Machine Learning Technique to Detect Radiations in the Brain

The brain of humans and other organisms is affected in various ways through the electromagneticfield(EMF)radiations generated by mobile phones and cell phone towers.Morphological variations in the brain are caused by the neurological changes due to the revelation of EMF.Cellular level analysis is used to measure and detect the effect of mobile radiations,but its utilization seems very expensive,and it is a tedious process,where its analysis requires the preparation of cell suspension.In this regard,this research article proposes optimal broadcast-ing learning to detect changes in brain morphology due to the revelation of EMF.Here,Drosophila melanogaster acts as a specimen under the revelation of EMF.Automatic segmentation is performed for the brain to attain the microscopic images from the prejudicial geometrical characteristics that are removed to detect the effect of revelation of EMF.The geometrical characteristics of the brain image of that is microscopic segmented are analyzed.Analysis results reveal the occur-rence of several prejudicial characteristics that can be processed by machine learn-ing techniques.The important prejudicial characteristics are given to four varieties of classifiers such as naïve Bayes,artificial neural network,support vector machine,and unsystematic forest for the classification of open or nonopen micro-scopic image of D.melanogaster brain.The results are attained through various experimental evaluations,and the said classifiers perform well by achieving 96.44%using the prejudicial characteristics chosen by the feature selection meth-od.The proposed system is an optimal approach that automatically identifies the effect of revelation of EMF with minimal time complexity,where the machine learning techniques produce an effective framework for image processing.

Cross Layer QoS Aware Scheduling based on Loss-Based Proportional Fairness with Multihop CRN

As huge users are involved,there is a difficulty in spectrum allocation and scheduling in Cognitive Radio Networks(CRNs).Collision increases when there is no allocation of spectrum and these results in huge drop rate and network performance degradation.To solve these problems and allocate appropriate spectrum,a novel method is introduced termed as Quality of Service(QoS)Improvement Proper Scheduling(QIPS).The major contribution of the work is to design a new cross layer QoS Aware Scheduling based on Loss-based Proportional Fairness with Multihop(QoSAS-LBPFM).In Medium Access Control(MAC)multi-channel network environment mobile nodes practice concurrent broadcast between several channels.Acquiring the advantage of introduced cross layer design,the real-time channel conditions offered by Cognitive Radio(CR)function allows adaptive sub channel choice for every broadcast.To optimize the resources of network,the LBPFM adaptively plans the radio resources for allocating to diverse services without lessening the quality of service.Results obtained from simulation proved that QoSAS-LBPFM provides enhanced QoS guaranteed performance against other existing QIPS algorithm.

Deep Learning Framework for the Prediction of Childhood Medulloblastoma

This research work develops new and better prognostic markers for predicting Childhood MedulloBlastoma(CMB)using a well-defined deep learning architecture.A deep learning architecture could be designed using ideas from image processing and neural networks to predict CMB using histopathological images.First,a convolution process transforms the histopathological image into deep features that uniquely describe it using different two-dimensional filters of various sizes.A 10-layer deep learning architecture is designed to extract deep features.The introduction of pooling layers in the architecture reduces the feature dimension.The extracted and dimension-reduced deep features from the arrangement of convolution layers and pooling layers are used to classify histopathological images using a neural network classifier.The performance of the CMB classification system is evaluated using 1414(10×magnification)and 1071(100×magnification)augmented histopathological images with five classes of CMB such as desmoplastic,nodular,large cell,classic,and normal.Experimental results show that the average classification accuracy of 99.38%(10×)and 99.07%(100×)is attained by the proposed CNB classification system.