检索结果-内蒙古大学图书馆

Predicting Yeast Protein Localization Sites by a New clustering algorithm Based on Weighted Feature Ensemble

JOURNAL OF COMPUTATIONAL AND THEORETICAL NANOSCIENCE 2014年第6期11卷 1563-1568页

作者： Fan, Jiancong Feng, Zheng Liu, Wenhua Pang, Jinrong Liang, Yongquan Shandong Univ Sci & Technol Coll Informat Sci & Engn Qingdao 266590 Peoples R China

The analysis of protein localization sites is an important task in bioinformatics. Predicting the yeast protein localization sites is a promising domain among numerous research methods based on the yeast protein measurement data which have multiple indexes/features. In order to reflect the different contributions of those features to predicting tasks, a clustering algorithm based on weighted feature ensemble (WFE) is proposed to predict yeast protein localization sites on the basis of the gathered yeast protein localization data. WFE process firstly assigns different weights to features, and then the results are computed and presented to obtain the best outcome. Experimental results on our algorithm based on WFE and other several clustering algorithms based on the ideas of weighted features have shown that our new algorithm outperformed the other feature weighting type algorithms in accuracy and stability.

关键词： clustering algorithm Yeast Protein Data clustering Feature Weighting Ensemble Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

DBCURE-MR: An efficient density-based clustering algorithm for large data using MapReduce

引用

INFORMATION SYSTEMS 2014年第Jun.期42卷 15-35页

作者： Kim, Younghoon Shim, Kyuseok Kim, Min-Soeng Lee, June Sup Seoul Natl Univ Sch Elect & Comp Engn Seoul 151600 South Korea SK Planet Seoul South Korea

clustering is a useful data mining technique which groups data points such that the points within a single group have similar characteristics, while the points in different groups are dissimilar. Density-based clustering algorithms such as DBSCAN and OPTICS are one kind of widely used clustering algorithms. As there is an increasing trend of applications to deal with vast amounts of data, clustering such big data is a challenging problem. Recently, parallelizing clustering algorithms on a large cluster of commodity machines using the MapReduce framework have received a lot of attention. In this paper, we first propose the new density-based clustering algorithm, called DBCURE, which is robust to find clusters with varying densities and suitable for parallelizing the algorithm with MapReduce. We next develop DBCURE-MR, which is a parallelized DBCURE using MapReduce. While traditional density-based algorithms find each cluster one by one, our DBCURE-MR finds several clusters together in parallel. We prove that both DBCURE and DBCURE-MR find the clusters correctly based on the definition of density-based clusters. Our experimental results with various data sets confirm that DBCURE-MR finds clusters efficiently without being sensitive to the clusters with varying densities and scales up well with the MapReduce framework. (C) 2013 Published by Elsevier Ltd.

关键词： clustering algorithm Density-based clustering Parallel algorithm MapReduce

来源：评论

学校读者我要写书评

暂无评论

Optimizing Environment-aware VANET clustering using Machine Learning

引用

INTERNATIONAL JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS RESEARCH 2023年第3期21卷 394-408页

作者： Fahmy, Yasmine Alsuhli, Ghada Khattab, Ahmed Cairo Univ EECE Dept Giza Egypt Khalifa Univ Syst On Chip Ctr SoCC Abu Dhabi U Arab Emirates

clustering is important to improve the quality of service in many VANET protocols and applications, such as data dissemination, media access control, Internet of vehicles and intrusion detection systems. Since the performance of a clustering algorithm is highly influenced by the surrounding environment, an environment-aware clustering algorithm that can adapt itself to follow the changes in the environment features is required. In this paper, we propose a machine learning-based framework to include this awareness to an arbitrary clustering algorithm. This is done by optimizing the clustering algorithm's parameters taking into consideration the road structure and the traffic features that affect the clustering performance. Our framework aims to model how the optimum values of different configuration parameters change with the considered features. Then, these models are used to allow the clustering algorithm to adjust its configurations in real-time according to the measured environment features. After applying this framework on a state-of-the-art clustering algorithm, the performance of the resulting algorithm is compared to other clustering schemes as well as the original algorithm. The obtained results prove the efficiency of the proposed approach reflected by the significant improvements in the different quality metrics and maintaining these metrics in the highest possible levels despite the changes in the considered environment features.

