检索结果-内蒙古大学图书馆

11th International Conference on computer Engineering and Networks, CENet2021

作者： Wang, Ruonan Gu, Yu Zhou, Zou Wang, Zhehao Xu, Fangwen Luo, Jian Ma, Lulu Qiu, Hongbing Provincial Ministry of Education Key Laboratory of Cognitive Radio and Information Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9789811665530

With three advantages of information sharing, system survival, and cost-effective exchange, Unmanned Aerial Vehicle (UAV) swarms can perform tasks at risk, such as emitter reconnaissance and positioning. Due to high risk, it’s impossible to maintain the expected effect of inter-individual cooperation among an UAV swarm. The loss of positioning UAVs and the spatiotemporal agility of a target model will also reduce the accuracy in positioning the target. Therefore, the reasonable and effective dynamic assignment of emitter reconnaissance and confrontation tasks has also become one new challenge. This paper proposes a dynamic swarm task assignment strategy to solve the above problem. For emitter reconnaissance and positioning, we study the multi-target cooperation among an UAV swarm, and take UAV relative position structure into consideration. This strategy uses the unique role conversion of the artificial bee colony algorithm to assign tasks. We also constructed a joint optimization model based on range difference and the Cramer-Rao Lower Bound with time, space and target adaptability. When the original flight trajectory does not change, the self-organizing and cooperative swarm can optimize positioning formation clustering. Simulation results show that this strategy can quickly achieve higher positioning accuracy and lower energy consumption with UAV loss rate of 8%. After 5 dynamic task assignments, the Root Mean Square Error is less than 50 m. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Rotation-DPeak: Improving Density Peaks Selection for Imbalanced Data 1

引用

8th China computer Federation International Conference on Big Data, CCF BIGDATA 2020

作者： Hu, Xiaoliang Yan, Ming Chen, Yewang Yang, Lijie Du, Jixiang The College of Computer Science and Technology Huaqiao University Xiamen China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China

ISBN: (数字)9789811607059

ISBN: (纸本)9789811607042

Density Peak (DPeak) is an effective clustering algorithm. It maps arbitrary dimensional data onto a 2-dimensional space, which yields cluster centers and outliers automatically distribute on upper right and upper left corner, respectively. However, DPeak is not suitable for imbalanced data set with large difference in density, where sparse clusters are usually not identified. Hence, an improved DPeak, namely Rotation-DPeak, is proposed to overcome this drawback according to an simple idea: the higher density of a point p, the larger δ it should have such that p can be picked as a density peak, where δ is the distance from p to its nearest neighbor with higher density. Then, we use a quadratic curve to select points with the largest decision gap as density peaks, instead of choosing points with the largest γ, where γ= ρ× δ. Experiments shows that the proposed algorithm obtains better performance on imbalanced data set, which proves that it is promising. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Multi-station Signal Sorting Method Based on Time Difference Pair and Azimuth information 12th

A Multi-station Signal Sorting Method Based on Time Differen...

引用

12th International Conference on computer Engineering and Networks, CENet 2022

作者： Xiang, Zhexi Zhou, Zou Gu, Yu Bai, Xiao Liang, Caisheng Provincial Ministry of Education Key Laboratory of Cognitive Radio and Information Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9789811969003

Current sorting methods based on time difference of arrival (TDOA) can not concurrently realize the high sorting accuracy and low computational complexity with pulse loss and interference. This paper proposes a multi-station signal sorting method based on time difference pair and azimuth information. Firstly, the time difference window is introduced to determine the pulse range in which the pulse may be correctly matched with the pulse in the selected master station. According to the multi-parameters information, pulses in the range are accurately matched to get the real pulse pair and the time difference pair. Finally, the received signals are sorted by the time difference pair and azimuth information within the error tolerance. The simulation results show that the proposed method can effectively sort the interleaved signals with the pulse loss, interference, and the received pulses with few numbers. Furthermore, the computational complexity of the proposed method is greatly reduced. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Time difference of arrival

