检索结果-内蒙古大学图书馆

Topological search and gradient descent boosted Runge-Kutta optimiser with application to engineering design and feature selection

引用

CAAI Transactions on intelligence Technology 2025年第2期10卷 557-614页

作者： Jinge Shi Yi Chen Ali Asghar Heidari Zhennao Cai Huiling Chen Guoxi Liang Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhouChina School of Surveying and Geospatial Engineering College of EngineeringUniversity of TehranTehranIran Department of Artificial Intelligence Wenzhou PolytechnicWenzhouChina

The Runge-Kutta optimiser(RUN)algorithm,renowned for its powerful optimisation capabilities,faces challenges in dealing with increasing complexity in real-world ***,it shows deficiencies in terms of limited local exploration capabilities and less precise ***,this research aims to integrate the topological search(TS)mechanism with the gradient search rule(GSR)into the framework of RUN,introducing an enhanced algorithm called TGRUN to improve the performance of the original *** TS mechanism employs a circular topological scheme to conduct a thorough exploration of solution regions surrounding each solution,enabling a careful examination of valuable solution areas and enhancing the algorithm’s effectiveness in local *** prevent the algorithm from becoming trapped in local optima,the GSR also integrates gradient descent principles to direct the algorithm in a wider investigation of the global solution *** study conducted a serious of experiments on the IEEE CEC2017 comprehensive benchmark function to assess the enhanced effectiveness of ***,the evaluation includes real-world engineering design and feature selection problems serving as an additional test for assessing the optimisation capabilities of the *** validation outcomes indicate a significant improvement in the optimisation capabilities and solution accuracy of TGRUN.

关键词： engineering design gradient search rule metaheuristic algorithm Runge-Kutta optimizer topological search

来源：评论

学校读者我要写书评

暂无评论

Improved Runge Kutta Optimization Using Compound Mutation Strategy in Reinforcement Learning Decision Making for Feature Selection

引用

Journal of Bionic engineering 2024年第5期21卷 2460-2496页

作者： Jinpeng Huang Yi Chen Ali Asghar Heidari Lei Liu Huiling Chen Guoxi Liang Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou325035China School of Surveying and Geospatial Engineering College of EngineeringUniversity of TehranTehran***Iran College of Computer Science Sichuan UniversityChengdu610065China Department of Artificial Intelligence Wenzhou PolytechnicWenzhou325035China

Runge Kutta Optimization(RUN)is a widely utilized metaheuristic ***,it suffers from these issues:the imbalance between exploration and exploitation and the tendency to fall into local optima when it solves real-world opti-mization *** address these challenges,this study aims to endow each individual in the population with a certain level of intelligence,allowing them to make autonomous decisions about their next optimization *** incorporating Reinforcement Learning(RL)and the Composite Mutation Strategy(CMS),each individual in the population goes through additional self-improvement steps after completing the original algorithmic phases,referred to as *** is,each individual in the RUN population is trained intelligently using RL to independently choose three different differentiation strategies in CMS when solving different *** validate the competitiveness of RLRUN,comprehensive empirical tests were conducted using the IEEE CEC 2017 benchmark *** comparative experiments with 13 conventional algorithms and 10 advanced algorithms were *** experimental results demonstrated that RLRUN excels in convergence accuracy and speed,surpassing even some champion ***,this study introduced a binary version of RLRUN,named bRLRUN,which was employed for the feature selection *** 24 high-dimensional datasets encompassing UCI datasets and SBCB machine learning library microarray datasets,bRLRUN occupies the top position in classification accuracy and the number of selected feature subsets compared to some *** conclusion,the proposed algorithm demonstrated that it exhibits a strong competitive advantage in high-dimensional feature selection for complex datasets.

关键词： Runge Kutta optimization Metaheuristic algorithm Feature selection Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Attribute grouping-based naive Bayesian classifier

引用

science China(Information sciences) 2025年第3期68卷 125-149页

作者： Yulin HE Guiliang OU Philippe FOURNIER-VIGER Joshua Zhexue HUANG Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) College of Computer Science & Software Engineering Shenzhen University

The naive Bayesian classifier(NBC) is a supervised machine learning algorithm having a simple model structure and good theoretical interpretability. However, the generalization performance of NBC is limited to a large extent by the assumption of attribute independence. To address this issue, this paper proposes a novel attribute grouping-based NBC(AG-NBC), which is a variant of the classical NBC trained with different attribute groups. AG-NBC first applies a novel effective objective function to automatically identify optimal dependent attribute groups(DAGs). Condition attributes in the same DAG are strongly dependent on the class attribute, whereas attributes in different DAGs are independent of one another. Then,for each DAG, a random vector functional link network with a SoftMax layer is trained to output posterior probabilities in the form of joint probability density estimation. The NBC is trained using the grouping attributes that correspond to the original condition attributes. Extensive experiments were conducted to validate the rationality, feasibility, and effectiveness of AG-NBC. Our findings showed that the attribute groups chosen for NBC can accurately represent attribute dependencies and reduce overlaps between different posterior probability densities. In addition, the comparative results with NBC, flexible NBC(FNBC), tree augmented Bayes network(TAN), gain ratio-based attribute weighted naive Bayes(GRAWNB), averaged one-dependence estimators(AODE), weighted AODE(WAODE), independent component analysis-based NBC(ICA-NBC), hidden naive Bayesian(HNB) classifier, and correlation-based feature weighting filter for naive Bayes(CFW) show that AG-NBC obtains statistically better testing accuracies, higher area under the receiver operating characteristic curves(AUCs), and fewer probability mean square errors(PMSEs) than other Bayesian classifiers. The experimental results demonstrate that AG-NBC is a valid and efficient approach for alleviating the attribute i

