检索结果-内蒙古大学图书馆

Critical node measuring method improved based on pagerank and betweenness

学校读者我要写书评

暂无评论

ICIC Express Letters, Part B: Applications 2016年第11期7卷 2381-2387页

作者： Wang, Lei Dong, Jun Ren, Jiadong College of Information Science and Engineering Yanshan University No. 438 Hebei Ave. Qinhuangdao066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province No. 438 Hebei Ave. Qinhuangdao066004 China E&A College Hebei Normal University of Science and Technology No. 360 Hebei Ave. Qinhuangdao066004 China

In software execution network, PageRank and betweenness methods are used to determine the importance of nodes. The experiment results show that the differences between nodes are not strong and cannot reflect the software nodes’ importance degree. In order to solve this problem, this paper adds the entropy weight method to the calculation of node weights, and puts the weights of nodes into the computing of two measuring methods above. Finally, we get the ranking result of nodes’ importance which means we can find out the critical nodes from top ones. Experimental results indicate that the method is efficient for critical node measuring. © 2016 ICIC International.

关键词： Surveying

Human lunar base:“Lunar Palace 1”team of Beihang University unveils China’s“Lunar Palace”plan

学校读者我要写书评

暂无评论

The Innovation 2024年第2期5卷 3-4页

作者： Hui Liu Zhikai Yao Hong Liu Institute of Environmental Biology and Life Support Technology School of Biological Science and Medical EngineeringBeihang UniversityBeijing 100083China Internet Joint Research Center of Aerospace Biotechnology&Medical Engineering Beihang UniversityBeijing 100083China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100083China

Recently,the“Lunar Palace 1”team of Beihang University,China,in response to the long-term habitation and healthcare of humans on the Moon,released the“Lunar Palace”plan through the official account“Beihang University”on WeChat’s video *** the development of crewed deep-space exploration,human permanent residence on the Moon is no longer an unattainable dream but an anticipated *** on the Moon will live in a Lunar Palace equipped with a bioregenerative life support system(BLSS),creating an Earth-like environment,much like the Lunar Palace 1 facility on Earth.

关键词： Earth Human equipped

Distributed Task Offloading based on Multi-Agent Deep Reinforcement Learning

学校读者我要写书评

暂无评论

Distributed Task Offloading based on Multi-Agent Deep Reinfo...

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Shucheng Hu Tao Ren Jianwei Niu Zheyuan Hu Guoliang Xing State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China The Chinese University of Hong Kong HKSAR China

ISBN: (纸本)9781665406697

Recent years have witnessed the increasing popularity of mobile applications, e.g., virtual reality, unmanned driving, which are generally computation-intensive and latency-sensitive, posing a major challenge for resource-limited user equipment (UE). Mobile edge computing (MEC) has been proposed as a promising approach to alleviate the problem, by offloading mobile tasks to the edge server (ES) deployed in close proximity to UE. However, most existing task offloading algorithms are primarily based on centralized scheduling, which could suffer from the ‘curse of dimensionality’ in large MEC environments. To address this issue, this paper proposes a fully distributed task offloading approach based on multi-agent deep reinforcement learning, whose critic and actor neural networks are trained under the assistance of global and local network states, respectively. In addition, we design a model parameter aggregation mechanism, along with a normalized fine-tuned reward function, to further improve the learning efficiency of the training process. Simulation results show that our proposed approach could achieve substantial performance improvements over baseline approaches.