来源：评论

学校读者我要写书评

暂无评论

EPI-Mamba: State Space Model for Semantic Segmentation from Light Fields

EPI-Mamba: State Space Model for Semantic Segmentation from ...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yan Li Jianan Chen Qiong Wang Jinshan Xu College of Computer Science & Technology Zhejiang University of Technology Hangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Global contextual dependency is of significance for semantic segmentation from light fields. However, previous works mostly exploit attention mechanisms to model spatial context dependency and angular context dependency separately, since a light field capture is very data-intensive. Considering that self-attention is resource-consuming, existing methods only use it to capture spatial contextual dependency for the central view of light fields, and employ resource-efficient attention mechanisms to model angular view dependencies instead. Inspired by the recent success of State Space Sequence model (SSM), we present a novel SSM-based encoder for light field semantic segmentation, which models spatio-angular contextual dependency together. The proposed method is evaluated on the existing light field semantic segmentation datasets, and experimental results show that the proposed method significantly outperforms previous state-of-the-art methods. The code and models used in this work are available in https://***/YanWQ/EPI-Mamba

关键词： Geometry Attention mechanisms Codes Semantic segmentation Semantics Signal processing Light fields Acoustics Speech processing Context modeling

来源：评论

学校读者我要写书评

暂无评论

A New Image Encryption Strategy Based on Arnold Transformation and Logistic Map 11th

A New Image Encryption Strategy Based on Arnold Transformati...

引用

11th International Conference on computer Engineering and Networks, CENet2021

作者： Sun, Xiyu Chen, Zhong College of Computer Science and Technology Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

ISBN: (纸本)9789811665530

Aiming at the problem of digital image encryption, an image encryption algorithm is proposed. The algorithm is divided into preparation stage and permutation diffusion stage. In the preparation stage, Arnold algorithm is improved and combined with Logistic chaotic map to generate the necessary sequence for the next stage. In the permutation diffusion stage, the final encrypted image is obtained by permutation, positive XOR operation, shift operation, S-box substitution and reverse XOR operation. The experimental results show that the algorithm can effectively resist the common attacks. For the 128 × 128 Lena gray image, the resistance performance number of pixel change rate (NPCR) is 99.6090, unified average changing intensity (UACI) is 33.4316. In addition, the time consumption of the algorithm is about 0.0055 s, and the experiments show that the algorithm has high security and real-time performance. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

A Radar Working Mode Recognition Algorithm with Approximate Coherent Metric and Multi-Agent PSR Model 12th

A Radar Working Mode Recognition Algorithm with Approximate ...

引用

12th International Conference on computer Engineering and Networks, CENet 2022

作者： Zhou, Zou Fei, Wenhao Zheng, Fei Luo, Jian Provincial Ministry of Education Key Laboratory of Cognitive Radio and Information Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9789811969003

Multifunctional radar(MFR) has non-cooperative, narrow beam, and flexible agile characteristics. The traditional radar feature parameters and syntactic modeling methods are difficult to make the information of radar working mode recognition complete and noise separation. The classical prediction state representation(PSR) model constructs a dynamic transition probability matrix by extracting temporal features. To achieve the mode estimation of radar transfer behavior, the probability distribution under each mode is calculated by the filter algorithm. However, the method is difficult to implement in actual confrontation scenarios because of the need to train numerous pulses. In this study, distributed sensors such as UAV clusters can effectively improve the incomplete information acquisition by the wide-area coverage sampling. The approximation coherent metric at the feature level is introduced, and propose a collective representation method of multi-agent perceptual data. This method achieves noise and dimensionality reduction while ensuring information integrity. For each mode of working, the probability distribution is obtained by training the PSR model using the collective representation information, and grid filter to track its dynamics. Determination of the mode is done by the maximum a posteriori estimator. The simulation results show that the proposed method has a good recognition effect. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

A new S-box construction method meeting strict avalanche criterion

A new S-box construction method meeting strict avalanche cri...

