检索结果-内蒙古大学图书馆

Neural Networks, Information and Communication Engineering (NNICE), International Conference on

作者： Yu Wang Hong Zhang Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China

A new fine-grained image recognition algorithm (P-ResViT, Paired Interaction Res50-ViT) based on CNN-Transformer is proposed to address the issue of existing fine-grained image recognition methods based on convolutional neural networks (CNN) lacking attention mechanisms and difficulty in accurately locating key regions, as well as weak ability to extract contextual information and global features. This algorithm introduces paired interaction attention mechanisms to supplement external attention. This algorithm can utilize the self attention mechanism of the Vision Transformer and the external attention mechanism formed by paired image inputs during training to achieve precise positioning, while preserving the inductive bias and local feature extraction capabilities of CNN. Firstly, the fine-tuning improved ResNet-50 completes local feature extraction and obtains high-resolution feature maps. Secondly, the Transformer encodes the tokenized image blocks of the feature map as input sequences for extracting global context. Finally, the Transformer completes global feature extraction and outputs the classification sequence. In addition, two external attention mechanisms were introduced by inputting image pairs during training, including collaborative attention mechanisms for similar images and cross attention mechanisms for heterogeneous images, fully utilizing the correlation information between images. After experimental evaluation, the P-ResViT proposed in this article has reached advanced levels in three fine-grained image datasets CUB, CAR, and AIR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stable Control and Disturbance Rejection Strategy for Planar 2R Underactuated Robot via intelligent Algorithm 48

Stable Control and Disturbance Rejection Strategy for Planar...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Huang, Zixin Wan, Xiao Zhou, Yaosheng Wang, Lejun Wang, Liheng School of Electrical and Information Engineering Wuhan Institute of Technology Hubei Key Laboratory of Digital Textile Equipment Wuhan Textile University Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan Institute of Technology School of Electrical and Information Engineering Wuhan China Wuhan Institute of Technology School of Innovation and Entrepreneurship Wuhan China Chongqing University of Posts and Telecommunications Chongqing Key Laboratory of Complex Systems and Bionic Control Chongqing China

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Stable control and active disturbance rejection strategy is proposed for planar 2R underactuated robot via intelligent algorithm in this paper. At first, we build the dynamic model and describe the control characteristic. After that, we design PD controller for the active link. According to the underactuated constraint, we then optimize the parameters of controller by using the differential evolution algorithm (DEA), so that we can ensure the target states of all links could eventually be reached at the identical time. And the simulation results indicate the strategy is effective. © 2022 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Effects of thermophilic and acidophilic microbial consortia on maize wet-milling steeping

引用

Bioresources and Bioprocessing 2024年第1期11卷 922-932页

作者： Yaqin Sun Wenjing Xia Langjun Tang Zhilong Xiu Weiwu Jin Xiaoyan Wang Jin Tao Haijun Liu Hongyan An Yi Li Yi Tong MOE Key Laboratory of Bio-Intelligent Manufacturing School of BioengineeringDalian University of TechnologyNo.2 Linggong RoadGanjingzi DistrictDalian CityLiaoning Province 116024P.R.China Jilin COFCO Biochemistry Co. Ltd.(National Engineering Research Center of Corn Deep Processing)1717 Xiantai StreetNanguan DistrictChangchun CityJilin Province 130033P.R.China

To understand the ecology of species and promote biotechnology through beneficial strain selection for improving starch yield in maize wet-milling steeping,bacterial diversity and community structure during the counter-current steeping process in a commercial steeping system were characterized and *** microbial diversity in the steeping liquor,which consisted of 16 phyla,131 families,and 290 genera,was more abundant compared to those present on the surface of unsteeped *** the counter-current steeping progressed,exposing newer maize to the older steepwater,Lactobacillus dominated,replacing Rahnella,Pseudomonas,Pantoea,and *** thermophilic and acidophilic microbial consortia were enriched through adaptive evolution engineering and employed to improve starch *** steeping strategies were evaluated,including water alone,SO2 alone,mono-culture of ***,microbial consortia,and a combination of consortium and *** the microbial consortium with SO2 significantly increased the starch yield to,about 66.4±0.5%,a 22%and 46%increase over SO2 alone and the consortium alone,*** electron microscope(SEM)of steeped maize structure indicated that the combination of consortium and SO2 disrupted the protein matrix and widened gaps between starch granules in maize *** released proteins into the steepwater and left starch granules in the aleurone *** steeping strategy of using thermophilic and acidophilic microbial consortium as additives shows potential application as an environmentally friendly alternative to conventional maize steeping procedures.

关键词： Maize steeping Microbial consortium Thermophilic and acidophilic Protein matrix Adaptive evolution engineering

来源：评论

学校读者我要写书评

暂无评论

Transient Electro-thermal and Bandgap Narrowing Analysis of the bipolar transistor

Transient Electro-thermal and Bandgap Narrowing Analysis of ...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Xiao, Hui Ren, Xingang Yan, Yeqiang Huang, Zhixiang Wu, Xianliang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan23700 China Engineering Technology Research Center of Specific Power Devices with Novel Semiconductor Materials Anhui Province Chizhou247100 China Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781733509657

Given the bandgap narrowing (BGN) effect caused by heavy doping of the bipolar transistor and the self-heating effect (SHE) in the practical work environment, a transient electro-thermal and bandgap narrowing model is proposed in this paper, which is based on the Slotboom model and the modification of the drift-diffusion equation based on semiconductor equations and the heat conduction equation. The transient characteristics of the bipolar transistor in amplification mode are simulated using the differential method, and the results show that the terminal current of the bipolar transistor decreases after considering the SHE and the BGN effect. The model developed and the results obtained in this work can provide some reference significance for the optimization of the amplification characteristics of the bipolar transistor. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Energy gap

