检索结果-内蒙古大学图书馆

DCS-SOCP-SVM:A Novel integrated Sampling and Classification algorithm for Imbalanced Datasets

Computers, Materials & Continua 2025年第5期83卷 2143-2159页

作者： Xuewen Mu Bingcong Zhao School of Mathematics and Statistics Xidian UniversityXi’an710071China

When dealing with imbalanced datasets,the traditional support vectormachine(SVM)tends to produce a classification hyperplane that is biased towards the majority class,which exhibits poor *** paper proposes a high-performance classification algorithm specifically designed for imbalanced *** proposed method first uses a biased second-order cone programming support vectormachine(B-SOCP-SVM)to identify the support vectors(SVs)and non-support vectors(NSVs)in the imbalanced ***,it applies the synthetic minority over-sampling technique(SV-SMOTE)to oversample the support vectors of the minority class and uses the random under-sampling technique(NSV-RUS)multiple times to undersample the non-support vectors of the majority *** the above-obtained minority class data set withmultiple majority class datasets can obtainmultiple new balanced data ***,SOCP-SVM is used to classify each data set,and the final result is obtained through the integrated *** results demonstrate that the proposed method performs excellently on imbalanced datasets.

关键词： DCS-SOCP-SVM imbalanced datasets sampling method ensemble method integrated algorithm

来源：评论

学校读者我要写书评

暂无评论

An Accurate Recommendation Method of University Library Digital Resources Based on User Interest

引用

International Journal of High Speed Electronics and Systems 2025年

作者： Wu, Xiuhua Sang, Guoqiang Zhejiang College of Security Technology Zhejiang Province Wenzhou City325000 China Wenzhou University Zhejiang Province Wenzhou City325000 China

With the advent of the digital age, university libraries are faced with the challenge of how to efficiently manage and recommend huge digital resources to meet the diversified needs of users. Traditional recommendation system (RS) often ignores the evolution of user interests over time and the importance of personalized recommendation. This research aims to solve the above problems through the accurate recommendation algorithm of university library digital resources that integrates the evolution of users’ interests. This paper first discusses the background of the dynamic change in user interest and the urgent need for an efficient and accurate RS. The motivation is to better understand and predict user interests through a new algorithmic framework to improve the accuracy and user satisfaction of the RS. We propose a RS framework that combines the user interest evolution model and attention mechanism based on Transformer, and design a hybrid RS by combining content recommendation and collaborative filtering technologies. The system is designed to capture subtle changes in user interests and solve cold start problems, thereby providing more personalized and accurate recommendations. In the experimental part, we use the real university library digital resource dataset to verify. Experimental results show that compared with traditional RSs, our approach has significantly improved on several evaluation indicators such as accuracy, recall rate and F1 score, while also performing well in terms of diversity and novelty. This proves that our approach can effectively improve user satisfaction and interactive experience. © The Author(s)

关键词： digital resources integrated algorithm precise recommendation university libraries User interest

来源：评论

学校读者我要写书评

暂无评论

integrated OPTIMIZATION OF HYBRID STEAM-SOLVENT INJECTION IN POST-CHOPS RESERVOIRS UNDER UNCERTAINTY 42

INTEGRATED OPTIMIZATION OF HYBRID STEAM-SOLVENT INJECTION IN...

引用

ASME 42nd International Conference on Ocean, Offshore and Arctic Engineering (OMAE)

作者： Hou, Senhan Yang, Shikai Jiang, Liwu Yang, Daoyong Univ Regina Regina SK Canada

ISBN: (纸本)9780791886915

In this paper, an integrated algorithm is proposed to optimize the hybrid steam-solvent injection-production schemes for post-CHOPS reservoirs under uncertainty. First of all, the newly developed pressure-gradient-based (PGB) sand failure criterion is employed to generate dendritic (or fractal-like) and regional wormhole networks, based on which the net present value (NPV) is defined and used as the objective function. A hybrid optimization technique based on the genetic algorithm (GA) is then integrated with the orthogonal array (OA) and Tabu search to maximize the objective function by rationalizing the injection and production parameters and simultaneously retarding the displacement front to extend the reservoir life under uncertainty. In a given CHOPS well, not only can the proposed method be used to determine the overall morphology of the wormhole network, including intensity and coverage, but also design, evaluate, and optimize performance of any potential EOR processes in a post-CHOPS reservoir within a unified, efficient, and accurate framework.

