Neural Interpretation Diagram Research Articles

Knowledge Extraction from Artificial Neural Networks for Rainfall-Runoff Model Combination Systems

Artificial neural networks (ANNs) are generally regarded to behave as black-box systems. Recent research explores various methods that can provide an insight into the internal connections and relationships existing within the network. Various methodologies that understand the input variable contribution are analyzed in detail, and rule extraction approaches for a trained artificial neural network are addressed. To understand the contribution of input variables to rainfall-runoff model combination systems, this paper for the first time investigates knowledge extraction from artificial neural network, which is used to combine the results obtained from different competing rainfall-runoff models, using three different approaches: (1) Garson’s algorithm; (2) neural interpretation diagram (NID); and (3) sensitivity analysis (SA). For the purpose of investigating knowledge extraction techniques, the trained multilayer perceptron neural network to combine the results from four different rainfall-runoff models for the Brosna Catchment located in Ireland has been chosen. The results of the three approaches obtained in this study indicate that they can be used to reduce the complexity of rainfall-runoff model combination systems by eliminating the least significant contributing input variables. Based on these approaches, the paper helps to provide guidance in the optimal number of rainfall-runoff models that best perform in a combination system.

Prediction of ultimate bearing capacity of eccentrically inclined loaded strip footing by ANN: Part II

Laboratory model tests were conducted on a strip footing resting over dry sand bed subjected to eccentrically inclined load in reinforced condition to determine the ultimate bearing capacity. Eccentrically inclined load on a strip footing can be referred to as partially compensated when the line of load application at the base of the footing is inclined toward the centerline of the foundation or reinforced when the line of load application is inclined away from the centerline. Based on the model load test results, a neural network model was developed to predict the reduction factor that will be used in computing the ultimate bearing capacity of an eccentrically inclined loaded strip footing. This reduction factor (RF) is the ratio of the ultimate bearing capacity of the footing subjected to an eccentrically inclined load to the ultimate bearing capacity of the footing subjected to a centric vertical load. A thorough sensitivity analysis was carried out to evaluate the parameters affecting the reduction factor. Based on the weights of the developed neural network model, a neural interpretation diagram is developed to find out whether the input parameters have direct or inverse effect on the output. A prediction model equation is established using the trained weights of the neural network model. The results were compared with the developed empirical equation for the reduction factor (Patra et al., 2012b). The ANN model results were found to be more accurate than the regression equation proposed by Patra et al. (2012b) based on the laboratory model test data and the predictability was reasonably good.

Prediction of ultimate bearing capacity of eccentrically inclined loaded strip footing by ANN, part I

Extensive laboratory model tests were conducted on a strip foundation lying over sand bed subjected to an eccentrically inclined load to determine the ultimate bearing capacity. Based on the model test results, a neural network model was developed to predict the reduction factor. This reduction factor (RF) is the ratio of the ultimate bearing capacity of the foundation subjected to an eccentrically inclined load to the ultimate bearing capacity of the foundation subjected to a centric vertical load. Different sensitivity analysis was carried out to evaluate the parameters affecting the reduction factor. Emphasis is given on the construction of neural interpretation diagram, based on the weights of the developed neural network model, to find out direct or inverse effect of input parameters on the output. A prediction model equation is established using the trained weights of the neural network model. The predictions from artificial neural network (ANN), and those from two other approaches, were compared with the laboratory model test results. The ANN model results found to be more accurate and well matched with other results.

Prediction of residual friction angle of clays using artificial neural network

The residual strength of clay is very important to evaluate long term stability of proposed and existing slopes and for remedial measure for failure slopes. Various attempts have been made to correlate the residual friction angle (ϕ r) with index properties of soil. This paper presents a neural network model to predict the residual friction angle based on clay fraction and Atterberg's limits. Different sensitivity analysis was made to find out the important parameters affecting the residual friction angle. Emphasis is placed on the construction of neural interpretation diagram, based on the weights of the developed neural network model, to find out direct or inverse effect of soil properties on the residual shear angle. A prediction model equation is established with the weights of the neural network as the model parameters.

Undrained lateral load capacity of piles in clay using artificial neural network

This paper describes the application of the artificial neural network model to predict the lateral load capacity of piles in clay. Three criteria were selected to compare the ANN model with the available empirical models: the best fit line for predicted lateral load capacity ( Q p) and measured lateral load capacity ( Q m), the mean and standard deviation of the ratio Q p/ Q m and the cumulative probability for Q p/ Q m. Different sensitivity analysis to identify the most important input parameters is discussed. A neural interpretation diagram is presented showing the effects of input parameters. A model equation is presented based on neural network parameters.

Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks

With the growth of statistical modeling in the ecological sciences, researchers are using more complex methods, such as artificial neural networks (ANNs), to address problems associated with pattern recognition and prediction. Although in many studies ANNs have been shown to exhibit superior predictive power compared to traditional approaches, they have also been labeled a “black box” because they provide little explanatory insight into the relative influence of the independent variables in the prediction process. This lack of explanatory power is a major concern to ecologists since the interpretation of statistical models is desirable for gaining knowledge of the causal relationships driving ecological phenomena. In this study, we describe a number of methods for understanding the mechanics of ANNs (e.g. Neural Interpretation Diagram, Garson's algorithm, sensitivity analysis). Next, we propose and demonstrate a randomization approach for statistically assessing the importance of axon connection weights and the contribution of input variables in the neural network. This approach provides researchers with the ability to eliminate null-connections between neurons whose weights do not significantly influence the network output (i.e. predicted response variable), thus facilitating the interpretation of individual and interacting contributions of the input variables in the network. Furthermore, the randomization approach can identify variables that significantly contribute to network predictions, thereby providing a variable selection method for ANNs. We show that by extending randomization approaches to ANNs, the “black box” mechanics of ANNs can be greatly illuminated. Thus, by coupling this new explanatory power of neural networks with its strong predictive abilities, ANNs promise to be a valuable quantitative tool to evaluate, understand, and predict ecological phenomena.