检索结果-内蒙古大学图书馆

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Xiaosong Han Chengyang Zhou Yanchun Liang Renchu Guan Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun China Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Zhuhai Laboratory of Key Laboratory for Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Zhuhai College of Science and Technology Zhuhai China

Particle Swarm Optimization with Migration (MPSO) is proposed to solve the issue that PSO will encounter unbearable time cost problems when dealing with High-dimension, Expensive and Black-box objective function tasks. The Migration operator is inspired by the migration of Salmon. Salmon will start a dangerous journey from the ocean to the home rivers for reproduction. The process of the entire behavior is similar to the reduction and recovery of dimension. Therefore, we design the Migration operator where a pretrained Wasserstein Autoencoders (WAE) is applied to simulate the migration behavior to accelerate the process of evolution in PSO, and we use Least-Squares Regression in lower space to produce better generation. In comparison with famous baseline methods in some benchmark functions, MPSO converges faster and more accurately, which shows the great potential of migration operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic multi-objective optimization algorithm based on weighted differential prediction model 4

Dynamic multi-objective optimization algorithm based on weig...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Zhao, Yumeng Wang, Xianpeng Dong, Zhiming Wang, Yao Lou, Hangyu Hu, Tenghui Fu, Kai Tang, Lixin Northeastern University Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Shenyang110819 China Northeastern University Liaoning Engineering Laboratory of Operation Analytics and Optimization for Smart Industry Liaoning Key Laboratory of Manufacturing System and Logistics Ministry of Education Shenyang110819 China Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Shenyang110819 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

In this paper, a new algorithm for solving dynamic multi-objective optimization problems(DMOPs) is proposed. Most of the traditional dynamic multi-objective optimization algorithms will make predictions based on the overall average evolutionary direction of the population, which is hardly applicable to problems where the solution set and frontier do not vary with the environmental rules. In this paper, a dynamic multi-objective optimization algorithm based on weight difference prediction model is designed to solve such problems. The algorithm contains a weighted differential prediction strategy, and a differential model is built for each individual using the weights to predict the initial population after environmental changes. With this approach, each individual in the population can be made to respond quickly to environmental changes. We used three classical comparison algorithms to conduct experiments on a series of test problems. The experimental results show that the WD-MOEA/D algorithm can significantly improve the dynamic optimization performance and is effective in solving different types of dynamic problems. © 2022 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss 38

Semi-supervised Multi-label Learning with Balanced Binary An...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Ximing Liang, Silong Li, Changchun Wang, Pengfei Gu, Fangming College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Computer Network Information Center Chinese Academy of Sciences China University of Chinese Academy of Sciences Chinese Academy of Sciences China

Semi-supervised multi-label learning (SSMLL) refers to inducing classifiers using a small number of samples with multiple labels and many unlabeled samples. The prevalent solution of SSMLL involves forming pseudo-labels for unlabeled samples and inducing classifiers using both labeled and pseudo-labeled samples in a self-training manner. Unfortunately, with the commonly used binary type of loss and negative sampling, we have empirically found that learning with labeled and pseudo-labeled samples can result in the variance bias problem between the feature distributions of positive and negative samples for each label. To alleviate this problem, we aim to balance the variance bias between positive and negative samples from the perspective of the feature angle distribution for each label. Specifically, we extend the traditional binary angular margin loss to a balanced extension with feature angle distribution transformations under the Gaussian assumption, where the distributions are iteratively updated during classifier training. We also suggest an efficient prototype-based negative sampling method to maintain high-quality negative samples for each label. With this insight, we propose a novel SSMLL method, namely Semi-Supervised Multi-Label Learning with Balanced Binary Angular Margin loss (S2ML2-BBAM). To evaluate the effectiveness of S2ML2-BBAM, we compare it with existing competitors on benchmark datasets. The experimental results validate that S2ML2-BBAM can achieve very competitive performance. © 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

Plus ça change, plus c'est la même chose – The Australian Records Management Case 18th

Plus ça change, plus c'est la même chose – The Australian...

引用

18th International Conference on Information for a Better World: Normality, Virtuality, Physicality, Inclusivity, iConference 2023

作者： Xie, Sherry L. Gao, Yubao Ma, Linqing School of Information Resource Management Renmin University of China Beijing100872 China Center for Digital Records Management Research Renmin University of China Beijing100872 China Key Laboratory of Data Engineering and Data Knowledge of the Ministry of Education of China Beijing100872 China Center for Archival Undertakings Renmin University of China Beijing100872 China

ISBN: (纸本)9783031280344

Intrigued by the information management replacing records management phenomenon, this study aimed at shedding light on it. Relying on preserved websites, the study examined relevant contents from 2007 to early 2022. It discovered the battle between records and information, and later on information asset. This battle incurred dazzling changes in managerial considerations, yet the challenges to management – either towards records, information, information and records, or information asset – remained the same. So were the unsatisfactory outcomes. A case seemed perfect to tell the plus ça change, plus c'est la même chose story. It is our hope that future studies can gather mighty strengthen and thus settle down the records-information battle once for all. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Reynosin protects neuronal cells from microglial neuroinflammation by suppressing NLRP3 inflammasome activation mediated by NADPH oxidase

