检索结果-内蒙古大学图书馆

Computational Politeness in Natural Language Processing: A Survey

ACM Computing Surveys 2024年第9期56卷 1-42页

作者： Priya, Priyanshu Firdaus, Mauajama Ekbal, Asif Computer Science and Engineering Indian Institute of Technology Patna Bihar Patna India University of Alberta EdmontonAB Canada

Computational approach to politeness is the task of automatically predicting and/or generating politeness in text. This is a pivotal task for conversational analysis, given the ubiquity and challenges of politeness in interactions. The computational approach to politeness has witnessed great interest from the conversational analysis community. This article is a compilation of past works in computational politeness in natural language processing. We view four milestones in the research so far, viz. supervised and weakly supervised feature extraction to identify and induce politeness in a given text, incorporation of context beyond the target text, study of politeness across different social factors, and study the relationship between politeness and various socio-linguistic cues. In this article, we describe the datasets, approaches, trends, and issues in computational politeness research. We also discuss representative performance values and provide pointers to future works, as given in the prior works. In terms of resources to understand the state of the art, this survey presents several valuable illustrations - most prominently, a table summarizing the past papers along different dimensions, such as the types of features, annotation techniques, and datasets used. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Computational methods

来源：评论

学校读者我要写书评

暂无评论

A trajectory-level robot skill learning method based on fuzzy systems

引用

science China(Information sciences) 2025年第5期68卷 38-52页

作者： Chao ZENG Zhen DENG Boyang TI Yongsheng GAO Department of Computer Science University of Liverpool School of Mechanical Engineering and Automation Fuzhou University State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences State Key Laboratory of Robotics and System Harbin Institute of Technology

Learning from demonstration(LfD) allows for the effective transfer of human manipulation skills to a robot by building a model that represents these skills based on a limited number of demonstrated ***,a skilllearning model that can comprehensively satisfy multiple requirements,such as computational complexity,modeling accuracy,trajectory smoothness,and robustness,is still ***,this work aims to provide such a model by employing fuzzy ***,we introduce an LfD model named Takagi-Sugeno-Kang fuzzy system-based movement primitives(TSKFMPs),which exploits the advantages of the fuzzy theory for effective robotic imitation learning of human *** work formulates the TSK fuzzy system and gradient descent(GD) as imitation learning models,leveraging recent advancements in GD-based optimization for fuzzy *** study takes a two-step strategy.(ⅰ) The input-output relationships of the model are established using TSK fuzzy systems based on demonstration *** this way,the skill is encoded by the model parameter in the latent space.(ⅱ) GD is used to optimize the model parameter to increase the modeling accuracy and trajectory *** further explain how learned trajectories are adapted to new task scenarios through local *** conduct multiple tests using an open dataset to validate our method,and the results demonstrate performance comparable with those of other ***,we implement it in a real-world case study.

关键词： robot skill learning movement primitives TSK fuzzy systems gradient descent robotics

来源：评论

学校读者我要写书评

暂无评论

Causality Based Front-door Defense Against Backdoor Attack on Language Models 41

Causality Based Front-door Defense Against Backdoor Attack o...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Yiran Xu, Xiaoang Hou, Zhiyi Yu, Yang Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China School of Computer Science and Technology Harbin University of Science and Technology Harbin China Faculty of Computing Harbin Institute of Technology Harbin China School of Economics and Management China University of Petroleum Beijing China

We have developed a new framework based on the theory of causal inference to protect language models against backdoor attacks. Backdoor attackers can poison language models with different types of triggers, such as words, sentences, grammar, and style, enabling them to selectively modify the decision-making of the victim model. However, existing defense approaches are only effective when the backdoor attack form meets specific assumptions, making it difficult to counter diverse backdoor attacks. We propose a new defense framework Front-door Adjustment for Backdoor Elimination (FABE) based on causal reasoning that does not rely on assumptions about the form of triggers. This method effectively differentiates between spurious and legitimate associations by creating a'front door' that maps out the actual causal relationships. The term'front door' refers to a text that retains the semantic equivalence of the initial input, which is generated by an additional, fine-tuned language model, denoted as the defense model. Our defense experiments against various attack methods at the token, sentence, and syntactic levels reduced the attack success rate from 93.63% to 15.12%, improving the defense effect by 2.91 times compared to the best baseline result of 66.61%, achieving state-of-the-art results. Through ablation study analysis, we analyzed the effect of each module in FABE, demonstrating the importance of complying with the front-door criterion and front-door adjustment formula, which also explains why previous methods failed. Our code to reproduce the experiments is available at: https://***/lyr17/FrontdoorAdjustment-Backdoor-Elimination. Copyright 2024 by the author(s)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Smart contract token-based privacy-preserving access control system for industrial Internet of Things

