检索结果-内蒙古大学图书馆

Traffic Sign detection Under Challenging Conditions: A Deeper Look into Performance Variations and Spectral Characteristics

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2020年第9期21卷 3663-3673页

作者： Temel, Dogancan Chen, Min-Hung AlRegib, Ghassan Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA

Traffic signs are critical for maintaining the safety and efficiency of our roads. Therefore, we need to carefully assess the capabilities and limitations of automated traffic sign detection systems. Existing traffic sign datasets are limited in terms of type and severity of challenging conditions. Metadata corresponding to these conditions are unavailable and it is not possible to investigate the effect of a single factor because of the simultaneous changes in numerous conditions. To overcome the shortcomings in existing datasets, we introduced the CURE-TSD-Real dataset, which is based on simulated challenging conditions that correspond to adversaries that can occur in real-world environments and systems. We test the performance of two benchmark algorithms and show that severe conditions can result in an average performance degradation of 29% in precision and 68% in recall. We investigate the effect of challenging conditions through spectral analysis and show that the challenging conditions can lead to distinct magnitude spectrum characteristics. Moreover, we show that mean magnitude spectrum of changes in video sequences under challenging conditions can be an indicator of detection performance. The CURE-TSD-Real dataset is available online at https://***/olivesgatech/CURE-TSD.

关键词： Video sequences Lenses Image color analysis detection algorithms Cameras Intelligent transportation systems Metadata Autonomous vehicles traffic sign detection and recognition challenging conditions dataset magnitude spectrum machine learning

来源：评论

学校读者我要写书评

暂无评论

Radio Transient detection in Radio Astronomical Arrays

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2020年 68卷 5648-5663页

作者： Antman, Avishay Leshem, Amir Bar Ilan Univ Fac Engn IL-5290002 Ramat Gan Israel

Celestial transient radio sources have attracted considerable scientific interest recently, but their investigation is hampered by the fact that they cannot be effectively detected by commonly used radio astronomy signal processing techniques. One significant obstacle to observing radio transients is intermittent terrestrial radio frequency interference, which can appear as a transient signal. In this article we present a generalized likelihood ratio test detector for near field sources, such as terrestrial interferences, for which no prior knowledge about the steering vector is assumed. The proposed detector has the desirable property of a constant false alarm rate. Computer simulation results suggest that it outperforms the detector used by the Low Frequency Array (LOFAR) radio telescope, and that it can also be harnessed for the detection of far-field signals.

关键词： Colored noise detection algorithms Gaussian rank-one signals generalized likelihood ratio test radio astronomy

来源：评论

学校读者我要写书评

暂无评论

Community detection Algorithm for Heterogeneous Networks Based on Central Node and Seed Community Extension 3

Community Detection Algorithm for Heterogeneous Networks Bas...

引用

2021年第三届先进计算机技术、信息科学与通信国际会议(CTISC2021)

作者： Qichao Peng Kebin Chen Qi Liu Yaofeng Su Yunjun Lu College of Information and Communication National University of Defense Technology

ISBN: (纸本)9781665418683

In reality, most complex networks are heterogeneous and large-scale, they contain a variety of entity types and entity relationships, and their community structure often has the characteristics of overlap, complexity and diversity. The existing community detection algorithms do not fully consider the above characteristics, and the algorithm has low accuracy and large time complexity. In this paper, we study the community detection problem of large-scale heterogeneous complex networks based on general topology. We propose a multi-dimensional community detection algorithm Hete based on the community of central node, which can accurately detect the overlapping and heterogeneous communities of complex networks from multiple dimensions, has low time complexity and is suitable for large-scale heterogeneous complex networks.

关键词： Information science Complex networks Heterogeneous networks Topology Complexity theory detection algorithms Time complexity

来源：评论

学校读者我要写书评

暂无评论

Convolutional-Neural-Network-Based detection Algorithm for Uplink Multiuser Massive MIMO Systems

引用

IEEE ACCESS 2020年 8卷 64250-64265页

作者： Li, Lin Hou, Huijun Meng, Weixiao Nanjing Univ Posts & Telecommun Jiangsu Key Lab Broadband Wireless Commun & Inter Nanjing 210046 Peoples R China Nanjing Univ Posts & Telecommun Sch Internet Things Nanjing 210046 Peoples R China CETC 14th Res Inst Nanjing 210039 Peoples R China Harbin Inst Technol Commun Res Ctr Harbin 150001 Peoples R China

In the coming 6th generation (6G) and beyond in wireless communication, an increasing number of ultrascale intelligent factors, including mobile robot users and smart cars, will result in interference exploitation. The management of this exploitation will be a great challenge for detection algorithms in uplink massive multiple-input and multiple-output (MIMO) systems, especially for high-order quadrature amplitude modulation (QAM) signals. Artificial intelligence technology employing machine learning is one of the key approaches among the 6G technical solutions. In this paper, a convolutional-neural-network-based likelihood ascent search (CNNLAS) detection algorithm is proposed on the basis of a graphical detection model for uplink multiuser massive MIMO systems. Compared with other algorithms, the proposed CNNLAS detection algorithm has a stronger robustness against the channel estimation errors, and requires lower average received signal-to-noise ratios to obtain better bit error rate performance and to achieve the theoretical spectral efficiency with a lower polynomial average per symbol computational complexity, both for the graphical low-order and high-order QAM signals in uplink multiuser massive MIMO systems.

