检索结果-内蒙古大学图书馆

A Server Placement Algorithm for Reducing Risk and Improving Power Utilization in Data Centers

Tsinghua science and technology 2024年第1期29卷 158-173页

作者： Rui Chen Huikang Huang Xiaoxuan Luo Weiwei Lin School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China Peng Cheng Laboratory Shenzhen 518066China

As the power demand in data centers is increasing,the power capacity of the power supply system has become an essential resource to be *** many data centers use power oversubscription to make full use of the power capacity,there are unavoidable power supply risks associated with ***,how to improve the data center power capacity utilization while ensuring power supply security has become an important *** solve this problem,we first define it and propose a risk evaluation metric called Weighted Power Supply Risk(WPSRisk).Then,a method,named Hybrid Genetic Algorithm with Ant Colony System(HGAACS),is proposed to improve power capacity utilization and reduce power supply risks by optimizing the server placement in the power supply *** uses historical power data of each server to find a better placement solution by population *** possesses not only the remarkable local search ability of Ant Colony System(ACS),but also enhances the global search capability by incorporating genetic operators from Genetic Algorithm(GA).To verify the performance of HGAACS,we experimentally compare it with five other placement *** experimental results show that HGAACS can perform better than other algorithms in both improving power utilization and reducing the riskof powersupply system.

关键词： server placement power utilization power supply risk swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

Autonomous embodied navigation task generation from natural language dialogues

引用

science China(Information sciences) 2025年第5期68卷 119-132页

作者： Haifeng XU Yongchang LI Lumeng MA Chunwen LI Yanzhi DONG Xiaohu YUAN Huaping LIU Department of Automation Tsinghua University School of Physics and Electronic Information Yantai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Department of Computer Science and Technology Tsinghua University

Robots are increasingly being deployed in densely populated environments, such as homes, hotels, and office buildings, where they rely on explicit instructions from humans to perform tasks. However, complex tasks often require multiple instructions and prolonged monitoring, which can be time-consuming and demanding for users. Despite this, there is limited research on enabling robots to autonomously generate tasks based on real-life scenarios. Advanced intelligence necessitates robots to autonomously observe and analyze their environment and then generate tasks autonomously to fulfill human requirements without explicit commands. To address this gap, we propose the autonomous generation of navigation tasks using natural language dialogues. Specifically, a robot autonomously generates tasks by analyzing dialogues involving multiple persons in a real office environment to facilitate the completion of item transportation between various *** propose the leveraging of a large language model(LLM) through chain-of-thought prompting to generate a navigation sequence for a robot from dialogues. We also construct a benchmark dataset consisting of 625 multiperson dialogues using the generation capability of LLMs. Evaluation results and real-world experiments in an office building demonstrate the effectiveness of the proposed method.

关键词： proactive robot robot navigation service robot large language model

来源：评论

学校读者我要写书评

暂无评论

Analytical review and study on various course recommendation systems

引用

International Journal of Wireless and Mobile Computing 2023年第2期25卷 160-170页

作者： Anupama, V. Elayidom, M. Sudheep Division of Computer Science School of Engineering Cochin University of Science and Technology Kerala Kochi India

In the educational system, online courses are significant in developing the knowledge of users. The selection of courses is important for college students because of large unknown optional courses. The course recommendation systems are provided with suggestions and improve course selection during the pre-registration stage. This survey presents the analysis of 50 research papers for course recommendation. The course recommendation systems are grouped under three categories, namely machine learning-based techniques, collaborative-based and data mining-based techniques. Besides, the classification of techniques, utilised tools, implemented software tools and performance metrics are considered for analysis. Moreover, the research gaps identified in the existing course recommendation system are discussed. The machine learningbased approach is mostly used for course recommendation among several approaches. Most existing course recommendation techniques use Java as the implementation tool and the Moodle log database. Also, F-measure, MAE, accuracy and RMS have been commonly used as performance metrics. © 2023 Inderscience Enterprises Ltd.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

