检索结果-南通市图书馆

Novel multi-objective optimization algorithm

在线全文

学校读者我要写书评

暂无评论

系统工程与电子技术：英文版 2014年第4期25卷 697-710页

作者： Jie Zeng Wei Nie College of information Engineering Shenzhen University Modern Communication and information processing key laboratory Shenzhen University

Many multi-objective evolutionary algorithms(MOEAs)can converge to the Pareto optimal front and work well on two or three objectives, but they deteriorate when faced with manyobjective problems. Indicator-based MOEAs, which adopt various indicators to evaluate the fitness values(instead of the Paretodominance relation to select candidate solutions), have been regarded as promising schemes that yield more satisfactory results than well-known algorithms, such as non-dominated sorting genetic algorithm(NSGA-II) and strength Pareto evolutionary algorithm(SPEA2). However, they can suffer from having a slow convergence speed. This paper proposes a new indicatorbased multi-objective optimization algorithm, namely, the multiobjective shuffled frog leaping algorithm based on the ε indicator(ε-MOSFLA). This algorithm adopts a memetic meta-heuristic,namely, the SFLA, which is characterized by the powerful capability of global search and quick convergence as an evolutionary strategy and a simple and effective ε-indicator as a fitness assignment scheme to conduct the search procedure. Experimental results, in comparison with other representative indicator-based MOEAs and traditional Pareto-based MOEAs on several standard test problems with up to 50 objectives, show that ε-MOSFLA is the best algorithm for solving many-objective optimization problems in terms of the solution quality as well as the speed of convergence.

关键词： evolutionary algorithm multi-objective optimization shuffled frog leaping algorithm(SFLA) convergence

Text Detection in Natural Scene Images Using Morphological Component Analysis and Laplacian Dictionary

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 214-222页

作者： Shuping Liu Yantuan Xian Huafeng Li Zhengtao Yu School of information Engineering and Automation and key laboratory of Intelligent information processing Kunming University of Science and Technology

Text in natural scene images usually carries abundant semantic information. However, due to variations of text and complexity of background, detecting text in scene images becomes a critical and challenging task. In this paper, we present a novel method to detect text from scene images. Firstly, we decompose scene images into background and text components using morphological component analysis(MCA), which will reduce the adverse effects of complex backgrounds on the detection *** order to improve the performance of image decomposition,two discriminative dictionaries of background and text are learned from the training samples. Moreover, Laplacian sparse regularization is introduced into our proposed dictionary learning method which improves discrimination of dictionary. Based on the text dictionary and the sparse-representation coefficients of text, we can construct the text component. After that, the text in the query image can be detected by applying certain heuristic rules. The results of experiments show the effectiveness of the proposed method.

关键词： Dictionary learning Laplacian sparse regularization morphological component analysis(MCA) sparse representation text detection

Periodic radio variability in NRAO 530:phase dispersion minimization analysis

在线全文

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2012年第6期12卷 643-650页

作者： Jun-Chao Lu Jun-Yi Wang Tao An Ji-Ming Lin Hong-Bing Qiu key laboratory of cognitive radio&information processing the Ministry of EducationGuilinUniversity of Electronic TechnologyGuilin 541004China School of Mathematics and Computational Science Xiangtan UniversityXiangtan 411105China Shanghai Astronomical Observatory Chinese Academy of SciencesShanghai 200030China key laboratory of radio Astronomy Chinese Academy of SciencesNanjing 210008China

A periodicity analysis of the radio light curves of the blazar NRAO 530 at 14.5, 8.0, and 4.8 GHz is presented employing an improved phase dispersion mini- mization technique. The result, which shows two persistent periodic components of 6 and ~ 10 yr at all three frequencies, is consistent with the results obtained with the Lomb-Scargle periodogram and weighted wavelet Z-transform algorithms. The reliability of the derived periodicities is confirmed by the Monte Carlo numerical sim- ulations which show a high statistical confidence. （Quasi-）Periodic fluctuations of the radio luminosity of NRAO 530 might be associated with the oscillations of the accre- tion disk triggered by hydrodynamic instabilities of the accreted flow.

关键词： methods: statistical -- galaxies: active -- galaxies: quasar: individual:NRAO 530

More relaxed condition for dynamics of discrete time delayed Hopfield neural networks

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2008年第1期17卷 125-128页

作者：张强 Liaoning key laboratory of Intelligent information processing Dalian University

The dynamics of discrete time delayed Hopfield neural networks is investigated. By using a difference inequality combining with the linear matrix inequality, a sufficient condition ensuring global exponential stability of the unique equilibrium point of the networks is found. The result obtained holds not only for constant delay but also for time-varying delays.