引用

Digital Communications and Networks 2023年第2期9卷 337-346页

作者： Weizheng Wang Huakun Huang Zhimeng Yin Thippa Reddy Gadekallu Mamoun Alazab Chunhua Su Department of Computer Science City University of Hong KongHong Kong SAR999077China Division of Computer Science University of AizuFukushima965-8580Japan School of Information Technology and Engineering Vellore Institute of TechnologyTamil NaduIndia College of Engineering IT and EnvironmentCharles Darwin UniversityAustralia School of Computer Science and Cyber Engineering Guangzhou UniversityChina

Due to mobile Internet technology's rapid popularization,the Industrial Internet of Things(IIoT)can be seen everywhere in our daily *** IIoT brings us much convenience,a series of security and scalability issues related to permission operations rise to the surface during device ***,at present,a reliable and dynamic access control management system for IIoT is in urgent *** till now,numerous access control architectures have been proposed for ***,owing to centralized models and heterogeneous devices,security and scalability requirements still cannot be *** this paper,we offer a smart contract token-based solution for decentralized access control in IIoT ***,there are three smart contracts in our system,including the Token Issue Contract(TIC),User Register Contract(URC),and Manage Contract(MC).These three contracts collaboratively supervise and manage various events in IIoT *** also utilize the lightweight and post-quantum encryption algorithm-Nth-degree Truncated Polynomial Ring Units(NTRU)to preserve user privacy during the registration ***,to evaluate our proposed architecture's performance,we build a prototype platform that connects to the local ***,experiment results show that our scheme has achieved secure and dynamic access control for the IIoT system compared with related research.

关键词： Blockchain Privacy preservation Smart contract Industrial IoT

来源：评论

学校读者我要写书评

暂无评论

Machine learning investigation of the effects of elemental doping on the mechanical properties of Fe-Cr-Ni-Al high-entropy alloys

引用

science China Technological sciences 2025年

作者： Jingteng XUE Jingtao HUANG Zhonghong LAI Nan QU Yong LIU Jingchuan ZHU School of Materials Science and Engineering Harbin Institute of Technology Department of Forensic Science and Technology Zhengzhou Police University Center for Analysis Measurement and Computing Harbin Institute of Technology National Key Laboratory for Precision Hot Processing of Metals Harbin Institute of Technology

This study investigates how doping various elements from the periodic table affects the mechanical properties of ***26representative elements, which were subsequently used to establish doping structure models. The elastic constants and intrinsic mechanical properties of these alloy configurations were evaluated using first-principles calculations. Chemical compositions wereconvertedintophysicalfeatures,servingasinputvariablesformultiplemachinelearningalgorithmstopredictthe properties of alloys with common dopants. Furthermore, elements were clustered according to their influence on alloy properties. The results reveal significant variability in the effects of different elements. Notably, Young’s modulus and toughness often exhibited opposing trends. For instance, Zn and Co enhanced toughness, whereas Li and Pb led to increased ***, elements such as Pt, Ti, and Mn achieved a favorable balance between stiffness and ductility. Comparisons between experimental data and predicted results confirmed the accuracy of our approach. This method provides theoretical guidance for the compositional design of high-entropy alloys and offers insights into accelerating first-principles calculations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Sensor Fault Detection and Isolation Based on Nonlinear Kalman Filter

Dual-Channel Sensor Fault Detection and Isolation Based on N...