关键词： integrated algorithm post-CHOPS uncertainty wormhole networks framework

来源：评论

学校读者我要写书评

暂无评论

An integrated Medical Recommendation Mechanism Combining Promote Product Singular Value Decomposition and Knowledge Graph 18th

An Integrated Medical Recommendation Mechanism Combining Pro...

引用

18th International Conference on Advanced Data Mining and Applications (ADMA)

作者： Sun, Yibo Liu, Chenlei Tong, Xue Hu, Bing Univ Queensland St Lucia Qld 4072 Australia Nanjing Univ Posts & Telecommun Post Big Data Technol & Applicat Engn Res Ctr Jia Post Ind Technol Res & Dev Ctr State Posts BurInternet Things Technol Nanjing Peoples R China Nanjing Univ Posts & Telecommun Minist Educ Broadband Wireless Commun Technol Engn Res Ctr Nanjing Peoples R China

ISBN: (纸本)9783031220630;9783031220647

Due to the increasingly serious problem of information overload, it is difficult for medical staff to accurately screen out data conducive to patient consultation when dealing with massive amounts of diagnostic information. In this paper, we propose a hybrid recommendation mechanism integrating the improved Singular Value Decomposition and Knowledge Graph for medical information. It can effectively analyze the characteristic relationship between patients and medical item information and give appropriate medical recommendation scheme information based on patients' interests and preferences. We design the Promote Product Singular Value Decomposition (PPSVD) algorithm and integrate knowledge graph technology to construct the medical system's recommendation model. Finally, the experimental results show that the integrated medical recommendation model proposed has higher accuracy and usability than any other algorithms.

关键词： Medical recommendation system integrated algorithm PPSVD Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

End-to-end integrated service provision and protection scheme in IP over WDM networks

End-to-end integrated service provision and protection schem...

引用

Conference on Network Architectures, Management and Applications II

作者： Zhu, YH Lin, RJ Shanghai Univ Sch Engn & Comp Sci Shanghai 200072 Peoples R China

ISBN: (纸本)0819455806

Generalized Multiprotocol Label Switching (GMPLS), which is developed to support common control of packet, TDM, wavelength, and fiber services, is the key enabler of the new network model. The survivability of IP over WDM networks gains importance as network traffic keeps growing. In this paper, we propose an integrated provisioning scheme to dynamically allocate Label Switched Paths (LSPs) in IP over WDM networks. This scheme takes advantage of information sharing between layers (e.g., link state information, bandwidth usage, and protection capability) to eliminate redundancies and inefficiencies in the traditional layer-independent service provisioning. The integration of information is facilitated by GMPLS signaling. The proposed scheme also uses GMPLS capabilities to provide end-to-end survivability against network failures. The ability to provision across all network layers ensures efficient bandwidth usage. We propose two integrated routing algorithms: availability-based integrated routing algorithm and joint availability-based integrated routing algorithm. The simulation is made to evaluate the performance of our proposed integrated provisioning mechanism. As a result, network performance can be optimized over all layers. This could lead to significant cost savings for service providers.