关键词： Training Solid modeling Processor scheduling Simulation Reinforcement learning virtual reality Scheduling

Naive gabor networks for hyperspectral image classification

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Chenying Li, Jun He, Lin Plaza, Antonio Li, Shutao Li, Bo Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation School of Geography and Planning Sun Yat-sen University Guangzhou510275 China School of Automation Science and Engineering South China University of Technology Guangzhou510640 China College of Electrical and Information Engineering Hunan University Changsha410082 China Hyperspectral Computing Laboratory Department of Technology of Computers and Communications Escuela Politécnica University of Extremadura CáceresE-10071 Spain Beijing Key Laboratory of Digital Media School of Computer Science and Engineering State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Recently, many convolutional neural network (CNN) methods have been designed for hyperspectral image (HSI) classification since CNNs are able to produce good representations of data, which greatly benefits from a huge number of parameters. However, solving such a high-dimensional optimization problem often requires a large amount of training samples in order to avoid overfitting. Additionally, it is a typical non-convex problem affected by many local minima and flat regions. To address these problems, in this paper, we introduce naive Gabor Networks or Gabor-Nets which, for the first time in the literature, design and learn CNN kernels strictly in the form of Gabor filters, aiming to reduce the number of involved parameters and constrain the solution space, and hence improve the performances of CNNs. Specifically, we develop an innovative phase-induced Gabor kernel, which is trickily designed to perform the Gabor feature learning via a linear combination of local low-frequency and high-frequency components of data controlled by the kernel phase. With the phase-induced Gabor kernel, the proposed Gabor-Nets gains the ability to automatically adapt to the local harmonic characteristics of the HSI data and thus yields more representative harmonic features. Also, this kernel can fulfill the traditional complex-valued Gabor filtering in a real-valued manner, hence making Gabor-Nets easily perform in a usual CNN thread. We evaluated our newly developed Gabor-Nets on three well-known HSIs, suggesting that our proposed Gabor-Nets can significantly improve the performance of CNNs, particularly with a small training set. Copyright © 2019, The Authors. All rights reserved.

关键词： Spectroscopy

CIA-Net: Robust nuclei instance segmentation with contour-aware information aggregation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhou, Yanning Onder, Omer Fahri Dou, Qi Tsougenis, Efstratios Chen, Hao Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Hong Kong Imsight Medical Technology Co. Ltd. Hong Kong Hong Kong Department of Computing Imperial College London London United Kingdom Department of Computer Science and Engineering Chinese University of Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Accurate segmenting nuclei instances is a crucial step in computer-aided image analysis to extract rich features for cellular estimation and following diagnosis as well as treatment. While it still remains challenging because the wide existence of nuclei clusters, along with the large morphological variances among different organs make nuclei instance segmentation susceptible to over-/under-segmentation. Additionally, the inevitably subjective annotating and mislabeling prevent the network learning from reliable samples and eventually reduce the generalization capability for robustly segmenting unseen organ nuclei. To address these issues, we propose a novel deep neural network, namely Contour-aware Informative Aggregation Network (CIA-Net) with multilevel information aggregation module between two task-specific decoders. Rather than independent decoders, it leverages the merit of spatial and texture dependencies between nuclei and contour by bi-directionally aggregating task-specific features. Furthermore, we proposed a novel smooth truncated loss that modulates losses to reduce the perturbation from outliers. Consequently, the network can focus on learning from reliable and informative samples, which inherently improves the generalization capability. Experiments on the 2018 MICCAI challenge of Multi-Organ-Nuclei-Segmentation validated the effectiveness of our proposed method, surpassing all the other 35 competitive teams by a significant margin. Copyright © 2019, The Authors. All rights reserved.

关键词：

An Efficient Lossless Dual Images Secret Sharing Scheme Using Turtle Shell Reference Matrix

学校读者我要写书评

暂无评论

International Journal of Network Security 2021年第2期23卷 195-204页

作者： Lin, Jiang Yi Chen, Yu Chang, Chin Chen Hu, Yu Chen School of Computer and Information Engineering Xiamen University of Technology China Key Laboratory of Fujian Universities for Virtual Reality and 3D Visualization China Department of Information Engineering and Computer Science Feng Chia University No. 100 Wenhua Road Xitun District Taichung40724 Taiwan School of Information Science and Engineering Fujian University of Technology China Department of Computer Science and Information Management Providence University Taiwan

