A multiscale input strategy for multiview deep learning is proposed for supervised multispectral land-use classification, and it is validated on a well-known data set. The hypothesis that simultaneous multiscale views can improve composition-based inference of classes containing size-varying objects compared to single-scale multiview is investigated. The end-to-end learning system learns a hierarchical feature representation with the aid of convolutional layers to shift the burden of feature determination from hand-engineering to a deep convolutional neural network (DCNN). This allows the classifier to obtain problem-specific features that are optimal for minimizing the multinomial logistic regression objective, as opposed to user-defined features which trade optimality for generality. A heuristic approach to the optimization of the DCNN hyperparameters is used, based on empirical performance evidence. It is shown that a single DCNN can be trained simultaneously with multiscale views to improve prediction accuracy over multiple single-scale views. Competitive performance is achieved for the UC Merced data set, where the 93.48% accuracy of multiview deep learning outperforms the 85.37% accuracy of SIFT-based methods and the 90.26% accuracy of unsupervised feature learning.

With the advent of nanotechnology, concepts related to the Internet of Things, such as the Internet of NanoThings and Internet of Bio-NanoThings (IoBNT) have also emerged in the classical literature. The main concern of this paper is the IoBNT, which projects the prospective application domain where the activities of very tiny, biocompatible, and non-intrusive devices operating in an in-body nanonetwork can be monitored and controlled through the Internet. In this paper, we present an illustrative scenario and system model of an IoBNT for application in an advanced healthcare delivery system. To address one of the major challenges of the IoBNT, we present an exemplary architecture and model of a bio-cyber interface for connecting the conventional electromagnetic-based Internet to the biochemical signaling-based bionanonetwork. The bio-cyber interface is designed and modeled by employing biological concepts, such as the responsiveness of certain biomolecules to thermal and light stimuli, and the bioluminescence phenomenon of some biochemical reactions. The analysis in this paper focuses on the system that comprises the bio-cyber interface and the information propagation network of the blood vessel that leads to the in-body nanonetwork location. The effects of the system and design parameters associated with the IoBNT models presented are numerically evaluated.

This paper presents a multi-user, multi-class and multi-layer edge computing-based framework for effective task offloading and computation processes. Important system requirements that were not captured in the existing multi-layer solutions such as offloading, computations and deadline requirements were captured in the system modeling, while both wireless communications and task computation constraints were considered. We considered three layers system, where each device offloads its generated tasks in each time slot to any selected layer for computation. On its arrival at such a selected layer, the task is only accepted if the queue size is below the pre-defined threshold, otherwise, such a task is offloaded to the next layer. Tasks were classified into class 1 and class 2 tasks following tasks’ quality of service requirements. We adopted stochastic geometry, parallel computing and queueing theory techniques to model the performance of the considered integrated edge-fog-cloud computing environment and obtained analysis for various performance metrics of interest. The obtained analyses demonstrate the importance of multi-layer and multi-class edge computing systems towards improving the experience of both delay-sensitive and mission-critical applications in any task offloading environment.

Cognitive radio networks (CRN), in their quest to become the preferred next-generation wireless communication paradigm, will depend heavily on their ability to efficiently manage the limited resources at their disposal in meeting the demands of their numerous users and driving their operations. As a result, a considerable amount of research work has been recently dedicated to investigating and developing resource allocation (RA) models that capture the essentials of CRN. The various ideas put forward by researchers to address RA problems in CRN have been somewhat diverse, and somehow, there seem to be no links that bring cohesion and clarity of purpose and ideas. To address this problem and bridge the gap, in this paper, a comprehensive study on the prevalent techniques developed for addressing RA problems in CRN is carried out, with an intent to put some structure, relevance and meaning to the various solution approaches. The solution models are therefore grouped and/or classified based on certain outstanding criteria, and their strengths and weaknesses highlighted. Open-ended problems are identified, and suggestions for improving solution models are given. The study therefore gives good directions for further investigations on developing RA solutions in CRN.