引用

Chinese Journal of Natural Medicines 2024年第6期22卷 486-500页

作者： YANG Yanqiu CHE Yue FANG Mingxia YAO Xiaohu ZHOU Di WANG Feng CHEN Gang LIANG Dong LI Ning HOU Yue Key Laboratory of Bioresource Research and Development of Liaoning Province College of Life and Health SciencesNorth-eastern UniversityShenyang 110000China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Key Laboratory of Data Analytics and Optimization for Smart IndustryMinistry of EducationNortheastern UniversityShenyang 110000China School of Traditional Chinese Materia Medica Key Laboratory of Innovative Traditional Chinese Medicine for Major Chronic Diseases of Liaoning provinceKey Laboratory for TCM Material Basis Study and Innovative Drug Development of Shenyang CityShenyang Pharmaceutical UniversityShenyang 110000China State Key Laboratory for Chemistry and Molecular Engineering of Medicinal Resources School of Chemistry and Pharmaceutical SciencesGuangxi Normal UniversityGuilin 541000China

Neuroinflammation,mediated by the nucleotide-binding oligomerization domain-like receptor family pyrin domain-containing-3(NLRP3)inflammasome,is a significant contributor to the pathogenesis of neurodegenerative diseases(NDDs).Reynos-in,a natural sesquiterpene lactone(SL),exhibits a broad spectrum of pharmacological effects,suggesting its potential therapeutic ***,the effects and mechanism of reynosin on neuroinflammation remain *** current study explores the effects and mechanisms of reynosin on neuroinflammation using mice and BV-2 microglial cells treated with lipopolysaccharide(LPS).Our findings reveal that reynosin effectively reduces microglial inflammation in vitro,as demonstrated by decreased CD11b expression and lowered interleukin-1 beta(IL-1β)and interleukin-18(IL-18)mRNA and protein ***,in vivo,results showed a re-duction in the number of Iba-1 positive cells and alleviation of morphological alterations,alongside decreased expressions of IL-1βand *** analysis indicates that reynosin inhibits NLRP3 inflammasome activation,evidenced by reduced transcription of NLRP3 and caspase-1,diminished NLRP3 protein expression,inhibited apoptosis-associated speck-like protein containing a CARD(ASC)oli-gomerization,and decreased caspase-1 ***,reynosin curtailed the activation of nicotinamide adenine dinuc-leotide phosphate(NADPH)oxidase,demonstrated by reduced NADP^(+)and NADPH levels,downregulation of gp91^(phox) mRNA,pro-tein expression,suppression of p47^(phox) expression and translocation to the ***,reynosin exhibited a neuroprotective effect against microglial inflammation in vivo and in *** collective findings underscore reynosin’s capacity to mitigate mi-croglial inflammation by inhibiting the NLRP3 inflammasome,thus highlighting its potential as a therapeutic agent for managing neuroinflammation.

关键词： Microglia NLRP3 inflammasome Reactive oxygen species NADPH oxidase Neuron Reynosin

来源：评论

学校读者我要写书评

暂无评论

PNESR-DDI: An Effective Drug-Drug Interaction Prediction Model Based on Pretraining Method and Enhanced Subgraph Reconstruction

PNESR-DDI: An Effective Drug-Drug Interaction Prediction Mod...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ke Chen Xiaosong Han Xiaoran Li Yanchun Liang Dong Xu Renchu Guan Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Software Jilin University Changchun China Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education School of Computer Science Zhuhai College of Science and Technology Zhuhai China Department of Electrical Engineering and Computer Science Christopher S. Bond Life Sciences Center University of Missouri Columbia USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Drug-Drug Interaction (DDI) task plays a crucial role in clinical treatment and drug development. Recently, deep learning methods have been successfully applied for DDI prediction. However, training deep learning models always need large amount of data, while known DDIs are scarce. To address this challenge, a graph neural network-based DDI prediction model named PNESR-DDI is proposed, which compensates for the lack of DDIs by enriching drug representations. First, to obtain initial node representations that incorporate rich semantic information from the biomedical knowledge graph (KG), a link prediction pre-training method on external KG is proposed in the node embedding pre-training module. Then, considering the large scale of the KG, subgraph extraction for the target drug pairs is introduced to reduce noise and decrease computational complexity in the subgraph anchoring module. After that, the subgraph is updated, and node similarities are propagated in the subgraph reconstruction module. Based on the node similarity scores, the subgraph is pruned and reconstructed, which adjusts node representations to be more conducive to DDI prediction. Finally, the drug embeddings, subgraph representations, and drug fingerprint features are concatenated to predict DDIs. PNESRDDI is evaluated on two benchmark DDI datasets: DrugBank and TWOSIDES. Experiment results show that PNESR-DDI achieves better performance than baselines. Ablation results validate the effectiveness of the pre-training method and the adaptive subgraph reconstruction strategy.

