检索结果-内蒙古大学图书馆

A semantic and emotion-based dual latent variable generation model for a dialogue system

CAAI Transactions on Intelligence Technology 2023年第2期8卷 319-330页

作者： Ming Yan Xingrui Lou Chien Aun Chan Yan Wang Wei Jiang State Key Laboratory of Media Convergence and Communication Communication University of ChinaBeijingChina School of Information and Communications Engineering Communication University of ChinaBeijingChina Key Laboratory of Acoustic Visual Technology and Intelligent Control System Communication University of ChinaBeijingChina Department of Electrical and Electronic Engineering The University of MelbourneMelbourneVictoriaAustralia School of Data Science and Intelligent Media Communication University of ChinaBeijingChina

With the development of intelligent agents pursuing humanisation,artificial intelligence must consider emotion,the most basic spiritual need in human *** emotional dialogue systems usually use an external emotional dictionary to select appropriate emotional words to add to the response or concatenate emotional tags and semantic features in the decoding step to generate appropriate ***,selecting emotional words from a fixed emotional dictionary may result in loss of the diversity and consistency of the *** propose a semantic and emotion-based dual latent variable generation model(Dual-LVG)for dialogue systems,which is able to generate appropriate emotional responses without an emotional *** from previous work,the conditional variational autoencoder(CVAE)adopts the standard transformer ***,Dual-LVG regularises the CVAE latent space by introducing a dual latent space of semantics and *** content diversity and emotional accuracy of the generated responses are improved by learning emotion and semantic features ***,the average attention mechanism is adopted to better extract semantic features at the sequence level,and the semi-supervised attention mechanism is used in the decoding step to strengthen the fusion of emotional features of the *** results show that Dual-LVG can successfully achieve the effect of generating different content by controlling emotional factors.

关键词： conditional variational autoencoder dual latent space emotional responses latent variable generation

来源：评论

学校读者我要写书评

暂无评论

Tooth number abnormality:from bench to bedside

引用

International Journal of Oral Science 2023年第1期15卷 1-15页

作者： Han Zhang Xuyan Gong Xiaoqiao Xu Xiaogang Wang Yao Sun Department of Implantology Stomatological Hospital and Dental School of Tongji UniversityShanghai Engineering Research Center of Tooth Restoration and RegenerationShanghaiChina Key Laboratory of Big Data-Based Precision Medicine School of Engineering MedicineBeihang UniversityBeijingChina

Tooth number abnormality is one of the most common dental developmental diseases,which includes both tooth agenesis and supernumerary *** development is regulated by numerous developmental signals,such as the well-known Wnt,BMP,FGF,Shh and Eda pathways,which mediate the ongoing complex interactions between epithelium and *** expression of these crutial signalling during this process may eventually lead to the development of anomalies in tooth number;however,the underlying mechanisms remain *** this review,we summarized the major process of tooth development,the latest progress of mechanism studies and newly reported clinical investigations of tooth number *** addition,potential treatment approaches for tooth number abnormality based on developmental biology are also *** review not only provides a reference for the diagnosis and treatment of tooth number abnormality in clinical practice but also facilitates the translation of basic research to the clinical application.

关键词： abnormality diagnosis epithelium

来源：评论

学校读者我要写书评

暂无评论

A HIGH ORDER SCHEME FOR FRACTIONAL DIFFERENTIAL EQUATIONS WITH THE CAPUTO-HADAMARD DERIVATIVE

引用

Journal of Computational Mathematics 2025年第3期43卷 615-640页

作者： Xingyang Ye Junying Cao Chuanju Xu School of Science Jimei UniversityXiamen 361021China School of Data Science and Information Engineering Guizhou Minzu UniversityGuiyang 550025China School of Mathematical Sciences and Fujian Provincial Key Laboratory of Mathematical Modeling and High Performance Scientific Computing Xiamen UniversityXiamen 361005China

In this paper,we consider numerical solutions of the fractional diffusion equation with theαorder time fractional derivative defined in the Caputo-Hadamard sense.A high order time-stepping scheme is constructed,analyzed,and numerically *** contribution of the paper is twofold:1)regularity of the solution to the underlying equation is investigated,2)a rigorous stability and convergence analysis for the proposed scheme is performed,which shows that the proposed scheme is 3+αorder *** numerical examples are provided to verify the theoretical statement.

