Cascade-forward Network Research Articles

A hybridized artificial neural network and imperialist competitive algorithm optimization approach for prediction of soil compaction in soil bin facility

We were inspired to furnish information concerning the promising applicability of a hybrid approach involving artificial neural networks (ANNs), with manifold network functions, and a meta-heuristic optimization algorithm for prediction of soil compaction indices. The employed network functions were the prevailed feed-forward network and the novel cascade-forward network algorithms to accommodate multivariate inputs of wheel load, tire inflation pressure, number of passage, slippage, and velocity each at three different levels for estimating the study objectives of soil compaction (i.e. penetration resistance and soil sinkage). The experimentations were carried out in a soil bin facility utilizing a single wheel-tester. Each ANN trials was developed merely and then by merging with the recently introduced evolutionary optimization technique of imperialist competitive algorithm (ICA). The results were compared on the basis of a modified performance function (MSEREG) and coefficient of determination (R2). Our results elucidated that hybrid ICA–ANN further succeeded to denote lower modeling error amongst which, cascade-forward network optimized by ICA managed to yield the highest quality solutions.

Determination of Women Iron Deficiency Anemia Using Neural Networks

Iron deficiency anemia (IDA) is a common type of anemia which most often occurs in young adult women. Detection of Iron deficiency requires blood tests and doctors' decision. Doing so can be costly and difficult especially in undeveloped countries. In this study, we developed an application by using Feedforward Networks (FFN), Cascade Forward Networks (CFN), Distributed Delay Networks (DDN), Time Delay Networks (TDN), Probabilistic Neural Network (PNN), and Learning Vector Quantization (LVQ) networks that can diagnose iron deficiency anemia in women.

Alternative methods in the development of pedotransfer functions for soil hydraulic characteristics

Soil hydraulic properties are needed in the modeling of water flow and solute movement in the vadose zone. Pedotransfer functions (PTFs) have received the attention of many researchers for indirect determination of hydraulic properties from basic soil properties as an alternative to direct measurement. The objective of this study was to compare the performance of cascade forward network (CFN), multiple-linear regression (MLR), and seemingly unrelated regression (SUR) methods using prediction capabilities of point and parametric PTFs developed by these methods. The point PTFs estimated field capacity (FC), permanent wilting point (PWP), available water capacity (AWC), and saturated hydraulic conductivity (Ks) and the parametric PTFs estimated the van Genuchten retention parameters. A total of 180 soil samples was extracted from the UNSODA database and divided into two groups as 135 for the development and 45 for the validation of the PTFs. The model performances were evaluated with three statistical tools: the maximum error (ME), the model efficiency (EF), and the D index (D) using the observed and predicted values of a given parameter. Despite the fact that the differences among the three methods in prediction accuracies of the point and parametric PTFs were not statistically significant (p > 0.05) except θr and α (p < 0.05) based on the ANOVA test, overall MLR and SUR were somewhat better than CFN in prediction of the point PTFs, whereas CFN performed better than the other two methods in prediction of the parametric PTFs. The F.F values of FC and θr for CFN, MLR, and SUR methods were 0.705. 0.805, 0.795 and 0.356, −0.290, −0.290, respectively, which refer to the best and worst predictions. Properties (Ks, θr, α) having some difficulty in prediction were better predicted by CFN and SUR methods, where these methods predict all hydraulic properties from basic soil properties simultaneously rather than individually as in MLR. This suggests that multivariate analysis using such functional relationships between hydraulic properties and basic soil properties can be utilized in developing more accurate point and parametric PTFs with less time and effort.

UTILIZATION OF TWO ARTIFICIAL NEURAL NETWORK METHODS IN SURFACE WATER QUALITY MODELING

Artificial neural networks (ANNs) are capable of learning the relationships between the dependent and predictor surface water quality variables and have a high ability to predict from the new data set. In this study, two different ANN methods, the feedforward network (FFN) and the cascadeforward network (CFN) were applied to predict two surface water quality variables such as chlorophyll-a (Chl-a) and fecal coliform (FC) using twelve other variables as an input to the models. Both methods, for developing and training the ANN, are multilayer, leading to the same architecture of the feedforward neural network trained by back-propagation learning algorithm. The networks were supplied with two subsets of water quality data, with two-thirds being used for training and one-third for testing the performance of the networks, after pre-processing of the data set (110 samples) by normalization and moving average techniques. The performances of both ANN methods were evaluated visually by plotting and quantitatively by using five statistical parameters. The training procedures of both ANN methods for Chl-a and FC were very successful and a perfect match was obtained between the measured and predicted values with the correlation coefficient (R) of 1.00. The testing or prediction results also produced good agreements with the measured data of Chl-a and FC in terms of R values of 0.83, 0.93 (for FFN), and 0.89, 0.91 (for CFN), respectively. Results of this study show that ANN methods are able to predict Chl-a and FC with reasonable accuracy, suggesting that ANN is a valuable and powerful tool for surface water quality modeling and management.

Modeling of submerged membrane bioreactor treating cheese whey wastewater by artificial neural network

A submerged membrane bioreactor receiving cheese whey was modeled by artificial neural network and its performance over a period of 100 days at different solids retention times was evaluated with this robust tool. A cascade-forward network was used to model the membrane bioreactor and normalization was used as a preprocessing method. The network was fed with two subsets of operational data, with two-thirds being used for training and one-third for testing the performance of the artificial neural network. The training procedure for effluent chemical oxygen demand (COD), ammonia, nitrate and total phosphate concentrations was very successful and a perfect match was obtained between the measured and the calculated concentrations. The results of the confirmation (or testing) procedure for effluent ammonia and nitrate concentrations were very successful; however, the results of the confirmation procedure for effluent COD and total phosphate concentrations were only satisfactory.