检索结果-内蒙古大学图书馆

A two-population artificial tree algorithm based on adaptive updating strategy for dominant populations

Soft Computing 2025年第4期29卷 2075-2106页

作者： Xiao, Yaping Niu, Linfeng Li, Qiqi School of Economics Central South University of Forestry and Technology Hunan Province Changsha City410004 China College of Mechanical and Vehicle Engineering Changsha University of Science & Technology Hunan Province Changsha City410114 China

An artificial tree (AT) algorithm has been proposed recently, and the performance of AT has been enhanced because of the introduction of improved AT algorithm with two-population (IATTP). However, the branch update operators of IATTP cannot effectively balance exploration and exploitation, which limits the optimization accuracy and efficiency of IATTP. To further improve the performance of IATTP, this work proposes a two-population artificial tree algorithm based on adaptive updating strategy for dominant populations (TATAD). In TATAD, six operators named self-evolution operator 2, crossover operator 2, improved self-evolution operator, gradient descent update operator, Gauss and Cauchy variational operator, and random traceless Sigma variational operator are applied to form an operator library. A dominant operator dynamic following mechanism is proposed to assign these six operators to the two populations in an optimal pairing scheme. Both populations and operators compete with each other, and the advantages of all operators are fully utilized. Moreover, the combination of diverse operators and dominant operator dynamic following mechanism can effectively balance the exploration and exploitation of TATAD. The performance of TATAD is compared with four AT algorithms and six efficient algorithms through typical test functions, and their results are bested by Wilcoxon rank sum test (WRST) and Friedman ranking test. It is found that TATAD is the most competitive algorithm among these algorithms for solving these optimization problems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

ARCHER:a ReRAM-based accelerator for compressed recommendation systems

引用

Frontiers of computer science 2024年第5期18卷 147-160页

作者： Xinyang SHEN Xiaofei LIAO Long ZHENG Yu HUANG Dan CHEN Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

Modern recommendation systems are widely used in modern data *** random and sparse embedding lookup operations are the main performance bottleneck for processing recommendation systems on traditional platforms as they induce abundant data movements between computing units and ***-based processing-in-memory(PIM)can resolve this problem by processing embedding vectors where they are ***,the embedding table can easily exceed the capacity limit of a monolithic ReRAM-based PIM chip,which induces off-chip accesses that may offset the PIM ***,we deploy the decomposed model on-chip and leverage the high computing efficiency of ReRAM to compensate for the decompression performance *** this paper,we propose ARCHER,a ReRAM-based PIM architecture that implements fully yon-chip recommendations under resource ***,we make a full analysis of the computation pattern and access pattern on the decomposed *** on the computation pattern,we unify the operations of each layer of the decomposed model in multiply-and-accumulate *** on the access observation,we propose a hierarchical mapping schema and a specialized hardware design to maximize resource *** the unified computation and mapping strategy,we can coordinatethe inter-processing elements *** evaluation shows that ARCHER outperforms the state-of-the-art GPU-based DLRM system,the state-of-the-art near-memory processing recommendation system RecNMP,and the ReRAM-based recommendation accelerator REREC by 15.79×,2.21×,and 1.21× in terms of performance and 56.06×,6.45×,and 1.71× in terms of energy savings,respectively.

关键词： recommendation system ReRAM processing-in-memory embedding layer

来源：评论

学校读者我要写书评

暂无评论

Traffic sign recognition model based on scale sequence features and high-order spatial interactions

引用

Neural Computing and Applications 2025年第5期37卷 3605-3620页

作者： Zhang, Gan Wang, Yafei Li, Wenju Fu, Xianping School of Information Science and Technology Dalian Maritime University Dalian116026 China School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai201418 China Pengcheng Laboratory Shenzhen518055 China

