Search

An important and promising application for the network function virtualization (NFV) technology is in network security, where can dynamically and flexibly accomplish the chaining virtualized security network functions (VSNFs), e.g., network address translation, antispam and packet filter firewall, etc., and thus inspect, monitor or filter traffic flows in the cloud datacenter networks. However, the traffic flows addressed by the VSNFs mainly depend on the security service requirements from mobile users, such as the network security level, end-to-end latency, and security resource, etc. Considering the dynamic nature of cloud datacenter networks, determining the embedding of VSNFs and routing security service paths that optimizes the security resource utilization is a challenging problem, particularly without violating the end-to-end delay constraints and security service requirements. This can also be called security service chain dynamic embedding problem (SSC-DMP). In this paper, we present an NFV-enabled framework for a system that achieves the SSC dynamic embedding in the cloud datacenter networks. We first formulate an integer linear programming (ILP) model to solve the SSC-DMP exactly in small-scale network topology. Then, in order to reduce the time complexity when applying the large-scale network topology, we propose an efficient SSC dynamic embedding solution that is based on the particle swarm optimization. Extensive simulation results show that the proposed algorithm could significantly outperform the current benchmarks at least 35.2% and 23.1% in terms of resource consumption and end-to-end delay, respectively.

Structural optimization has always been the main solution for increasing the stability of flexible screens. The bending method used to test a flexible display screen is an important factor in assessing the functionality and practicability of the electronic device. The bending mode of the display screen impacts the screen service life. In this study, 2D simulation models with different bending radii, bending directions, and bending times were constructed in ABAQUS and compared to determine the effects on the flexible screen from changing the stress value, the location of the stress concentration area and the deformation state of the screen under U- and water-drop-shaped bending. The simulation results show that U-shaped bending severely strains the junction between the bent and unbent areas of a model, whereas water-drop-shaped bending can avoid such problems. In addition, the results of multiple bending experiments were used to determine an appropriate reserved length of r=2.1~2.4 mm for a model under water-drop-shaped bending.

The detection of Thermal Power Plants (TPPs) is a meaningful task for remote sensing image interpretation. It is challenging due to the variations in appearance and complex structures. In this article, we propose a novel end-to-end detection framework for TPPs based on deep convolutional neural networks. Specifically, a large-scale TPPs Dataset for Detection (AIR-TPPDD) in remote sensing images is presented. AIR-TPPDD is collected from the Google Earth worldwide, and provides detailed annotations including names and locations. To the best of our knowledge, this is the first publicly available dataset for TPP detection. Then, based on Faster R-CNN, a saliency enhanced module is proposed to strengthen the ability in representing complex structure, as well as alleviate distractions in the background. In addition, we design a multi-scale feature module to adapt to the large size range of TPPs. Experiments show that the proposed method outperforms the state-of-the-art methods and achieves 76.7% mAP on the challenging AIR-TPPDD.

Edge computing has become one of the most critical technologies in the Internet of Things (IoT), which is vulnerable to be hacked itself due to its closing to the terminals’ wide variety of applications and digital assets. Aiming to find a new paradigm for cybersecurity based on edge computing at the device level, we leverage the storage, communication, and computational capabilities of edge computing devices to acquire and transform the massive amounts of data generated during work into the states. Through the analysis of the states, the security threats of the edge computing device can be identified. Based on the complex network theory, a security state awareness model is established, which can accurately indicate a device’s current security state, be aware of the attack behavior, and perform protection methods.

A fundamental bottleneck in text-to-image synthesis is that there are rarely subjective quality evaluation metrics for a single generated image. To address this issue, this paper proposed a procedure to evaluate the single generated image, which includes a specific dataset named multiple metrics quality assessment for birds(MMQA Birds) and a learning model named blind generated image evaluator(BGIE). The motivation of our proposal is twofold. On the one hand, subjective image quality evaluation is a human perceptual task; Therefore, it tends to be a process of supervised learning. To the best of our knowledge, there are not any datasets for this study. Thus, we handle this problem via designing a specific dataset. On the other hand, we observed that the spatial content of generated image attracts more attention when humans judge its quality; According to this finding, an efficient machine-learning model that combines both pixel-level features and spatial features is proposed. Extensive experiments manifest our method can solve this problem to some extent. In the generated image dataset, BGIE surpasses the state-of-art NSS-based method by 6.3% in PLCC and SRCC. In practice, we further discuss the rationality of the MMQA Birds dataset and the application of BGIE. It proves that both in subjective and objective aspects, our method achieves convincing results.