检索结果-内蒙古大学图书馆

Data Driven Control and Learning Systems (DDCLS)

作者： Dan Yang Xin Peng Cheng Su Dayu Tan Chaoyang Chen Weimin Zhong Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei Anhui China School of Information and Electrical Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Transfer learning aims to leverage the knowledge of the source domain to help the learning of unlabeled target domain models. However, all conventional transfer learning methods assume that samples from source and target domains are always freely accessible. However, this assumption is rarely plausible in real-world due to data privacy. To combat this challenge, we introduce Structure-constrain Source Free Domain Adaptation with regularized Knowledge Distillation of source model (SSFDA-KD). Our method is based on the observations that a deterministic classification result can be obtained when the target data distribution aligns with the source data distribution, and a well-trained model not only yields a deterministic classification for a sample but also has clear category boundaries, which implies samples that are close together belong to the same category. From those, we first generate the source model with labeled source data, which is regarded as a well-trained model. Then, we identify target prototypes with lower self-entropy and assign the pseudo-labels to other samples according to the neighborhood structure. Finally, we refine the target model by minimizing prediction loss, constraining internal structure via triplet loss, and reducing knowledge distillation loss. Experiments of fault diagnosis based on WWTPs are conducted to validate its effectiveness.

关键词： Fault diagnosis Learning systems Adaptation models Data privacy Transfer learning Prototypes Predictive models

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Prediction with Attention-based Spatial-Temporal Graph Network

Network Traffic Prediction with Attention-based Spatial-Temp...

引用

IEEE Workshop on High Performance Switching and Routing

作者： Yufei Peng Yingya Guo Run Hao Junda Lin Department of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University

Network traffic prediction plays a significant role in network management. Previous network traffic prediction methods mainly focus on the temporal relationship between network traffic, and used time series models to predict network traffic, ignoring the spatial information contained in traffic data. Therefore, the prediction accuracy is limited, especially in long-term prediction. To improve the prediction accuracy of the dynamic network traffic in the long term, we propose an Attention-based Spatial-Temporal Graph Network (ASTGN) model for network traffic prediction to better capture both the temporal and spatial relations between the network traffic. Specifically, in ASTGN, we exploit an encoder-decoder architecture, where the encoder encodes the input network traffic and the decoder outputs the predicted network traffic sequences, integrating the temporal and spatial information of the network traffic data through the Spatio-Temporal Embedding module. The experimental results demonstrate the superiority of our proposed method ASTGN in long-term prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simple Broadband Slotted Circularly Polarization Antenna

A Simple Broadband Slotted Circularly Polarization Antenna

引用

IEEE International Workshop on Electromagnetics, Applications and Student Innovation (iWEM)

作者： Lihua Wang Yingsong Li Zhixiang Huang Tian Hong Loh College of Information and Communication Engineering Harbin Engineering University Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China Electromagnetic and Eletrochemical Technologies Department National Physical Laboratory Middlesex UK

A simple broadband slotted circularly-polarized (CP) antenna (SBS-CP) is presented, which mainly consists of a ground structure with a modified slot and an asymmetric feeding structure. The two structures can give different CP characteristics in low and high frequencies. By etching rectangular slots in the ground structure, the coupling effect between feeding and ground structure will be improved and the bandwidth will be broadened. By modeling and optimizing the antenna, the proposed antenna impedance bandwidth (IBW) and axial ratio bandwidth (ARBW) are 113% (2.08~7.46 GHz) and 97% (2.5~7.24 GHz), respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 2074-2083页

作者： Shoutao Guo Shaolei Zhang Zhengrui Ma Min Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) Beijing China University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of AI Safety Chinese Academy of Sciences Beijing China

Simultaneous Machine Translation (SiMT) generates target translations in real-time while reading the source sentence. It relies on a policy to determine the optimal timing for producing translations, aiming to achieve both low response latency and high translation quality. Existing SiMT methods typically utilize the traditional Transformer architecture, employing complicated dynamic programming algorithms to jointly optimize policy decisions and translation generation. While these methods excel at determining policies, their translation capabilities are suboptimal. In contrast, Large Language Models (LLMs), trained on extensive corpora, exhibit exceptional generation capabilities but struggle to learn translation policies through traditional Transformer-based training methods. To address these limitations, we introduce Agent-SiMT, a novel framework combining the strengths of LLMs and traditional SiMT methods. Agent-SiMT contains a policy-decision agent and a translation agent. The policy-decision agent is managed by a SiMT model, which determines the policy using partial source sentences and translations. The translation agent, powered by an LLM, generates the target translation according to the policy decisions. These two agents work collaboratively to perform SiMT. Experiments demonstrate that our method attains state-of-the-art performance.

关键词： Translation Hidden Markov models Transformers Training Large language models Collaboration Vocabulary Speech processing Memory modules Machine translation

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of a Modified ZNN with Dynamic Parameter for Time Varying Generalized Sylvester Equation

Design and Analysis of a Modified ZNN with Dynamic Parameter...

