检索结果-内蒙古大学图书馆

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Zhang, Shuaixiang Yang, Yixuan Tong, Hao Yao, Xin Lingnan University Department of Computing and Decision Sciences Hong Kong Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9798350308365

The uncapacitated facility location problem (UFLP) is a well-known combinational optimization problem, attracting numerous heuristic and meta-heuristic methods. However, these effective algorithms still encounter challenges when solving large-scale UFLP instances. To deal with the thousands of decision variables, one possible approach is to predict and remove unimportant facilities and thus decreases the dimensionality of problem instances. This paper explores the problem reduction of large-scale instances of UFLP. We propose suitable features of facilities to construct machine learning models for UFLP by learning from small instances. Based on this model, we introduce a novel problem reduction strategy-based optimization framework, and apply it to large instances. Through comprehen-sive experiments, we show that the proposed problem reduction strategy can effectively transform the UFLP instances to smaller ones. The performance of existing solution methods can be significantly enhanced, especially on large-scale instances. Under the proposed framework, we also show the generalization abilities of our models, which can be improved further. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Chemical environment adaptive learning for optical band gap prediction of doped graphitic carbon nitride nanosheets

引用

Neural computing and Applications 2025年第5期37卷 3287-3301页

作者： Chen, Chen Xu, Enze Yang, Defu Yan, Chenggang Wei, Tao Chen, Hanning Wei, Yong Chen, Minghan Intelligent Information Processing Laboratory Hangzhou Dianzi University Hangzhou China Department of Computer Science Wake Forest University Winston-SalemNC United States Department of Chemical Engineering Howard University WashingtonDC United States Texas Advanced Computing Center University of Texas at Austin AustinTX United States Department of Computer Science & Information Systems University of North Georgia DahlonegaGA United States

This study presents a new machine learning algorithm, named Chemical Environment Graph Neural Network (ChemGNN), designed to accelerate materials property prediction and advance new materials discovery. Graphitic carbon nitride (g-C3N4) and its doped variants have gained significant interest for their potential as optical materials. Accurate prediction of their band gaps is crucial for practical applications;however, traditional quantum simulation methods are computationally expensive and challenging to explore the vast space of possible doped molecular structures. The proposed ChemGNN leverages the learning ability of current graph neural networks (GNNs) to satisfactorily capture the characteristics of atoms' chemical environment underlying complex molecular structures. Our experimental results demonstrate more than 100% improvement in band gap prediction accuracy over existing GNNs on g-C3N4. Furthermore, the general ChemGNN model can precisely foresee band gaps of various doped g-C3N4 structures, making it a valuable tool for performing high-throughput prediction in materials design and development. © The Author(s) 2024.

关键词： Graphitic Carbon Nitride

来源：评论

学校读者我要写书评

暂无评论

Pre-processing of RDF data for METIS partitioning

引用

International Journal of Metadata, Semantics and Ontologies 2023年第2期16卷 152-171页

作者： Benhamed, Siham Nait-Bahloul, Safia LITIO Laboratory University Oran 1 Ahmed Ben Bella Oran Algeria Department of Computing and Mathematics University Abdelhamid Ibn Badis – Mostaganem Mostaganem Algeria LITIO Laboratory Department of Computer Science University Oran 1 Ahmed Ben Bella Oran Algeria

The partitioning of RDF data on a large scale allows generating a set of RDF data subgraphs. METIS is a graph partitioning technique that minimises the cost of partitioning. METIS applies, among other things, to RDF graphs. However, the semantics introduced in the description of RDF data is not taken into account in the partitioning process in METIS. For this, we propose in this paper a step of pre-processing RDF data before partitioning these data. The objective of this step is to improve the quality of semantic partitioning of RDF graphs. The evaluation of the RDF pre-processing step for METIS was performed on real and synthetic data. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

OFDM-structure based waveform designs for integrated sensing and communication

引用

science China(Information sciences) 2025年第5期68卷 267-284页

作者： Jiaqi LIU Ping YANG Ke JIANG Jiarong ZHAO Wei XIANG Jianping WEI Ruixiang DUAN Saviour ZAMMIT Tony Q.S.QUEK National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China School of Computing Engineering and Mathematical Sciences La Trobe University Meituan Academy of Robotics Department of Communications and Computer Engineering University of Malta Information Systems Technology and Design Pillar Singapore University of Technology and Design

