The paper presents a fuzzy least squares support vector machine (LS-FSVM) which is implemented with the help of neo-fuzzy neurons (NFN) and which is essentially a zero order Takagi-Sugeno fuzzy inference system. The proposed LS-FSVM-NFN is numerically simple because it’s generated with NFNs, it also has a small number of adjustable parameters and high speed associated with the possibility of ap...

Water Quality plays an important role in attaining a sustainable aquaculture system, its cumulative effect can make or mar the entire system. The amount of dissolved oxygen (DO) alongside other parameters such as temperature, pH, alkalinity and conductivity are often used to estimate the water quality index (WQI) in aquaculture. There exist different approaches for the estimation of the quality...

This study developed a neural fuzzy network (NFN) model with evolutionary learning algorithm for use in the field of food mycology for predicting growth in foodborne fungi. The evolutionary learning algorithm in the proposed model is a hybrid Taguchi-genetic algorithm (HTGA) that simultaneously finds the optimal antecedent and consequent parameters by directly minimizing root-mean-squared error...

our study performed upon an extended series of 28 compounds of 1,2,4-triazole derivativesthat demonstrate substantial in vitro antimicrobial activities by serial plate dilution method,using quantitative structure-activity relationship (qsar) methods that imply analysis ofcorrelations and multiple linear regression (mlr); a significant collection of moleculardescriptors was used e.g., edge adjac...

ABSTRACT Genetic algorithm (multiparameter linear regression; GA-MLR) and genetic algorithm-artificial neural network (GA-ANN) global models have been used for prediction of the toxicity of phenols to Tetrahymena pyriformis. The data set was divided into 150 molecules for training, 50 molecules for validation, and 50 molecules for prediction sets. A large number of descriptors were calculated a...

The protocol developed in our laboratory for the assessment of hearing, involving the middle latency response (MLR), is described. Applications are illustrated in cases: (1) where the MLR was used to identify residual low frequency hearing and (2) where the MLR provided the only available threshold data because brainstem damage compromised the use of the ABR for hearing assessment. An understan...

The objectives of this trial were to develop multiple linear regression (MLR) models and three-layer Levenberg-Marquardt back propagation (BP3) neural network models using the Cornell Net Carbohydrate and Protein System (CNCPS) carbohydrate fractions as dietary variables for predicting in vitro rumen volatile fatty acid (VFA) production and further compare MLR and BP3 models. Two datasets were ...

a robust and reliable quantitative structure-property relationship (qspr) study was established to forecast the melting points (mps)  of a diverse and long set including 250 drug-like compounds. based on the calculated descriptors by dragon software package, to detect homogeneities and to split the whole dataset into training and test sets, a principal component analysis (pca) approach was used...

The development of retention prediction models for the seven ginsenosides (Rf, Rg1, Rd, Re, Rc, Rb2 and Rb1) on a polyvinyl alcohol (PVA)-bonded stationary phase at subambient temperatures is presented. The models were derived using multiple linear regression (MLR) and artificial neural network (ANN) using the logarithm of the retention factor (log k) as the dependent variable. Using stepwise M...