引用

2022 International Conference on Machine Learning, Cloud computing and intelligent Mining, MLCCIM 2022

作者： Zhang, Yongsheng Chen, Jifeng He, Yongjun Peng, Hao Li, Ping College of Information and Mechatronics Engineering Hunan International Economics University Changsha410205 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410205 China

ISBN: (数字)9781665498586

ISBN: (纸本)9781665498586

The time varying generalized Sylvester equation (TVGSE) is widely used in many domains such as mathematics, engineering and control system. Differing from the zeroing neural network (ZNN) and varying parameter ZNN (VPZNN), a novel neural network algorithm based on a novel time-varying parameter, named modified VPZNN (MVPZNN), is presented and studied for handling TVGSE in this work. In particular, the proposed MVPZNN possesses faster convergence capacity when activated by the linear and sign-bi-power activation function, respectively. Numerical simulation indicates that MVPZNN has superiority in convergence rate in coping with TVGSE compared with fixed parameter ZNN and other VPZNN models. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training 24

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Lang...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availability of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly available image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial Language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are available at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

The grad-div conforming virtual element method for the quad-div problem in three dimensions

arXiv

引用

arXiv 2024年

作者： Dong, Xiaojing Han, Yibing Huang, Yunqing Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Er huan Road Hunan Xiangtan411105 China

We propose a new stable variational formulation for the quad-div problem in three dimensions and prove its well-posedness. Using this weak form, we develop and analyze the H(grad-div)-conforming virtual element method of arbitrary approximation orders on polyhedral meshes. Three families of H(grad-div)conforming virtual elements are constructed based on the structure of a de Rham sub-complex with enhanced smoothness, resulting in an exact discrete virtual element complex. In the lowest-order case, the simplest element has only one degree of freedom at each vertex and face, respectively. We rigorously prove the interpolation error estimates, the stability of discrete bilinear forms, the well-posedness of discrete formulation and the optimal error estimates. Some numerical examples are shown to verify the theoretical results. © 2024, CC BY-NC-ND.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

High Contrast Ratio 4-to-2 Plasmonic Encoder Utilizing Cascaded Ring Resonators

High Contrast Ratio 4-to-2 Plasmonic Encoder Utilizing Casca...

引用

International Conference on Electronic Engineering and Informatics (EEI)

作者： Yan Chen Yiyuan Xie Junxiong Chai Yichen Ye College of Electronic and Information Engineering Southwest University Chongqing China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing China Key Laboratory of Networks and Cloud Computing Security of Universities in Chongqing Chongqing China

ISBN: (数字)9798350353594

ISBN: (纸本)9798350353600

In this paper, a novel plasmonic 4-to-2 encoder comprising cascaded ring resonators coated with graphene layers and two metal-insulator-metal (MIM) waveguides. The encoding function operates at 850 nm by modulating the intensity of pump beam focused on the graphene layer to manipulate the state of the plasmonic resonators. The performance of the encoder is analyzed utilizing the finite-difference time-domain method, demonstrating a high contrast ratio of 15.1 dB. Thus, this efficient 4-to-2 optical encoder is well-suited for integration into optical integrated computing devices.

关键词： Integrated optics Optical switches Graphene Plasmons Optical pumping Encoding Optical modulation Optical ring resonators Optical devices Finite difference methods

来源：评论

学校读者我要写书评

暂无评论

Ptpfusion: A Progressive Infrared and Visible Image Fusion Network Based on Texture Preserving

SSRN

引用

SSRN 2024年

作者： Lu, Yixiang Zhang, Weijian Zhao, Dawei Qian, Yucheng Maksim, Davydau Gao, Qingwei The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China The Belarusian State University of Informatics and Radioelectronics Minsk Belarus State Grid Anhui Electric Power Research Institute China

Infrared and visible image fusion is to provide a more comprehensive image for downstream tasks by highlighting the main tar get and maintaining rich texture information. Image fusion methods based on deep learning suffer from insufficient multimodal information extraction and texture loss. In this paper, we propose a texture preserving progressive fusion network to extract comple mentary information from multimodal images (PTPFusion) to solve these issues. To reduce image texture loss, we design multiple consecutive texture-preserving blocks (TPB) to enhance fused texture. The TPB can enhance the features by using a parallel ar chitecture consisting with a residual block and a derivative operators. In addition, a novel cross-channel attention (CCA) fusion module is developed to obtain complementary information by modeling global feature interactions via cross-queries mechanism, followed by information fusion to highlight the feature of salient target. To avoid information loss, the extracted features at different stages are merged as the output of TPB. Finally, the fused image will be generated by the decoder. Extensive experiments on three datasets show that our proposed fusion algorithm is better than existing state-of-the-art methods. © 2024, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Extended Coprime Arrays with Sum-Difference Coarray for DOA Estimation 5

Extended Coprime Arrays with Sum-Difference Coarray for DOA ...

引用

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Xin, Wei Xu, Lin Gao, Jincheng Li, Yingsong Huang, Zhixiang College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Wuhan Second Ship Design and Research Institute Wuhan China Zhaojin Mining Industry Co. Ltd. Zhaoyuan China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

A modified coprime array (CA) with a name of extended CA (ECA) is presented and constructed to reduce over-lapping sensors between sum and difference coarray using conventional CA (CCA) to get a sum-difference coarray with high degrees- of-freedoms (DOFs). The devised ECA is to shift a sub array of CCA to reduce redundancy and then to flip part of shifted sub array around zero point that is regarded as symmetric center. The onstructed ECA expands the inter-element separations with lower mutual coupling. Numerical simulation are provided to verify superiority of the devised ECA. © 2022 IEEE.

关键词： Direction of arrival

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：