检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Huang, Lei Zhou, Yi Liu, Li Zhu, Fan Shao, Ling SKLSDE Institute of Artificial Intelligence Beihang University Beijing China MOE Key Laboratory of Computer Network and Information Integration Southeast University China Abu Dhabi United Arab Emirates

Batch normalization (BN) is an important technique commonly incorporated into deep learning models to perform standardization within mini-batches. The merits of BN in improving a model's learning efficiency can be further amplified by applying whitening, while its drawbacks in estimating population statistics for inference can be avoided through group normalization (GN). This paper proposes group whitening (GW), which exploits the advantages of the whitening operation and avoids the disadvantages of normalization within mini-batches. In addition, we analyze the constraints imposed on features by normalization, and show how the batch size (group number) affects the performance of batch (group) normalized networks, from the perspective of model's representational capacity. This analysis provides theoretical guidance for applying GW in practice. Finally, we apply the proposed GW to ResNet and ResNeXt architectures and conduct experiments on the ImageNet and COCO benchmarks. Results show that GW consistently improves the performance of different architectures, with absolute gains of 1.02% ∼ 1.49% in top-1 accuracy on ImageNet and 1.82% ∼ 3.21% in bounding box AP on COCO. Copyright © 2020, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

A Topology-Adaptive Deep Model for Power System Multifault Diagnosis

A Topology-Adaptive Deep Model for Power System Multifault D...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yangyang Liu Aibo Song Jiahui Jin Mingyu zhai Yingying Xue Feng Li School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China NARI Group Corporation/State Grid Electric Power Research Institute Nanjing China

ISBN: (数字)9781728185262

ISBN: (纸本)9781728185279

Quickly identifying faulty sections is tremendously important for power systems, yet challenging due to handling the variations of complex alarm patterns. Existing works have focused on finding fault section clues solely from alarm information (and ignoring power system topology information). So they are only sensitive to alarms from power systems with pre-assumed topology structures, and encounter difficulties when a system's topology changes. To adapt to unknown or varying system topologies, here we present a Topology-Adaptive Deep Model (TADM) for power system multifault diagnosis. TADM mines the underlying mapping from alarm and topology information to each section's fault status. It consists of a deep iterative network (DIN), a one-layer fully connected network (FCN), and section-wise multifault diagnosis (SWMD) subnetwork. TADM first models a fault power system as a graph, from which DIN iteratively integrates the alarm and topology information in the region from each node to its T -hop neighbors, and learns their local correlation. Limited to T 's size, FCN then combines all local correlations to determine the global correlation between alarm and topology information across the entire power system. To implement multifault diagnosis, learned local and global correlations serve as topology-related fault representations for input as an SWMD (to predict all sections' fault states one by one). A comprehensive experimental study demonstrates that TADM outperforms state-of-the-art models in both multifault diagnosis and adapting to system topologies. The source code of the TADM is available onlline 1 .

关键词： Knowledge engineering Adaptation models Correlation network topology Social networking (online) Topology Power systems

来源：评论

学校读者我要写书评

暂无评论

No-Reference Defocused Image Quality Assessment Based on Human Visual System

No-Reference Defocused Image Quality Assessment Based on Hum...

引用

2019 IEEE International Conference on Signal, information and Data Processing, ICSIDP 2019

作者： Dong, Han Shen, Aodong Kong, Youyong Shen, Yu Shu, Huazhong School of Computer Science and Engineering Southeast University Sipailou 2 Nanjing210096 China Key Laboratory of Computer Network and Infomration Display and Visualization Southeast University Nanjing China International Joint Laboratory of Infomration Integration Southeast University Nanjing China

ISBN: (纸本)9781728123455

The no-reference image quality assessment is receiving more and more attention. With no need for clear images as a reference during the evaluation process, it has a wide range of application scenarios. By analyzing the characteristics of the defocused image and combining with the Human Visual System (HVS), this paper proposed a No-Reference Visual System Index (NRVSI) approach for the image quality assessment of defoused images. Both the qualitative and quantitative assessments demonstrated the performance of the proposed method. © 2019 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Automated Authentication of Large-Scale IoT Devices with Hybrid Feature Selection 7th

Automated Authentication of Large-Scale IoT Devices with Hyb...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Chen, Qi Song, Yubo Hu, Aiqun Wang, Junbo Key Laboratory of Computer Network Technology of Jiangsu Province School of Cyber Science and Engineering Southeast University Nanjing211189 China Purple Mountain Laboratories Nanjing211189 China National Mobile Communications Research Laboratory Nanjing211189 China School of Information Science and Engineering Southeast University Nanjing211189 China

