检索结果-内蒙古大学图书馆

7th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2024

作者： Xu, Xingchao Pang, Baohe Li, Yingsong Li, Liping Zou, Dingcheng Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Innopolis University Faculty of Computer and Engineering Sciences Innopolis Russia

ISBN: (纸本)9798350384437

In addressing the issue of localizing near-field source signals in the presence of impulse noise, this manuscript introduces a novel de-impact function designed for preprocessing received signals to alleviate the interference caused by impulse noise. Simulation experiments verify the effectiveness of the proposed de-impact function in effectively suppressing impulse noise. Furthermore, to augment estimation precision, a novel algorithm for near-field source localization is proposed. Building upon the framework of correlation entropy theory, a new correntropy covariance matrix is formulated to replace the original signal covariance matrix for signal processing. Through a succession of low-bias approximations between near-field and far-field scenarios, the algorithm converts the original 2-D search into 1-D operations. Additionally, the conventional spectral peak search is replaced by polynomial solving to further mitigate the computational complexity of the algorithm. © 2024 IEEE.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

Low Coupling Sparse Array Based on Uniform Linear Array Fitting Method 7

Low Coupling Sparse Array Based on Uniform Linear Array Fitt...

引用

7th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2024

作者： Yao, Yichang Li, Yingsong Li, Liping Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Innopolis University Faculty of Computer and Engineering Sciences Innopolis Russia

ISBN: (纸本)9798350384437

In order to solve the problem that traditional sparse arrays only emphasize high degrees of freedom and ignore low coupling, uniform array fitting method can design arrays with low coupling. However, the existing array coupling based on uniform array fitting method still has room for decline, and the value of weight function is not the minimum, so the performance of array DOA estimation needs to be further optimized. Therefore, based on the uniform matrix fitting method, a uniform matrix fitting 6-base-layer array is designed. By extending the spacing of each subarray of the uniform subarray in the base layer, the number of small array element spacing pairs in the differential cooperative array is reduced, and the coupling between the elements of the whole sparse array is reduced as a whole. The performance of DOA estimation of the designed array is simulated and analyzed by using spatial smoothing multiple signal classification algorithm. © 2024 IEEE.

关键词： Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

CSCL-DTI: Predicting drug-target interaction through cross-view and self-supervised contrastive learning

CSCL-DTI: Predicting drug-target interaction through cross-v...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xuan Zhang, Xi Yu, Zu-Guo Long, Yahui Zeng, Xiangxiang Yu, Philip S. Xiangtan University College of Computer Science China Xiangtan University Key Laboratory of Intelligent Computing and Information Processing Ministry of Education China Singapore Hunan University College of Information Science and Engineering China University of Illinois Chicago Department of Computer Science United States

ISBN: (纸本)9798350386226

Accurately predicting drug-target interactions (DTI) is a critical step in drug discovery. Existing methods of DTI prediction primarily employ Simplified Molecular-Input Line-Entry System (SMILES) sequences or molecular graphs to learn drug representations. However, the features learned by such single-view approach is prone to incomplete. While some multiview methods that consider the views of both SMILES sequences and molecular graphs have been developed, these methods often fall in short in capturing potential interactions between views. In this work, we propose a novel dual contrastive learning framework CSCL-DTI for DTI prediction. First, we design a contrastive-enhanced cross-view representation learning (CVRL) to learn representations for drugs. In this module, Transformer-based and graph convolutional network (GCN)-based encoders are separately adopted to learn view-specific representations, followed by contrastive learning to enrich the representations by accounting for the potential interplay between local chemical context and topological structure. Second, we combine Transformer with self-supervised contrastive learning (SSCL) to learn representations for targets by modelling protein amino acids sequences. The scheme allows to effectively preserve the intrinsic characteristics of the sequences. Finally, we introduce a bilinear attention network to obtain an integrated representation by adaptively incorporating drug and target representations. Benchmarking experiments on two datasets demonstrated that CSCL-DTI1 outperforms six state-of-the-art methods. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Beyond MLE: Convex Learning for Text Generation 37

Beyond MLE: Convex Learning for Text Generation

引用

37th Conference on Neural information processing Systems, NeurIPS 2023

作者： Shao, Chenze Ma, Zhengrui Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Future Science and Engineering Soochow University China

ISBN: (纸本)9781713899921

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at https://***/ictnlp/Convex-Learning. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

IF-Font: Ideographic Description Sequence-Following Font Generation 38

IF-Font: Ideographic Description Sequence-Following Font Gen...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Chen, Xinping Ke, Xiao Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Broadband Circularly Polarized Filtering Patch Antenna with Stacked Structure 12

A Broadband Circularly Polarized Filtering Patch Antenna wit...