The future sixth-generation(6G) paradigm aims to seamlessly integrate communication and environmental sensing capabilities into a single radio signal, promising improved efficiency and cost-effectiveness through simultaneous data communications and environmental perception. At the core of this evolution, orthogonal frequency division multiplexing(OFDM) and its advanced waveforms emerge as pivotal for integrated sensing and communications(ISAC). This study introduces a concise and unified ISAC waveform design framework based on orthogonal multicarriers. This framework supports versatile applications of OFDM and its derivative waveforms within a generalized ISAC system, marking a significant leap in integrating communication and sensing capabilities. A distinguishing feature of this framework is its adaptability,allowing users to intelligently select modulation strategies based on their specific environmental needs. This adaptability optimizes performance across diverse scenarios. Central to our innovations is the proposal of discrete Fourier transformspread OFDM with index modulation(DFT-S-OFDM-IM). This framework is paired with newly proposed signal processing methods for single-input single-output and multiple-input multiple-output(MIMO) systems. Extensive evaluations highlight DFT-S-OFDM-IM's superiority, including dramatically reduced peak-to-average power ratios(PAPRs), competitive communication performance, and exceptional sensing capabilities, striking an elegant balance between communication capacity and environmental sensing precision.

关键词： DFT-S-OFDM-IM index modulation integrated sensing and communication OFDM

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Multivariate Time Series Anomaly Detection in IoT

引用

computers, Materials & Continua 2023年第6期75卷 5027-5047页

作者： Shiming He Meng Guo Bo Yang Osama Alfarraj Amr Tolba Pradip Kumar Sharma Xi’ai Yan School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410114China Computer Science Department Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia Department of Computing Science University of AberdeenAberdeenAB243FXUK Hunan Provincial Key Laboratory of Network Investigational Technology Hunan Police AcademyChangsha410138China

Sensors produce a large amount of multivariate time series data to record the states of Internet of Things(IoT)*** time series timestamp anomaly detection(TSAD)can identify timestamps of attacks and ***,it is necessary to determine which sensor or indicator is abnormal to facilitate a more detailed diagnosis,a process referred to as fine-grained anomaly detection(FGAD).Although further FGAD can be extended based on TSAD methods,existing works do not provide a quantitative evaluation,and the performance is ***,to tackle the FGAD problem,this paper first verifies that the TSAD methods achieve low performance when applied to the FGAD task directly because of the excessive fusion of features and the ignoring of the relationship’s dynamic changes between ***,this paper proposes a mul-tivariate time series fine-grained anomaly detection(MFGAD)*** avoid excessive fusion of features,MFGAD constructs two sub-models to independently identify the abnormal timestamp and abnormal indicator instead of a single model and then combines the two kinds of abnormal results to detect the fine-grained *** on this framework,an algorithm based on Graph Attention Neural Network(GAT)and Attention Convolutional Long-Short Term Memory(A-ConvLSTM)is proposed,in which GAT learns temporal features of multiple indicators to detect abnormal timestamps and A-ConvLSTM captures the dynamic relationship between indicators to identify abnormal *** simulations on a real-world dataset demonstrate that the proposed algorithm can achieve a higher F1 score and hit rate than the extension of existing TSAD methods with the benefit of two independent sub-models for timestamp and indicator detection.

关键词： Multivariate time series graph attention neural network fine-grained anomaly detection

来源：评论

学校读者我要写书评

暂无评论

End-to-end differentiability and tensor processing unit computing to accelerate materials’ inverse design

引用

npj Computational Materials 2023年第1期9卷 1072-1083页

作者： Han Liu Yuhan Liu Kevin Li Zhangji Zhao Samuel S.Schoenholz Ekin D.Cubuk Puneet Gupta Mathieu Bauchy SOlids inFormaTics AI-Laboratory(SOFT-AI-Lab) College of Polymer Science and EngineeringSichuan UniversityChengdu 610065China AIMSOLID Research Wuhan 430223China Physics of AmoRphous and Inorganic Solids Laboratory(PARISlab) Department of Civil and Environmental EngineeringUniversity of CaliforniaLos AngelesCA 90095USA Department of Computer Science University of CaliforniaLos AngelesCA 90095USA Google Research Brain TeamMountain ViewCAUSA Department of Electrical and Computer Engineering University of CaliforniaLos AngelesCA 90095USA

Numerical simulations have revolutionized material ***,although simulations excel at mapping an input material to its output property,their direct application to inverse design has traditionally been limited by their high computing cost and lack of ***,taking the example of the inverse design of a porous matrix featuring targeted sorption isotherm,we introduce a computational inverse design framework that addresses these challenges,by programming differentiable simulation on TensorFlow platform that leverages automated end-to-end *** to its differentiability,the simulation is used to directly train a deep generative model,which outputs an optimal porous matrix based on an arbitrary input sorption isotherm ***,this inverse design pipeline leverages the power of tensor processing units(TPU)—an emerging family of dedicated chips,which,although they are specialized in deep learning,are flexible enough for intensive scientific *** approach holds promise to accelerate inverse materials design.

