Companies built IT Center and operated an on-premise system because IT is a kind of asset. But the pace of change in management is accelerating and the pressure on cost efficiency in the IT sector is increasing. Cloud...
详细信息
Companies built IT Center and operated an on-premise system because IT is a kind of asset. But the pace of change in management is accelerating and the pressure on cost efficiency in the IT sector is increasing. Cloud computing is considered to secure system reliability and reduce management costs. IT resources can be efficiently utilized and paid for used. Cloud computing for each service unit was considered as a way to meet an efficient utilization of IT resources without compromising existing system reliability when providing new services. Cloud system enables real-time orchestration, and has excellent security. As a hybrid method that implemented cloud computing while maintaining the existing infrastructure, it was possible to operate an uninterrupted system as a result of system construction Therefore, companies were deploying and migrating their intranet services to cloud servers. However, it is also true that cloud migration makes system complexity increase, and system reliability is compromised by the increase of management points especially securities. It is necessary to learn about practice-oriented cloud migration and how to maintain mixed security policies when maintaining on-premises systems is effective.
We describe the artifact, publicly available at [1], that implements the proposal in [2], and the reproduction of the experimental results. It is an extended and distributed version of the Mondrian anonymization algor...
详细信息
We describe the artifact, publicly available at [1], that implements the proposal in [2], and the reproduction of the experimental results. It is an extended and distributed version of the Mondrian anonymization algorithm. Our solution anonymizes large datasets by partitioning data among workers in a distributed setting. It provides parallel execution on a dynamically chosen number of workers, limiting their interaction and data exchange.
The proceedings contain 130 papers. The special focus in this conference is on Intelligent computing. The topics include: A Comparable Study on Dimensionality Reduction Methods for Endmember Extraction;Hyperspectral I...
ISBN:
(纸本)9783030845315
The proceedings contain 130 papers. The special focus in this conference is on Intelligent computing. The topics include: A Comparable Study on Dimensionality Reduction Methods for Endmember Extraction;Hyperspectral Image Classification with Locally Linear Embedding, 2D Spatial Filtering, and SVM;a Hierarchical Retrieval Method Based on Hash Table for Audio Fingerprinting;Automatic Extraction of Document Information Based on OCR and Image Registration Technology;using Simplified Slime Mould Algorithm for Wireless Sensor Network Coverage Problem;super-Large Medical Image Storage and Display Technology Based on Concentrated Points of Interest;person Re-identification Based on Hash;a Robust and Automatic Recognition Method of Pointer Instruments in Power System;partial Distillation of Deep Feature for Unsupervised Image Anomaly Detection and Segmentation;an Evolutionary Neuron Model with Dendritic Computation for Classification and Prediction;Speech Recognition Method for Home Service Robots Based on CLSTM-HMM Hybrid Acoustic Model;serialized Local Feature Representation Learning for Infrared-Visible Person Re-identification;a Novel Decision Mechanism for Image Edge Detection;Rapid Earthquake Assessment from Satellite Imagery Using RPN and Yolo v3;attention-Based Deep Multi-scale Network for Plant Leaf Recognition;short Video Users’ Personal Privacy Leakage and Protection Measures;An Efficient Video Steganography Method Based on HEVC;analysis on the Application of Blockchain Technology in Ideological and Political Education in Universities;parallel Security Video Streaming in Cloud Server Environment;An Efficient Video Steganography Scheme for Data Protection in H.265/HEVC;an Improved Genetic Algorithm for distributed Job Shop Scheduling Problem;A Robust Lossless Steganography Method Based on H.264/AVC;detection of Pointing Position by Omnidirectional Camera.
Large number of physical systems such as electric vehicles and energy storage elements are connected to the main grid. Monitoring and regulating of this interconnected cyberphysical power system state within a short p...
详细信息
Large number of physical systems such as electric vehicles and energy storage elements are connected to the main grid. Monitoring and regulating of this interconnected cyberphysical power system state within a short period of time is a challenging task, and it can perform by the process of grid state estimation. This paper proposes a multi-agent based optimal distributed dynamic state estimation algorithm for smart grid incorporating intermittent electric vehicles and turbines. After mathematically representation of large-scale grid systems into a compact state-space framework, the smart sensors are installed to get real-time measurements which are manipulated by environmental noise. A distributed smart grid state estimation process is developed and verified. Each agent learns and runs an innovation and consensus type distributed scheme based on local measurements, previous and neighbouring estimated grid states. In this way, each local agent estimated grid state converges to the global consensus estimation over time. The proposed algorithm can effectively reconstruct the original grid states.