关键词： Caputo-Hadamard derivative Fractional differential equations High order scheme Stability and convergence analysis

来源：评论

学校读者我要写书评

暂无评论

A method based on improved ant colony algorithm feature selection combined with GWO-SVR model for predicting chlorophyll-a concentration in Wuliangsu Lake

引用

Water Science and Technology 2024年第1期89卷 20-37页

作者： Wu, Chenhao Fu, Xueliang Li, Honghui Hu, Hua Li, Xue Zhang, Liqian College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China Inner Mongolia Autonomous Region Key Laboratory of Big Data Research Application of Agriculture and Animal Husbandry Hohhot China

Chlorophyll-a (Chl-a) is an important parameter in water bodies. Due to the complexity of optics in water bodies, it is difficult to accurately predict Chl-a concentrations in water bodies by current traditional methods. In this paper, using Sentinel-2 remote sensing images as the data source combined with measured data, taking Wuliangsu Lake as the study area, a new intelligent algorithm is proposed for prediction of Chl-a concentration, which uses the adaptive ant colony exhaustive optimization algorithm (A-ACEO) for feature selection and the gray wolf optimization algorithm (GWO) to optimize support vector regression (SVR) to achieve Chl-a concentration prediction. The ant colony optimization algorithm is improved to select remote sensing feature bands for Chl-a concentration by introducing relevant optimization strategies. The GWO-SVR model is built by optimizing SVR using GWO with the selected feature bands as input and comparing it with the traditional SVR model. The results show that the usage of feature bands selected by the presented A-ACEO algorithm as inputs can effectively reduce complexity and improve the prediction performance of the model, under the condition of the same model, which can provide valuable references for monitoring the Chl-a concentration in Wuliangsu Lake. © 2024 The Authors.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Numerical study on the optimal power distribution of server racks in a data center

引用

Building Simulation 2023年第6期16卷 983-995页

作者： MengXuan Song Kai Chen School of Energy and Materials Shanghai Key Laboratory of Engineering Materials Application and EvaluationShanghai Polytechnic UniversityShanghai201209China Shanghai Thermophysical Properties Big Data Professional Technical Service Platform Shanghai Engineering Research Center of Advanced Thermal Functional MaterialsShanghai201209China Key Laboratory of Enhanced Heat Transfer and Energy Conservation of the Ministry of Education School of Chemistry and Chemical EngineeringSouth China University of TechnologyGuangzhou510640China

data centers,as the infrastructure of all information services,cost tremendous amount of *** the hot spot temperature in the data center room is benefit to prevent overheating of devices,and to increase cooling system *** this paper,we study the problem of optimal power distribution among racks for minimal hot spot *** temperature rise matrix(TRM)model is used for the purpose of fast estimation of the thermal *** accuracy of the model is evaluated by conducting numerical simulations of computational fluid dynamics(CFD).Using the TRM model,optimal distributing of heating power is converted into a linear programming problem,which can be solved by highly efficient algorithms,such as ***,with realistic constraints including rack idle power and power upper limit,an iteration method is proposed to calculate the optimal power distribution along with the optimal on/off states of the *** solutions are discussed and validated by comparing with CFD *** show that the TRM model is acceptable in evaluating temperature rises in the forced-convection-dominated scenarios,and the proposed method is able to obtain optimal power distributions under various levels of total power demand.

