检索结果-内蒙古大学图书馆

3rd International Conference on computer, Artificial Intelligence and Control Engineering, CAICE 2024

作者： Yu, Bo Lu, Mingde Shi, Yi Lin, Juxing Zeng, Mingjie School of Computer Science and Technology Harbin University of Science and Technology Harbin China

ISBN: (纸本)9798400716942

Learning weariness is a common psychological problem, which will affect students' learning effect and life quality. Currently, most ways to relieve the learning weariness require the intervention of a professional counselor or teacher, but these resources are often limited or difficult to access. In order to provide a low cost, high efficiency and easy to use tool for relieving the learning weariness, this paper introduces a dialogue system model based on text clustering algorithm and natural language processing algorithm to relieve the learning weariness of students. This dialogue system model provides learning emotion assessment function, learning weariness relieving function, and self-counseling advice function for students. Among them, the learning weariness relieving function is the highlight of this system model. Text clustering algorithm is the core technology of this function, which is able to classify the corpus according to different topics and train a specialized dialogue mod-el for each topic using natural language processing algorithm. In this way, when students ask questions, the learning weariness relieving function can select the most appropriate dialogue model to generate replies according to the topic of the question, so as to improve the quality and effect of the dialogue. In this paper, BLEU value is used as the evaluation index of the dialogue model, and F1-score is used as the evaluation index of text clustering model. Experimental results show that the dialogue system model can accurately distinguish the topic of the question and generate high quality replies. Therefore, this paper plans to improve the quality of the corpus used to train the models and try other data augmentation techniques in the future. © 2024 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

M3-Mixer:A Multimodal Mixer for Multimodal Sentiment Analysis with Multi-Head Loss 4

M3-Mixer:A Multimodal Mixer for Multimodal Sentiment Analysi...

引用

4th International Conference on Electronic Information Engineering and computer technology, EIECT 2024

作者： Hu, Keqin Sun, Dongpu Harbin University of Science and Technology School of Computer Science and Technology Harbin China

ISBN: (纸本)9798331528850

Multimodal Sentiment Analysis (MSA) often requires substantial computational resources to attain top-tier performance. Contemporary cutting-edge methods frequently rely on intricate processes, which entail considerable computational overhead. Recently, MLP (Multilayer Perceptron)-based approaches have achieved remarkable results, especially in computer vision. Drawing inspiration from these successes, we present M3-Mixer-a framework derived from the MLP-Mixer model and employing multi-head loss. M3-Mixer stands out due to its straightforward design and improved computational efficiency. Specifically, M3-Mixer uses text as a guide to split the model into two branches, each containing three independent MLP modules. These MLP modules exchange information across three directions: sequence, modality, and channel. Each module comprises two fully connected layers, an activation functions, and a skip connection. We evaluate M3-Mixer on two sentiment analysis datasets, CMU-MOSI and CMU-MOSEI. The results demonstrate that M3-Mixer achieves competitive performance with significantly lower computational cost. © 2024 IEEE.

关键词： Mixers (machinery)

来源：评论

学校读者我要写书评

暂无评论

Designing a hybrid microstructure of Ti-43Al-9V-0.3Y alloy and its non-equilibrium phase transition mechanism via two-step forging

引用

Journal of Materials science & technology 2024年第25期192卷 251-264页

作者： Yuan Ye Yu Zhang Shuzhi Zhang Yuyong Chen Jianfei Sun School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China School of Materials Science and Engineering Yanshan UniversityQinhuangdao 066004China The National Key Laboratory for Precision Hot Forming of Metals Harbin 150001China