关键词： Vehicular Ad hoc Network (VANET) clustering algorithm Machine learning

来源：评论

学校读者我要写书评

暂无评论

A new methodology for building energy performance benchmarking: An approach based on intelligent clustering algorithm

引用

ENERGY AND BUILDINGS 2014年 84卷 607-616页

作者： Gao, Xuefeng Malkawi, Ali Univ Penn Dept Architecture Philadelphia PA 19104 USA

Though many building energy benchmarking programs have been developed during the past decades, they hold certain limitations. The major concern is that they may cause misleading benchmarking due to not fully considering the impacts of the multiple features of buildings on energy performance. The existing methods classify buildings according to only one of many features of buildings the use type, which may result in a comparison between two buildings that are tremendously different in other features and not properly comparable as a result. This paper aims to tackle this challenge by proposing a new methodology based on the clustering concept. The clustering concept, which reflects on machine learning algorithms, classifies buildings based on a multi-dimensional domain of building features, rather than the single dimension of use type. Buildings with the greatest similarity of features that influence energy performance are classified into the same cluster, and benchmarked according to the centroid reference of the cluster. The proposed methodology contains four steps: feature selection, clustering algorithm adaptation, results validation, and interpretation. The experimentation was carried out with a comparison between the proposed methodology and the Energy Star approach. It was shown that the proposed methodology could account for the total building energy performance and was able to provide a more comprehensive approach to benchmarking. In addition, the multi-dimensional clustering concept enables energy benchmarking among different types of buildings, and inspires a new perspective to investigate building performance typology. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Building performance Energy benchmarking clustering algorithm Multi-dimensional features

来源：评论

学校读者我要写书评

暂无评论

Study on the Application of Dynamic Continuous Trust Assessment Model Based on clustering Mechanism in Network Security Optimization

引用

Journal of Mobile Multimedia 2025年第1期14卷 47-74页

作者： Wu, Weidong Tian, Zheng Sun, Yizhen Li, Yongfa Cui, Yu State Grid Hunan Electric Power Company Limited ChangSha HuNan 410007 China Information and Communication Branch of State Grid Hunan Electric Power Company ChangSha HuNan 410007 China State Grid Informationn & Telecommunication Group CO. LTD. 102211 China

Due to the rapid development of network technology and the increasing size of networks, the security of networks in today’s society is facing great challenges. The study of network security is based on the study of network security frameworks, connections, and models to improve network security so that the network becomes controllable, manageable, and survivable. In this paper, we propose a dynamic continuous trust assessment model based on the clustering mechanism and apply this model to the network security model optimization problem. The specific conclusions are as follows: (1) The problems in previous clustering algorithms are analyzed, and corresponding solutions are proposed for the problems. Then, the particle swarm algorithm is briefly introduced, the inertia weight coefficients in the particle swarm algorithm are improved, and the dormant mechanism of neighboring node groups is introduced. (2) A new algorithm for calculating direct trust value is proposed. (3) A method for evaluating the overall trust value level of the network is proposed. The method first selects the N nodes with the highest number of interactions and then evaluates the overall trust level of the network in which these N nodes are located by using the associative memory capability of the clustering algorithm. (4) The experimental analysis shows that the randomly generated rule set in the model of this paper tends to evolve to a stable state after 60∼80 rounds of operation, with a higher success rate, and at 180∼200 rounds of operation, the rule set evolves to a stable state again, with the success rate still improved;after 240 rounds of operation, the network environment is restored to the initial state, and although the roles of some of the nodes are changed, the model still evolves to a high level again. Level. The dynamic continuous trust evaluation model proposed in this paper can be effective in the network security optimization, but the practical application of the model should be d

关键词： clustering algorithm cyber-physical security dynamic persistent trust Security in mobile networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Steganography Scheme Using Logistic Map, BRISK Descriptor, and K-Means clustering 11th

A Novel Steganography Scheme Using Logistic Map, BRISK Descr...