关键词： data center numerical simulation temperature rising matrix power distribution optimization

来源：评论

学校读者我要写书评

暂无评论

A Low-Rank Matching Attention Based Cross-Modal Feature Fusion Method for Conversational Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年第02期16卷 1177-1189页

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo Xi'An Jiaotong School of Computer Science and Technology Ministry of Education Key Laboratory for Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi'an710049 China Xi'An Jiaotong School of Computer Science and Technology Shaanxi Xi'an710049 China BigKEJoint Innovation Center SHMEEA Shanghai China Xi'An Jiaotong University School of Mathematics and Statistics Xi'an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Personalized Clustering via Targeted Representation Learning

arXiv

引用

arXiv 2024年

作者： Geng, Xiwen Zhao, Suyun Yu, Yixin Peng, Borui Du, Pan Chen, Hong Li, Cuiping Wang, Mengdie Key Lab of Data Engineering and Knowledge Engineering MOE Renmin University of China China School of Information Renmin University of China China School of Statistics Remin University of China China

Clustering traditionally aims to reveal a natural grouping structure within unlabeled data. However, this structure may not always align with users’ preferences. In this paper, we propose a personalized clustering method that explicitly performs targeted representation learning by interacting with users via modicum task information (e.g., must-link or cannot-link pairs) to guide the clustering direction. We query users with the most informative pairs, i.e., those pairs most hard to cluster and those most easy to miscluster, to facilitate the representation learning in terms of the clustering preference. Moreover, by exploiting attention mechanism, the targeted representation is learned and augmented. By leveraging the targeted representation and constrained contrastive loss as well, personalized clustering is obtained. Theoretically, we verify that the risk of personalized clustering is tightly bounded, guaranteeing that active queries to users do mitigate the clustering risk. Experimentally, extensive results show that our method performs well across different clustering tasks and datasets, even when only a limited number of queries are available. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Five-user quantum virtual local area network with an AlGaAs entangled photon source

引用

Science china(Physics,Mechanics & Astronomy) 2025年第3期68卷 61-73页

作者： Cheng Qian Hongkai Tian Xu Jing Yichen Liu Zhe Chen Huiran Luo Yuan Du Xiaodong Zheng Tangsheng Chen Yuechan Kong Hua-Lei Yin Dong Jiang Bin Niu Liangliang Lu Key Laboratory of State Manipulation and Advanced Materials in Provincial Universities School of Physical Science and TechnologyNanjing Normal UniversityNanjing210023China School of Internet Anhui UniversityHefei230039China National Key Laboratory of Solid-State Microwave Devices and Circuits Nanjing Chip Valley Industrial Technology InstituteNanjing Electronic Devices InstituteNanjing210016China Research Center for Quantum Optics and Quantum Communication School of ScienceQingdao University of TechnologyQingdao266520China Department of Physics and Beijing Key Laboratory of Opto-electronic Functional Materials and Micro-nano Devices Key Laboratory of Quantum State Construction and Manipulation(Ministry of Education)Renmin University of ChinaBeijing100872China Beijing Academy of Quantum Information Sciences Beijing100193China National Engineering Research Center of Agro-Ecological Big Data Analysis and Application Anhui UniversityHefei230601China National Laboratory of Solid-State Microstructures and School of Physics Nanjing UniversityNanjing210093China Hefei National Laboratory Hefei230088China

The promotion of quantum network applications demands the scalable connection of quantum *** is preferable to set up multiple logical networks coexisting on a single physical network infrastructure to accommodate a larger number of *** we present a quantum virtual network architecture that offers this level of scalability,without being constrained to a fixed physical-layer network relying solely on passive multiplexing *** architecture can be understood as arising from the superposition of a fully connected entanglement distribution network and port-based virtual local area network,which group multiusers by access *** terms of hardware,we leverage a semiconductor chip with a high figure-of-merit modal overlap to directly generate high-quality polarization entanglement,and a streamlined polarization analysis module,which requires only one single-photon detector for each end *** experimentally perform the BBM92 QKD protocol on the five-user quantum virtual network and demonstrate voice and image encryption on a campus area *** results may provide insights into the realization of large-scale quantum networks with integrated and cost-efficient photonic architecture.

