检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Chunxu Long, Guodong Guo, Hongkuan Fang, Xiao Song, Yang Liu, Zhaojie Zhou, Guorui Zhang, Zijian Liu, Yang Yang, Bo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China College of Computer Science and Technology Jilin University China Australian Artificial Intelligence Institute FEIT University of Technology Sydney Australia Kuaishou Technology China Institute for AI Industry Research Tsinghua University China

With the recent success of large language models, particularly foundation models with generalization abilities, applying foundation models for recommendations becomes a new paradigm to improve existing recommendation systems. It becomes a new open challenge to enable the foundation model to capture user preference changes in a timely manner with reasonable communication and computation costs while preserving privacy. This paper proposes a novel federated adaptation mechanism to enhance the foundation model-based recommendation system in a privacy-preserving manner. Specifically, each client will learn a lightweight personalized adapter using its private data. The adapter then collaborates with pre-trained foundation models to provide recommendation service efficiently with fine-grained manners. Importantly, users’ private behavioral data remains secure as it is not shared with the server. This data localization-based privacy preservation is embodied via the federated learning framework. The model can ensure that shared knowledge is incorporated into all adapters while simultaneously preserving each user’s personal preferences. Experimental results on four benchmark datasets demonstrate our method’s superior performance. Implementation code is available to ease reproducibility1 Copyright © 2024, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Detection of Glue Spray on Bottom of Vehicle Based on Machine Vision

Detection of Glue Spray on Bottom of Vehicle Based on Machin...

引用

2018 International Conference on Network, Communication, Computer engineering (NCCE 2018)

作者： Dongyang Liu Jindong Zhang Xiaofeng Zhang Xiaoyu Ma Yuxin Kou College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University College of Software Jilin University

ISBN: (纸本)9781510871076

With the continuous development of machine vision,intelligent detection of bottom spray glue has gradually become a *** this paper,we proposed an algorithm of detection the glue spray on bottom of vehicle based on machine *** sampling and detecting the spray interest area,the algorithm can obtain its features which were used for intelligent identification of the spray interest area,and then carry out the pseudo target and detect whether the detection area is complete or *** can test the vehicles on pipeline in real *** the average,each frame's processing time is less than 150 *** there is an unqualified area,it will alarm and inform the operators of the wrong *** algorithm can improve the quality of the vehicle and save human resources and identify the spray interest area with high *** research directions in the future is to accelerate the speed to meet the practical application requirements,and to solve the intelligent identification of the spray interest area which has the same color with the vehicle body.

关键词： Glue spray Machine vision intelligent detection

来源：评论

学校读者我要写书评

暂无评论

A populations evolution study using the genotype frequency data of single nucleotide polymorphism from Y-chromosome

A populations evolution study using the genotype frequency d...

引用

2007 1st International Conference on Bioinformatics and Biomedical engineering, ICBBE

作者： Pei, Zhili Kong, Ying Shi, Xiaohu Lian, Zhichao Tang, Xuning Liu, Lisha Cao, Zhongbo Liang, Yanchun Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Chang'chun 130012 China College of Mathematics and Computer Science Inner Mongolia University for Nationalities Tong'liao 028043 China Department of Biochemistry and Molecular Biology Institution of Glycobiology Dalian Medical University Da'lian 116027 China

ISBN: (纸本)1424411203

This paper proposes a novel way for the population evolution research. In the paper, it constructs the phylogenies tree of four populations using the single nucleotide polymorphism (SNP) genotype frequency of human's Y-chromosome provided by the international Hapmap project firstly, then a mathematical model is proposed to calculate the distance of any two races for all SNP genotype frequency. The simulation results suggest that the theory of constructing phylogenetic tree by analyzing SNP genotype frequency is effective. The accuracy of the adopted processing method is also shown by the simulation results. About the origination of modern human being, the result of this study can support the 'out of Africa' hypothesis, and this result is same as most evidences of paleontology. © 2007 IEEE.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Vector Quantization: A Case Study on Robust Medical Semantic Segmentation

SSRN

引用

SSRN 2024年

作者： Lang, Yijun Liu, Pingping Zhao, Hongwei Zhou, Qiuzhan College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China School of Mechanical Science and Engineering Jilin University Changchun130025 China College of Communication Engineering Jilin University Changchun130022 China

