检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Jiawei Zhao, Chunhui State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University China

Mixed time series (MiTS) comprising both continuous variables (CVs) and discrete variables (DVs) are frequently encountered yet under-explored in time series analysis. Essentially, CVs and DVs exhibit different temporal patterns and distribution types. Overlooking these heterogeneities would lead to insufficient and imbalanced representation learning, bringing biased results. This paper addresses the problem with two insights: 1) DVs may originate from intrinsic latent continuous variables (LCVs), which lose fine-grained information due to extrinsic discretization;2) LCVs and CVs share similar temporal patterns and interact spatially. Considering these similarities and interactions, we propose a general MiTS analysis framework MiTSformer, which recovers LCVs behind DVs for sufficient and balanced spatial-temporal modeling by designing two essential inductive biases: 1) hierarchically aggregating multi-scale temporal context information to enrich the information granularity of DVs;2) adaptively learning the aggregation processes via the adversarial guidance from CVs. Subsequently, MiTSformer captures complete spatial-temporal dependencies within and across LCVs and CVs via cascaded self- and cross-attention blocks. Empirically, MiTSformer achieves consistent SOTA on five mixed time series analysis tasks, including classification, extrinsic regression, anomaly detection, imputation, and long-term forecasting. The code is available at https://***/chunhuiz/MiTSformer. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Directed Acyclic Graphs With Tears

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 972-983页

作者： Chen, Zhichao Ge, Zhiqiang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Peng Cheng Laboratory Shenzhen518000 China

Bayesian network is a frequently used method for fault detection and diagnosis in industrial processes. The basis of Bayesian network is structure learning which learns a directed acyclic graph (DAG) from data. However, the search space will scale super-exponentially with the increase of process variables, which makes the data-driven structure learning a challenging problem. To this end, the DAGs with NOTEAR methods are being well studied not only for their conversion of the discrete optimization into continuous optimization problem but also their compatibility with deep learning framework. Nevertheless, there still remain challenges for NOTEAR-based methods: 1) the infeasible solution results from the gradient descent based optimization paradigm;2) the truncation operation to promise the learned graph acyclic. In this work, the reason for challenge 1) is analyzed theoretically, and a novel method named DAGs with tears method is proposed based on mix-integer programming to alleviate challenge 2). In addition, prior knowledge is able to incorporate into the new proposed method, making structure learning more practical and useful in industrial processes. Finally, a numerical example and an industrial example are adopted as case studies to demonstrate the superiority of the developed method. © 2020 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

RAGAN: Regression Attention Generative Adversarial Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1549-1563页

作者： Jiang, Xiaoyu Ge, Zhiqiang Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou310027 China Peng Cheng Laboratory Shenzhen518000 China

Despite surrounding by Big Data, we still need to learn from insufficient data in many scenarios. Building an accurate regression model for a small amount of data is a pretty tricky and exciting problem. At present, it is a promising solution to augment limited real data by generating data through generative adversarial networks (GANs). However, when GAN is used to generate labeled data in regression modeling, it lacks attention to the relationship between independent and dependent variables, resulting in poor performance of regression modeling. This article proposes a novel regression attention GAN (RA-GAN) for augmented regression modeling. Regression attention mechanisms are introduced into network parameters learning of both generator and discriminator in RA-GAN to establish a known relationship between variables. This makes RA-GAN restore the regression information during data generation. In addition, an indicator called cross regression score is designed to describe the quality of the generated data before augmented regression modeling, effectively evaluating data augmentation performance in advance. The effectiveness and superiority of the proposed methods are verified in an actual industrial soft-sensing case and a diabetes prediction case through data augmentation regression applications. © 2020 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

KNIGCN: key Node Identification in UAV Swarm Networks with Graph Convolution Networks

引用

IEEE Internet of Things Journal 2025年第11期12卷 16227-16242页

作者： Ai, Qixun Hou, Changbo Zhou, Zhichao Wu, Xiangyu Song, Zhen Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Harbin Engineering University College of Information and Communication Engineering Key Laboratory of Advanced Marine Communication and Information Technology Ministry of Industry and Information Technology Harbin150001 China