关键词： quantum network quantum entanglement distribution integrated photonics image and voice encryption

来源：评论

学校读者我要写书评

暂无评论

Continuous and generalized visual odometry based on FLANN_PSC-RANSAC_LSTM

引用

Journal of Intelligent and Fuzzy Systems 2024年第1-2期47卷 15-28页

作者： Li, Dengao Feng, Ran Wu, Fanming Zhao, Jinhua Zhao, Jumin College of Computer Science and Technology College of Data Science Taiyuan University of Technology Shanxi Taiyuan China College of Electronic Information and Optical Engineering Taiyuan University of Technology Shanxi Taiyuan China Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Taiyuan University of Technology Shanxi Taiyuan China Intelligent Perception Engineering Technology Center of Shanxi Taiyuan China

In the field of simultaneous localization and mapping (SLAM), visual odometry (VO) always has great application prospects. In recent years, with the progress in the field of machine learning, methods based on neural networks are constantly being updated and applied. In this paper, we propose a continuous and generalized monocular visual odometry method based on features and neural networks. First, the feature information of adjacent image sequences is extracted by matching and troubleshooting algorithm (FLANN_PSC-RANSAC), then it and the corresponding six-degree-of-freedom information are simultaneously input into the long short-term memory artificial neural network (LSTM) for model construction, which not only ensures the reliability of the mode but also eliminates the influence of illumination on the data. In the real environment test, it has been effectively proved in terms of trajectory recovery accuracy and generalization ability to different environments and different illuminations. © 2024 - IOS Press. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Simultaneous refinement of α-Mg grains and β-Mg_(17)Al_(12) in Mg-Al based alloys via heterogeneous nucleation on Al_(8)Mn_(4)Sm

引用

Journal of Magnesium and Alloys 2023年第1期11卷 348-360页

作者： Jun-Chen Chen Mei-Xuan Li Zhi-Yang Yu Zhao-Yuan Meng Cheng Wang Zhi-Zheng Yang Hui-Yuan Wang State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchun 130012PR China Key Laboratory of Automobile Materials of Ministry of Education&School of Materials Science and Engineering Jilin UniversityNanling CampusNo.5988 Renmin StreetChangchun 130025PR China International Center of Future Science Jilin UniversityChangchun 130012PR China

Due to the significant differences in the formation temperature and crystal structure between the primaryα-Mg and eutecticβ-Mg_(17)Al_(12),it is a great challenge to achieve simultaneous refinement of the primary and eutectic phases in Mg-Al based alloys via heterogeneous ***,we found that theα-Mg andβ-Mg_(17)Al_(12) in the AZ80 alloy can be simultaneously refined after 0.2 wt.%Sm addition,with the grain size decreasing from∼217±15μm to∼170±10μm and theβ-Mg_(17)Al_(12) morphology changing from a typical continuous network to a nod-like or spherical *** simultaneous refinement mechanism is investigated through solidification simulation,transmission electron microscopy(TEM),and differential thermal analysis(DTA).In the AZ80-0.2Sm alloy,many Al8Mn4Sm particles can be observed near the center of theα-Mg grains or inside theβ-Mg_(17)Al_(12).Crystallographic calculations further reveal that the Al8Mn4Sm has good crystallographic matching with both theα-Mg andβ-Mg_(17)Al_(12),so it possesses the potency to serve as heterogeneous nucleation sites for both *** promoted heterogeneous nucleation on the Al8Mn4Sm decreases the undercooling required by the nucleation of the primary and eutectic phases,which enhances the heterogeneous nucleation rate,thus causing the simultaneous refinement of theα-Mg andβ-Mg_(17)Al_(12).The orientation relationships between the Al8Mn4Sm and Mg/Mg_(17)Al_(12) are identified,which are[1210]_(Mg)//[010]_(Al8Mn4Sm),(1010)_(Mg)//(301)_(Al8Mn4Sm) and[112]_(Mg_(17)Al_(12))//[010]_(Al8Mn4Sm),(110)_(Mg_(17)Al_(12))//(301)_(Al8Mn4Sm),***,the refinement of theβ-Mg_(17)Al_(12) accelerates its dissolution during the solution treatment,which is beneficial for cost saving in industrial *** Al8Mn4RE compounds such as Al8Mn4Y might have the same positive effect on the simultaneous refinement due to the similar physicochemical properties of rare earth *** work not only proves the po

关键词： Magnesium alloys Microstructure refinement Primaryα-Mg Eutecticβ-Mg_(17)Al_(12) Rare earth Heterogeneous nucleation

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：