Understanding the non-equilibrium phase transition mechanism is critical to controlling the transform-ing microstructures and thus material *** order to improve the problem of low room-temperature ductility of TiAl alloys with traditional microstructures,a two-step forging with an interme-diate heat preservation process is proposed to prepare a hybrid microstructure via non-equilibrium phase transition in this *** hybrid microstructure is composed ofβ_(0)/γlamellar colony,a structure with innerα_(2)/γand outerβ_(0)/γlamellae surrounded byβ_(0)phase,a structure ofγgrains embedded withinα_(2)/γlamellar colony,and some granularβ_(0)withinγ*** hybrid microstructure exhibits excellent room-temperature mechanical properties with a total elongation to failure of 2.15%and tensile strength of 920 ***,the evolution mechanisms of these various structures are analyzed from the perspective of solute element diffusion and distribution in front of the phase transition ***-gation of V element in front of theγgrowth interface induces the elemental reaction deviating from the equilibrium phase transitionα→α_(2)+γ,andα→β(β_(0))+γtransition occurs,resulting in the formation ofβ(β_(0))/γlamellar *** hot forging,α→α_(2)+γtransition occurs to generateα_(2)/γlamellae in the initial transition stage(I)of solute *** the stable stage(II),the content of V element in front of the growth interface ofγlamellae increases to∼18.41%,andα→β(β_(0))+γtransition occurs,soβ(β_(0))/γlamellae are formed outside theα_(2)/γlamellar *** the final stage(III),the remainingαphase is less,and the diffusion of the V element is hindered,causing a sudden increase of the V element inαphase,resulting in the remainingαphase transformed into irregularβ(β_(0))***,the structure with innerα_(2)/γand outerβ_(0)/γlamellae surrounded byβ_(0)phase is ***,adjusting the cooling rate realizes the precise controlling of theα_(2)/γ,β_(0)

关键词： TiAl alloy Hybrid microstructure Lamellar structures Non-equilibrium phase transition Two-step forging

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Retrieval of High-Resolution Fingerprints Based on Pore Feature

Hierarchical Retrieval of High-Resolution Fingerprints Based...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ma, Jing Xu, Yuanrong Dong, Suyu Wang, Wei Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Harbin Institute of Technology School of Computer Science and Technology Weihai China Northeast Forestry University College of Computer and Control Engineering Harbin China

ISBN: (纸本)9798350386226

Faced with an escalating number of fingerprint images, most existing retrieval approachs suffer from a common problem: diminishing computational efficiency. This paper presents a hierarchical retrieval system tailored for high-resolution fingerprint images that utilizes abundant pore features and robust recognizability to improve retrieval performance. The framework comprises two core components. Firstly, a CNN-based feature extraction network is established, incorporating an attention mechanism to capture pore features in fingerprint images comprehensively. Subsequently, a hierarchical fingerprint retrieval approach is introduced, involving connection graph construction and a hierarchy of jump table structures for efficient retrieval of query pores. Empirical experiments conducted on high-resolution fingerprint image datasets underscore the system's effectiveness. Compared with other advanced pore-based fingerprint retrieval methods, the proposed method exhibits a notable rise in the hit rate with reduced penetration rates, significantly reducing the retrieval time. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5805-5820页

作者： Qi, Biqing Gao, Junqi Chen, Xinquan Li, Dong Liu, Jianxing Wu, Ligang Zhou, Bowen Tsinghua University Department of Electronic Engineering Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China Harbin Institute of Technology Department of Control Science and Engineering Harbin China Harbin Institute of Technology School of Mathematics Harbin China

Few-Shot Class-Incremental Learning (FSCIL) has gained considerable attention in recent years for its pivotal role in addressing continuously arriving classes. However, it encounters additional challenges. The scarcity of samples in new sessions intensifies overfitting, causing incompatibility between the output features of new and old classes, thereby escalating catastrophic forgetting. A prevalent strategy involves mitigating catastrophic forgetting through the Explicit Memory (EM), which comprise of class prototypes. However, current EM-based methods retrieves memory globally by performing Vector-to-Vector (V2V) interaction between features corresponding to the input and prototypes stored in EM, neglecting the geometric structure of local features. This hinders the accurate modeling of their positional relationships. To incorporate information of local geometric structure, we extend the V2V interaction to Graph-to-Graph (G2G) interaction. For enhancing local structures for better G2G alignment and the prevention of local feature collapse, we propose the Local Graph Preservation (LGP) mechanism. Additionally, to address sample scarcity in classes from new sessions, the Contrast-Augmented G2G (CAG2G) is introduced to promote the aggregation of same class features thus helps few-shot learning. Extensive comparisons on CIFAR100, CUB200, and the challenging ImageNet-R dataset demonstrate the superiority of our method over existing methods. © 1991-2012 IEEE.