关键词： naive Bayesian classifier attribute independence assumption attribute grouping dependent attribute group posterior probability class-conditional probability

来源：评论

学校读者我要写书评

暂无评论

Learner Phase of Partial Reinforcement Optimizer with Nelder-Mead Simplex for Parameter Extraction of Photovoltaic Models

引用

Journal of Bionic engineering 2024年第6期21卷 3041-3075页

作者： Jinpeng Huang Zhennao Cai Ali Asghar Heidari Lei Liu Huiling Chen Guoxi Liang Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou325035China School of Surveying and Geospatial Engineering College of EngineeringUniversity of TehranTehran***Iran College of Computer Science Sichuan UniversityChengdu610065SichuanChina Department of Artificial Intelligence Wenzhou PolytechnicWenzhou325035China

This paper proposes an improved version of the Partial Reinforcement Optimizer(PRO),termed *** LNPRO has undergone a learner phase,which allows for further communication of information among the PRO population,changing the state of the PRO in terms of ***,the Nelder-Mead simplex is used to optimize the best agent in the population,accelerating the convergence speed and improving the accuracy of the PRO *** comparing LNPRO with nine advanced algorithms in the IEEE CEC 2022 benchmark function,the convergence accuracy of the LNPRO has been *** accuracy and stability of simulated data and real data in the parameter extraction of PV systems are *** to the PRO,the precision and stability of LNPRO have indeed been enhanced in four types of photovoltaic components,and it is also superior to other excellent *** further verify the parameter extraction problem of LNPRO in complex environments,LNPRO has been applied to three types of manufacturer data,demonstrating excellent results under varying irradiation and *** summary,LNPRO holds immense potential in solving the parameter extraction problems in PV systems.

关键词： Partial reinforcement optimizer Learner phase Nelder-Mead simplex algorithm Parameter extraction

来源：评论

学校读者我要写书评

暂无评论

DcnnGrasp: towards accurate grasp pattern recognition with adaptive regularizer learning

引用

science China(Information sciences) 2024年第12期67卷 323-324页

作者： Xiaoqin ZHANG Ziwei HUANG Jingjing ZHENG Shuo WANG Xianta JIANG College of Computer Science and Artificial Intelligence Wenzhou University Department of Computer Science Memorial University of Newfoundland

Vision-based grasp pattern recognition1)identifies the specific hand pose（fingers and palm configuration） for the object to be grasped based on visual information of household objects, which benefits tasks such as upper limb prosthesis control and gesture-based human-robot interaction. Various methods, including convolutional neural networks（CNN）,have been proposed for grasp pattern recognition, leading to advancements in fields such as robot imitation, humanrobot interaction, prosthetic design, and robot control.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

SGformer:Boosting transformers for indoor lighting estimation from a single image

引用

Computational Visual Media 2024年第4期10卷 671-686页

作者： Junhong Zhao Bing Xue Mengjie Zhang Centre for Data Science and Artificial Intelligence&School of Engineering and Computer Science Victoria University of WellingtonWellington 6012New Zealand

Estimating lighting from standard images can effectively circumvent the need for resourceintensive high-dynamic-range(HDR)lighting ***,this task is often ill-posed and challenging,particularly for indoor scenes,due to the intricacy and ambiguity inherent in various indoor illumination *** propose an innovative transformer-based method called SGformer for lighting estimation through modeling spherical Gaussian(SG)distributions—a compact yet expressive lighting *** from previous approaches,we explore underlying local and global dependencies in lighting features,which are crucial for reliable lighting ***,we investigate the structural relationships spanning various resolutions of SG distributions,ranging from sparse to dense,aiming to enhance structural consistency and curtail potential stochastic noise stemming from independent SG component *** harnessing the synergy of local–global lighting representation learning and incorporating consistency constraints from various SG resolutions,the proposed method yields more accurate lighting estimates,allowing for more realistic lighting effects in object relighting and *** code and model implementing our work can be found at https://***/junhong-jennifer-zhao/SGformer.