关键词： discrete time delayed Hopfield neural networks difference inequality

Phrase-based hashtag recommendation for microblog posts

在线全文

学校读者我要写书评

暂无评论

Science China(information Sciences) 2017年第1期60卷 132-144页

作者： Yeyun GONG Qi ZHANG Xiaoying HAN Xuanjing HUANG Shanghai key laboratory of Intelligent information processing School of Computer Science Fudan University

In microblogs, authors use hashtags to mark keywords or topics. These manually labeled tags can be used to benefit various live social media applications(e.g., microblog retrieval, classification). However,because only a small portion of microblogs contain hashtags, recommending hashtags for use in microblogs are a worthwhile exercise. In addition, human inference often relies on the intrinsic grouping of words into ***, existing work uses only unigrams to model corpora. In this work, we propose a novel phrase-based topical translation model to address this problem. We use the bag-of-phrases model to better capture the underlying topics of posted microblogs. We regard the phrases and hashtags in a microblog as two different languages that are talking about the same thing. Thus, the hashtag recommendation task can be viewed as a translation process from phrases to hashtags. To handle the topical information of microblogs, the proposed model regards translation probability as being topic specific. We test the methods on data collected from realworld microblogging services. The results demonstrate that the proposed method outperforms state-of-the-art methods that use the unigram model.

关键词： recommendation topic model translation phrase extraction hashtag

A novel DEM reconstruction strategy based on multi-frequency In SAR in highly sloped terrain

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2017年第8期60卷 243-245页

作者： Tao ZENG Tiandong LIU Zegang DING Qi ZHANG Zhen WANG Teng LONG Beijing key laboratory of Embedded Real-time information processing Technology Beijing Institute of Technology

Interferometric Synthetic Aperture Radar(InSAR)has been proposed as a technique for the reconstruction of the Digital Elevation Model(DEM),which is widely used in global terrain mapping mission[1].The DEM reconstruction methods of In SAR technique are usually based on the so-called phase unwrapping(PU)*** highly sloped terrain,the interferometric phase gradients(IPG)of the adjacent pixels are more thanπ.Therefore,the traditional PU methods

关键词： SAR In of DEM IPG on Figure LAPS A novel DEM reconstruction strategy based on multi-frequency In SAR in highly sloped terrain

Lightweight Object Detection Networks for UAV Aerial Images Based on YOLO

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第4期33卷 997-1009页

作者： Yanshan LI Jiarong WANG Kunhua ZHANG Jiawei YI Miaomiao WEI Lirong ZHENG Weixin XIE ATR National key laboratory of Defense Technology Shenzhen University Guangdong key laboratory of Intelligent information processing Shenzhen University

Existing high-precision object detection algorithms for UAV(unmanned aerial vehicle) aerial images often have a large number of parameters and heavy weight, which makes it difficult to be applied to mobile *** propose three YOLO-based lightweight object detection networks for UAVs, named YOLO-L, YOLO-S, and YOLO-M, respectively. In YOLO-L, we adopt a deconvolution approach to explore suitable upsampling rules during training to improve the detection accuracy. The convolution-batch normalization-Si LU activation function(CBS)structure is replaced with Ghost CBS to reduce the number of parameters and weight, meanwhile Maxpool maximum pooling operation is proposed to replace the CBS structure to avoid generating parameters and weight. YOLO-S greatly reduces the weight of the network by directly introducing CSPGhost Neck residual structures, so that the parameters and weight are respectively decreased by about 15% at the expense of 2.4% mAP. And YOLO-M adopts the CSPGhost Neck residual structure and deconvolution to reduce parameters by 5.6% and weight by 5.7%, while m AP only by 1.8%. The results show that the three lightweight detection networks proposed in this paper have good performance in UAV aerial image object detection task.

关键词： Training YOLO Deconvolution Accuracy Object detection Autonomous aerial vehicles Feature extraction

Secrecy outage analysis for underlay cognitive radio networks over correlated channels

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2017年第2期60卷 107-115页

作者： Jiliang ZHANG Hui ZHAO Gaofeng PAN Chongqing key laboratory of Nonlinear Circuits and Intelligent information processing School of Electronic and Information Engineering Southwest University

This paper investigates the secrecy outage performance of underlay cognitive radio networks, in which a source in a secondary system transmits its confidential information to a legitimate destination in the presence of an eavesdropper. Specifically, the main(the source-to-destination) and eavesdropping(the sourceto-eavesdropper) channels are assumed to be correlated. Moreover, it is also assumed that the main channel and the channel from the source to the primary user's receiver are correlated. Tight closed-form analytical expression for secrecy outage probability and the closed-form analytical expression for the probability of non-zero secrecy capacity are derived and validated by simulation results when the interference temperature limit is comparably large.

关键词： cognitive radio networks correlated fading channels probability of non-zero secrecy capacity secrecy outage probability

Face Liveness Detection Based on the Improved CNN with Context and Texture information

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第6期28卷 1092-1098页

作者： GAO Chenqiang LI Xindou ZHOU Fengshun MU Song School of Communication and information Engineering Chongqing University of Posts and Telecommunications Chongqing key laboratory of Signal and information processing

Face liveness detection, as a key module of real face recognition systems, is to distinguish a fake face from a real one. In this paper, we propose an improved Convolutional neural network(CNN) architecture with two bypass connections to simultaneously utilize low-level detailed information and high-level semantic *** the importance of the texture information for describing face images, texture features are also adopted under the conventional recognition framework of Support vector machine(SVM). The improved CNN and the texture feature based SVM are fused. Context information which is usually neglected by existing methods is well utilized in this paper. Two widely used datasets are used to test the proposed method. Extensive experiments show that our method outperforms the state-of-the-art methods.

关键词： Face liveness detection Deep learning Context information Texture information