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

Transient Electro-thermal Analysis of the Bipolar Transistor

Transient Electro-thermal Analysis of the Bipolar Transistor

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-Monterey 2023

作者： Xiao, Hui Ren, Xingang Yan, Yeqiang Si, Junjie Cai, Xueyuan Wu, Bo Huang, Zhixiang Wu, Xianliang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan23700 China Engineering Technology Research Center of Specific Power Devices with Novel Semiconductor Materials Anhui Province Chizhou247100 China Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781733509633

This paper describes the transient electro-thermal properties of the bipolar transistor by a two-dimensional transient electro-thermal simulation, in which model the coupled heat conduction equation and drift-diffusion equations are solved. The backward difference scheme with the second-order accuracy was used to discretize the time derivative. The increment of bipolar transistor temperature will affect the drift and diffusion of carriers and thus its electrical characteristics. Through the transient study of electro-thermal characteristics of the bipolar transistor, the influence of the self-heating effect on bipolar transistor characteristic has considered in amplification mode. The developed model and results obtained in this work can be used to optimize the thermal design of bipolar transistor. © 2023 ACES.

关键词： Thermoanalysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Broadband EBG Structure For Simultaneous Switching Noise Suppression

A Novel Broadband EBG Structure For Simultaneous Switching N...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-Monterey 2023

作者： Sun, Guoxing Yan, Yeqiang Ren, Xingang Cai, Xueyuan Wu, Bo Ju, Huping Tao, Wei Wang, Gang Zou, Bao Huang, Zhixiang Wu, Xianliang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan23700 China Engineering Technology Research Center of Specific Power Devices with Novel Semiconductor Materials Anhui Province Chizhou247100 China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei230601 China

ISBN: (纸本)9781733509633

In this paper, a compact electromagnetic bandgap (EBG) structure for suppressing simultaneous switching noise (SSN) in high-speed circuits is proposed. At the bandwidth level of 0.35GHz to 20GHz, an ultra-wideband SSN suppression feature with a suppression depth of -40dB is achieved. The basic unit structure of the presented EBG is formed by etching an annular groove in the square patch and connecting the separated patches inside and outside the groove with a bridge adjacent to the end. An improved L-type bridge is used between the EBG units to further improve the EBG performance. Compared with the traditional L-type bridge, the suppression depth of the proposed electromagnetic bandgap structure is improved from -30dB to - 40dB. In addition, the time domain eye simulation results show that the structure has good signal integrity. © 2023 ACES.

关键词： Energy gap

来源：评论

学校读者我要写书评

暂无评论

EDGE: Unknown-aware Multi-label Learning by Energy Distribution Gap Expansion 39

EDGE: Unknown-aware Multi-label Learning by Energy Distribut...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Sun, Yuchen Xu, Qianqian Wang, Zitai Yang, Zhiyong He, Junwei Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)157735897X

Multi-label Out-Of-Distribution (OOD) detection aims to discriminate the OOD samples from the multi-label In-Distribution (ID) ones. Compared with its multiclass counterpart, it is crucial to model the joint information among classes. To this end, JointEnergy, which is a representative multi-label OOD inference criterion, summarizes the logits of all the classes. However, we find that JointEnergy can produce an imbalance problem in OOD detection, especially when the model lacks enough discrimination ability. Specifically, we find that the samples only related to minority classes tend to be classified as OOD samples due to the ambiguous energy decision boundary. Besides, imbalanced multi-label learning methods, originally designed for ID ones, would not be suitable for OOD detection scenarios, even producing a serious negative transfer effect. In this paper, we resort to auxiliary outlier exposure (OE) and propose an unknown-aware multi-label learning framework to reshape the uncertainty energy space layout. In this framework, the energy score is separately optimized for tail ID samples and unknown samples, and the energy distribution gap between them is expanded, such that the tail ID samples can have a significantly larger energy score than the OOD ones. What's more, a simple yet effective measure is designed to select more informative OE datasets. Finally, comprehensive experimental results on multiple multi-label and OOD datasets reveal the effectiveness of the proposed method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VAGeo: View-specific Attention for Cross-View Object Geo-Localization

arXiv

引用

arXiv 2025年

作者： Li, Zhongyang Yuan, Xin Liu, Wei Xu, Xin School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China

Cross-view object geo-localization (CVOGL) aims to locate an object of interest in a captured ground- or drone-view image within the satellite image. However, existing works treat ground-view and drone-view query images equivalently, overlooking their inherent viewpoint discrepancies and the spatial correlation between the query image and the satellite-view reference image. To this end, this paper proposes a novel View-specific Attention Geo-localization method (VAGeo) for accurate CVOGL. Specifically, VAGeo contains two key modules: view-specific positional encoding (VSPE) module and channel-spatial hybrid attention (CSHA) module. In object-level, according to the characteristics of different viewpoints of ground and drone query images, viewpoint-specific positional codings are designed to more accurately identify the click-point object of the query image in the VSPE module. In feature-level, a hybrid attention in the CSHA module is introduced by combining channel attention and spatial attention mechanisms simultaneously for learning discriminative features. Extensive experimental results demonstrate that the proposed VAGeo gains a significant performance improvement, i.e., improving acc@0.25/acc@0.5 on the CVOGL dataset from 45.43%/42.24% to 48.21%/45.22% for ground-view, and from 61.97%/57.66% to 66.19%/61.87% for drone-view. Copyright © 2025, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

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：