Pixel-wise medical image segmentation is essential for accurate disease diagnosis and analysis. Although these models exhibit high accuracy and impressive performance, they often face issues of trustworthiness due to their sensitivity to minor perturbations in the original images, which can cause significant deviations in segmentation tasks. To address these challenges, we focus on enhancing both the accuracy and the robustness of these systems against adversarial perturbations. We introduce a robust projection-head that utilizes a non-parametric method, Vector Quantization Momentum (VQM), to increase the hypothesis margin in the input space and reduce disturbances in the feature space. Additionally, we propose a new loss function, Anchor-based Vector Quantization (AVQ), designed to achieve denser pixel-prototype embedding. Our evaluation, using two white-box adversarial attack algorithms across two datasets, demonstrates a defense improvement of up to 14.46%. © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Judge System for Old Man Fall Down

Design and Implementation of Judge System for Old Man Fall D...

引用

2017 International Conference on Mechanical,Electronic,Control and Automation engineering(MECAE 2017)

作者： Chao Sun Jindong Zhang Jiajia Lin Rui Song Xuan Zang Xiaohan Liu College of Software Jilin University College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University

ISBN: (纸本)9781510838451

This paper taking into account the universal use of Android phones, designs and implements judgments and notices the old man falling cell phone App. By calling the phones accelerometer, gyroscope collection campaigns after processing according to human body dynamics model to determine the specific state of the elderly, and get the specific latitude and longitude via GPS;Cell phone judge after the old man falls can send text messages to bound phone number in advance and inform the GPS to obtain location coordinates, after the fall in the elderly will be able to make the necessary relief in a timely manner.

关键词： APP Fall down Dynamic models GPS

来源：评论

学校读者我要写书评

暂无评论

A Stable Stochastic Optimization Algorithm for Triangulation of Bayesian Networks

A Stable Stochastic Optimization Algorithm for Triangulation...

引用

International Workshop on knowledge Discovery and Data Mining (WKDD)

作者： Xuchu Dong Dantong Ouyang Yuxin Ye Shasha Feng Haihong Yu Department of Computer Science and Technology Jilin University Changchun Jilin China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun Jilin China

ISBN: (纸本)9781424453979

In this paper, we present a novel deterministic heuristic and a new genetic algorithm to solve the problem of optimal triangulation of Bayesian networks. The heuristic, named MinFillWeight, aims to select variables minimizing the multiplication of the weights on nodes of fill-in edges. The genetic algorithm, named GA-MFW, uses a new rank-reserving crossover operator and a 2-fold mutation mechanism utilizing the MinFillWeight heuristic. Experiments on representative benchmark show that the deterministic heuristic and the stochastic algorithm have good performance and stability to various problems.

关键词： Stochastic processes Bayesian methods Tree graphs Ethics Genetic algorithms Inference algorithms Genetic mutations Stability Ant colony optimization Data mining

来源：评论

学校读者我要写书评

暂无评论

RiWalk: Fast Structural Node Embedding via Role Identification

RiWalk: Fast Structural Node Embedding via Role Identificati...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Xuewei Ma Geng Qin Zhiyang Qiu Mingxin Zheng Zhe Wang College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

Nodes performing different functions in a network have different roles, and these roles can be gleaned from the structure of the network. Learning latent representations for the roles of nodes helps to understand the network and to transfer knowledge across networks. However, most existing structural embedding approaches suffer from high computation and space cost or rely on heuristic feature engineering. Here we propose RiWalk, a flexible paradigm for learning structural node representations as it decouples the structural embedding problem into a role identification procedure and a network embedding procedure. Through role identification, rooted kernels with structural dependencies kept are built to better integrate network embedding methods. To demonstrate the effectiveness of RiWalk, we develop two different role identification methods named RiWalk-SP and RiWalk-WL respectively and employ random walk based network embedding methods. Experiments on within-network classification tasks show that our proposed algorithms achieve comparable performance with other baselines while being an order of magnitude more efficient. Besides, we also conduct across-network role classification tasks. The results show potential of structural embeddings in transfer learning. RiWalk is also scalable, making it capable of capturing structural roles in massive networks.