关键词： detection algorithms Uplink Massive MIMO Transmitting antennas Quadrature amplitude modulation Bit error rate Wireless communication massive multiple-input and multiple-output (MIMO) convolutional neural network (CNN) detection algorithm high-order modulation bit error rate (BER) computational complexity

来源：评论

学校读者我要写书评

暂无评论

Community detection by Fuzzy Relations

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING 2020年第2期8卷 478-492页

作者： Luo, Wenjian Yan, Zhenglong Bu, Chenyang Zhang, Daofu Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230027 Anhui Peoples R China Univ Sci & Technol China Anhui Prov Key Lab Software Engn Comp & Commun Hefei 230027 Anhui Peoples R China

The increasing demand for knowledge from network data poses significant challenges in many tasks. Discovering community structure from a network is one of the classic and significant problems faced in network analysis. In this paper, we study the network structure from the perspective of the composition of fuzzy relations, and a novel algorithm based on fuzzy relations, i.e., CDFR (Community detection by Fuzzy Relations), is proposed for non-overlapping community detection. The key idea of CDFR is to find the NGC node (Nearest node with Greater Centrality) for each node and compute the fuzzy relation between them. Then, the community to which a node belongs depends on its NGC node. In addition, the decision graph will be constructed to guide community detection. Experimental results on artificial and real-world networks verify the effectiveness and superiority of our CDFR algorithm.

关键词： detection algorithms Clustering algorithms Image edge detection Social network services Partitioning algorithms Sun Complexity theory Social network community detection fuzzy relation

来源：评论

学校读者我要写书评

暂无评论

A Community detection Method Based on Local Optimization in Social Networks

引用

IEEE NETWORK 2020年第4期34卷 42-48页

作者： Xu, Guangxia Wu, Xinkai Liu, Jun Liu, Yanbing Chongqing Univ Posts & Telecommun Chongqing Peoples R China Chongqing Univ Posts & Telecommun Software Engn Chongqing Peoples R China Chongqing Univ Posts & Telecommun Sch Software Engn Chongqing Peoples R China

Social networks are a kind of communal structure composed of many nodes according to different kinds of relationships. Community detection can help people understand the topology of a network and identify meaningful clusters. A large variety of community detection algorithms have been proposed. However, many of these algorithms are suitable for unweighted networks since they ignore the social properties of the links between nodes. Meanwhile, their discovery results may lead to the emergence of huge communities. Therefore, a weighted method and local community stability for social networks based on LFM is proposed in this article. This WSLFM algorithm uses a weighted method based on the social attributes of the link and the degree of common neighboring nodes to update the fitness function. It also introduces the concept of stability to control the expansion of local communities. The proposed WSLFM algorithm was tested and proved to be effective on a synthetic network and a real-world network for finding smaller and more meaningful clusters.

关键词： Social networking (online) Clustering algorithms Optimization detection algorithms Stability criteria Thermal stability

来源：评论

学校读者我要写书评

暂无评论

A Network Reduction-Based Multiobjective Evolutionary Algorithm for Community detection in Large-Scale Complex Networks

引用

IEEE TRANSACTIONS ON CYBERNETICS 2020年第2期50卷 703-716页

作者： Zhang, Xingyi Zhou, Kefei Pan, Hebin Zhang, Lei Zeng, Xiangxiang Jin, Yaochu Anhui Univ Sch Comp Sci & Technol Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei 230039 Peoples R China Xiamen Univ Dept Comp Sci Xiamen 361005 Peoples R China Univ Surrey Dept Comp Sci Guildford GU2 7XH Surrey England

Evolutionary algorithms have been demonstrated to be very competitive in the community detection for complex networks. They, however, show poor scalability to large-scale networks due to the exponential increase of search space. In this paper, we suggest a network reduction-based multiobjective evolutionary algorithm for community detection in large-scale networks, where the size of the networks is recursively reduced as the evolution proceeds. In each reduction of the network, the local communities found by the elite individuals in the population are identified as nodes of the reduced network for further evolution, thereby considerably reducing the search space. A local community repairing strategy is also suggested to correct the misidentified nodes after each network reduction during the evolution. Experimental results on synthetic and real-world networks demonstrate the superiority of the proposed algorithm over several state-of-the-art community detection algorithms for large-scale networks, in terms of both computational efficiency and detection performance.