引用

11th Pacific-Rim Symposium on Image and Video Technology (PSIVT)

作者： Azooz, Hassan Jameel Ben Salah, Khawla Kherallah, Monji Naceur, Mohamed Saber Univ Almuthanna Samawah Iraq Univ Sfax Sfax Tunisia Univ Carthage Carthage Tunisia Univ Sfax Natl Engn Sch Sfax Tunisia

ISBN: (纸本)9789819703753;9789819703760

This paper introduces a novel steganography method for embedding and extracting a secret message from an image file using three stages. In the first stage, Binary Robust Invariant Scalable Keypoints (BRISK) and Good Features to Track are utilized to identify keypoints in the image. In the second stage, the k-means clustering algorithm is applied to these identified keypoints. The keypoints derived from the good features to track algorithm serve as cluster centers while the keypoints from the BRISK algorithm are distributed around these centers. In the last stage, the logistic map algorithm is employed to add more randomness to the obtained keypoints. This is done by distributing the points using the random list property. The results obtained indicate that the proposed method surpasses comparable techniques in terms of PSNR (Peak Signal-to-Noise Ratio), SSIM (Structural Similarity Index), and BER (Bit Error Rate) values metrics. Thus, the proposed scheme offers a performance advantage over existing methodologies.

关键词： clustering algorithm BRISK embedding steganography

来源：评论

学校读者我要写书评

暂无评论

Proteome-wide assessment of differential missense variant clustering in neurodevelopmental disorders and cancer

引用

CELL GENOMICS 2025年第4期5卷 100807-100807页

作者： Ng, Jeffrey K. Chen, Yilin Akinwe, Titilope M. Heins, Hillary B. Mehinovic, Elvisa Chang, Yoonhoo Gutmann, David H. Gurnett, Christina A. Payne, Zachary L. Manuel, Juana G. Karchin, Rachel Turner, Tychele N. Washington Univ Sch Med Dept Genet St Louis MO 63110 USA Johns Hopkins Univ Dept Biomed Engn Baltimore MD 21205 USA Washington Univ Sch Med Mol Genet & Genom Grad Program St Louis MO 63110 USA Washington Univ Sch Med Human & Stat Genet Grad Program St Louis MO 63110 USA Washington Univ Sch Med Dept Neurol St Louis MO 63110 USA Washington Univ Sch Med Intellectual & Dev Disabil Res Ctr St Louis MO 63110 USA Johns Hopkins Univ Dept Comp Sci Baltimore MD 21205 USA Johns Hopkins Univ Sch Med Sidney Kimmel Comprehens Canc Ctr Baltimore MD 21205 USA Johns Hopkins Univ Inst Computat Med Baltimore MD 21205 USA

Prior studies examining genomic variants suggest that some proteins contribute to both neurodevelopmental disorders (NDDs) and cancer. While there are several potential etiologies, here, we hypothesize that missense variation in proteins occurs in different clustering patterns, resulting in distinct phenotypic outcomes. This concept was first explored in 1D protein space and expanded using 3D protein structure models. Missense de novo variants were examined from 39,883 families with NDDs and missense somatic variants from 10,543 sequenced tumors covering five The Cancer Genome Atlas (TCGA) cancer types and two Catalog of Somatic Mutations in Cancer (COSMIC) pan-cancer aggregates of tissue types. We find 18 proteins with differential missense variation clustering in NDDs compared to cancers and 19 in cancers relative to NDDs. These proteins may be important for detailed assessments in thinking of future prognostic and therapeutic applications. We establish a framework for interpreting missense patterns in NDDs and cancer, using advances in 3D protein structure prediction.

关键词： neurodevelopmental disorders cancer clustering algorithm 3D protein structure models missense de novo somatic variant interpretation protein

来源：评论

学校读者我要写书评

暂无评论

Cluster-based deep ensemble learning for emotion classification in Internet memes

引用

JOURNAL OF INFORMATION SCIENCE 2025年第1期51卷 265-283页

作者： Guo, Xiaoyu Ma, Jing Zubiaga, Arkaitz Nanjing Univ Aeronaut & Astronaut Coll Econ & Management Nanjing Peoples R China Queen Mary Univ London Sch Elect Engn & Comp Sci London England Nanjing Univ Aeronaut & Astronaut Coll Econ & Management 29 Jiangjun Rd Nanjing 211100 Jiangsu Peoples R China