In the field of Internet of Things (IoT), Unmanned Aerial Vehicle (UAV) swarms are widely used to assist IoT communication due to their simple deployment, high mobility and high cost effectiveness to help improve IoT network coverage and topological flexibility. However, due to the openness of UAV swarm network, UAV nodes are vulnerable to malicious attacks and fail, especially some key nodes, which will seriously degrade the network performance. To solve this problem, a key node identification model based on Graph Convolutional Networks (GCN), named KNIGCN, is proposed. Specifically, the topology model of UAV cluster network is firstly built based on Flying Ad Hoc Network (FANET) communication architecture and Dijkstra's algorithm, then node criticality labels in the network are made by means of traffic statistics, and finally KNIGCN model is used to predict the criticality scores of each node and sort them so as to screen out a certain number of key nodes. The experimental results show that the model has good performance of key node identification. Compared with traditional methods, the proposed method makes a more reasonable judgment of node criticality, and the key nodes identified have a more important impact on network performance. Moreover, the proposed scheme can effectively improve the identification speed of key nodes in large-scale, complex or dynamically changing topology of UAV cluster networks. It can provide an effective scheme for maintaining the security and stability of UAV swarm network communication. © 2014 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Prediction model on hydrolysis kinetics of phthalate monoester:A density functional theory study

引用

Journal of Environmental Sciences 2024年第1期135卷 51-58页

作者： Tong Xu Jingwen Chen Deming Xia Weihao Tang Jiansheng Cui Chun Liu Shuangjiang Li College of Environmental Science and Engineering Hebei University of Science and TechnologyShijiazhuang 050000China Key Laboratory of Industrial Ecology and Environmental Engineering(Ministry of Education) School of Environmental Science and TechnologyDalian University of TechnologyDalian 116024China National-Regional Joint Engineering Research Center for Soil Pollution Control and Remediation in South China Guangdong Key Laboratory of Integrated Agro-environmental Pollution Control and ManagementInstitute of Eco-environmental and Soil SciencesGuangdong Academy of SciencesGuangzhou 510650China

As primary degradation products of phthalate esters,phthalate monoesters(MPEs)have been widely detected in various aquatic environments and drawn growing toxicological *** kinetics that is of importance for assessing environmental persistence of chemicals remain elusive for ***,kinetics of base-catalyzed and neutral hydrolysis for 18 MPEs with different leaving groups was investigated by density functional theory *** indicate that MPEs with leaving groups having p Kaof<10 prefer dissociative transition *** are more persistent than their parents,and their hydrolysis half-lives were calculated to vary from 3.4 min to 79.2 years(p H=7–9).A quantitative structure-activity relationship model was developed for predicting the hydrolysis kinetics *** was found that p Kaof the leaving groups and electronegativity of the MPEs are key factors determining the hydrolysis *** work may lay a theoretical foundation for better understanding the chemical process that governs MPE persistence in aquatic environments.

关键词： Phthalate monoesters Phthalate esters Hydrolysis Density functional theory Quantitative structure-activity relationship

来源：评论

学校读者我要写书评

暂无评论

Research Progress on the Solder Joint Reliability of Electronics Using in Deep Space Exploration

引用

Chinese Journal of Mechanical engineering 2023年第2期36卷 16-28页

作者： Qilong Guan Chunjin Hang Shengli Li Dan Yu Ying Ding Xiuli Wang Yanhong Tian State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin 150001China Beijing Institute of Control Engineering Beijing 100190China

The spacecraft for deep space exploration missions will face extreme environments,including cryogenic temperature,intense radiation,wide-range temperature variations and even the combination of conditions mentioned *** environments will lead to solder joints degradation or even failure,resulting in damage to onboard *** research activities on high reliability solder joints using in extreme environments can not only reduce the use of onboard protection devices,but effectively improve the overall reliability of spacecraft,which is of great significance to the aviation *** this paper,we review the reliability research on SnPb solder alloys,Sn-based lead-free solder alloys and In-based solder alloys in extreme environments,and try to provide some suggestions for the follow-up studies,which focus on solder joint reliability under extreme environments.