关键词： Prototypes Adaptation models Power capacitors Feature extraction Data models Accuracy Vectors Training Incremental learning Overfitting

来源：评论

学校读者我要写书评

暂无评论

Hot deformation behavior and microstructure evolution of Be/2024Al composites

引用

International Journal of Minerals,Metallurgy and Materials 2023年第11期30卷 2245-2258页

作者： Yixiao Xia Zeyang Kuang Ping Zhu Boyu Ju Guoqin Chen Ping Wu Wenshu Yang Gaohui Wu School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China Key Laboratory of Advanced Structure-Function Integrated Materials and Green Manufacturing Technology School of Materials Science and EngineeringHarbin Institute of TechnologyHarbin 150001China Key Laboratory of Advanced Science and Technology on High Power Microwave Xi'an 710024China Northwest Institute of Nuclear Technology Xi'an 710024China

The high temperature compression test of Be/2024Al composites with 62wt%Be was conducted at 500–575℃ and strain rate of0.003–0.1 s^(-1).The strain-compensated Arrhenius model and modified Johnson–Cook model were introduced to predict the hot deformation behavior of Be/2024Al *** result shows that the activation energy of Be/2024Al composites was 363.364 k J·mol^(-1).Compared with composites reinforced with traditional ceramics,Be/2024Al composites can be deformed with ultra-high content of reinforcement,attributing to the deformable property of Be *** average relative error of the two models shows that modified Johnson–Cook model was more suitable for low temperature condition while strain-compensated Arrhenius model was more suitable for high temperature *** processing map was generated and a hot extrusion experiment was conducted according to the map.A comparation of the microstructure of Be/2024Al composites before and after extrusion shows that the Be particle deformed coordinately with the matrix and elongated at the extrusion direction.

关键词： Be/Al composites hot deformation behavior constitutive model hot extrusion

来源：评论

学校读者我要写书评

暂无评论

Revealing the exceptional cryogenic strength-ductility synergy of a solid solution 6063 alloy by in-situ EBSD experiments

引用

材料科学技术（英文版） 2025年第5期208卷 313-322页

作者： Youhong Peng Li Wang Chenglu Liu Chao Xu Lin Geng Guohua Fan School of Materials Science and Engineering Harbin Institute of TechnologyHarbin150001China Key Laboratory for Light-weight Materials Nanjing Tech UniversityNanjing211816China

A solid solution 6063 aluminium alloy features an exceptional combination of strength and ductility at 77 ***,the deformation mechanisms responsible for superior strength-ductility synergy and excellent strain hardening capacity at a cryogenic temperature of the alloy were comparatively investigated by in-situ electron backscatter diffraction(EBSD)observations coupled with transmission electron microscopy(TEM)characterization and fracture morphologies at both 298 and 77 *** is found that kernel average misorientation(KAM)mappings and quantified KAM in degree suggest a higher proportion of geometri-cally necessary dislocations(GNDs)at 77 *** existence of orientation scatter partitions at 77 K implies the activation of multiple slip systems,which is consistent with the results of potential slip systems cal-culated by Taylor ***,dislocation tangles characterized by brief and curved dislocation cells and abundant small dimples have been observed at 77 *** temperature-mediated activation of dislo-cations facilitates the increased dislocations,thus enhancing the strain hardening capacity and ductility of the *** research enriches cryogenic deformation theory and provides valuable insights into the design of high-performance aluminium alloys that are suitable for cryogenic applications.