关键词： lighting estimation transformer spherical Gaussian(SG) augmented reality

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource Utilization Prediction Model for Cloud Datacenter

引用

IAENG International Journal of Applied Mathematics 2025年第2期55卷 307-331页

作者： Bliedy, Doaa Khafagy, Mohamed H. Badry, Rasha M. Department of Information Systems Faculty of Computers and Artificial Intelligence Fayoum University Egypt Department of Computer Science Faculty of Computers and Artificial Intelligence Fayoum University Egypt

Much research has been done on predicting resource utilization in the cloud to avoid over- and under-provisioning resources. Most existing systems focus on estimating the utilization of one or two resources at most, including memory, CPU, storage, network, or servers dedicated to cloud applications;they do not consider the correlation between resources. A maximum of one or two machine learning algorithms is employed for prediction purposes. Additionally, traditional prediction methods in the cloud provide a one-dimensional output. Most current solutions predict resources, such as memory and CPU utilization, as a single output. Unfortunately, a one-dimensional output in resource provision and usage cannot capture the relationship between the application requirements of different resources, such as CPU, memory, CPU cores, disk, and network;this results in incomplete and inaccurate information and prediction results. Efficient resource allocation and management require predicting several parameters using multivariate state variables. This study presents a multi-resource utilization prediction model that uses several machine learning approaches, such as support vector regression, random forests, MLP regression, neural networks (NN) using Adam and SGD optimizers, and decision tree regression. The prediction model is based on univariate and multivariate time series. Google cluster trace data is used to evaluate the work. Four experiments are executed on the dataset, seeking to predict the resources for different time series interval periods. The various algorithms’ mean absolute errors (MAE), root mean square error, mean absolute percentage error and R-squared are compared to determine which technique achieves the lowest error rate. The experimental results have shown that the prediction model yields better accuracy than previous research. © (2024), (International Association of Engineers). All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Deep learning framework for automatic detection and classification of sleep apnea severity from polysomnography signals

引用

Neural Computing and Applications 2024年第28期36卷 17483-17493页

作者： Raja Brundha, A. Lakshmi Sangeetha, A. Balajiganesh, A. Department of Artificial Intelligence and Data Science Sri Sai Ram Engineering College Chennai India Department of Computer Science Engineering Velammal Engineering College Chennai India

Sleep apnea (SA) is a sleep-related breathing disorder characterized by breathing pauses during sleep. A person’s sleep schedule is significantly influenced by that person’s hectic lifestyle, which may include unhealthy eating habits and their line of work. Polysomnographic (PSG) sleep studies examine sleep-related disorders by recording various biosignals from the human body. However, SA classification methods could be more robust in terms of performance because they rely on feature-engineering strategies or employ a particular signal from PSG recording for diagnosis. This study aims to classify the severity of SA according to the apnea–hypopnea index (AHI) into normal, mild, and moderate-to-severe groups using oxygen saturation (SpO2), electroencephalogram (EEG), and electrocardiogram (ECG) signals. The proposed deep neural network (DNN)-bidirectional long short-term memory (DNN-BiLSTM) framework addresses the issue of low detection accuracy in analysis. The DNN-BiLSTM approach employs features extracted from a multiscale dilation attention 1D convolutional neural network (MSDA-1DCNN) as input for detection and classification purposes. The MSDA-1DCNN network extracts deep features from processed SpO2, EEG, and ECG signals. The developed firefly combined electric fish optimization (FCEFO) algorithm improves performance by optimizing the hidden neuron count of the DNN and the learning rate of the BiLSTM framework. The performance measures proved the effectiveness of the model over conventional machine and deep learning approaches. With the integration of deep features, the proposed DNN-BiLSTM model provides enhanced performance in terms of accuracy and precision. Thus, the proposed approach is progressive and can be used for medical diagnosis. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based method for detection of copy-move forgery in videos

引用

Neural Computing and Applications 2025年第14期37卷 8451-8464页

作者： Elbarougy, Reda Abdelfatah, Osama Behery, G.M. El-Badry, Noha M. Department of Artificial Intelligence and Data Science College of Computer Science and Engineering University of Ha’il Ha’il81481 Saudi Arabia Department of Information Technology Faculty of Computer and Artificial Intelligence Damietta University New Damietta Kafr Saad Egypt Department of Computer Science Faculty of Computer and Artificial Intelligence Damietta University New Damietta Kafr Saad Egypt Department of Mathematics Faculty of Science Damietta University New Damietta Kafr Saad Egypt

Video forgery is one of the most serious problems affecting the credibility and reliability of video content. Therefore, detecting video forgery presents a major challenge for researchers due to the diversity of forgery types, the modernity of the programs used in forgery operations, and the abundance of information and content present in videos. The seriousness of this issue arises from the widespread use of videos in vital fields that require very high accuracy with no room for doubt or error, such as courtrooms, journalism, and others. Copy-move forgery is one of the most common and dangerous types of video forgery because of the difficulty in identifying it with the naked eye and the great diversity of forgery techniques involved in this particular type. One of the biggest challenges researchers have faced in the past is the complexity of the steps required to detect forgery in videos, leading to significant computational complexity and time consumption. The proposed method also aims to achieve better results than previous methods while reducing computational operations. Ultimately, forgery is detected with great efficiency. Compared to previous methods used for detecting copy-move forgery in the Rewind dataset, the proposed method achieves the highest F1, reaching 0.86, with a significant difference of 0.13 compared to the best result of the previous methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Deep 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：