关键词： Drugs Deep learning Adaptation models Visualization Biological system modeling Noise knowledge graphs Predictive models Fingerprint recognition Transformers

来源：评论

学校读者我要写书评

暂无评论

A Pruning Based Continuous RkNN Query Algorithm for Large k

引用

Chinese Journal of Electronics 2023年第3期21卷 523-527页

作者： Shengsheng WANG Sheng CHAI Qiannan LV College of Computer Science and Technology Key Laboratory of Symbolic Computing and Knowledge Engineering of Ministry of Education Jilin University Changchun China

Reverse k-nearest neighbor (RkNN) query is a hot-spot in spatio-temporal database. With the developing of mobile devices, continuous RkNN query becomes more and more important. Most of the previous methods use the two-step (filter-refinement) processing. However, for large k, the amount of calculation becomes very heavy, especially in the filter step. This is not acceptable for most mobile devices. This paper presents a novel algorithm for continuous RkNN queries based on pruning heuristics. The experiments show that the processing time of our method is still acceptable for most mobile devices when k is large.

关键词： Location awareness databases Heuristic algorithms Filtering algorithms Mobile handsets Mobile applications

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Framework for Delivery Capacity Scheduling with Vehicle Constraints 20

Reinforcement Learning Framework for Delivery Capacity Sched...

引用

20th IEEE International Conference on e-Business engineering, ICEBE 2024

作者： Ma, Zhongneng Qin, Zhuorui Shi, Shuxia Wu, Qingyao South China University of Technology Guangzhou China School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Guangzhou Henll Electronics Equipment Co. Ltd Guangzhou China Peng Cheng Laboratory China

ISBN: (纸本)9798350365856

Improving the risk prevention capability of grid operations is a crucial requirement for smart resilient grids, where efficient dispatch and scheduling of delivery capacity play a pivotal role in enhancing grid resilience. Therefore, it is necessary to develop targeted intelligent dispatch algorithms based on operational data. To address this issue, this paper proposes a framework with inherent constraints and utilizes reinforcement learning using recursive neural networks. A constraint module is designed to identify available vehicle combinations based on de-livery capacity, allocate goods considering vehicle number, load, and size constraints, and generate delivery routes sequentially. Additionally, a reinforcement learning model is introduced, using negative trip length as a reward signal, optimizing parameters of the recursive neural network through policy gradient methods to automatically improve strategies for selecting optimal deliv-ery routes with improved vehicle combinations. To validate the effectiveness of this algorithm, extensive experiments were conducted using both real-world application validation data and the TSPLIB public dataset. Within a limited computational budget, the proposed algorithm outperforms several mature methods in terms of effectiveness and real-time performance, achieving near-optimal results in Euclidean graphs with nearly 100 nodes. These results demonstrate that this approach effectively addresses the intelligent scheduling of delivery capacity in digital twin systems for power storage © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

A real-time temperature prediction method based on CNN-LSTM with MODE in steelmaking process

A real-time temperature prediction method based on CNN-LSTM ...

引用

IISE Annual Conference and Expo 2024

作者： Wang, Dan Liu, Chang Tang, Lixin Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Liaoning Key Laboratory of Manufacturing System and Logistics Optimization Shenyang110819 China Ministry of Education Shenyang110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China

ISBN: (纸本)9781713877851

Prediction of molten steel quality is a key issue in the converter steelmaking process. Due to high temperature and physical-chemical reaction, it is difficult to predict the temperature of molten steel in real time through mechanism analysis. This is a challenging problem with black box characteristics. Here we propose a Convolutional neural networks (CNN) and long short-term memory (LSTM) networks model based on multi-objective differential evolution algorithm (MODE) for the real-time prediction problem in the steelmaking process. Specifically, the CNN is used to extract feature between multiple variables that affect the temperature of molten steel, and the LSTM is suitable for the time series model based on the irregular trends information. The multi-step output CNN-LSTM method is used to construct the temperature prediction model of molten steel, and a knee solution strategy is applied to MODE, which can balance the model accuracy and generalization ability. The experiments were conducted using real data collected from the converter steelmaking process. The results verify the effectiveness of the proposed model on multiple steel grades and outperform other artificial intelligence methods in multi-task prediction. © IISE Annual Conference and Expo *** rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Simple Graph Contrastive Learning Framework for Short Text Classification

arXiv

引用

arXiv 2025年

作者： Liu, Yonghao Giunchiglia, Fausto Huang, Lan Li, Ximing Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University China University of Trento Italy

Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown promising results in addressing the challenges of semantic sparsity and limited labeled data in short text classification. However, existing models have certain limitations. They rely on explicit data augmentation techniques to generate contrastive views, resulting in semantic corruption and noise. Additionally, these models only focus on learning the intrinsic consistency between the generated views, neglecting valuable discriminative information from other potential views. To address these issues, we propose a Simple graph contrastive learning framework for Short Text Classification (SimSTC). Our approach involves performing graph learning on multiple text-related component graphs to obtain multi-view text embeddings. Subsequently, we directly apply contrastive learning on these embeddings. Notably, our method eliminates the need for data augmentation operations to generate contrastive views while still leveraging the benefits of multi-view contrastive learning. Despite its simplicity, our model achieves outstanding performance, surpassing large language models on various datasets. Copyright © 2025, 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

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：