关键词： Deep space exploration Extreme environments Solder joints Microstructure Electronics Reliability

来源：评论

学校读者我要写书评

暂无评论

A chitosan-based antibacterial hydrogel with injectable and self-healing capabilities

引用

marine Life Science & technology 2024年第1期6卷 115-125页

作者： Rui Chen Yanan Hao Secundo Francesco Xiangzhao Mao Wen-Can Huang State Key Laboratory of Marine Food Processing and Safety Control College of Food Science and EngineeringOcean University of ChinaQingdao 266404China Laboratory for Marine Drugs and Bioproducts of Qingdao National Laboratory for Marine Science and Technology Qingdao 266237China Qingdao Key Laboratory of Food Biotechnology Qingdao 266404China Key Laboratory of Biological Processing of Aquatic Products China National Light IndustryQingdao 266404China Istituto di Scienze e Tecnologie Chimiche“Giulio Natta” Consiglio Nazionale delle Ricerche via Mario Bianco 920131 MilanItaly

The presence of bacteria directly affects wound ***-based hydrogel biomaterials are a solution as they offer advantages for wound-healing applications due to their strong antimicrobial ***,a double-cross-linking chitosanbased hydrogel with antibacterial,self-healing,and injectable properties is *** chitosan was successfully prepared,and the thiolated chitosan molecules were cross-linked by Ag-S coordination to form a supramolecular ***,the amine groups in the thiolated chitosan covalently cross-linked with genipin to further promote hydrogel *** vitro experimental results indicate that hydrogel can release Ag^(+)over an extended time,achieving an antibacterial rate of over 99% against Escherichia coli and Staphylococcus *** to the reversible and dynamic feature of Ag-S coordination,an antibacterial hydrogel exhibited injectable and self-healing ***,the hydrogel showed excellent biocompatibility and biodegradability.

关键词： Hydrogel Chitosan Silver ion Cross-linking Antibacterial

来源：评论

学校读者我要写书评

暂无评论

Investigation on the Natural Modes of A Semi-Closed Floating Tank

引用

China Ocean engineering 2023年第4期37卷 580-587页

作者： WANG Guo KONG Yao-hua GE Jun-bo MA Yu-xiang SUN Lei State Key Laboratory of Ocean Engineering Shanghai Jiao Tong UniversityShanghai 200240China Marine Design and Research Institute of China Shanghai 200011China State Key Laboratory of Coastal and Offshore Engineering Dalian University of TechnologyDalian 116024China

Vessels with semi-closed tanks(i.e.,well docks)are widely applied in the military operation and maritime *** water is bound by the semi-closed floating tank and forced by both the incident waves and ship’s *** free surface oscillations inside the flooded well dock is thus distinctive and very *** far,the natural modes of semi-closed floating tanks have not yet been *** paper investigates the characteristics of natural modes of a floating semi-closed tank by combining a mode-resolving model based on mild-slope equations and a hydrodynamic model based on computational fluid *** show that the first three natural periods(i.e.,74,23.6,and 14 s)of the tank fall into the band of swell and infragravity waves and they could be triggered under certain ***-period free surface oscillations are observed inside the tank,including the longest natural period(i.e.,74 s),though the incident waves are monochromatic.A possible generation mechanism for the long-period mode is explained on the basis of liquid sloshing and harbor ***,a long-period component with a period close to the natural mode of well dock is observed in the ship motions,which is generated by the interaction between the waves and ship.

关键词： floating semi-closed tank water free surface oscillations natural period natural mode mild-slope equa-tions computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Selective hydrodeoxygenation of polyethylene terephthalate plastic wastes into 1;4-dimethylcyclohexane by Ir-ReO_(x)/SiO_(2)+HZSM-5 catalytic system

引用

Science China Chemistry 2025年第4期68卷 1563-1575页

作者： Nan Wang Jieyi Liu Junde Wei Sibao Liu Guozhu Liu Key Laboratory for Green Chemical Technology of Ministry of Education School of Chemical Engineering and Technology Tianjin 300072China Engineering Research Center of Polymer Green Recycling of Ministry of Education Fujian Key Laboratory of Pollution Control&Resource ReuseCollege of Environmental and ResourcesFujian Normal UniversityFuzhou 350007China Haihe Lab of Sustainable Chemical Transformations Tianjin 300192China