This work proposes a novel reversible (2, 2) secret sharing scheme based on turtle shells (TS) with dual images. According to the characteristic of the TS reference matrix in a 3x3 block, each pixel in the cover image can be used to conceal an octal digit by shifting it to the appropriate location, then two shadows with high quality are generated in the end. After the location conflict problem is solved, the hidden secret data can be extracted without any error as long as both shadows are gathered, and the cover image can be restored losslessly through the pixel orientational relationship located at two shadows. The experimental results demonstrate that the proposed scheme can achieve higher embedding capacity and maintain good image quality than some existing methods. In addition, the proposed scheme is effective against statistic attacks on pixel-value difference histograms (PDH). © 2021, International Journal of Network Security. All Rights Reserved.

关键词： Pixels

Rain scenes rendering algorithm combining metaball with mass-spring surface

学校读者我要写书评

暂无评论

Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and technology Edition) 2013年第SUPPL.1期43卷 230-234页

作者： Lyu, Meng-Ya Zheng, Xuan Tang, Yong College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of HeBei Province Qinhuangdao 066004 China

To solve the problems such as unreal effects, incomplete details in the rain scene, an algorithm to simulate water surface after rain hitting by combining Meatball with mass-spring water surface was presented. First, the raindrops model was estabished with particle system combining textures, and the water surface model was established with the mass-spring model. Secondly, the algorithm animated half globular bubbles after rain hitting with Meatball. Thirdly, water splash was simulated by means of the particle system and a gradual thinning and syncretizing technique. Finally, with the help of Cg language, the reflection and the refraction effect on the water surface, globular bubbles and water splash were simulated. The experiment shows that this approach can be used to simulate rain scenes efficiently and realistically.

关键词： Rain

Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Donghao Li, Jialin Li, Jinpeng Huang, Jiancheng Nie, Qiang Liu, Yong Gao, Bin-Bin Wang, Qiong Heng, Pheng-Ann Chen, Guangyong The Chinese University of Hong Kong Hong Kong Tencent YouTu Lab Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangzhou China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Zhejiang Lab Hangzhou China

Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could cause corrupt supervision signals and thus diminish detection performance. Motivated by the observation that the real ground-truth is usually situated in the aggregation region of the proposals assigned to a noisy ground-truth, we propose DIStribution-aware CalibratiOn (DISCO) to model the spatial distribution of proposals for calibrating supervision signals. In DISCO, spatial distribution modeling is performed to statistically extract the potential locations of objects. Based on the modeled distribution, three distribution-aware techniques, i.e., distribution-aware proposal augmentation (DA-Aug), distribution-aware box refinement (DA-Ref), and distribution-aware confidence estimation (DA-Est), are developed to improve classification, localization, and interpretability, respectively. Extensive experiments demonstrate that DISCO can achieve SOTA performance in this task, especially at high noise levels. Code is available at https://***/Correr-Zhou/DISCO. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gong, Jibing Wan, Yao Liu, Ye Li, Xuewen Zhao, Yi Wang, Cheng Lin, Yuting Fang, Xiaohan Feng, Wenzheng Zhang, Jingyi Tang, Jie School of Information Science and Engineering The Key Lab for Computer Virtual Technology and System Integration The Key Laboratory for Software Engineering of Hebei Province Yanshan University No. 438 West Hebei Avenue Hebei Qinhuangdao066004 China School of Computer Science and Technology Huazhong University of Science and Technology Luoyu Road 1037 Hubei Wuhan430074 China Salesforce Research 556 Xixi Road Chicago United States School of Cyber Science and Technology Beihang University 37 Xueyuan Road Beijing100191 China Department of Computer Science Tsinghua University Beijing100084 China

Massive open online courses (MOOCs), which offer open access and widespread interactive participation through the internet, are quickly becoming the preferred method for online and remote learning. Several MOOC platforms offer the service of course recommendation to users, to improve the learning experience of users. Despite the usefulness of this service, we consider that recommending courses to users directly may neglect their varying degrees of expertise. To mitigate this gap, we examine an interesting problem © 2022, CC BY.

关键词： Information services