ISBN: (纸本)9783030786205

Nowadays, large-scale IoT (Internet of Things) devices are connected to the network. However, due to the simplicity, limited memory and poor computing power of most IoT devices, it is difficult to apply complex security authentication protocols to these devices. Many attackers use this loophole, impersonating legitimate devices to launch malicious attacks on the network, threatening the security of other legitimate devices. Therefore, in order to strengthen the identification and management of devices, the existing device fingerprint identification technology based on machine learning is to extract device traffic at the access gateway and generate device fingerprinting to realize the identification of IoT devices. However, to achieve high recognition accuracy, existing device fingerprint algorithms need to extract a large number of fingerprint features from network traffic for machine learning, which increases the complexity of implementation and delay of device identification. Also, it is not suitable for the current large-scale access environment. Therefore, this paper proposes a hybrid feature selection method to preprocess features for the optimal feature subset, which can not only reduce the feature dimension, but also improve the accuracy of device recognition. Firstly, the method filters the irrelevant features according to the characteristic fluctuation and the entropy of correlation information between the feature and the target. Then, based on the classification accuracy of the learning algorithm, a random search method—forest optimization algorithm is used to further optimize the filtered feature subsets under the evaluation criteria. Experiments show that this method can reduce feature dimension by 81.0% and improve classification accuracy from 86.4% to 93.1%. © 2021, Springer Nature Switzerland AG.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Detecting and mitigating a sophisticated interest flooding attack in NDN from the network-wide view 1

Detecting and mitigating a sophisticated interest flooding a...

引用

1st International Workshop on network Meets Intelligent Computations, NMIC 2019

作者： Cheng, Guang Zhao, Lixia Hu, Xiaoyan Zheng, Shaoqi Wu, Hua Li, Ruidong Fan, Chengyu School of Cyber Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Ministry of Education of China Southeast University China Key Laboratory of Computer Network Technology of Jiangsu Province China National Institute of Information and Communications Technology Tokyo184-8795 Japan Computer Science Department Colorado State University Fort Collins United States

ISBN: (纸本)9781728143712

Interest Flooding Attack (IFA) is one of the main security threats for the Named Data networking (NDN). Most of its existing countermeasures enable intermediate routers near the attackers to independently detect the attack and consider the typical attack scenario in which attackers directly send malicious Interests at a constant and relatively high rate. Moreover, they may also throttle legitimate Interests when enforcing the existing defence measures at intermediate routers as it is still difficult for them to distinguish the Interests issued by attackers from those issued by legitimate consumers. Instead, this work aims at a more sophisticated attack scenario in which attackers start the attack at a relatively lower rate but gradually speed up to keep the Pending Interest Tables (PITs) of the victims increasing to finally deplete the PIT resources for legitimate consumers. It is relatively difficult for intermediate routers to independently and timely detect such a sophisticated IFA. To solve this problem, we propose a mechanism to detect the sophisticated IFA from the network-wide view. A central controller monitors the network and makes a comprehensive and prompt decision on whether there is an ongoing IFA based on the overall state of the whole network collected from the abnormity information reports sent by the first-hop routers of attackers. Attack sources can be directly located after an IFA is determined and then the malicious Interests can be prevented from entering the network without throttling legitimate Interests. We conduct an experimental study to evaluate the performance of the proposed mechanism and explore the parameter settings of the attack detection algorithm at access routers. The experimental results validate that our mechanism can timely detect and mitigate the sophisticated IFA without throttling requests from legitimate consumers. © 2019 IEEE.

关键词： computer network security Internet telecommunication network routing Attackers network security telecommunication network routing NDN gene incomplete Freund's adjuvant Interests Internets SYN flood THROTTLE VALVE Routers parameter setting

来源：评论

学校读者我要写书评

暂无评论

Learning Expectation of Label Distribution for Facial Age and Attractiveness Estimation

arXiv

引用

arXiv 2020年

作者： Gao, Bin-Bin Liu, Xin-Xin Zhou, Hong-Yu Wu, Jianxin Geng, Xin YouTu Lab Tencent Shenzhen518075 China National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China MOE Key Laboratory of Computer Network and Information Integration Southeast University Nanjing211189 China

Facial attributes (e.g., age and attractiveness) estimation performance has been greatly improved by using convolutional neural networks. However, existing methods have an inconsistency between the training objectives and the evaluation metric, so they may be suboptimal. In addition, these methods always adopt image classification or face recognition models with a large amount of parameters, which carry expensive computation cost and storage overhead. In this paper, we firstly analyze the essential relationship between two state-of-the-art methods (Ranking-CNN and DLDL) and show that the Ranking method is in fact learning label distribution implicitly. This result thus firstly unifies two existing popular state-of-the-art methods into the DLDL framework. Second, in order to alleviate the inconsistency and reduce resource consumption, we design a lightweight network architecture and propose a unified framework which can jointly learn facial attribute distribution and regress attribute value. The effectiveness of our approach has been demonstrated on both facial age and attractiveness estimation tasks. Our method achieves new state-of-the-art results using the single model with 36× fewer parameters and 3× faster inference speed on facial age/attractiveness estimation. Moreover, our method can achieve comparable results as the state-of-the-art even though the number of parameters is further reduced to 0.9M (3.8MB disk storage). Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Control Task Assignment Algorithm based on sub-graph isomorphism

A Control Task Assignment Algorithm based on sub-graph isomo...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Feng Yu Xixian Li Huimin Zhang Li-e Wang College of computer science Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China Guangxi Key Lab of Multi-source Information Mining & Security Guilin China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China

To enhance the controllability and trustworthiness of the Internet, a new network control architecture has been presented with control task extracted to the intra-domain control node and executed in distributed multi-domain cooperative style. The study on control task assigning approach plays a central role in this network control pattern and shares some features with virtual network mapping problem. Different from the previous heuristics-based algorithms, we designs a baseline assigning algorithm which tests if the control task request can be mapped to a sub-graph of substrate control network or not without control task migration. Subsequently, an extend version is described under task migration considered. Our experiment evaluations show the impact of parameters on the runtime and assigning accuracy rate.