In order to mitigate the environmental impact of polyethylene terephthalate(PET)plastic pollution and enhance waste resource utilization;we developed a novel Ir-ReO_(x)/SiO_(2)+HZSM-5 catalytic system for the hydrodeoxygenation(HDO)of PET plastic wastes into cycloalkanes;particularly 1;4-dimethylcyclohexane(DMCH).Under mild conditions(190℃;3 MPa H_(2))with a certain amount of water in cyclopentane solvent;the highest yield of DMCH reached 95.8%;contributing to an overall yield of cycloalkanes at 98.4%within a reaction time of 4 h from HDO of virgin *** HDO of PET into DMCH involved initial hydrogenation of PET aromatic ring;then depolymerized by direct hydrogenolysis of acyl C-O bond in the ester group and subsequent cascade HDO of alcoholic C-O bond to saturated ester and alcohol intermediates;and further HDO of these oxygenates converting into desired DMCH *** Ir-ReO_(x)/SiO_(2) catalyst exhibits fully reduced metallic Ir nanoparticles along with partially reduced ReO_(x) species that are highly dispersed on both SiO_(2) surface and Ir nanoparticle *** oxophilic nature of ReO_(x) species facilitates the activation of C-O bonds;the acidic HZSM-5 zeolite for the promotion of dehydration reaction;and the protic property of H_(2)O for the enhancement of hydrogenation PET contributed to highly HDO activity of this ***;the catalytic system is applicable for the HDO of diverse real-world PET plastic wastes including Coca-ColaTM bottles;green Sprite bottles and white and red discarded fiber cloths;generating DMCH with a yield of up to 95.9%and cycloalkanes with a yield of up to 99.5%.This innovative process presents a new avenue for efficient hydrodeoxygenation conversion of PET into easily separable DMCH which serves as a crucial building block for the production of terephthalic acid to realize the chemical recycling of PET plastic wastes towards a green circular economy.

关键词： plastic wastes PET hydrodeoxygenation cycloalkane Ir-ReO_(x)/SiO_(2)

来源：评论

学校读者我要写书评

暂无评论

Biodegradation of Crystalline Chitin:A Review of Recent Advancement,Challenges,and Future Study Directions

引用

Journal of Ocean University of China 2024年第5期23卷 1319-1328页

作者： SONG Jianlin SU Haipeng SUN Jianan MAO Xiangzhao Sanya Institute of Oceanography Ocean University of ChinaSanya 572000China State Key Laboratory of Marine Food Processing and Safety Control College of Food Science and EngineeringOcean University of ChinaQingdao 266404China Qingdao Key Laboratory of Food Biotechnology Qingdao 266404China Key Laboratory of Biological Processing of Aquatic Products China National Light IndustryQingdao 266404China Laboratory for Marine Drugs and Bioproducts of Laoshan Laboratory Qingdao 266237China

Chitin is the second most abundant renewable polysaccharide on *** degradation of chitin into soluble and bioactive N-acetyl chitooligosaccharides(NCOSs)and N-acetyl-D-glucosamine(GlcNAc)has emerged as a pivotal step in the efficient and sustainable utilization of chitin ***,because of its dense structure,high crystallinity,and poor solubility,chitin typically needs pretreatment via chemical,physical,and other methods before enzymatic conversion to enhance the accessibility between substrates and enzyme ***,there has been considerable interest in exploring the direct biological degradation of crystalline chitin as a cost-effective and environment-friendly *** review endeavors to present several biological methods for the direct degradation of *** primarily focused on the importance of chitinase containing chitin-binding domain(CBD).Additionally,various modification strategies for increasing the degradation efficiency of crystalline chitin were ***,the review systematically elucidated critical components of multi-enzyme catalytic systems,highlighting their potential for chitin ***,the application of microorganisms in the degradation of crystalline chitin was also *** insights in this review contribute to the explorations and investigations of enzymatic and microbial approaches for the direct degradation of crystalline chitin,thereby fostering advancements in biomass conversion.

关键词： crystalline chitin chitinase biological degradation engineering microorganisms

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：