Traffic sign recognition is an integral part of driver assistance systems play a crucial role in enhancing road safety. Due to a large number of challenging targets, such as occlusion, distortion, and small targets in actual scenes, existing methods still have bottlenecks in the accuracy of detection and recognition. Therefore, this paper proposes a real-time traffic sign recognition model based on scale sequence features (SSFs) and high-order spatial interactions (HOSIs) on the basis of YOLOv5. This model extracted scale-invariant SSF using a high-dimensional convolution on the underlying feature map to improve the detection effect of multi-scale targets. At the same time, recursive gated convolution modules are integrated into the feature pyramid network, expanding the interactions to arbitrary order and providing richer feature information for high-order convolutions. In addition, a cross-stage partial (CSP) structure is incorporated into the spatial pooling pyramid, which improves the structure’s performance without introducing excessive computational complexity. The experimental results show that the proposed model achieves 95.5% and 99.92% of mAP on Tsinghua–Tencent 100K (TT100K) and German Traffic Sign Recognition Benchmark (GTSRB), respectively, which surpass the performance of the most advanced model and meets the requirements of real-time detection. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Scale Quantum Harmonic Oscillator Algorithm with Opposition-based Learning 13

Enhanced Multi-Scale Quantum Harmonic Oscillator Algorithm w...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Ye, Xinggui Li, Jianping Wang, Peng School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Technology Southwest Minzu University Chengdu China

ISBN: (纸本)9798350308365

Multi-scale Quantum Harmonic Oscillator Algorith-m (MQHOA) is a recently proposed metaheuristic algorithm (MA), which simulates the photoelectron moves from high energy level down to the ground energy level. It requires few parameters, yet verified effective and efficient to solve numerical problems. However, it is easy to get trapped into local optima and suffer from premature convergence. This work proposes an enhanced MQHOA with opposition-based learning (OMQHOA) to balance the exploration and exploitation. An adaptive scaling strategy and a jumping rate scheme are proposed to enhance the diversity of the particles. The performance of the proposed algorithm is validated by evaluating on several benchmark problems with different dimensions, including the success rate of finding the global optimum over multiple independent trials, trajectory of convergence, and Wilcoxon rank-sum tests. The empirical results are compared with MQHOA, recent variants of MQHOA, and some state-of-the-art MAs, which show the superiority or at least competitiveness of the proposed approach. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimal Contract for Data Rewarding with Network Effects

引用

IEEE Transactions on Control of Network Systems 2024年第2期12卷 1332-1341页

作者： Baneshi, Alireza Montazeri, Mina Kebriaei, Hamed University of Tehran School of Electrical and Computer Engineering College of Engineering Tehran Iran Swiss Federal Laboratories for Materials Science and Technology Urban Energy Systems Laboratory Dübendorf Switzerland School of Computer Science Tehran Iran

Data rewarding is a novel business model that leads to an economic trend in mobile networks. In this scheme, the advertiser incentivizes mobile users (MUs) to watch advertisement (ads) and, in return, receive a reward in the form of mobile data. In this work, we model the interaction between an advertiser who has asymmetric information about MUs and MUs who are connected to each other under a network, using the contract theory approach. We obtain the necessary and sufficient conditions for an optimal and practical contract to motivate MUs to participate in the data rewarding scheme and encourage them to declare their private information truthfully. The formulation of this contract is a non-convex-constrained optimization problem. Using lemmas and propositions, we reformulate the initial optimization problem that is challenging to solve as an optimization problem with convex constraints and prove that these two problems are equivalent. Then, with the help of a distributed and non-convex algorithm, we obtain the amount of ads demand and incentive reward. © 2014 IEEE.

关键词： Contracts Optimization Social networking (online) Data models Network systems Control systems Indexes Distributed algorithms Couplings Complexity theory

来源：评论

学校读者我要写书评

暂无评论

XGBoost and ANOVA-based Analysis of Sailboat Prices and Their Influencing Factors 3

XGBoost and ANOVA-based Analysis of Sailboat Prices and Thei...