Memes have gained popularity as a means to share visual ideas through the Internet and social media by mixing text, images and videos, often for humorous purposes. Research enabling automated analysis of memes has gained attention in recent years, including among others the task of classifying the emotion expressed in memes. In this article, we propose a novel model, cluster-based deep ensemble learning (CDEL), for emotion classification in memes. CDEL is a hybrid model that leverages the benefits of a deep learning model in combination with a clustering algorithm, which enhances the model with additional information after clustering memes with similar facial features. We evaluate the performance of CDEL on a benchmark data set for emotion classification, proving its effectiveness by outperforming a wide range of baseline models and achieving state-of-the-art performance. Further evaluation through ablated models demonstrates the effectiveness of the different components of CDEL.

关键词： clustering algorithm emotion classification ensemble learning Internet memes

来源：评论

学校读者我要写书评

暂无评论

Evaluation on the state of sand filling layer and the influence on segment deformation of immersed tunnels

引用

Underground Space 2024年第3期16卷 224-238页

作者： Ziyao Xu Ailan Che Chao Su School of Naval Architecture Ocean and Civil EngineeringShanghai Jiao Tong UniversityShanghai 200240China CCCC Second Harbor Engineering Company Ltd. Wuhan 430040China

The immersed tunnel is considered an effective solution for traffic problems across rivers and *** sand filling layer,as an important part of immersed tunnel foundation treatments,directly affects segment attitude *** to difficulties in quality control of concealed construction and the complex hydrodynamic environment,the sand filling layer is prone to compaction defects,further leading to changes in segment ***,limited by structural concealment and state complexity,most studies consider the sand filling layer part of the foundation to study its impact on settlement while neglecting its influence on segment *** research proposes an evaluation method for the sand filling layer state based on elastic wave testing and the elastic wave characteristic parameters selected come from analysis of the time domain,frequency domain and time–frequency *** classifying the elastic wave characteristic parameters through the K-means clustering method,the relationship between the state of the sand filling layer and the elastic wave characteristic parameters is *** state of the sand filling layer is divided into dense,incompact,and void.A numerical model is established based on the Guangzhou BI-UT immersed tunnel with incompact and void sand filling layer states to simulate deformation and *** results indicate that the settlement of the tunnel segment is low in the eastern region and high in the western region due to the presence of a less dense sand filling layer,with a maximum differential settlement of 0.04 *** evaluation method plays a crucial role in guiding the construction of immersed tube tunnels.

关键词： Sand filling layer state Immersed tunnel Elastic wave test clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

A single-valued neutrosophic affinity propagation approach for engineering geological zoning of open-pit mine slopes

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 146卷

作者： Qin, Jibo Sun, Xiaoming Du, Shigui Ye, Jun Ningbo Univ Inst Rock Mech Ningbo 315211 Zhejiang Peoples R China China Univ Min & Technol Beijing State Key Lab Tunnel Engn Beijing 100083 Peoples R China China Univ Min & Technol Beijing Sch Mech & Civil Engn Beijing 100083 Peoples R China

Engineering geological zoning is an important foundation for assessing the stability of open-pit mine (OPM) slopes. Because of the complexity and uncertainty of geological conditions, this work brings great challenges to mining engineers and researchers. This paper presents a single-valued neutrosophic affinity propagation (SVNSAP) approach for engineering geological zoning of OPM slopes. The approach utilizes the concept of a singlevalued neutrosophic set (SVNS) to express the inconsistent and indeterminate information present in the influencing factors of engineering geological conditions through truth, indeterminate and falsity membership functions. Then, the similarity measure of SVNS is integrated into the affinity propagation (AP) algorithm to calculate the degree of similarity between the data points. Finally, the modified silhouette index is used to evaluate the clustering results and decide the optimal number of clusters. The practical application results of the engineering geological zoning of Lanping lead-zinc OPM demonstrate that the SVNS-AP method is an effective way for engineering geological zoning of OPM slopes in the uncertain environment. clustering results based on datasets in the literature and the UC Irvine Machine Learning Repository show that the proposed method can be used as a general clustering algorithm.

关键词： clustering algorithm Single-valued neutrosophic set Neutrosophic similarity measure Affinity propagation method Engineering geological zoning Open-pit mine

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：