引用

作者： Li, Lang Liu, Jinggen Guo, Ying Liu, Botao College of Computer Science and Technology Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

S-box is the main security component in lightweight block ciphers. Finding new algorithms and technical applications to generate S-box is still a current research topic. We proposed an S-box construction method that satisfies the strict avalanche criterion. It includes a nonlinear layer and a diffusion layer. These layers enable the constructed S-box to maintain good nonlinearity, differential uniformity, strict avalanche criterion, and a high number of algebraic terms. Secondly, we listed 20 existing classic 4 × 4 S-boxes and tested their cryptographic properties such as nonlinearity, difference uniformity, strict avalanche criterion, algebraic degree, algebraic item number, and fixed point. At the same time, the test results are compared with the proposed S-box. The results show that these cryptographic properties of our proposed S-box are superior to other S-boxes. In addition, we evaluated the proposed S-box hardware implementation overhead. To evaluate our S-box more objectively, we tested the above 20 S-boxes hardware implementation overhead under the same conditions, and the results show that the S-box we constructed achieved a good balance between cryptographic properties and hardware overhead. © 2022 Elsevier Ltd

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Hyperchaotic Image Encryption Algorithm Based on BD-Zigzag Transformation and DNA Coding 12th

Hyperchaotic Image Encryption Algorithm Based on BD-Zigzag T...

引用

12th International Conference on computer Engineering and Networks, CENet 2022

作者： Wang, Lujie Chen, Zhong College of Computer Science and Technology Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

ISBN: (纸本)9789811969003

For the features of Zigzag transformation, a Bidirectional Deformed Zigzag (BD-Zigzag) transformation is proposed in this paper, which starts from both sides of the diagonal and crosses in both directions. This method is more complex than the traditional Zigzag transformation method and has better dislocation effect. Then, a Hyperchaotic image encryption algorithm based on BD-Zigzag transformation and DNA coding is proposed. First, the images are processed with multiple rounds of permutations using the BD-Zigzag transformation. Second, a 4D-hyperchaotic Lorenz system is used to produce random numbers to permute the images at the bit level. Finally, DNA encoding is used to diffuse the pixels in the image. The experimental simulations and performance analysis data can prove that the encryption algorithm has high-level security capability. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

A robust and automatic method for the recognition of speech category in online learning discourse

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第12期15卷 3913-3924页

作者： Jiang, Dazhi He, Zhihui Chen, Yifei Xu, Linyan Lin, Jiali Guangdong Provincial Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510399 China Department of Computer Science Shantou University Shantou515063 China Department of Management Economics and Industrial Engineering Politecnico di Milano MI Milan20156 Italy School of Business Shantou University Shantou515063 China

It is a rapid and irresistible developing trend that the traditional classroom learning mode is transformed into an online learning mode. In the online learning process, it is important to achieve effective voice separation and provide a good lecture experience for students. In this paper, a robust and automatic method for the recognition of speech categories (teacher speech, student speech, silence speech and overlapping speech) is presented. The system, which is part of artificial intelligence in education (AIED), is a hybrid speech processing system that includes GMM modeling, GMM clustering, silence processing and overlapping processing. The online learning environment we are based on is not a customized environment that defines the roles of teachers or students, but a more casual, broader and more general online environment. The method proposed and designed based on this situation has better adaptability and scalability. The experimental results show that our automatic detection of speech categories fares well when compared to the results from professional coders. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A New Encryption Scheme Based on RSA Encryption Algorithm and Chen Chaotic System 12th

A New Encryption Scheme Based on RSA Encryption Algorithm an...

引用

12th International Conference on computer Engineering and Networks, CENet 2022

作者： He, Chenchen Chen, Zhong College of Computer Science and Technology Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

ISBN: (纸本)9789811969003

Nowadays the security of images is obviously more important. Some scholars have applied Rivest-Shamir-Adleman (RSA) algorithm and Chen chaotic system to image encryption. However, the application of the two methods in image encryption can still be explored. In this paper, it proposes an encryption scheme which uses asymmetric cipher RSA encryption algorithm and Chen chaotic system to scramble and diffuse the image. In this encryption scheme, firstly, it applies the RSA algorithm to obtain the public key and uses the specified formula to calculate the initial value of the Chen chaotic system. Secondly, the four chaotic sequences generated by Chen chaotic system are applied to the scrambling stage and the diffusion stage of the image process respectively. In the scrambling phase, it uses Arnold scrambling. It performs forward XOR diffusion and then performs reverse XOR diffusion in the diffusion stage. Finally, the encryption process is all completed and the encrypted image is obtained. Moreover, after appropriate experiments, the encryption algorithm is proved to have a good guarantee for the security of the image. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diffusion

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：