There are three major strategies to form neural network ensembles. The simplest one is the Cross Validation strategy in which all members are trained with the same training data. Bagging and boosting strategies pro-duce perturbed sample from training data. This paper provides an ideal model based on two important factors: activation function and number of neurons in the hidden layer and based u...

backgrund: imprinted genes are a unique subset of few genes, which have been differentially methylated region (dmr) in a parental origin-dependent manner during gametogenesis, and these genes are highly protected during pre-implantation epigenetic reprogramming. several studies heve shown that the particular vulnerability of imprinting genes during suboptimal pre- and peri-conception microenvir...

Abstract A dataset of (E)-N’-benzylideneisonicotinohydrazide derivatives as a potent anti-mycobacterium tuberculosis has been investigated utilizing Quantitative Structure-Activity Relationship (QSAR) techniques. Genetic Function Algorithm (GFA) and Multiple Linear Regression Analysis (MLRA) were used to select the descriptors and to generate the correlation QSAR models that relate the Mi...

When constructing a model of the behavior of a software system, model validation is necessary in order to assure that the model accuratly describes the system at an appropriate level of abstraction. How to validate a model is however not obvious, since a model is an abstraction of the real system. This paper presents an approach for validation of temporal behavior models, targeting complex indu...

Abstract One of the critical measures to control infectious diseases is a lockdown. Once past lockdown stage in many parts world, crucial question now concerns effects relaxing and finding best ways implement further lockdown(s), if required, spread. With relaxation lockdown, people migrate different cities enhance spread disease. This work presents population migration model for n-cities appli...