检索结果-内蒙古大学图书馆

A more compact object detector head network with feature enhancement and relational reasoning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Wenchao Fu, Chong Chang, Xiangshi Zhao, Tengfei Li, Xiang Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China Baidu Smart Life Group NO. 10 Xibeiwang East Street Ke Ji Yuan Haidian District Beijing100193 China School of Computer Science University of Auckland New Zealand

Modeling implicit feature interaction patterns is of significant importance to object detection tasks. However, in the two-stage detectors, due to the excessive use of hand-crafted components, it is very difficult to reason about the implicit relationship of the instance features. To tackle this problem, we analyze three different levels of feature interaction relationships, namely, the dependency relationship between the cropped local features and global features, the feature autocorrelation within the instance, and the cross-correlation relationship between the instances. To this end, we propose a more compact object detector head network (CODH), which can not only preserve global context information and condense the information density, but also allows instance-wise feature enhancement and relational reasoning in a larger matrix space. Without bells and whistles, our method can effectively improve the detection performance while significantly reducing the parameters of the model, e.g., with our method, the parameters of the head network is 0.6× smaller than the state-of-the-art Cascade R-CNN, yet the performance boost is 1.3% on COCO test-dev. Without losing generality, we can also build a more lighter head network for other multi-stage detectors by assembling our method. Copyright © 2021, The Authors. All rights reserved.

关键词： Object detection

Revisiting Recent and Current Anomaly Detection based on Machine Learning in Ad-Hoc networks 5

学校读者我要写书评

暂无评论

Revisiting Recent and Current Anomaly Detection based on Mac...

5th Annual International Conference on network and Information Systems for Computers, ICNISC 2019

作者： Wang, Zhixiao Chen, Mingyu Yan, Wenyao Wang, Wendong Gao, Ang Nie, Gaoyang Wang, Feng Yang, Shaobo Xi'An University of Technology Xi'an710048 China Goettingen University Goettingen37077 Germany Xi'An Jiaotong University Xi'an710049 China Shaanxi Provincial Key Laboratory of Network Computing and Security Technology Xi'an710048 China College of xi'An Innovation Yan'An University Xi'an710100 China Yan'An University Yan'an716000 China National Satellite Meteorological Center China Meteorological Administration Beijing100081 China

Ad-Hoc network which is one kind of self-organized networks is much more vulnerable than the infrastructural network with the properties of highly changeable linkage, dynamic structure, and wireless connections so that the tradition intrusion detection system (IDS) should be improved to adapt in such network with limited computing resources and open channels. To ensure the security in Ad-Hoc network, the efficient anomaly detection methods should be probed. Over the past years, many studies have implemented anomaly detection methods (intrusion detection techniques) based on machine-learning methods in this field. This article analyzes the existing security problem in Ad-Hoc network, presents the basic theory of intrusion detection for Ad-Hoc network, and reviews the current and recent anomaly detection methods used machine learning techniques in the intrusion detection system. © Published under licence by IOP Publishing Ltd.

关键词： Intrusion detection

Deep Learning for Password Guessing and Password Strength Evaluation, A Survey

学校读者我要写书评

暂无评论

Deep Learning for Password Guessing and Password Strength Ev...

IEEE International Conference on Trust, security and Privacy in computing and Communications (TrustCom)

作者： Tao Zhang Zelei Cheng Yi Qin Qiang Li Lin Shi Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Hybrid Computation and IC Design Analysis Guangxi University for Nationalities Nanning China Department of Computer and Information Technology Purdue University West Lafayette USA PLA Information Engineering University Zhengzhou China Henan Key Laboratory of Network Cryptography Technology Zhengzhou China Cloud Computing and Big Data Research Institute China Academy of Information and Communications Technology Beijing China

ISBN: (数字)9781665403924

ISBN: (纸本)9781665403931

Text passwords are the most widely used authentication methods and will also be used in the future. Text passwords can be regarded as meaningful strings, and deep learning methods have an advantage of text processing. LSTM, RNN, GAN and other deep learning models have been using in password guessing and password strength measurements. In the paper, we make a survey on state-of-the-art deep learning methods for password guessing and password strength evaluation, including password pattern extraction, candidate password generation and password strength measurement. Compared with traditional methods, neural networks based methods can achieve better results and performance.