引用

12th IEEE International Conference on Computer Science and Network Technology, ICCSNT 2024

作者： Zhang, Jinping Kholodnyak, Dmitry Huang, Zhixiang Li, Yingsong Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Saint Petersburg Electrotechnical University Department of Microwave Electronics Russia Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350350791

A double-layer stacked patch filtering antenna with broadband circular polarization performance is proposed in this paper. The main patch consists of a corner-Truncated square patch with two shorting pins. The designed two shorting pins are located in the main patch and the upper stacked patch structure are introduced and designed, which can gain two radiation nulls for realizing the filtering effect of the proposed antenna. The circularly polarized (CP) operation is realized by corner-Truncated square patch. In addition, to increase the axial ratio (AR) bandwidth, a rectangular slot is carved on the ground plane. The simulated results indicate that the researched antenna can provide the impedance bandwidth of 20.58% (2.68-3.29 GHz) and AR bandwidth of 9.5% (2.80-3.08 GHz). Moreover, The average realized gain of the simulation is 6.48 dBic over bandwidth. © 2024 IEEE.

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation

Viterbi Decoding of Directed Acyclic Transformer for Non-Aut...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Shao, Chenze Ma, Zhengrui Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential dependency with a directed acyclic graph. Consequently, it has to apply a sequential decision process at inference time, which harms the global translation accuracy. In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. Experimental results demonstrate that our approach consistently improves the performance of DA-Transformer while maintaining a similar decoding speedup. © 2022 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Spring pair method of finding saddle points using the minimum energy path as a compass

引用

Physical Review E 2024年第6期110卷 064123-064123页

作者： Gang Cui Kai Jiang Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Xiangtan Hunan 411105 China

Finding index-1 saddle points is crucial for understanding phase transitions. In this work, we propose a simple yet efficient approach, the spring pair method (SPM), to accurately locate saddle points. Without requiring the Hessian information, the SPM evolves a single pair of spring-coupled particles on an energy surface. By designing complementary drifting and climbing dynamics based on gradient decomposition, the spring pair converges onto the minimum energy path (MEP) and spontaneously aligns its orientation with the MEP tangent, providing a reliable ascent direction for efficient convergence to saddle points. The SPM fundamentally differs from traditional surface walking methods that rely on the eigenvectors of the Hessian, which may deviate from the MEP tangent and potentially lead to convergence failure or undesired saddle points. The efficiency of the SPM for finding saddle points is verified by ample examples, including Lennard-Jones clusters, Morse clusters, water clusters, and the Landau energy functional involving quasicrystal phase transitions.

关键词： Lennard-Jones potential

来源：评论

学校读者我要写书评

暂无评论

Optimized Multi-kernel Dictionary Learning and Its Application in Complex Industrial Processes Monitoring 41

Optimized Multi-kernel Dictionary Learning and Its Applicati...

引用

第41届中国控制会议

作者： Kai Zhong Zhengping Ding Donghui Pan Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Institutes of Physical Science and Information TechnologyAnhui University School of Mathematical Science Anhui University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The data in the chemical process is often complex in structure,and the coupling and correlation between variables are ***,it is difficult for conventional monitoring models to learn the essential characteristics of process data,which greatly affects the performance of the *** at the above problems,this paper proposes an optimized multi-kernel dictionary learning method,which is suitable for the industrial processes with strong nonlinearity and complex data ***,the synthetic kernel fused by multiple kernel functions is used to map the process data to a new high-dimensional feature space to mine the multivariate distribution characteristics of the ***,the grid search method is used to optimize the model parameters in the kernel function for better model ***,the effectiveness and practicability of the proposed method in fault detection are verified on TE benchmark platform.

关键词： Dictionary learning Multi-kernel function Chemical process monitoring

来源：评论

学校读者我要写书评

暂无评论

Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer 29

Improving Fake News Detection of Influential Domain via Doma...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Nan, Qiong Wang, Danding Zhu, Yongchun Sheng, Qiang Shi, Yuhui Cao, Juan Li, Jintao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Both real and fake news in various domains, such as politics, health, and entertainment are spread via online social media every day, necessitating fake news detection for multiple domains. Among them, fake news in specific domains like politics and health has more serious potential negative impacts on the real world (e.g., the infodemic led by COVID-19 misinformation). Previous studies focus on multi-domain fake news detection, by equally mining and modeling the correlation between domains. However, these multi-domain methods suffer from a seesaw problem: the performance of some domains is often improved at the cost of hurting the performance of other domains, which could lead to an unsatisfying performance in specific domains. To address this issue, we propose a Domain- and Instance-level Transfer Framework for Fake News Detection (DITFEND), which could improve the performance of specific target domains. To transfer coarse-grained domain-level knowledge, we train a general model with data of all domains from the meta-learning perspective. To transfer fine-grained instance-level knowledge and adapt the general model to a target domain, we train a language model on the target domain to evaluate the transferability of each data instance in source domains and re-weigh each instance’s contribution. Offline experiments on two datasets demonstrate the effectiveness of DITFEND. Online experiments show that DITFEND brings additional improvements over the base models in a real-world scenario. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Fake detection

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：