关键词： provisioning protection IP-over-WDM survivability integrated algorithm

来源：评论

学校读者我要写书评

暂无评论

Modelling and analysis of initial icing roughness with fixed-grid enthalpy method based on DPM-VOF algorithm

引用

Chinese Journal of Aeronautics 2022年第7期35卷 168-178页

作者： Jie LIU Peng KE Department of Civil Helicopter Research and Development China Helicopter Research and Development InstituteTianjin 300000China School of Transportation Science and Engineering Beihang UniversityBeijing 100191China

Ice particles could form under the continuous impingement of incoming supercooled droplets in icing conditions,which will change the surface roughness to enhance the further heat and mass transfer during icing process.A fixed-grid porous enthalpy method based on the improved Discrete Phase Model(DPM)and Volume of Fluid(VOF)integrated algorithm is developed to solve the multiphase heat transfer problem to give more detailed demonstration of the formation of initial ice *** algorithms to determine the criterion of transformation from DPM to VOF and the allocation of source items during transformation are improved to the general DPM-VOF *** verification cases,namely two glycerine-solution droplets impact and single droplet freeze,are conducted to verify the accuracy and reliability of the enthalpy-DPMVOF method,where the simulation results match well with experiment *** roughness on a NACA0012 airfoil is precisely captured and the effects on convective heat transfer characteristics are preliminarily *** results illustrate that the enthalpy-DPM-VOF method could successfully capture the characteristics of motion and the phase change process of droplet,as well as balance the calculation accuracy and efficiency.

关键词： Discrete phase model Fixed-grid porous enthalpy method Ice roughness Icing modelling integrated algorithm Multiphase heat transfer Volume of fluid

来源：评论

学校读者我要写书评

暂无评论

Cancer gene search with data-mining and genetic algorithms

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2007年第2期37卷 251-261页

作者： Shah, Shital Kusiak, Andrew Univ Iowa Intelligent Syst Lab MIE Iowa City IA 52242 USA

Cancer leads to approximately 25% of all mortalities, making it the second leading cause of death in the United States. Early and accurate detection of cancer is critical to the well being of patients. Analysis of gene expression data leads to cancer identification and classification, which will facilitate proper treatment selection and drug development. Gene expression data sets for ovarian, prostate, and lung cancer were analyzed in this research. An integrated gene-search algorithm for genetic expression data analysis was proposed. This integrated algorithm involves a genetic algorithm and correlation-based heuristics for data preprocessing (on partitioned data sets) and data mining (decision tree and support vector machines algorithms) for making predictions. Knowledge derived by the proposed algorithm has high classification accuracy with the ability to identify the most significant genes. Bagging and stacking algorithms were applied to further enhance the classification accuracy. The results were compared with that reported in the literature. Mapping of genotype information to the phenotype parameters will ultimately reduce the cost and complexity of cancer detection and classification. (c) 2006 Elsevier Ltd. All rights reserved.

关键词： gene selection integrated algorithm data mining genetic algorithm genetic expression ovarian cancer prostate cancer lung cancer

来源：评论

学校读者我要写书评

暂无评论

Effect of combined strategy on mitigating air pollution in China

引用

CLEAN TECHNOLOGIES AND ENVIRONMENTAL POLICY 2021年第3期23卷 1027-1043页

作者： Jia, Shuwei Henan Agr Univ Coll Informat & Management Sci 15 Longzi Lake Zhengzhou 450046 Henan Peoples R China

Air pollution has worsened as a result of increased traffic congestion in cities. Using air pollution caused by motor vehicle emissions (mainly by carbon monoxide, hydrocarbon, nitrogen oxide, and particulate matter) as an example, in this study, we applied an integrated algorithm comprising system dynamics, entropy weight method, and gray system theory to establish a weighted logic function. A vehicle pollutant control model (including the transport, health, and environmental subsystems) was established by VENSIM software. The medium- and long-term key variable analysis showed that the integrated algorithm, fully reflecting the advantages of system dynamics and gray system theory, more accurately described air pollution caused by vehicle emissions. Our research results also revealed that the combined strategy of penalties and air pollution charging fee had a threefold effect: reduced congestion and emissions, improved health impact index, and reduced number of illegal trips. Specifically, the degree of traffic congestion, number of illegal trips, and the degree of air pollution decreased by approximately 82.40%, 69.35%, and 68.91%, respectively, whereas the health impact index increased by about 279.03%. This finding provides guidance for improving policy and optimizing management and control modes. [GRAPHICS] .