引用

TEPEN International Workshop on Fault Diagnostics and Prognostics, TEPEN-IWFDP 2024

作者： Wang, Ying Cao, Yunpeng Li, Shuying Zhu, Linhai Yao, Kun College of Power and Energy Engineering Harbin Engineering University Harbin150001 China School of Energy Science and Engineering Harbin Institute of Technology Harbin150001 China Shenzhen518055 China

ISBN: (纸本)9783031734069

In order to solve the problems caused by the inherent complex nonlinearity and the limitation of traditional linear modeling technology in engine fault diagnosis, the Equilibrium manifold model is introduced in this paper, The equilibrium manifold model can describe the actual operating state of the engine more accurately, and capture the higher-order nonlinear characteristics that are ignored by the traditional linear ***, a dual-channel sensor fault diagnosis and isolation approach is proposed, which integrates the nonlinear engine model with the Cubature Kalman filter. Simulations conducted that, compared to traditional Kalman filter-based methods, this approach not only reduces the demands on data storage and computational resources but also achieves accurate sensor fault diagnosis. Crucially, it effectively separates engine gas path faults from sensor faults, thus eliminating the potential interference of gas path faults on sensor fault diagnosis and isolation outcomes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Microstructure,mechanical properties and post-weld heat treatments of dissimilar laser-welded Ti_(2)AlNb/Ti60 sheet

引用

Rare Metals 2023年第4期42卷 1332-1342页

作者： Yong Wu Gang Liu Zhi-Qiang Liu Ze-Jun Tang Bin Wang State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin150001China School of Materials Science and Engineering Harbin Institute of TechnologyHarbin150001China College of Mechanical and Electrical Engineering Nanjing University of Aeronautics and AstronauticsNanjing211106China Beijing Xinghang Mechanical-Electrical Equipment Co. Ltd.Beijing100074China

Dissimilar joining of Ti_(2)AlNb and Ti60 rolled sheet was performed by laser beam *** microstructures and mechanical properties of as-welded and post-weld heat-treated Ti_(2)AlNb/Ti60 joints were investigated by microstructure observation and mechanical properties *** fusion zone(FZ)of the as-welded joint consisted of B_(2)/βmatrix and small S2 *** heataffected zones HAZ-Ti_(2)AINb and HAZ-Ti60 for the aswelded joint were characterized asα_(2)+B_(2)/β+O andα'+α+β+S_(2),*** tensile strength and elongation of as-welded sheet were 597.5 MPa and 6.2%at650℃,*** of the plastic deformation was taken place at the side of Ti60 *** the increase in the heat treatment temperature,the anchoring strength between each other of B_(2)/βgrains was enhanced by the precipitated lamellarα'and O grains at the *** depth of the fracture dimples increased with the heat treat temperature *** heat-treated welding joint at970℃presented a good balance of the tensile strength and plasticity,where the tensile strength and the elongation were enhanced to 669.7 MPa and 7.1%at 650℃,respectively.

关键词： Ti_(2)AlNb Laser beam welding Post-weld heat treatment Mechanical properties Dissimilar welding

来源：评论

学校读者我要写书评

暂无评论

Viscoelastic negative stiffness metamaterial with multistage load bearing and programmable energy absorption ability

引用

International Journal of Smart and Nano Materials 2025年第1期16卷 1-23页

作者： Tianzhen Liu Cheng Lin Yonglin Zhang Jianguo Cai Jinglei Yang Key Laboratory of C&PC Structures of Ministry of Education National Prestress Engineering Research CenterSoutheast UniversityNanjingChina National key laboratory of science and technology on advanced composites in special environments Harbin Institute of TechnologyHarbinChina Department of Mechanical and Aerospace Engineering Hong Kong University of Science and TechnologyHong KongChina HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute ShenzhenChina

The mechanical properties of negative stiffness(NS)metamaterial could be customized and tuned in a wide range for various requirements,achieving programmable performances by the design from the aspect of structure and *** work investigates the viscoelastic NS metamaterial based on double curved beams using a combined approach of experiments,simulations,and analytical modeling with an emphasis on multistage loading bearing and programmable energy absorption *** simulations are first implemented based on the finite element models of three types of metamaterial cells,which provide comparisons of load bearing and energy absorption ***,the effects of geometric parameters of multistage metamaterial element and the mechanisms are *** analytical discrete model is then innovatively developed to provide straightforward understandings of the geometric effects and reveal the role of viscoelasticity by examining the instantaneous loading responses and rate-dependent ***,we fabricate the metamaterial samples using 3D-printing technique and perform compression tests to validate the properties based on different boundary conditions,loading rates and cyclic loading and *** of this work show the potential of wide programmable room for mechanical properties through structure and functional material design,such as multistage load bearing capacity and energy absorption ability.

