检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information processing Systems

作者： Shangshang Yang Xiaoshan Yu Ye Tian Xueming Yan Haiping Ma Xingyi Zhang Anhui University and Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Guangdong University of Foreign Studies Anhui University and Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education and Department of Information Materials and Intelligent Sensing Laboratory of Anhui Province

Transformer has achieved excellent performance in the knowledge tracing (KT) task, but they are criticized for the manually selected input features for fusion and the defect of single global context modelling to directly capture students' forgetting behavior in KT, when the related records are distant from the current record in terms of time. To address the issues, this paper first considers adding convolution operations to the Transformer to enhance its local context modelling ability used for students' forgetting behavior, then proposes an evolutionary neural architecture search approach to automate the input feature selection and automatically determine where to apply which operation for achieving the balancing of the local/global context modelling. In the search space design, the original global path containing the attention module in Transformer is replaced with the sum of a global path and a local path that could contain different convolutions, and the selection of input features is also considered. To search the best architecture, we employ an effective evolutionary algorithm to explore the search space and also suggest a search space reduction strategy to accelerate the convergence of the algorithm. Experimental results on the two largest and most challenging education datasets demonstrate the effectiveness of the architecture found by the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structure-constrain Source Free Domain Adaptation with Regularized Knowledge Distillation of Source Model 13

Structure-constrain Source Free Domain Adaptation with Regul...

引用

13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Yang, Dan Peng, Xin Su, Cheng Tan, Dayu Chen, Chaoyang Zhong, Weimin Ministry of Education East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai200237 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Anhui Hefei230601 China School of Information and Electrical Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9798350361674

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. © 2024 IEEE.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

ADHD diagnosis guided by functional brain networks combined with domain knowledge

引用

Computers in Biology and Medicine 2024年 177卷 108611-108611页

作者： Cao, Chunhong Fu, Huawei Li, Gai Wang, Mengyang Gao, Xieping MOE Key Laboratory of Intelligent Computing and Information Processing Xiangtan University Xiangtan411100 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China

Utilizing functional magnetic resonance imaging (fMRI) to model functional brain networks (FBNs) is increasingly prominent in attention-deficit/hyperactivity disorder (ADHD) research, revealing neural impact and mechanisms through the exploration of activated brain regions. However, current FBNs-based methods face two major challenges. The primary challenge stems from the limitations of existing modeling methods in accurately capturing both regional correlations and long-distance dependencies (LDDs) within the dynamic brain, thereby affecting the diagnostic accuracy of FBNs as biomarkers. Additionally, limited sample size and class imbalance also pose a challenge to the learning performance of the model. To address the issues, we propose an automated diagnostic framework, which integrates modeling, multimodal fusion, and classification into a unified process. It aims to extract representative FBNs and efficiently incorporate domain knowledge to guide ADHD classification. Our work mainly includes three-fold: 1) A multi-head attention-based region-enhancement module (MAREM) is designed to simultaneously capture regional correlations and LDDs across the entire sequence of brain activity, which facilitates the construction of representative FBNs. 2) The multimodal supplementary learning module (MSLM) is proposed to integrate domain knowledge from phenotype data with FBNs from neuroimaging data, achieving information complementarity and alleviating the problems of insufficient medical data and unbalanced sample categories. 3) An ADHD automatic diagnosis framework guided by FBNs and domain knowledge (ADF-FAD) is proposed to help doctors make more accurate decisions, which is applied to the ADHD-200 dataset to confirm its effectiveness. The results indicate that the FBNs extracted by MAREM perform well in modeling and classification. After with MSLM, the model achieves accuracy of 92.4%, 74.4%, and 80% at NYU, PU, and KKI, respectively, demonstrating its ability to effecti

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A method for generating Dunhuang dance instrumental images based on optimized diffusion model

A method for generating Dunhuang dance instrumental images b...

引用

2024 International Conference on Algorithms, High Performance computing, and Artificial Intelligence, AHPCAI 2024

作者： Wang, Jiaxin He, Xiangzhen Suzuki, Kenneth M. Northwest Minzu University Key Laboratory of Linguistic and Cultural Computing Ministry of Education Gansu Lanzhou730030 China Northwest Minzu University Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing Gansu Lanzhou730030 China

ISBN: (纸本)9781510685840

Dunhuang culture is a treasure house of human history and culture. As an integral part of Dunhuang culture, Dunhuang dance is famous for its unique national characteristics and artistic characteristics. In the form of Dunhuang dance, instrumental music and props are used to greatly enrich the stage expression, forming a unique dance form of "holding music while dancing, dancing with instruments". However, the phenomenon of homogenization of instrumental props occurs frequently, which hinders the overall presentation effect and beauty of Dunhuang dance. The development based on the generative diffusion model provides new ideas for the design of Dunhuang dance instrumental props. First, the role played by musical instruments and props in the presentation of Dunhuang dance art was sorted out, and the Dunhuang dance instrumental props were digitally collected and processed, and a special data set was constructed. Secondly, based on the recognition of related instruments, a diffusion model instrumental prop image generation that can be used in the Chinese context is trained. Experimental results show that the instrumental props generated by this method not only conform to realistic logic but also have strong applicability. © 2024 SPIE.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Linear-to-Circular Polarization Converter Based on Transmission Metamaterial 4

Linear-to-Circular Polarization Converter Based on Transmiss...

