检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Huang, Yangpeng Feng, Naixing Cai, Yijun Smart Sensing Integrated Circuit Engineering Research Center of Universities in Fujian Province Xiamen University of Technology Xiamen361000 China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei230601 China

It is well known that the inverse design of terahertz (THz) multi-resonant graphene metasurfaces by using traditional deep neural networks (DNNs) has limited generalization ability. In this paper, we propose improved Transformer and conditional generative adversarial neural networks (CGAN) for the inverse design of graphene metasurfaces based upon THz multi-resonant absorption spectra. The improved Transformer can obtain higher accuracy and generalization performance in the StoV (Spectrum to Vector) design compared to traditional multilayer perceptron (MLP) neural networks, while the StoI (Spectrum to Image) design achieved through CGAN can provide more comprehensive information and higher accuracy than the StoV design obtained by MLP. Moreover, the improved CGAN can achieve the inverse design of graphene metasurface images directly from the desired multi-resonant absorption spectra. It is turned out that this work can finish facilitating the design process of artificial intelligence-generated metasurfaces (AIGM), and even provide a useful guide for developing complex THz metasurfaces based on 2D materials using generative neural networks. Copyright © 2023, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Critical Node Detection for Sequential Attacks in Complex Networks via Multi-objective Optimization 2

Critical Node Detection for Sequential Attacks in Complex Ne...

引用

2nd International Conference on Industrial Artificial Intelligence, IAI 2020

作者： Zhang, Lei Liu, Qing Xia, Jiajun Yang, Haipeng Zhang, Xingyi Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University China

ISBN: (纸本)9781728182162

The critical node detection for sequential attacks based on cascading failure model is an important way for analyzing network vulnerability, which has attracted the attention of many researchers in the field of complex network recently. However, most of the existing cascading critical node detection algorithms focus on designing effective attack strategies leading to the maximal damage to the network (i.e. attack effect), while ignoring the cost of attacks. To this end, we transform the cascading critical node detection for sequential attacks as a bi-objective optimization problem (named BCVNDSeq), where the attack cost and the attack effect are simultaneously optimized. In order to solve the transformed problem, we propose a multiobjective cascading critical node detection algorithm (named MO-BCVNDSeq), which can provide decision makers with a holistic view for analyzing the network vulnerability. In MO-BCVNDSeq, a local search strategy based on sequential matrix is proposed to accelerate the population convergence and an individual repairing strategy is also suggested to further improve the search efficiency. Finally, the experimental results on 6 real-world complex networks demonstrate the effectiveness of the proposed algorithm compared with several representative baselines. © 2020 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Data Fusion Based on Temporal-Spatial Composite Sequential Three-Way Decision

SSRN

引用

SSRN 2022年

作者： Xu, Yi Qiu, Ziheng Sun, Xiaojun Department of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China

Three-way decision is the representative of trisecting-acting-outcome(TAO) model. Considering the temporality, in dynamic information systems, the objects may be inserted or deleted,attributes may be added or removed, and attributes values may be updated or modified. These variations can be reflected by the TAO model, which cares about consideration at different levels, acquisition of strategies, and handling of issues based on Strategies. Considering the spatiality, different levels, and different perspectives of granular structure are created by the sequential approach of three-way decision. In this paper, in order to fuse hybrid data, a sequential three-way decision is proposed by the combination of temporality and spatiality. Firstly, We present the frameworks of spatiality-based and temporality-based and focus on temporal-spatial three-way decision. Then we provide three operations to construct the composite POS structure by combining a family of approximations. Based on the composite POS structure, three different strategies for the fusion of dynamic hybrid data are adopted. Finally, we design the algorithm and implement a series of comparison experiments to verify our model is effective. © 2022, The Authors. All rights reserved.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

On -additive polycyclic codes and their Gray images

引用

Designs, Codes and Cryptography 2021年第11期90卷 2551-2562页

作者： Wu, Rongsheng Shi, Minjia Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei P.R. China