A Software Defect Prediction Method Using a Multivariate Heterogeneous Hybrid Deep Learning Algorithm

引用

computers, Materials & Continua 2025年第2期82卷 3251-3279页

作者： Qi Fei Haojun Hu Guisheng Yin Zhian Sun College of Computer Science and Technology Harbin Engineering UniversityHarbin150001China Information Technology Research Department Jiangsu Automation Research InstituteLianyungang222062China School of Computer Science and Technology Harbin Institute of TechnologyShenzhen518055China

Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detection efficiency. Additionally, this technology provides developers with a means to quickly identify errors, thereby improving software robustness and overall quality. However, current research in software defect prediction often faces challenges, such as relying on a single data source or failing to adequately account for the characteristics of multiple coexisting data sources. This approach may overlook the differences and potential value of various data sources, affecting the accuracy and generalization performance of prediction results. To address this issue, this study proposes a multivariate heterogeneous hybrid deep learning algorithm for defect prediction (DP-MHHDL). Initially, Abstract Syntax Tree (AST), Code Dependency Network (CDN), and code static quality metrics are extracted from source code files and used as inputs to ensure data diversity. Subsequently, for the three types of heterogeneous data, the study employs a graph convolutional network optimization model based on adjacency and spatial topologies, a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) hybrid neural network model, and a TabNet model to extract data features. These features are then concatenated and processed through a fully connected neural network for defect prediction. Finally, the proposed framework is evaluated using ten promise defect repository projects, and performance is assessed with three metrics: F1, Area under the curve (AUC), and Matthews correlation coefficient (MCC). The experimental results demonstrate that the proposed algorithm outperforms existing methods, offering a novel solution for software defect prediction.

关键词： Software defect prediction multiple heterogeneous data graph convolutional network models based on adjacency and spatial topologies CNN-BiLSTM TabNet

来源：评论

学校读者我要写书评

暂无评论

Semi-Discrete Optimal Transport for Long-Tailed Classification

引用

计算机科学技术学报（英文版） 2025年第1期40卷 252-266页

作者：金连宝雷娜罗钟铉吴瑾艾超顾险峰 School of Mathematical Sciences Dalian University of Technology Dalian China International School of Information Science and Engineering Dalian University of Technology Dalian China School of Software Technology Dalian University of Technology Dalian China Huawei Technologies Co. Ltd Shenzhen China Department of Computer Science Stony Brook University New York USA

The long-tailed data distribution poses an enormous challenge for training neural networks in classification.A classification network can be decoupled into a feature extractor and a *** paper takes a semi-discrete opti-mal transport(OT)perspective to analyze the long-tailed classification problem,where the feature space is viewed as a continuous source domain,and the classifier weights are viewed as a discrete target *** classifier is indeed to find a cell decomposition of the feature space with each cell corresponding to one *** imbalanced training set causes the more frequent classes to have larger volume cells,which means that the classifier's decision boundary is biased towards less frequent classes,resulting in reduced classification performance in the inference ***,we propose a novel OT-dynamic softmax loss,which dynamically adjusts the decision boundary in the training phase to avoid overfitting in the tail *** addition,our method incorporates the supervised contrastive loss so that the feature space can satisfy the uniform distribution *** and comprehensive experiments demonstrate that our method achieves state-of-the-art performance on multiple long-tailed recognition benchmarks,including CIFAR-LT,ImageNet-LT,iNaturalist 2018,and Places-LT.