关键词： Deep learning Training Transfer learning security Gallium nitride Password Text processing

Clustering-based codebook design for MIMO communication system

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jiang, Jing Wang, Xiaojing Sidhu, Guftaar Ahmad Sardar Zhen, Li Gao, Runchen Shaanxi Key Laboratory of Information Communication Network and Security Xi'An University of Posts and Telecommunications Xi'an China COMSATS Institute of Information Technology Islamabad Pakistan

Codebook design is one of the core technologies in limited feedback multi-input multi-output (MIMO) communication systems. However, the conventional codebook designs usually assume MIMO vectors are uniformly distributed or isotropic. Motivated by the excellent classfication and analysis ability of clustering algorithms, we propose a K-means clustering based codebook design. First, large amounts of channel state information (CSI) is stored as the input data of the clustering, and finally divided into N clusters according to the minimal distance. The clustering centroids are used as the statistic channel information of the codebook construction which the sum distance is minimal to the real channel information. Simulation results consist with theoretical analysis in terms of the achievable rate, and demonstrate that the proposed codebook design outperforms conventional schemes, especially in the non-uniform distribution of channel scenarios. Copyright © 2019, The Authors. All rights reserved.

关键词： K-means clustering

Dynamic hybrid precoding relying on twin-resolution phase shifters in millimeter-wave communication systems

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Feng, Chenghao Shen, Wenqian Gao, Xinyu An, Jianping Hanzo, Lajos School of Information and Electronics Beijing Institute of Technology Beijing100081 China Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts & Telecommunications Xi’anShaanxi710121 China Huawei Technologies Co. Ltd Beijing100085 China Department of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

Hybrid analog/digital precoding in millimeter-wave (mmWave) multi-input multi-ouput (MIMO) systems is capable of achieving the near-optimal full-digital performance at reduced hardware cost and power consumption compared to its full-RF digital counterpart. However, having numerous phase shifters is still costly, especially when the phase shifters are of high resolution. In this paper, we propose a novel twin-resolution phase-shifter network for mmWave MIMO systems, which reduces the power consumption of an entirely high-resolution network, whilst mitigating the severe array gain reduction of an entirely low-resolution network. The connections between the twin phase shifters having different resolutions and the antennas are either fixed or dynamically configured. In the latter, we jointly design the phase-shifter network and the hybrid precoding matrix, where the phase of each entry in the analog precoding matrix can be dynamically designed according to the required resolution. This method is slightly modified for the fixed network’s hybrid precoding matrix. Furthermore, we extend the proposed method to multi-user MIMO systems and provide its performance analysis. Our simulation results show that the proposed dynamic hybrid precoding method strikes an attractive performance vs. power consumption trade-off. © 2020, CC-BY.

关键词： Phase shifters

A Hole Repairing Method Based on Edge-Preserving Projection 12th

学校读者我要写书评

暂无评论

A Hole Repairing Method Based on Edge-Preserving Projection

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Wang, Yinghui Zhao, Yanni Wang, Ningna Ning, Xiaojuan Shi, Zhenghao Zhao, Minghua Lv, Ke Huang, Liangyi Institute of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an China Department of Computer Science Shannxi Vocational and Technical College Xi’an China Booking B.V. Herengracht 597 Amsterdam1017 CE Netherlands Institute of Automation Chinese Academy of Sciences Beijing China School of Engineering and Applied Science George Washington University Washington D.C. United States

ISBN: (纸本)9783030237110

A point cloud hole repairing method based on edge-preserving projection is proposed in order to maintain sharp features of holes. First, the hole boundary points are acquired by quadrants and angles, then connections among 3D hole boundary points are projected onto the two-dimensional plane using the edge-preserving projection. Secondly, the two-dimensional region obtained from projection is subjected to point collectivization for obtaining filling points, at the same time, the radial-basis interpolation mapping technique is used to construct the hole surface according to the 3D hole boundary point. Finally, the two-dimensional filling points are reflected onto the surface of the constructed hole to complete hole repairing. Experimental results show that our method can effectively repair the hole of the point cloud and restore the sharp features of the hole. © 2019, Springer Nature Switzerland AG.