关键词： Cloud computing Backtracking Runtime Heuristic algorithms Process control Big Data Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Secure Data Propagation in Edge-Cloud Orchestrated Computing Paradigms: Statistcs and Taxonomy

Secure Data Propagation in Edge-Cloud Orchestrated Computing...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Feng Yu Xixian Li Huimin Zhang Li-e Wang College of computer science Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China Guangxi Key Lab of Multi-source Information Mining &Security Guilin China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China

Despite the importance of the secure data propagation in the edge-cloud orchestrated computing paradigms, to the best of our knowledge, there is lack of systematic and comprehensive review on this research topic. The purpose of this article is to provide a systematic literature survey on secure data propagation in edge-cloud orchestrated computing environment to examine the current technical achievements published between 2010 and February 2020. The brief contributions of the paper are as follows: (1)providing a comprehensive literature review of the secure data propagation approaches in the edge-cloud orchestrated computing paradigms, (2) designing a methodology for document retrieval and selection, (3) presenting analysis and comparison for main technique methods of secure data propagation in hybrid edge-cloud environment.

关键词： Systematics Bibliographies Taxonomy Big Data

来源：评论

学校读者我要写书评

暂无评论

A High-Fidelity Virtual Liver Model Incorporating Biological Characteristics

SSRN

引用

SSRN 2022年

作者： Zhang, Xiaorui Zhang, Wenzheng Sun, Wei Song, Aiguo Xu, Tong Wuxi Research Institute Nanjing University of Information Science & Technology Wuxi214100 China Engineering Research Center of Digital Forensics Ministry of Education Jiangsu Engineering Center of Network Monitoring School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China School of Automation Nanjing University of Information Science & Technology Nanjing210044 China State Key Laboratory of Bioelectronics Jiangsu Key Lab of Remote Measurement and Control School of Instrument Science and Engineering Southeast University Nanjing210096 China University of Southern California Los AngelesCA United States

Flexible tissue modeling plays an important role in the field of telemedicine. It is related to whether the soft tissue deformation process can be accurately, real-time and vividly simulated during surgery. Most existing models lack the unique biological characteristics. To enhance visual perception ability, a high-fidelity virtual liver model incorporating biological characteristics, such as the viscoelastic, anisotropic and nonlinear biological characteristics, is proposed based on the finite element model with the fourth-order Runge-Kutta method. When simulating the resection of diseased livers, the model undergoes a plastic deformation process where the model loses elasticity due to excessive deformation, but does not reach the cutting fracture threshold. To improve the fidelity of the liver model, this study is the first to introduce the viscoplasticity of biological tissues to the liver model. The 3DMax2020 and OpenGL4.6 were used to build a liver surgery simulation platform, and the PHANTOM OMNI manual controller was used to sense the feedback force during the operation. The proposed model was verified from three aspects of accuracy, fidelity and real-time performance. The experimental results show that the proposed virtual liver model can achieve real visual reproduction, with natural deformation effect, accurate simulation and high fidelity. © 2022, The Authors. All rights reserved.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

Uncertain Ontology Embeddings

Uncertain Ontology Embeddings

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Khaoula Boutouhami Guilin Qi Qiu Ji Jiatao Zhang Huan Gao School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing China School of Modern Posts & Institute of Modern Posts Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9781728170862

ISBN: (纸本)9781728170879

Ontologies are an expressive power used as a crucial element to enrich knowledge graphs by their rich data and ontological concepts that are often necessary for logical inference. Recently, ontology embedding has gained increasing attention in real-world ontologies for its ability to learn sub-sumption axioms, unary and binary assertions in these ontologies, while maintaining some syntactic, semantic properties and deductive closures. In general, learning methods assume an ontology to be complete while there are different situations in which it can be excepted to be uncertain, for example when they are provided by human annotators in classification, or even missing. However, embedding such uncertain ontologies is typically ignored. In this paper, we propose a novel embedding approach, UOE, which can embed uncertain lightweight ontology encoded in DL-lite in order to better capture the relationships between the uncertainty and the ontologies in the semantic space. Experimental results show that our model can robustly learn representations of uncertain ontologies when evaluated on publicly available datasets used on machine learning benchmarks.

关键词： Training Uncertainty Semantics Ontologies Benchmark testing Syntactics Task analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：