关键词： Negative stiffness viscoelasticity discrete model energy absorption

来源：评论

学校读者我要写书评

暂无评论

Beneficial effects of deep cryogenic treatment on mechanical properties of additively manufactured high entropy alloy:cyclic vs single cryogenic cooling

引用

Journal of Materials science & technology 2022年第20期115卷 40-51页

作者： Hongge Li Wenjie Zhao Tian Chen Yongjiang Huang Jianfei Sun Ping Zhu Yunzhuo Lu Alfonso H.W.Ngan Daqing Wei Qing Du Yongchun Zou School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China School of Materials Science and Engineering Dalian Jiaotong UniversityDalian 116028China Department of Mechanical Engineering The University of Hong KongHong KongChina Center of Analysis Measurement and Computing Harbin Institute of TechnologyHarbin 150001China

Additively manufactured(AM)metallic materials commonly possess substantial tensile surface residual stress,which is detrimental to the load-bearing service ***,we demonstrated that deep cryogenic treatment(DCT)is an effective method for improving the tensile properties of CoCrFeMnNi high-entropy alloy(HEA)samples fabricated by laser melting deposition(LMD),by introducing high compressive residual stress and deformation microstructures without destroying the AM ***,carrying out the DCT in a single-step mode does not improve the residual stress gradients inherent from the LMD process,which are undesirable as the mechanical properties will not be homogeneous within the *** this work,we show that carrying out the DCT in a cyclic mode with repeated cryogenic cooling and reheating can significantly homogenize the residual stress in LMD-fabricated Co Cr Fe Mn Ni HEA,and improve tensile strength and ductility,compared with single-step DCT of the same cryogenic soaking *** cyclic DCT,the thermal stress is re-elevated to a high value at each cryogenic cooling step,leading to the formation of denser and more intersecting reinforcing crystalline defects and hcp phase transformation,compared to single-step DCT of the same total cryogenic soaking duration in which the thermal stress relaxes towards a low value over *** enhancement of defect formation in the cyclic mode of DCT also leads to more uniform residual stress distribution in the sample after the *** results here provide important insights on optimizing DCT processes for post-fabrication improvement of mechanical properties of AM metallic net shapes.

关键词： Additive manufacturing High entropy alloy Deep cryogenic treatment Residual stress Mechanical properties

来源：评论

学校读者我要写书评

暂无评论

Task scheduling and data replication in cloud with improved correlation strategy

引用

International Journal of computers and Applications 2023年第11期45卷 697-708页

作者： Rambabu, D. Govardhan, A. Department of Computer Science and Engineering Sreenidhi Institute of Science and Technology Hyderabad India Department of Computer Science and Engineering Jawaharlal Nehru Technological University Hyderabad Hyderabad India

Cloud providers frequently utilize two tightly coupled resource management strategies like task scheduling & data replication to boost the performance of the system generally, guaranteeing service level agreement (SLA) compliance, as well as protecting their own financial gain. An Improved Correlation strategy-based Task Scheduling and Data Replication in Cloud (ICTSDC) is what this work aims to give. The suggested system's primary phases are as follows: Management of replication and task scheduling. Initial job scheduling will be optimization-based and take into account goals such bottleneck value, migration cost, VM load, enhanced correlation, and replication, respectively. For this, a brand-new extended DMO algorithm called Self-adaptive Dwarf Mongoose Optimization (SADMO) is presented. In the replication management stage, the potential copies must first be identified based on the prior objective. The suggested SADMO model implements the optimization technique for replica placement throughout the replication management process. The outcomes of the ICTSDC technique are evaluated to other methods using a variety of metrics, like bottleneck value, migration cost, Virtual Machine (VM) load, improved correlation, as well as replication efficiency. A lower mean value of 0.324 is gained with the ICTSDC scheme for fitness. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Virtual machine

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：