关键词： Kernel Task analysis knowledge engineering Machine learning Bridges Proteins Network topology

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization for distributed collaborative beamforming in mobile wireless sensor networks

Multi-objective optimization for distributed collaborative b...

引用

IEEE Symposium on Computers and Communications

作者： Geng Sun Yanheng Liu Guojun Shen Aimin Wang Ying Zhang Victor C. M. Leung School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China Department of Electrical and Computer Engineering University of British Columbia Vancouver BC Canada

Mobile wireless sensor networks (MWSN) are resource constrained, and have limited energy and transmission range. Distributed collaborative beamforming (DCB) in MWSN based on a virtual node antenna array (VNAA) can increase the transmission distance and enhance energy efficiency of a single sensor node. To achieve a lower maximum sidelobe level (SLL), sensor nodes can move to optimal locations with optimal excitation currents for DCB. However, this leads to an extra motion energy consumption. In this paper, we construct a multi-objective optimization framework to jointly optimize the maximum SLL, the transmission power and the motion energy consumption of the DCB nodes in MWSN. Moreover, an improved non-dorminated sorting genetic algorithm-II (INSGA-II) is proposed for solving the optimization problem. Simulation results show that the maximum SLL, the transmission power and the motion energy consumption of the VNAA can be effectively optimized by the proposed algorithms.

关键词： Mobile wireless sensor networks Collaborative beamforming Antenna arrays Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative Study on Metaheuristic-Based Feature Selection for Cotton Foreign Fibers Recognition

Comparative Study on Metaheuristic-Based Feature Selection f...

引用

The 9th International Conference on Computer and Computing Technologies in Agriculture (CCTA 2015)

作者： Xuehua Zhao Xueyan Liu Daoliang Li Huiling Chen Shuangyin Liu Xinbin Yang Shaobin Zhan Wenyong Zhao School of Digital Media Shenzhen Institute of Information Technology Key Laboratory of Symbolic Computation and Knowledge Engineer (Jilin University) Ministry of Education College of Information and Electrical Engineering China Agricultural University College of Physics and Electronic Information Wenzhou University College of Information Guangdong Ocean University

ISBN: (纸本)9783319483566

The excellent feature set or feature combination of cotton foreign fibers is great significant to improve the performance of machine-vision-based recognition system of cotton foreign fibers. To find the excellent feature sets offoreign fibers, in this paper presents three metaheuristic-based feature selection approaches for cotton foreign fibers recognition, which are particle swarm optimization, ant colony optimization and genetic algorithm, respectively. The k-nearest neighbor classifier and support vector machine classifier with k-fold cross validation are used to evaluate the quality offeature subset and identify the cotton foreign fibers. The results show that the metaheuristic-based feature selection methods can efficiently find the optimal feature sets consisting of a few features. It is highly significant to improve the performance of recognition system for cotton foreign fibers.

关键词： Metaheuristic Feature selection Foreign fibers Recognition system Feature extraction recognition system Fiber Fibrous materials Cotton Support Vector Network

来源：评论

学校读者我要写书评

暂无评论

Optimization strategy of top-down join enumeration on modern multi-core CPUs

引用

Journal of Computers 2011年第10期6卷 2004-2012页

作者： Zuo, Wanli Chen, Yongheng He, Fenglin Chen, Kerui Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China

Most contemporary database systems query optimizers exploit System-R's bottom-up dynamic programming method (DP) to find the optimal query execution plan (QEP) without evaluating redundant subplans. The distinguished exceptions are Volcano/Cascades using transforms to generate new plans according to a topdown approach. As recent research has revealed, bottom-up dynamic programming can improve performance with respect to the shape of the join graph and parallelism. However top-down join enumeration dynamic programming method can derive upper bounds for the costs of the plans it generates which is not available to typical bottom-up DP method. In this paper, we propose a comprehensive and practical framework for parallelizing top-down dynamic programming query optimization with complex non-inner join in the multi-core processor architecture, referred as PTDhyp. We have implemented such a search strategy and experimental results show that can improve optimization time effective compared to known existing algorithms. © 2011 ACADEMY PUBLISHER.

关键词： Dynamic programming

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：