Nông nghiệp
• Artificial neural networks
• Bulk density
• Cone index
• Regression models
• Water content
• The artificial neural networks
• Well log data
• The lithology physical parameters
• Cuu Long basin
• Bridge deck condition rating based on artificial neural networks
• The Design Load and Main Structure Design
• Neglectable effects on the ANN’s performance
• Accordingly the maintenance need
• Summary of engineering doctoral thesis
• Building regionallinked hydroelectric turbine speed control systems
• The basis of fuzzy logic and artificial neural networks
• Regional linked hydropower turbine
• Artificial Intelligence
• Lecture Artificial Intelligence
• Trí tuệ nhân tạo
• Neural networks
• Multilayer perceptrons
• RELAP5 simulation program
• VVER 1000 reactor technology
• ANN based model
• Fire resistance
• Wooden floor assembly
• Sensitivity analysis
• Artificial neural network
• Multiple regression analysis
• Method development
• Mixture of ascorbic acid
• Solar irradiance forecasting
• Root mean square error
• Artificial neural networks via assessment
• Mean absolute error
• ANN representations
• Perceptron Training
• Multilayer networks
• Remarks on the Backpropagation algorithm
• Neural network application development
• Rule Extraction from Artificial Neural Networks
• Feedforward neural networks for classification
• Rulle exttractition ffrom neurall nettworkks Examples
• Different types of classification rules
• RegressionRegression rulesrules
• Lecture note Artificial Intelligence
• Bài giảng trí tuệ nhân tạo
• Khoa học máy tính
• International Journal of Computer Science & Communication Networks
• Design of intrusion detection system
• Artificial neural network and application of rough set
• Intrusions in a network
• Chromatography A
• Quantitative structure–retention relationships
• Multiple linear regression
• Genetic algorithm
• Biological Neural Networks
• Neural Network
• Artificial Neural
• Delta Rule
• The Backpropagation
• Hebbian Learning
• Tạp chí khoa học
• Feature subset selection
• Dynamic stability assessment
• Power system
• Journal of Automation and Control Engineering
• Approximation of the piecewise function
• Neural fuzzy networks
• Artificial bee colony algorithm
• Sum of squares error
• Relative error
• Rainfall runoff modelling
• Rainfall runoff model based
• Construction project management
• Multi layer perceptron
• Radial basis function
• Non uniform hexagonal cross sections
• Thin walled functionally graded beams
• Hexagonal cross section
• Thin walled beam
• Fault diagnosis of rolling bearings
• Singular spectrum analysis
• Identifying bearing damage
• AI for estimating damage
• ANN based damage identification
• Machine learning
• Lecture Machine learning
• Machine learning algorithms
• Data analysis methods
• Magnetic material modeling
• Coupled properties
• Field computation
• Magnetic media modeling
• Utilizing neural networks
• Healthcare
• Computerized Classification
• ECG Classification
• Heart Patients
• Electrocardiogram
• Applying artificial intelligence on e learning
• Compare E learning
• Traditional learning
• Learn 1 1 with virtual assistant
• Artificial Neural Networks (ANN) algorithms
• Feed Forward Neural Networks
• Recurrent Neural Networks
• Total Quality Management
• Indian service industrY