引用

4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021

作者： Li, Huixiang Wu, Xianliang Zhang, Liang Anhui University Key Laboratory of Intelligent Computing Signal Processing Hefei China Anhui Province Key Laboratory of Simulation and Design for Electronic Information Key Laboratory of Intelligent Computing Signal Processing Hefei Normal University Hefei China

ISBN: (纸本)9781733509619

A broadband transmissive linear-to-circular polarization conversion metamaterial composed of 5-layer '-shaped units was designed, and it was placed directly above the ordinary linear polarization antenna so that the antenna can radiate circular polarization waves. The 3dB axial ratio bandwidth is 11.5GHz-14.5GHz, and the relative axial ratio bandwidth reaches 23%, which proves that the polarization conversion surface has good polarization conversion characteristics. © 2021 Applied Computational Electromagnetics Society (ACES).

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Design of Microstrip Type Broadband Directional Coupler

Design of Microstrip Type Broadband Directional Coupler

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Hang Yan Xianliang Wu Ruikang Wang Gang Wang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

A microstrip line broadband directional coupler is designed based on microstrip line theory. The bandwidth of the coupler is extended by using a cascade of multiple coupled lines. The isolation of the directional coupler is greatly improved by covering the microstrip line with a dielectric layer [1] and by loading the branching compensation capacitor to compensate for the odd-even mode phase velocity difference. Simulation results of ANSYS HFSS 2019 show that the return loss ( $S_{11}$ ) is greater than 20 dB, the insertion loss ( $S_{21}$ ) is less than 1.7 dB, the coupling degree (S31) is about −6dB(±0.8dB), the isolation degree (S41) is greater than 23.4dB, and the minimum directionality is greater than 17dB during 700 MHz-3700 MHz. The physical size of coupler is $18\text{mm}\times 60\text{mm}$ , which meets the design requirements of 6dB coupler.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MSCA-UNet: Multi-Scale Channel Adaptive Sensing Module for Medical Image Segmentation

MSCA-UNet: Multi-Scale Channel Adaptive Sensing Module for M...

引用

2024 International Conference on New Trends in Computational Intelligence, NTCI 2024

作者： Diao, Liangjin Shen, Longfeng Chen, Jiacong Ge, Fangzhen Li, Mengwen College of Computer Science and Technology Huaibei Normal University Anhui Huaibei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui Hefei China

ISBN: (纸本)9798331517021

Recent advancements in CNNs for medical image segmentation have focused on the combination of CNN and Transformer architectures to capture both local and global features. However, challenges remain, such as effectively utilizing fused features at the encoder-decoder bottleneck and addressing blurred object edges in datasets. To tackle these issues, we introduce a multi-scale channel adaptive sensing module, enhancing the model's representational and perceptual capabilities by integrating multi-scale and channel-specific information. Additionally, we propose a cross-perception module and multi-scale segmentation head to improve global coordination and multi-scale information gathering. Experiments on the ACDC and Synapse datasets demonstrate our model's superiority. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Parallel Coupled Microstrip Wideband Bandpass Filter Loaded with CSRR and SRR Structures

Parallel Coupled Microstrip Wideband Bandpass Filter Loaded ...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Zijian Yu Xiaodi Song Chen Li Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

This paper presents a parallel coupled line bandpass filter for X-band applications, which has low insertion loss, broadband and easy processing. By loading the CSRR (Complementary Split Ring Resonator) and SRR (Split Ring Resonator) structures, three additional transmission zeros are added to improve the out-of-band rejection performance of the filter. Moreover, the rectangular DGS structure below the triple-parallel coupling line reduces the insertion loss of the filter. The simulation results show that the filter center frequency is 9.5GHz, the insertion loss is 0.8dB, S11

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a Miniaturised Wide-Stopband SIW Filter

Design of a Miniaturised Wide-Stopband SIW Filter

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Chen Li Minquan Li Xin Qu Shuang Xiao Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

In this paper, we propose a miniaturized wide-stopband SIW dual-band filter. SIW limits the propagation of electromagnetic waves and thus enables the miniaturization of the filter. A passband below the waveguide cutoff frequency is generated by etching the CSRR structure on the surface of the SIW, while a modified CSRR-DGS structure is etched on the backside of the SIW structure, and the other passband is generated by coupling the CSRR etched on the surface of the SIW to the ground. In addition, the CSRR-DGS structure broadens the stopband without increasing the filter size. Through the circuit equivalent analysis and parameter optimization of the filter structure, the final simulation results are as follows: the filter has a passband of 3.5 GHz (WIMAX) and 5.2 GHz (WLAN), the 3dB bandwidths of the two bands are 130MHz and 180MHz respectively, the insertion loss is 0.5 dB and 0.65 dB, and the size is $0.18\lambda_{\mathrm{g}}\times 0.27\lambda_{\mathrm{g}}$ . Overall, it achieves high performance and also has a wide range of applications.

关键词：

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：