关键词： semi-discrete optimal transport long-tailed classification decision boundary supervised contrastive loss

来源：评论

学校读者我要写书评

暂无评论

LightNestle: Quick and Accurate Neural Sequential Tensor Completion via Meta Learning 42

LightNestle: Quick and Accurate Neural Sequential Tensor Com...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Li, Yuhui Liang, Wei Xie, Kun Zhang, Dafang Xie, Songyou Li, KuanChing Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan411201 China

ISBN: (纸本)9798350334142

Network operation and maintenance rely heavily on network traffic monitoring. Due to the measurement overhead reduction, lack of measurement infrastructure, and unexpected transmission error, network traffic monitoring systems suffer from incomplete observed data and high data sparsity problems. Recent studies model missing data recovery as a tensor completion task and show good performance. Although promising, the current tensor completion models adopted in network traffic data recovery lack an effective and efficient retraining scheme to adapt to newly arrived data while retaining historical information. To solve the problem, we propose LightNestle, a novel sequential tensor completion scheme based on meta-learning, which designs (1) an expressive neural network to transfer spatial knowledge from previous embeddings to current embeddings;(2) an attention-based module to transfer temporal patterns into current embeddings in linear complexity;and (3) meta-learning-based algorithms to iteratively recover missing data and update transfer modules to catch up with learned knowledge. We conduct extensive experiments on two real-world network traffic datasets to assess our performance. Results show that our proposed methods achieve both fast retraining and high recovery accuracy. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Designing new low alloyed Mg-RE alloys with high strength and ductility via high-speed extrusion

引用

International Journal of Minerals,Metallurgy and Materials 2023年第1期30卷 82-91页

作者： Jinshu Xie Zhi Zhang Shujuan Liu Jinghuai Zhang Jun Wang Yuying He Liwei Lu Yunlei Jiao Ruizhi Wu Key Laboratory of Superlight Material and Surface Technology Ministry of EducationCollege of Materials Science and Chemical EngineeringHarbin Engineering UniversityHarbin 150001China School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China Ningbo Branch Ordnance Science Institute of ChinaNingbo 315103China School of Materials Science and Engineering Hunan University of Science and TechnologyXiangtan 411201China

Two new low-alloyed Mg-2RE-0.8Mn-0.6Ca-0.5Zn(wt%,RE=Sm or Y)alloys are developed,which can be produced on an in-dustrial scale via relatively high-speed *** two alloys are not only comparable to commercial AZ31 alloy in extrudability,but also have superior mechanical properties,especially in terms of yield strength(YS).The excellent extrudability is related to less coarse second-phase particles and high initial melting point of the two as-cast *** high strength-ductility mainly comes from the formation of fine grains,nano-spaced submicron/nano precipitates,and weak ***,it is worth noting that the YS of the two alloys can maintain above 160 MPa at elevated temperature of 250°C,significantly higher than that of AZ31 alloy(YS:45 MPa).The Zn/Ca solute segregation at grain boundaries,the improved heat resistance of matrix due to addition of RE,and the high melting points of strengthening particles(Mn,MgZn_(2),and Mg-Zn-RE/Mg-Zn-RE-Ca)are mainly responsible for the excellent high-temperature strength.

关键词： magnesium alloys high-speed extrusion high strength high ductility solute segregation

来源：评论

学校读者我要写书评

暂无评论

Renaissance of Fuzzy and Fast Matching Entity with DSHS Algorithm

引用

SN computer science 2024年第6期5卷 1-14页

作者： Kari, Venkatram Amalanathan, Geetha Mary School of Computer Science and Engineering Vellore Institute of Technology University

Entity matching is a crucial aspect of data management systems, requiring the identification of real-world entities from diverse expressions. Despite the human ability to recognize equivalences among entities, machines struggle due to variations in expression. This challenge underscores the necessity for a robust framework capable of matching entities based on their attributes. While previous studies have explored transformation techniques, NLP, and deep learning, they often fall short in accuracy and scalability or overlook internal constraints. Such shortcomings result in costly rework and compromised business decisions. To address these issues, proposed “Deep Semantic Homophonic Synonymy” (DSHS) algorithm, a hybrid approach integrating rule-based, NLP, and deep learning techniques. By employing semantic matching, rule-based preprocessing, NLP enrichment, phonetic analysis, abbreviation variations, and spelling corrections, the DSHS algorithm effectively overcomes entity matching challenges. This solution, comprising six modules including Preprocessing, Transformation, Translation, Word Embedding, Attribute Similarity, and Classification, outperforms existing EM models in terms of accuracy and scalability. This solution is a comprehensive entity matching, offering significant advancements in the field and providing a reliable framework for resolving complex matching requirements. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Data pipeline Data sync up MDDR Message queue Schema registry