I/O Memory Management Unit (IOMMU) is im-portant hardware support for I/O virtualization, and it is widely used in device passthrough. However, IOMMU sacrifices memory utilization due to the static mapping requirement...
详细信息
I/O Memory Management Unit (IOMMU) is im-portant hardware support for I/O virtualization, and it is widely used in device passthrough. However, IOMMU sacrifices memory utilization due to the static mapping requirement. Moreover, it lacks DMA security guarantees inside the guest. IOMMU virtual-ization is a decent solution among existing studies to address these problems. Nevertheless, pure software IOMMU virtualization suffers from high overhead, while hardware-assisted IOMMU virtualization needs complex hardware redesign. Therefore, en-abling efficient design with low hardware overhead remains chal-lenging. In this paper, we propose an efficient hardware-software co-design of IOMMU virtualization, named LA-vIOMMU, to achieve high I/O performance with low hardware overhead. LA-vIOMMU is designed based on the existing vIOMMU mode and can be adapted to other platforms. We describe the design and implementation of LA-vIOMMU. The LA-vIOMMU combines hardware expansion and software optimization to minimize the performance cost. Furthermore, we evaluate the effectiveness and security of LA-vIOMMU and analyze the advantages compared with the existing design in x86. The experiment results show that LA-vIOMMU can get superior throughput than existing software approaches and achieve throughput pretty close to hardware-assisted virtualization with fewer hardware design changes and less verification overhead.
Network virtualization recognized as an enabling technology for the forthcoming networks is utterly popular. One of the main challenges of network virtualization is called the virtual network embedding problem. Virtua...
详细信息
ISBN:
(纸本)9781728185262
Network virtualization recognized as an enabling technology for the forthcoming networks is utterly popular. One of the main challenges of network virtualization is called the virtual network embedding problem. Virtual network embedding (VNE) aims to allocate a set of virtual machines onto a set of interconnected physical hardware in the cloud computing environment. Traditional exact solutions, considered as a time-consuming process to achieve a global optimal solution, have been proofed to be NP-hard. On the other hand, some existing heuristic solutions tend to decouple VNE problems into two stages: virtual node mapping (VNoM) and virtual link mapping (VLiM). Undoubtedly, these kinds of decomposition would result in low acceptance ratio and inefficient substrate resource utilization. In this paper, we propose a distributedparallel Genetic Algorithm combined with graph theory for solving VNE in one-stage. Our proposed algorithm achieves better performance than previous baseline solutions while meeting the stringent time requirements for online VNE problems.
The linear programming model based on active power sensitivity ignores the influence of voltage and network loss, the preventive control strategy is difficult to meet the calculation accuracy requirements after AC pow...
详细信息
ISBN:
(纸本)9781665499002
The linear programming model based on active power sensitivity ignores the influence of voltage and network loss, the preventive control strategy is difficult to meet the calculation accuracy requirements after AC power flow. An online decision-making method for the overload preventive control of transmission equipment based on the control objects relaxation is proposed. According to the overload safety margin to determine the key equipment which participating in the control and the active power sensitivity under the corresponding expected fault, and convert the allowable current carrying capacity of the line and transformer into the active power limit, establish a linear programming model for online decision-making of overload preventive control. According to the active power precision of preventive control, the active power limit of key equipment is relaxed into multiple gears, different calculation schemes are formed through enumeration-combination, and the online control strategy is determined according to the control cost and checking result of each calculation scheme. Reduce the dimension of the search space of preventive control measures by cluster analysis, and use the parallelcomputing method to solve the preventive control strategy and static safety checking in two stages, which improves the solution efficiency. The correctness and effectiveness of the proposed method are verified through the analysis of the actual power grid.
Local feature extraction is one of the most important tasks to build robust video representation in human action recognition. Recent advances in computing visual features, especially deep-learned features, have achiev...