关键词： enough inverse isotherm

来源：评论

学校读者我要写书评

暂无评论

Prediction of miRNA family based on class-incremental learning

Prediction of miRNA family based on class-incremental learni...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Yajun Qiu, Lulu Li, Aimin Fei, Rong Li, Junhuai Wu, Fang-Xiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China Division of Biomedical Engineering Department of Mechanical Engineering Department of Computer Science Saskatoon Canada

ISBN: (纸本)9798350386226

With the development of deep sequencing, recent studies indicate that a miRNA precursor can generate multiple miRNA isoforms (isomiRs). The family prediction of canonical miRNAs and isomiRs could provide a basis for miRNA functional research. In this study, we propose a novel method for family identification of canonical miRNA and isomiRs based on incremental learning. First, a benchmark dataset is constructed by processing data based on miRNA sequences and their family annotation. Moreover, sequence embedding and RNN are used for capturing essential features and inherent dependencies within a sequence. Finally, incremental learning is applied to accommodate the continuous influx of miRNA sequencing data, enabling RNN to stay relevant and effective over time. Comparative experiments and ablation studies illustrate the effectiveness of our model, which can help to comprehensively understand miRNA's function. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Approach of Analyzing Classroom Student Engagement in Multimodal Environment by Using Deep Learning 9

An Approach of Analyzing Classroom Student Engagement in Mul...

引用

9th IEEE International Women in Engineering (WIE) Conference on Electrical and computer Engineering, WIECON-ECE 2023

作者： Nuha, Nishat Sultana Mahmud, Tanjim Rezaoana, Noortaz Hossain, Mohammad Shahadat Andersson, Karl University of Chittagong Department of Computer Science and Engineering Chittagong4331 Bangladesh Rangamati Science and Technology University Department of Computer Science and Engineering Rangamati4500 Bangladesh Luleå University of Technology Pervasive and Mobile Computing Laboratory Sweden

ISBN: (纸本)9798350319651

Student engagement refers to the level of involve-ment, interest, attention, and active participation that students demonstrate during their learning experiences. As the engage-ment rate increases the learning rate, teachers always try to mea-sure the engagement rate in the classroom in various ways. This paper introduces a multimodal approach for detecting student engagement, a vital aspect of effective learning. Leveraging Convolutional Neural Networks (CNNs), video and audio data are integrated to capture comprehensive insights into engagement levels. The objective is to classify student engagement into three categories: highly engaged, engaged, and not engaged. Separate unimodal models are employed for speech and video data., achieving notable accuracies of 92.87 % and 94.77 %, respectively, in recognizing engagement levels. The combined model, achieved through feature-level fusion, yields a competitive accuracy of 69.36%, benefiting from the strengths of both modalities. Al-though the combined model exhibits slightly lower test accuracy compared to the individual speech and video models, its enhanced interpretability and comprehensive insights make it a promising avenue for future research. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Sampling Methods for Efficient Training of Graph Convolutional Networks:A Survey

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 205-234页

作者： Xin Liu Mingyu Yan Lei Deng Guoqi Li Xiaochun Ye Dongrui Fan State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of SciencesBeijing 100086 School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049 IEEE Department of Precision Instrument Center for Brain Inspired Computing ResearchTsinghua UniversityBeijing 100084China

Graph convolutional networks(GCNs)have received significant attention from various research fields due to the excellent performance in learning graph *** GCN performs well compared with other methods,it still faces *** a GCN model for large-scale graphs in a conventional way requires high computation and storage ***,motivated by an urgent need in terms of efficiency and scalability in training GCN,sampling methods have been proposed and achieved a significant *** this paper,we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of *** highlight the characteristics and differences of sampling methods,we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all ***,we discuss some challenges and future research directions of the sampling methods.

关键词： Efficient training graph convolutional networks(GCNs) graph neural networks(GNNs) sampling method

来源：评论

学校读者我要写书评

暂无评论

GHVC-Net: Hypervolume Contribution Approximation Based on Graph Neural Network

GHVC-Net: Hypervolume Contribution Approximation Based on Gr...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wu, Guotong Nan, Yang Shang, Ke Ishibuchi, Hisao Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China

ISBN: (纸本)9781665410205

This paper proposes a framework called GHVC-Net that uses the graph neural network (GNN) model to approximate each solution's hypervolume contribution (HVC). GHVC-Net is permutation invariant and can handle solution sets of arbitrary size, similar to the properties of GNN. Compared to HVC-Net (i.e., a machine learning model for HVC approximation), GHVC-Net achieves better accuracy with less training time. GHVC-Net is also compared with traditional approximation methods, such as line-based and point-based methods, to demonstrate its ability to identify the solution with the smallest (largest) HVC. © 2024 IEEE.

关键词： Neural network models

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：