In this paper, we first generalize the polycyclic codes over finite fields to polycyclic codes over the mixed alphabet $$\mathbb {Z}_2\mathbb {Z}_4$$ , and we show that these codes can be identified as $$\mathbb {Z}_4[x]$$ -submodules of $$\mathcal {R}_{\alpha ,\beta }$$ with $$\mathcal {R}_{\alpha ,\beta }=\mathbb {Z}_2[x]/\langle t_1(x)\rangle \times \mathbb {Z}_4[x]/\langle t_2(x)\rangle $$ , where $$t_1(x)$$ and $$t_2(x)$$ are monic polynomials over $$\mathbb {Z}_2$$ and $$\mathbb {Z}_4$$ , respectively. Then we provide the generator polynomials and minimal generating sets for this family of codes based on the strong Gröbner basis. In particular, under the proper defined inner product, we study the dual of $$\mathbb {Z}_2\mathbb {Z}_4$$ -additive polycyclic codes. Finally, we focus on the characterization of the $$\mathbb {Z}_2\mathbb {Z}_4$$ -MDSS and MDSR codes, and as examples, we also present some (almost) optimal binary codes derived from the $$\mathbb {Z}_2\mathbb {Z}_4$$ -additive polycyclic codes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method to Verify Internal Parameters of Camera Calibration in World Coordinate System

A Method to Verify Internal Parameters of Camera Calibration...

引用

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Zheng Xing Qingchun Wang Yingsong Li Junwei Qi College of Information and Communication Engineering Harbin Engineering University Harbin China Shanghai Yanding Information Technology Co. Ltd. Shanghai China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

Aiming at the problem that reprojection error (RE) cannot reflect the camera calibration accuracy intuitively, this paper proposes a method to verify the camera calibration results in world coordinate system. Firstly, the checkerboard calibration target is photographed with the camera under test, and the internal parameters and distortion parameters of the camera are calculated by using the pinhole model and the Kannala-Brandt (KB) fisheye model, respectively. Then, the same camera is used to shoot two targets in the field of view (FOV), and the pixel coordinates of the two target points are detected from the image. Thirdly, the inverse projection model is used to calculate the distance between the two objects and the angle between the camera and the two objects, and the real distance and angle are compared. The experimental results show that the average distance errors of the pinhole model and the KB fisheye model are 0.34% and 0.35%, respectively, and the angle errors are 0.40% and 0.12%, respectively, which proves that the verification method can effectively characterize the calibration accuracy of the camera.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens

arXiv

引用

arXiv 2024年

作者： Sun, Dengdi Pan, Yajie Lu, Andong Li, Chenglong Luo, Bin The Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education School of Artificial Intelligence Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230026 China The Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Many RGBT tracking researches primarily focus on modal fusion design, while overlooking the effective handling of target appearance changes. While some approaches have introduced historical frames or fuse and replace initial templates to incorporate temporal information, they have the risk of disrupting the original target appearance and accumulating errors over time. To alleviate these limitations, we propose a novel Transformer RGBT tracking approach, which mixes spatio-temporal multimodal tokens from the static multimodal templates and multimodal search regions in Transformer to handle target appearance changes, for robust RGBT tracking. We introduce independent dynamic template tokens to interact with the search region, embedding temporal information to address appearance changes, while also retaining the involvement of the initial static template tokens in the joint feature extraction process to ensure the preservation of the original reliable target appearance information that prevent deviations from the target appearance caused by traditional temporal updates. We also use attention mechanisms to enhance the target features of multimodal template tokens by incorporating supplementary modal cues, and make the multimodal search region tokens interact with multimodal dynamic template tokens via attention mechanisms, which facilitates the conveyance of multimodal-enhanced target change information. Our module is inserted into the transformer backbone network and inherits joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three RGBT benchmark datasets show that the proposed approach maintains competitive performance compared to other state-of-the-art tracking algorithms while running at 39.1 FPS. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improved Uniform Linear Array Fitting Scheme with Increased Lower Bound on Uniform Degrees of Freedom for DOA Estimation

TechRxiv

引用

TechRxiv 2022年

作者： Shi, Wanlu Li, Yingsong The College of Information and Communication Engineering Harbin Engineering University Harbin150001 China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei China