引用

3rd IEEE International Conference on Electrical engineering, Big Data and Algorithms, EEBDA 2024

作者： Wang, Yuhang Fan, Yushan School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9798350380989

The sailboat market is a dynamic industry characterized by fluctuations in demand and pricing due to factors such as economic conditions, area as well as the hull. Analyzing the factors influencing the listing price of sailboats has its pros and cons;the pros include a better understanding of market trends, informed decision-making for buyers and sellers, and insights into the most significant value drivers. The purpose of this study is to analyze the multiple influences on sailboat pricing. First, this paper finds that sailboat characteristics have little impact on pricing and other factors are more critical. The analysis shows that geographic region has an impact on pricing, but not significantly, while different sailboat types have different impacts in different regions. Finally, this paper finds that catamarans have a significantly greater impact on price than monohulls, emphasizing the importance of hull type in pricing. These findings deepen the understanding of sailboat pricing factors and have important implications for the market and consumer demand. © 2024 IEEE.

关键词： Multiple influences Pricing Sailboat Sailboat types

来源：评论

学校读者我要写书评

暂无评论

Copper oxide-modified highly reversible Zn powder anode for aqueous Zn metal batteries

引用

Rare Metals 2024年第10期43卷 5005-5016页

作者： Guan-Qun Liu Biao Fu Zhe-Xuan Liu Lan-Yan Li Shu-Quan Liang Guo-Zhao Fang School of Materials Science and Engineering Key Laboratory of Electronic Packaging and Advanced Functional Materials of Hunan ProvinceCentral South UniversityChangsha 410083China School of Science Hunan University of Technology and BusinessChangsha 410205China National Energy Metal Resources and New Materials Key Laboratory Central South UniversityChangsha 410083China

With the advantages of mature preparation technology,structural adjustability and suitability for large-scale application,Zn powder anode is considered to be an ideal electrode for realizing low-cost,high-energy-density aqueous Zn metal ***,the high specific surface of Zn powders leads to severe side reactions such as hydrogen evolution and corrosion,thus limiting their widespread use Here,this work develops a novel CuO@Zn powder anode with a synergy effect of surface wrapping and *** powders are uniformly wrapped by small CuO particles due to the strong adsorption between Zn and *** wrapped CuO particles build a good conductive framework to inhibit the structural collapse of the Zn powder caused by corrosion and non-uniform ***,CuO can also be used as a seed to guide the uniform deposition of Zn ions through its strong binding energy with *** a result,the Cu O@Zn anode can maintain a long cyclic life of 900 h at current density of 1 mA·cm^(-2)and capacity of 1 mAh·cm^(-2),as well as contribute to an excellent capacity retention of 92% after 800cycles for CuO@Zn||NH_(4)V_(4)O_(10)full *** at high current density of 5 A·g^(-1),the full cell exhibits a specific capacity of more than 200 mAh·g^(-1)after 800 cycles,with a good capacity retention of 89%.This work provides a new idea for developing high-performance Zn powder-based anodes.

关键词： Zn powder Copper oxide Surface wrapping Zn anode Aqueous Zn metal batteries

来源：评论

学校读者我要写书评

暂无评论

A One-Dimensional Residual Network and Physical Fitness-Based Exercise Prescription Recommendation Method 10

A One-Dimensional Residual Network and Physical Fitness-Base...

引用

10th IEEE International Conference on Cyber Security and Cloud Computing and 9th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Fan, Runqing Peng, Zhenlian Cao, Buqing Liu, Jianxun Che, Peng Chen, Tieping Hunan University of Science and Technology School of Computer Science and Engineering Hunan Provincial Key Laboratory for Services Computing and Novel Software Technology Xiangtan China Hunan University of Science and Technology School of Physical Education Xiangtan China