详细信息
ISBN:
(纸本)9781728154534
Local feature extraction is one of the most important tasks to build robust video representation in human action recognition. Recent advances in computing visual features, especially deep-learned features, have achieved excellent performance on a variety of action datasets. However, the extraction process is computing-intensive and extremely time-consuming when conducting it on large-scale video data. Consequently, to extract video features over big data, most of the existing methods that run on single machine become inefficient due to the limit of computation power and memory capacity. In this paper, we propose the elastic solutions for feature extraction based on the Spark framework. Particularly, exploiting the in-memory computing capability of Spark, the process of computing features are parallelized by partitioning video data into videos or frames and place them into resilient distributed datasets (RDDs) for the subsequent processing. Then, we present the parallel algorithms to extract the state-of-the-art deep-learned features on the Spark cluster. Subsequently, using the distributed encoding, the extracted features are aggregated into the global representation which is fed into the learned classifier to recognize actions in videos. Experimental results on a benchmark dataset demonstrate that our proposed methods can significantly speed up the extraction process and achieve the promising scalability performance.
The proceedings contain 130 papers. The special focus in this conference is on Intelligent computing. The topics include: A Comparable Study on Dimensionality Reduction Methods for Endmember Extraction;Hyperspectral I...
ISBN:
(纸本)9783030845285
The proceedings contain 130 papers. The special focus in this conference is on Intelligent computing. The topics include: A Comparable Study on Dimensionality Reduction Methods for Endmember Extraction;Hyperspectral Image Classification with Locally Linear Embedding, 2D Spatial Filtering, and SVM;a Hierarchical Retrieval Method Based on Hash Table for Audio Fingerprinting;Automatic Extraction of Document Information Based on OCR and Image Registration Technology;using Simplified Slime Mould Algorithm for Wireless Sensor Network Coverage Problem;super-Large Medical Image Storage and Display Technology Based on Concentrated Points of Interest;person Re-identification Based on Hash;a Robust and Automatic Recognition Method of Pointer Instruments in Power System;partial Distillation of Deep Feature for Unsupervised Image Anomaly Detection and Segmentation;an Evolutionary Neuron Model with Dendritic Computation for Classification and Prediction;Speech Recognition Method for Home Service Robots Based on CLSTM-HMM Hybrid Acoustic Model;serialized Local Feature Representation Learning for Infrared-Visible Person Re-identification;a Novel Decision Mechanism for Image Edge Detection;Rapid Earthquake Assessment from Satellite Imagery Using RPN and Yolo v3;attention-Based Deep Multi-scale Network for Plant Leaf Recognition;short Video Users’ Personal Privacy Leakage and Protection Measures;An Efficient Video Steganography Method Based on HEVC;analysis on the Application of Blockchain Technology in Ideological and Political Education in Universities;parallel Security Video Streaming in Cloud Server Environment;An Efficient Video Steganography Scheme for Data Protection in H.265/HEVC;an Improved Genetic Algorithm for distributed Job Shop Scheduling Problem;A Robust Lossless Steganography Method Based on H.264/AVC;detection of Pointing Position by Omnidirectional Camera.
With the increasingly widespread application of Internet of Things (IoT), network attacks has become a main threat of IoT devices' security. Due to the network traffic data is the carrier of information from users...
详细信息
With the increasingly widespread application of Internet of Things (IoT), network attacks has become a main threat of IoT devices' security. Due to the network traffic data is the carrier of information from users and devices, the traffic-based IoT malicious behavior detection has become an effective solution to prevent such threats. In order to identify malicious traffic in IoT while protecting users' personal privacy, researchers introduce Federated Learning (FL) into malicious network traffic detection. However, most of the current FL frameworks need all clients to own labeled data to train a high-performance detection model jointly. In addition, they require different clients must design the same model structure to meet the requirement of parameter sharing, which is unreasonable because each client faces problems such as data heterogeneity. And it will degrade the detection performance of some clients. In this research, Semi-Supervised Federated Learning for Malicious Traffic Detection (SFMD) is proposed, aiming to assist the clients who do not have the ability to label their data to train a high-performance model with other clients together. Besides, another key feature of this framework is that it allows each client to train its personalized model according to their own situation. The experimental results indicate that SFMD can accurately identify the attack types for the unsupervised clients without labeled data. In addition, it has achieved high accuracy compared to other anomaly detection methods.
暂无评论