检索结果-内蒙古大学图书馆

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

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

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 training pattern recognition algorithm based on weight clustering for improving cooling load prediction accuracy of HVAC system

引用

JOURNAL OF BUILDING ENGINEERING 2022年 52卷

作者： Chen, Sihao Wang, Liangzhu (Leon) Li, Jing Zhou, Guang Zhou, Xiaoqing Guangzhou Univ Sch Civil Engn Guangdong Prov Key Lab Bldg Energy Efficiency & A Acad Bldg Energy Efficiency Guangzhou 510006 Peoples R China Concordia Univ Dept Bldg Civil & Environm Engn Ctr Zero Energy Bldg Studies Montreal PQ H3G 1M8 Canada Zhongkai Univ Agr & Engn Guangzhou 510225 Peoples R China

The cooling load-based optimal control is an advanced technology for the efficient operation of heating, ventilation, and air conditioning (HVAC). Thus, the prediction reliability of cooling load plays a key role in HVAC's optimal control. Current publications primarily focused on the structure optimization of prediction models, while less on the clustering-based cooling load prediction. However, the data quality determines the upper limit of the model's prediction performance. Thus, a training pattern recognition algorithm based on weight clustering is proposed for improving cooling load prediction accuracy. Compared with the existing clustering-based prediction methods, the main innovations of the proposed method are: (i) considering the input variables' weights on cooling load in the clustering process;and (ii) investigating the matching between the various prediction models and the K-means clustering algorithm. The case studies showed that the proposed method achieves a significant improvement in the prediction performance, such as MAPEs of the MLR, MNR, and ANN decrease by 34.67%, 35.56%, and 14.53% on average, respectively. Compared with the non-weights clustering method, the introduction of the weights can further improve the above models' prediction accuracy, such as their MAPEs decrease by 6.30%, 7.59%, and 3.07% on average, respectively. These results also demonstrated that the clustering-based prediction method is more suitable for the regression models (e.g., MLR and MNR) with low complexity compared to the ANN. When the clustering number is about 4, the models' prediction performances were more robust. Applying the proposed method to the time-series models (i.e., AR, ARX, and ANN) resulted in their MAPEs as low as 1.79%, 1.78%, and 2.06%, respectively. the proposed method can provide a new idea for improving the accuracy of cooling load prediction.

关键词： Cooling load prediction Pattern recognition clustering algorithm Data preprocessing Mode identification

来源：评论

学校读者我要写书评

暂无评论

Power Load Curve clustering Based on IGWOK-medoids 7

Power Load Curve Clustering Based on IGWOK-medoids

引用

7th International Conference on Energy, Electrical and Power Engineering (CEEPE)

作者： Zhang, Weifeng Wu, Binfeng Zhao, Xinyi Xu, Jing Zhang, Yihan Wu, Pingping Wang, Li Chen, Xi State Grid Zhejiang Elect Power Co Ltd Lishui Power Supply Co Lishui Peoples R China

ISBN: (纸本)9798350375794;9798350375800

This paper introduces an advanced clustering algorithm for power load curves, named IGWO-Kmedoids, addressing challenges faced by traditional clustering methods like k-means and DBSCAN in handling power system load data. These challenges include difficulty in parameter setting, slow clustering speeds, and suboptimal results. The proposed algorithm begins with data preprocessing, including outlier removal and filling missing values through interpolation, followed by standardization. It then employs Principal Component Analysis (PCA) for dimensionality reduction, easing the computational load for clustering. The core innovation lies in optimizing the K-medoids clustering algorithm with an Improved Grey Wolf Optimization (IGWO) approach, enhancing clustering accuracy and speed. This optimization significantly boosts the power system's operational efficiency and the optimization of scheduling policies.

关键词： clustering algorithm IGWO-Kmedoids PCA

来源：评论

学校读者我要写书评

暂无评论

A NOVEL clustering algorithm BASED ON P SYSTEMS

引用

INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL 2014年第2期10卷 753-765页

作者： Jiang, Yang Peng, Hong Huang, Xiaoli Zhang, Jiarong Shi, Peng Xihua Univ Ctr Radio Adm & Technol Dev Chengdu 610039 Sichuan Peoples R China Harbin Engn Univ Coll Automat Harbin 150001 Heilongjiang Peoples R China Victoria Univ Sch Engn & Sci Melbourne Vic 8001 Australia

Membrane computing (known as P systems) is a novel class of distributed parallel computing models. In this paper, a partition-based clustering algorithm under the framework of membrane computing is proposed. The clustering algorithm is based on a tissue-like P system, which is used to exploit the optimal cluster centers for a data set. Each object in the tissue-like P system represents a group of candidate cluster centers and is evolved through simulated annealing mechanism and mutation mechanism. Meanwhile, communication rules are used to exchange and share the objects between different elementary membranes and between elementary membranes and the environment. The proposed clustering algorithm is evaluated over two artificial data sets and two real-life data sets and is further compared with k-means algorithm and GA-based k-means algorithm respectively. The comparison results reveal the superiority of the proposed clustering algorithm in terms of clustering quality and stability.

关键词： Membrane computing Tissue-like P systems clustering algorithm Simulated annealing K-means

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：