An Adaptive Offloading Method for an IoT-Cloud Converged Virtual Machine System Using a Hybrid Deep Neural Network

A virtual machine with a conventional offloading scheme transmits and receives all context information to maintain program consistency during communication between local environments and the cloud server environment. Most overhead costs incurred during offloading are proportional to the size of the context information transmitted over the network. Therefore, the existing context information synchronization structure transmits context information that is not required for job execution when offloading, which increases the overhead costs of transmitting context information in low-performance Internet-of-Things (IoT) devices. In addition, the optimal offloading point should be determined by checking the server’s CPU usage and network quality. In this study, we propose a context management method and estimation method for CPU load using a hybrid deep neural network on a cloud-based offloading service that extracts contexts that require synchronization through static profiling and estimation. The proposed adaptive offloading method reduces network communication overheads and determines the optimal offloading time for low-computing-powered IoT devices and variable server performance. Using experiments, we verify that the proposed learning-based prediction method effectively estimates the CPU load model for IoT devices and can adaptively apply offloading according to the load of the server.

Cyclical comovements of the world equity indexes

Purpose – The purpose of this paper is to study synchronization in stock index cycles across 82 countries and the linkage between macroeconomic and financial integration and stock market synchronization. Design/methodology/approach – The author document the synchronization structure of the world equity index cycles and its evolution over time. The author examine the explanatory power of various economic and financial variables on cycle comovements. Findings – Trade openness, capital openness, and an EU membership contribute to higher stock index cycle synchronization. Additionally, the macroeconomic and financial variables have asymmetric impacts on countries of different development levels. Originality/value – The author is the first to thoroughly chronicle the turning points, i.e., bear and bull regimes, of world equity indexes and empirically examine determinants of their cyclical comovement across nations.

New Controller Design in QCNN and the Synchronization with Chaotic System

Synchronization problem between QCNN (Quantum Cellular Neural Networks) and duffing system was studied in the paper. Not only one new controller with less parameters in QCNN was designed, but it was proved by Lyapunov function that output signal would be convergent to reference signal, and meanwhile, forms of multi-dimension controllers were given. Then the synchronization structure was draw with the corresponding controllers. In the simulation results, the new controller has higher time efficiency, which shows applying the new controller to QCNN is feasible and effective and it can assure the achievement of synchronization. Furthermore, weak periodic signal can be detected in QCNN, which provides one new thought to detection of weak signal.