关键词： Complex networks detection algorithms Optimization Feature extraction Evolutionary computation Density measurement Scalability Community detection complex network evolutionary algorithm large-scale network multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Lightweight detection Algorithm For Collision-Optimized Divide-and-Conquer Attacks

引用

IEEE TRANSACTIONS ON COMPUTERS 2020年第11期69卷 1694-1706页

作者： Ou, Changhai Lam, Siew-Kei Zhou, Chengju Jiang, Guiyuan Zhang, Fan Nanyang Technol Univ Sch Comp Sci & Engn Hardware & Embedded Syst Lab HESL Singapore 639798 Singapore Zhejiang Univ Coll Comp Sci & Technol Sch Cyber Sci & Technol Hangzhou 310027 Zhejiang Peoples R China Alibaba Zhejiang Univ Joint Inst Frontier Technol Hangzhou 310027 Zhejiang Peoples R China

By introducing collision information into divide-and-conquer attacks, several existing works transform the original candidate space, which may be too large to enumerate, into a significantly smaller collision space, thus making key recovery possible. However, the inefficient collision detection algorithms and fault tolerance mechanisms make them time-consuming and their success rate low. Moreover, they may still leave very huge chain spaces that makes it difficult for key recovery. In this article, we exploit collision attack to optimize Template Attack (TA), and propose a Lightweight Collision detection (LCD) algorithm. The proposed method exploits a jump detection mechanism to efficiently reduce the repetitive collision detections on chains with the same prefix sub-chains. We then introduce guessing theory to reorder the collision detection of the sub-keys according to their guessing lengths, and provide us with an evaluation tool. Finally, we design a highly efficient fault tolerance mechanism for our LCD to allow flexible thresholds adjustment, and further optimize sieving mechanism to efficiently extract the best chains with the largest number of collisions. Experimental results fully demonstrate LCD's superiority.

关键词： Liquid crystal displays Collision avoidance Fault tolerance Fault tolerant systems Cryptography Transforms detection algorithms Collision detection LCD collision attack template attack fault tolerance key enumeration side-channel attack

来源：评论

学校读者我要写书评

暂无评论

Development of a Low-Power Microcontroller-Based Wrist-Worn Device With Resource-Constrained Activity detection Algorithm

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2020年第10期69卷 7522-7529页

作者： Chowdhury, Debjyoti Chattopadhyay, Madhurima Heritage Inst Technol Dept Appl Elect & Instrumentat Engn Kolkata 700107 India

This article deals with the development of a resource-constrained activity detection algorithm for microcontroller-based wrist-worn devices. The various market available activity detection devices lack adequate agility and ease of use in certain applications, as they heavily rely upon computationally intensive algorithms to detect physical activity and step count. Therefore, by extension, they always need to stay connected with a smartphone that can perform these computations. To address this problem, this article introduces a standalone wearable device with the simplified algorithm for activity detection in a human being. The developed system consists of microelectromechanical systems (MEMS) triaxial accelerometer connected to a low-power microcontroller with a wrist anchor-able form factor. The step detection algorithm uses a moving average threshold filter to detect the change in acceleration data to identify specific events. A detailed comparative study considering power consumption and the step detection made between the developed device (with the resource-constrained algorithm) against market available devices shows that the average detection error of the developed algorithm is approximately 2% under various test conditions (i.e., walking, fast walking, and running) and has an accuracy of 94.96% for activity detection. This study reveals that the use of the proposed algorithm for activity detection not only brings down the cost of the overall device but also reduces the power consumption (< 45.7 mW) with a minimal covering size (12.56 cm(2)) for the wearable part that can extend the application area of such devices.

关键词： Accelerometers Micromechanical devices Acceleration detection algorithms Matlab Calibration Mathematical model Activity detection microelectromechanical systems (MEMS) accelerometer resource-constrained algorithm wearable device wrist-worn

来源：评论

学校读者我要写书评

暂无评论

Safeness-Based Community Penetration

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2021年第7期68卷 2690-2694页

作者： Yu, Zisheng Jiang, Zhongyuan Ma, Jianfeng Zheng, Yu Xidian Univ Sch Cyber Engn Xian 710071 Peoples R China JD Com JD Intelligent Cities Res Beijing 100176 Peoples R China JD Digits JD Intelligent Cities Business Unit Beijing 100176 Peoples R China

Automatic community divisions often facilitate the convenience of rich community applications such as interest group recommendations. However, it faces a serious community security issue referred to as community penetration (CommPen) such that the colluding attackers might very smartly deceive the community detection mechanism and infiltrate into one or more social communities to disclose the community privacy by perturbating a budget limited social links. From the attacker perspective, the CommPen aims to maximally disperse a group of colluding users into other communities escaping the detections with low cost, which is very challenging in problem formulation, attack model building, and optimal solution. In this brief, we first introduce the CommPen problem against community detection, which has not been extensively focused on so far. Secondly, we formalize the CommPen as an optimization problem, which is a combination explosion problem. Thirdly, an efficient algorithm based on multi simulated annealing (MSA) is proposed to solve this problem by rewiring a small number of connections, leading to privacy protection. Finally, community penetration on real-world networks is conducted in experiments, which shows that our proposed method outperforms baselines, including Random Selection, Greedy Search, and Genetic Algorithm.

关键词： Image edge detection detection algorithms Circuits and systems Privacy Simulated annealing Optimization Topology Community detection community penetration multi simulated annealing privacy protection

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：