关键词： Aluminium alloy Cryogenic temperature Strength-ductility synergy In-situ EBSD Deformation mechanisms

来源：评论

学校读者我要写书评

暂无评论

Synthesis of high-performance single-crystal Li-rich cathode by self-combustion method

引用

Rare Metals 2023年第3期42卷 830-837页

作者： Lun-Te Li Ya-Fen Chen Yan-Chen Liu Qi Zhang Jun-Wei Wu Qun-Hui Yuan School of Materials Science and Engineering Harbin Institute of TechnologyShenzhen 518055China

Li-rich manganese-based oxide has been identified as the most promising cathode material for next-generation Li-ion batteries,due to its high capacity,high operating voltage,safety,and low ***,its wide application is restricted by low initial Columbic efficiency,undesirable cycle stability,and poor rate *** tackle these issues,single-crystal Li_(1.2)Mn_(0.54)Co_(0.13)Ni_(0.13)O_(2) is synthesized by a self-combustion *** with the poly-crystal Li-rich cathode,the specific discharge capacity of the single-crystal sample increased from 252.0 to304.6 mAh·g^(-1) at 0.1 C.

关键词： crystal high manganese

来源：评论

学校读者我要写书评

暂无评论

Robust 3D reconstruction and cell-type deconvolution approach for spatial transcriptomics by hybrid graph learning and iterative computation

Robust 3D reconstruction and cell-type deconvolution approac...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Zhengqian Chen, Binghong Wang, Jialiang Wang, Haiyu Yu, Tianshuo Ren, Junjun Zhang, Mingtao Liu, Chongyao Jiang, Wei Liu, Yongzhuang Harbin Institute of Technology School of Computer Science and Technology Harbin China Harbin Institute of Technology School of Mathematics Harbin China Harbin Institute of Technology Department of Fundamental Education Harbin China University of Glasgow James Watt School of Engineering Glasgow United Kingdom Future Technology Institute Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350386226

Spatial transcriptomics data provides new methods of exploring gene expressions. However, the results usually do not contain cell-level proportions, leaving a gap between the new technologies and the corresponding analysis. To address the issues, we propose a novel framework, OptiGraph3D, in this paper. Our approach starts with a pivoted sample-level sequential registration, eliminating potential cumulative errors in multiple registrations. The registration results provide sufficient spatial prior for our cell-type deconvolving process, which leverages the power of ADMM method by modelling the cell-type deconvolution task as a matrix inverse problem and proposes efficient solvers with guaranteed convergence. Furthermore, the cell-type deconvolution results can in turn perform as supervision for cluster recognition in 3D reconstruction. Our model introduces a semi-supervision training manner by introducing a specific class token in the multi-headed graph attention network, bridging the gap between gene-level expressions of spatial transcriptomics and presenting new angle for sample-wise analysis. Extensive experiments are performed on the human dorsolateral prefrontal cortex (DLPFC) and the developing human embryonic heart dataset, suggesting our approach's superiority over other methods. © 2024 IEEE.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Joint polarization and DOA estimation based on improved maximum likelihood estimator and performance analysis for conformal array

引用

Journal of Systems Engineering and Electronics 2023年第6期34卷 1490-1500页

作者： SUN Shili LIU Shuai WANG Jun YAN Fenggang JIN Ming School of Information Science and Engineering Harbin Institute of TechnologyWeihai 264209China

The conformal array can make full use of the aperture,save space,meet the requirements of aerodynamics,and is sensitive to polarization *** has broad application prospects in military,aerospace,and communication *** joint polarization and direction-of-arrival(DOA)estimation based on the conformal array and the theoretical analysis of its parameter estimation performance are the key factors to promote the engineering application of the conformal *** solve these problems,this paper establishes the wave field signal model of the conformal ***,for the case of a single target,the cost function of the maximum likelihood(ML)estimator is rewritten with Rayleigh quotient from a problem of maximizing the ratio of quadratic forms into those of minimizing quadratic *** this basis,rapid parameter estimation is achieved with the idea of manifold separation technology(MST).Compared with the modified variable projection(MVP)algorithm,it reduces the computational complexity and improves the parameter estimation ***,the MST is used to solve the partial derivative of the steering ***,the theoretical performance of ML,the multiple signal classification(MUSIC)estimator and Cramer-Rao bound(CRB)based on the conformal array are derived respectively,which provides theoretical foundation for the engineering application of the conformal ***,the simulation experiment verifies the effectiveness of the proposed method.

关键词： conformal array maximum likelihood(ML)estimator manifold separation technology(MST) parameter estimation Cramer-Rao bound(CRB).

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：