关键词： System dynamics Air pollution integrated algorithm Emission reduction Threefold effect

来源：评论

学校读者我要写书评

暂无评论

A Flight Arrival Time Prediction Method Based on Cluster Clustering-Based Modular With Deep Neural Network

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第6期25卷 6238-6247页

作者： Deng, Wu Li, Kunpeng Zhao, Huimin Civil Aviat Univ China Coll Elect Informat & Automat Tianjin 300300 Peoples R China

With the rapid development of the air transportation industry, air traffic is facing a severe test. The accurate prediction of the estimated arrival time (EAT) plays an important role in rational and efficient scheduling of flights. Aircraft EAT predictions often rely on aircraft performance parameters or physical trajectories. This gives poor consideration to the flight environment and take-off and landing conditions. This paper applies a data-driven methodology for ETA prediction. A Cluster clustering-based modular integrated DNN (CC-MIDNN) is proposed. According to the information of flight mission and flight environment, it decomposes complex modeling tasks into multiple distinct subtasks using cluster-based clustering. Then Bayesian optimization is used to design corresponding parallel sub-networks to learn different sub-tasks in order to reduce the complexity of the subsequent sub-networks. Finally, a new integration scheme is proposed to solve the overfitting problem due to the reliance on the training accuracy of sub-modules. To verify the effectiveness of the method, CC-MIDNN performs EAT prediction on flight data of European Airlines LIS airport in 2017. The experimental results show that the CC-MIDNN improves the time prediction accuracy by 5.92 minutes and keeps the error within 13 minutes. Compared with other deep learning algorithms and integration algorithms, the CC-MIDNN has high accuracy and stability.

关键词： Regression prediction estimated arrival time deep neural network cluster clustering-based modular integrated algorithm Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Improving generalization performance of landslide susceptibility model considering spatial heterogeneity by using the geomorphic label-based LightGBM

引用

BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT 2024年第9期83卷 361页

作者： Sun, Deliang Wu, Xiaoqing Wen, Haijia Shi, Shuxian Gu, Qingyu Chongqing Normal Univ Sch Geog & Tourism Key Lab GIS Applicat Res Chongqing 401331 Peoples R China Chongqing Univ Sch Civil Engn Key Lab New Technol Construct Cities Mt Area Natl Joint Engn Res Ctr Geohazards Prevent Reservo Chongqing 400045 Peoples R China East China Normal Univ Key Lab Geog Informat Sci Minist Educ Shanghai 200241 Peoples R China

Previous landslide susceptibility assessments often overlook the heterogeneity of landslides across different regions and their generalization ability. The objective of this study was to explore the landslide susceptibility model from geomorphic zones-based K-means constructed sub-regions to geomorphic label-based matching whole regions. To achieve this, we divided the study area into slope units based on curvature calculation and utilized a Light Gradient Boosting Machine (LightGBM) to construct the susceptibility model. For model training, we randomly selected fourteen townships in Fengjie County, Chongqing, China. By employing K-means clustering, we established geomorphic zones for the landslide susceptibility model, which were assigned a corresponding geomorphic label. Notably, the model divided the entire study area into four geomorphic zones, with zone 4 demonstrating the highest accuracy of 0.85. Additionally, we developed two comparative models to assess the effectiveness of our proposed approach. The first comparative model considered only ten conditioning factors, resulting in a model accuracy of 0.73. The second comparative model incorporated the classification results of geomorphic labels as explanatory variables for landslides and achieved a model accuracy of 0.75. In this study, we successfully established a model with an accuracy of 0.87 by automatically matching and generalizing the remaining townships with the existing geomorphic labels. Our findings suggest that a geomorphic label-based model, adopting a framework from sub-regions to the whole region, offers better quantification of the landslide occurrence mechanism in the region and demonstrates stronger generalization ability compared to the overall-based model.

关键词： Landslide susceptibility Geomorphic label Generalization ability Spatial heterogeneity LightGBM integrated algorithm

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：