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF TWO ANY ORDER SPECTRAL VOLUME METHODS FOR 1-D LINEAR HYPERBOLIC EQUATIONS WITH DEGENERATE VARIABLE COEFFICIENTS

引用

Journal of Computational Mathematics 2024年第6期42卷 1627-1655页

作者： Minqiang Xu Yanting Yuan Waixiang Cao Qingsong Zou College of Science Zhejiang University of TechnologyHangzhou 310023China School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510275China School of Mathematical Sciences Beijing Normal UniversityBeijing 100875China School of Computer Science and Engineering and Guangdong Province Key Laboratory of Computational ScienceSun Yat-sen UniversityGuangzhou 510275China

In this paper,we analyze two classes of spectral volume(SV)methods for one-dimensional hyperbolic equations with degenerate variable *** classes of SV methods are constructed by letting a piecewise k-th order(k≥1 is an integer)polynomial to satisfy the conservation law in each control volume,which is obtained by refining spectral volumes(SV)of the underlying mesh with k Gauss-Legendre points(LSV)or Radaus points(RSV)in each *** L^(2)-norm stability and optimal order convergence properties for both methods are rigorously proved for general non-uniform ***,we discover some very interesting superconvergence phenomena:At some special points,the SV flux function approximates the exact flux with(k+2)-th order and the SV solution itself approximates the exact solution with(k+3/2)-th order,some superconvergence behaviors for element averages errors have been also ***,these superconvergence phenomena are rigorously proved by using the so-called correction function *** theoretical findings are verified by several numerical experiments.

关键词： Spectral Volume Methods L^(2)stability Error estimates Superconvergence

来源：评论

学校读者我要写书评

暂无评论

Enhanced rate capability and cycle stability of Ti2C MXene for sodium storage through an aniline molecules welding strategy

引用

Tungsten 2025年第1期7卷 161-171页

作者： Hao Chen Ya-Qin Wang Dong-Ting Zhang Bei Zhao Min-Peng Li Chen-Yang Li Tian-Peng Xu Mao-Cheng Liu State Key Laboratory of Advanced Processing and Recycling of Non-Ferrous Metals Lanzhou University of Technology School of Materials Science and Engineering Lanzhou University of Technology School of Computer and Communication Technology Lanzhou University of Technology

MXenes obtained significant attention in the field of energy storage devices due to their characteristic layered structure,modifiable surface functional groups,large electrochemically active surface,and regulable interlayer ***,the self-restacking and sluggish ions diffusion kinetics performance of MXenes during the alkali metal ions insertion/extraction process severely impedes their cycle stability and rate *** paper proposes an aniline molecule welding strategy for welding p-phenylenediamine（PPDA） into the interlayers of Ti2C through a dehydration condensation *** welded PPDA molecules can contribute pillar effect to the layered structure of *** pillar effect effectively maintains the structural stability during the sodium ions insertion/extraction process and effectively expands the interlayer spacing of Ti2C from 1.16 to 1.38 nm,thereby enhancing ions diffusion kinetics performance and improving the long-term cycle *** Ti2C-PPDA demonstrates outstanding Na+storage capability,exhibiting a specific capacity of 100.2 mAh·g-1at a current density of 0.1 A·g-1over 960 cycles and delivering a remarkable rate capability 81.2 mAh·g-1at a current density of 5 A·*** study demonstrates that expanding interlayer spacing is a promising strategy to enhance the Na+storage capacity and improve long-term cycling stability,which provides significant guidance for the design of two-dimensional Na+storage materials with high-rate capability and cycle stability.

关键词： Ti_2C Expanding interlayer spacing Sodium ions storage Diffusion kinetics Rate capability

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：