Recently, uniform linear array (ULA) fitting (UF) principle is proposed for sparse array (SA) design using pseudo-polynomial equations. Typically, it is verified that the designed SAs via UF enjoy a lower bound on uniform degrees of freedom (uDOF), which is approximately 0.5N2 with N sensors. Herein, an improved UF (IUF) scheme is proposed to significantly increase the lower bound on uDOF, which is realized by introducing two sub-ULAs, with name of adjoint transfer arrays (ATAs), on both sides of a transfer sub-ULA. The ATAs together with the transfer sub-ULA serve as a new layer to construct an adjoint transfer layer (ATL) that has improved aperture in comparison with traditional transfer layer to improve the lower bound on uDOF, which is derived in detail. Furthermore, two novel SAs are developed based on the ATL to verify the effectiveness of the proposed IUF scheme to increase the uDOF. Numerical simulations verify the superiority of devised SAs for direction-of-arrival (DOA) estimations. © 2022, CC BY.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Compact Broadband Rectifier With Wide Input Power Range Based on Adaptive Input Power Distribution

TechRxiv

引用

TechRxiv 2022年

作者： Liu, Xin Li, Yingsong Zhang, Dawei College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei China

This paper presents a novel compact rectifier array with both broadband and wide input power range characteristics. The rectifier array consists of two rectifier units operating at low-power and high-power levels, respectively, and an adaptive input power distribution network (AIPDN) enabling automatic distribution of radio frequency (RF) energy at different power levels. In addition, a matching inductance is introduced to counteract the capacitance of the diode. As a result, the high RF-DC power conversion efficiency (PCE) is achieved in both broadband and wide input power range. For demonstration, a prototype of the presented rectifier array is fabricated and measured. The measured results are in good accordance with the simulated results. With an input power range of 8 – 25 dBm and a bandwidth of 1.82 – 2.75 GHz (fractional bandwidth of 40.7%), the PCE is greater than 50%. At 2.4 GHz, the input power ranges from -5.5 to 27.5 dBm with PCE greater than 50%. Besides, a peak PCE of 72.1% is obtained at an input power of 25 dBm. This work can lay the foundation for the development of a new RF energy harvest systems with wide frequency band and dynamic input power. © 2022, CC BY.

关键词： Horn antennas

来源：评论

学校读者我要写书评

暂无评论

Transient Convergence Analysis of Least Lncosh Algorithm

TechRxiv

引用

TechRxiv 2022年

作者： Sun, Zeyang Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Anhui Hefei China

Lncosh function has been used for constructing a cost function for devising an adaptive filter algorithm to provide a desired performance under non-Gaussian noise, naming as least Lncosh algorithm (LLA). However, its transient behavior analysis has not been analyzed and investigated. As an important characteristic for the LLA, the transient behavior affects its performance in real-world applications. Herein, we present the theoretical model for evaluating the mean weight behavior and the transient excess mean square error (EMSE) behavior of the LLA. In addition, the proposed models can also be used to predict the transient behavior of the adaptive filtering algorithms with error nonlinearities under non-Gaussian noises. The experiment results have verified the validity of the presented models. © 2022, CC BY.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

A Joint Learning Sentiment Analysis Method Incorporating Emoji-Augmentation

A Joint Learning Sentiment Analysis Method Incorporating Emo...

引用

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Jie Chen Luping Luo Bojing Ji Shu Zhao Yanping Zhang The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University China School of Big Data and Artificial Intelligence Chizhou University China

ISBN: (纸本)9781665456579

Social media is the platform for most people to share their opinions, emojis are also widely used to express moods, emotions, and feelings on social media. There have been many researched on emojis and sentiment analysis. However, existing methods mainly face two limitations. First, since deep learning relies on large amounts of labeled data, the training samples of emoji are not enough to achieve the training effect. Second, they consider the sentiment of emojis and texts separately, not fully exploring the impact of emojis on the sentiment polarity of texts. In this paper, we propose a joint learning sentiment analysis method incorporating emoji-augmentation, and the method has two advantages compared with the existing work. First, We optimize the easy data augmentation method so that the newly generated sentences can also preserve the semantic information of emojis, which relieves the problem of insufficient training data with emojis. Second, it fuses emojis and text features to allow the model to better learn the mutual emotional semantics between text and emojis, jointly training emojis and words to obtain the sentence representations containing more semantic information of both emojis and text. Our experimental results show that the proposed method can significantly improve the performance compared with several baselines on two datasets.

关键词： Training Sentiment analysis Social networking (online) Fuses Text recognition Mood Semantics

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：