Abstract The Internet of Things (IoT) is gaining momentum and continuously applied in several domains and in most cases, real-time data is used to study. There is a vast difference between the studies that are carried out in fixed wired and wireless networks. Thus in many studies relating to networking and wireless communication the network performance analytics and wireless sensor networks... The Internet of Things (IoT) is gaining momentum and continuously applied in several domains and in most cases, real-time data is used to study. There is a vast difference between the studies that are carried out in fixed wired and wireless networks. Thus in many studies relating to networking and wireless communication the network performance analytics and wireless sensor networks are addressed. In this current work, a project based approach of researching on both topics is addressed. This study highlights the inter relation effect of multidisciplinary learning by evaluating the performance of a wireless network for environmental (greenhouse) monitoring. We have designed a model of a typical wireless sensor network for medium-size green-house is simulated by using OPNET network modeller. The simulations are studied and the network performance was studied. The findings reveal that the influence of the network settings (such as network topology and the wireless transmission distances. Read More Read Less

Abstract For classifying the synthetic aperture radar data, we have developed a model for comparing complex valued (CV) deep Convolutional Networks (CNN). This model has feature extraction and classification of synthetic aperture radar patches. The image segmentation with deep learning is more popular as it can able to handle large databases and is welldeveloped. In this work we have introduced deep... For classifying the synthetic aperture radar data, we have developed a model for comparing complex valued (CV) deep Convolutional Networks (CNN). This model has feature extraction and classification of synthetic aperture radar patches. The image segmentation with deep learning is more popular as it can able to handle large databases and is welldeveloped. In this work we have introduced deep convolutional networks for Synthetic Aperture Radar patch classification. The experimentation was conducted with convolutional networks of 20 layers. The available layers are complex valued input layer, output layer and one or more hidden layers in the CNN. The Hidden layers consists of any combination of convolutional layers, pooling layers, activation functions, and are fully defined within complex valued domain. We have designed a model database of patches with three classes and parameters and are tested. Read More Read Less

Abstract Most people depend on mobile networks. The future autonomous networks largely depend on the virtual reality and Internet of Things with the support of modern technologies. We have studied the standards and features such as mobile cloud, cognitive radio, virtualization and software based networks of the fifth generation networks. We found that this new network can capable of transferring more... Most people depend on mobile networks. The future autonomous networks largely depend on the virtual reality and Internet of Things with the support of modern technologies. We have studied the standards and features such as mobile cloud, cognitive radio, virtualization and software based networks of the fifth generation networks. We found that this new network can capable of transferring more volume of data with high speed. We have studied the technical features and requirements of the network and resources. Read More Read Less