ISBN: (纸本)9798350312461

In the context of the national big data strategy, physical fitness test data has become one of the main influencing factors in guiding and promoting the participation of the population in sports and fitness. Recommending exercise prescriptions based on national physical fitness test data has become an important research topic. However, currently, there is little research on how to accurately use computer data processing technology to recommend exercise prescriptions based on physical fitness test data. In this study, we propose a ResNet-based Exercise Prescription (ResNet-EP) method that utilizes one-dimensional residual neural network technology to recommend exercise prescriptions based on physical fitness testing data. This method comprehensively analyzes physical fitness testing data and exercise prescription data and realizes the automatic recommendation of exercise prescriptions. Experimental results on a real dataset demonstrate that the ResNet-EP model outperforms other comparison models in terms of precision (79.98%), recall (83.73%), and F1 score (81.81%). This study provides novel insights into the combination of physical fitness testing and exercise. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MiRGraph: A hybrid deep learning approach to identify microRNA-target interactions by integrating heterogeneous regulatory network and genomic sequences

MiRGraph: A hybrid deep learning approach to identify microR...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Pei Liu, Ying Luo, Jiawei Li, Yue Hunan University College of Computer Science and Electronic Engineering Changsha China McGill University School of Computer Science MontrealQC Canada

ISBN: (纸本)9798350386226

MicroRNAs (miRNAs) mediates gene expression regulation by targeting specific messenger RNAs (mRNAs) in the cytoplasm. They can function as both tumor suppressors and oncogenes depending on the specific miRNA and its target genes. Detecting miRNA-target interactions (MTIs) is critical for unraveling the complex mechanisms of gene regulation and promising towards RNA therapy for cancer. There is currently a lack of MTIs prediction methods that simultaneously perform feature learning from heterogeneous gene regulatory network (GRN) and genomic sequences. To improve the prediction performance of MTIs, we present a novel transformer-based multi-view feature learning method - MiRGraph, which consists of two main modules for learning the sequence-based and GRN-based feature embedding. For the former, we utilize the mature miRNA sequences and the complete 3'UTR sequence of the target mRNAs to encode sequence features using a hybrid transformer and convolutional neural network (CNN) (TransCNN) architecture. For the latter, we utilize a heterogeneous graph transformer (HGT) module to extract the relational and structural information from the GRN consisting of miRNA-miRNA, gene-gene and miRNA-target interactions. The TransCNN and HGT modules can be learned end-to-end to predict experimentally validated MTIs from MiRTarBase. MiRGraph outperforms existing methods in not only recapitulating the true MTIs but also in predicting strength of the MTIs based on the in-vitro measurements of miRNA transfections. In a case study on breast cancer, we identified plausible target genes of an oncomir. © 2024 IEEE.

关键词： Gene expression regulation

来源：评论

学校读者我要写书评

暂无评论

Vehicle Motion Prediction Based on Selective Perception and Weak Lane Guidance 29

Vehicle Motion Prediction Based on Selective Perception and ...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Wang, Xiaoliang Zheng, Shiqi Zou, Junkang Liu, Yuzhen Hunan University of Science and Technology Department of Computer Science and Engineering Xiangtan China

ISBN: (纸本)9798350330717

Trajectory prediction is crucial for ensuring the safety and reliability of autonomous driving systems. Accurately predicting the future trajectory of a vehicle can aid drivers or automated driving systems in developing reasonable movement plans and avoiding potential collisions. In real-world scenarios, drivers selectively observe areas that influence their driving decisions based on real-time traffic scenarios, adapting to changing traffic situations to ensure safety. To simulate this behavior, we propose a selective perception module that utilizes historical trajectories and lane centerlines to extract vital information from the changing traffic scene. Furthermore, vehicles tend to follow lane guidance to some extent, we use a normalized flow decoder and small-scale guided loss to induce the distribution of predicted trajectories, slightly increasing the probability of lane centerlines in the predictions as a weak lane guidance. We conduct ablation studies using the public dataset nuScenes and comparative experiments with state-of-the-art methods, showcasing the predictive diversity of our approach while maintaining high accuracy. © 2023 IEEE.

关键词： autonomous driving motion prediction

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：