关键词： Repair

A Hole Repairing Method Based on Slicing 12th

学校读者我要写书评

暂无评论

A Hole Repairing Method Based on Slicing

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Zhao, Yanni Wang, Yinghui Wang, Ningna Ning, Xiaojuan Shi, Zhenghao Zhao, Minghua Lv, Ke Huang, Liangyi Institute of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an China Department of Computer Science Shannxi Vocational and Technical College Xi’an China Booking B.V. Herengracht 597 Amsterdam1017 CE Netherlands Institute of Automation Chinese Academy of Sciences Beijing China School of Engineering and Applied Science George Washington University Washington D.C. United States

ISBN: (纸本)9783030237110

The repairing of 3D point cloud holes has an important meaning to ensure the integrity of cloud data. We present a slice-based repairing method for 3D point cloud in this paper. Firstly, the model is horizontal sliced and each slice is projected on a two-dimensional plane, then the band-shaped points obtained during projection are clustered to select boundary points of the hole. Combined with optimal fitting points, the hole repairing point sets in the projection layer are re-sampled based on the cubic B-spline curve to fit boundary points. Finally, all hole repairing point sets in the projection layer are combined in 3D space to finish the entire hole recovery. The experimental results show that the proposed method can effectively repair complex holes for various point cloud models. © 2019, Springer Nature Switzerland AG.

关键词： Curve fitting

Global context aware RCNN for object detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Wenchao Fu, Chong Xie, Haoyu Zhu, Mai Tie, Ming Chen, Junxin School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China Science and Technology on Space Physics Laboratory Beijing100076 China College of Medicine and Biological Information Engineering Northeastern University Shenyang110819 China

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to generate a fixed size feature map. However, these cropped feature maps of local receptive fields will heavily lose global context information. To tackle this problem, we propose a novel end-to-end trainable framework, called Global Context Aware (GCA) RCNN, aiming at assisting the neural network in strengthening the spatial correlation between the background and the foreground by fusing global context information. The core component of our GCA framework is a context aware mechanism, in which both global feature pyramid and attention strategies are used for feature extraction and feature refinement, respectively. Specifically, we leverage the dense connection to improve the information flow of the global context at different stages in the top-down process of FPN, and further use the attention mechanism to refine the global context at each level in the feature pyramid. In the end, we also present a lightweight version of our method, which only slightly increases model complexity and computational burden. Experimental results on COCO benchmark dataset demonstrate the significant advantages of our approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

Optimizing network resource allocation with graph pointer neural network in large-scale AI systems

学校读者我要写书评

暂无评论

Digital Communications and networks 2024年

作者： Peiying Zhang Yilin Li Athanasios V. Vasilakos Konstantin Igorevich Kostromitin Jianyong Zhang Mohsen Guizani Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao 266580 China State Key Laboratory of Integrated Services Networks Xidian University Xi'an 710071 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250013 China Department of Networks and Communications College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University P.O. Box 1982 Dammam 31441 Saudi Arabia Department of Physics of Nanoscale Systems South Ural State University Chelyabinsk 454080 the Russian Federation Institute of Lightwave Technology Beijing Jiaotong University Beijing 100044 China Key Lab of All Optical Network and Advanced Telecommunication of EMC Institute of Lightwave Technology Beijing Jiaotong University Beijing 100044 China Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi 999041 United Arab Emirates

For increasingly complex communication demands of large-scale AI communication systems, the Space-Air-Ground Integrated network (SAGIN) better caters to demands but also raises concerns about resource scarcity and diversity. This paper innovatively combines Graph Pointer Neural networks (GPNN) and Reinforcement Learning (RL) to enhance resource allocation efficiency. The method leverages the advantages of GPNN in handling graph data and RL in optimizing decisions in dynamic environments. It also targets the optimization goal of maximizing resource allocation while minimizing deployment latency. This paper begins by modeling SAGIN and elucidating the SAGIN logical architecture based on Software-defined networking (SDN). Subsequently, it introduces an SFC deployment algorithm aimed at joint optimization of resource allocation and latency. The algorithm leverages GPNN and RL to deploy virtual nodes and links, with the goal of optimizing resource allocation and deployment latency. Experiment findings conclusively demonstrate that the efficacy of proposed algorithm in effectively weighing limited heterogeneous resources and minimum mapping delay. Notably, when compared to three other SFC mapping algorithms MLRL, NFVdeep, and RL, the proposed algorithm consistently outperforms them, with an average improvement of 10.17% in long-term average reward/cost, 11.21% in link resource utilization ratio, 15.34% in node resource utilization ratio, and 16.38% in acceptance ratio.

关键词： Space-air-ground integrated network Topological structure Reinforcement learning Service function chain Graph pointer neural network