检索结果-内蒙古大学图书馆

SAR Image Change Detection Based on Nonlocal Low-Rank Model and two-level clustering

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2020年 13卷 293-306页

作者： Sun, Yuli Lei, Lin Guan, Dongdong Li, Xiao Kuang, Gangyao Natl Univ Def Technol Coll Elect Sci Changsha 410073 Peoples R China

Change detection (CD) has found a wide range of applications in many fields. In this article, we propose a novel nonlocal low-rank (NLR) based method for multitemporal synthetic aperture radar image CD. This method jointly exploits the powerful NLR-based despeckling and the effective cascade clustering. First, the NLR model is used to generate the difference image (DI), which consists of a patch grouping process and a low-rank minimizing process. Especially, the NLR minimization model contains a data fidelity term, which is based on the statistical distribution of speckle noise, and a regularization term, which uses the weighted nuclear norm. Then, the alternating direction methods of multipliers is introduced to solve this minimization problem. Second, after DI is generated, the principal component analysis is employed to extract the feature and a two-level clustering method is used to generate the final change map, which separates the intermediate class by using the neighbor information with Gaussian weighted distance. Experiment results demonstrate the effectiveness of the proposed method by comparing with some state-of-the-art methods.

关键词： Low-rank modeling speckle reduction synthetic aperture radar (SAR) images two-level clustering unsupervised change detection (CD)

来源：评论

学校读者我要写书评

暂无评论

A two-level clustering based on fuzzy logic and content-based routing method in the internet of things

引用

PEER-TO-PEER NEtwoRKING AND APPLICATIONS 2022年第4期15卷 2142-2159页

作者： Kiamansouri, Ehsan Barati, Hamid Barati, Ali Islamic Azad Univ Dept Comp Engn Dezful Branch Dezful Iran

The Internet of Things (IoT) is a novel concept in the technology and communication world. Briefly, the "Internet of Things" is a modern technology in which any entity such as humans, animals, or objects can transmit data through communication networks like, the Internet or the Intranet. These networks have very important challenges such as energy consumption, and fast and reliable data transmission due to their heterogeneous and dynamic nature. In this paper, we propose a two-level clustering based on fuzzy logic and content-based routing method. In the first level clustering, several parameters are applied: energy, node capacity, and number of neighbors. Also, in the second level clustering, the centrality formula has been used to select super cluster head nodes. In the proposed routing process, we divide data into two types: high-volume data and low-volume data, and the routing process is performed based on the data type. We simulate the proposed method using MATLAB software. Then, simulation results are compared with the different schemes including, HEED, FLCFP, FBCFP, and ELCP. Experiments show that the proposed method outperforms others in terms of average energy consumption, the number of alive nodes, network lifetime, and packet delivery rate.

关键词： Internet of Things (IoT) Content-Based Routing two-level clustering Energy Consumption Fuzzy Logic

来源：评论

学校读者我要写书评

暂无评论

A data-driven two-level clustering model for driving pattern analysis of electric vehicles and a case study

引用

JOURNAL OF CLEANER PRODUCTION 2019年 206卷 827-837页

作者： Li, Xuefang Zhang, Qiang Peng, Zhanglin Wang, Anning Wang, Wanying Hefei Univ Technol Sch Management 193 Tunxi Rd Hefei 230009 Anhui Peoples R China Minist Educ Key Lab Proc Optimizat & Intelligent Decis Making Hefei 230009 Anhui Peoples R China

The driving patterns of the electric vehicles describe how users use their vehicles, reflecting the users' habits. These patterns have a positive effect on vehicle energy consumption. In this paper, a two-level clustering model is proposed to determine the driving patterns of electric vehicles. Firstly, the driving pattern characteristics are extracted from the data set of the electric vehicles. Then, the driving patterns including daily driving patterns and multifaceted driving patterns are obtained by a two-level clustering model. The data of 1463 electric vehicles in China were collected from September 1, 2015, to September 1, 2016. Using the proposed model, we obtain five types of daily driving patterns and four types of multifaceted driving patterns. Then, the features of clusters are extracted, and the geographical distribution analysis of the multifaceted driving patterns is conducted. The experimental results reveal that there are many driving patterns of the electric vehicles. Moreover, the effectiveness of the clustering models is verified by the experiments. The customer segmentation based on the driving patterns of electric vehicles is of a great significance for the development of personalized and targeted marketing strategies of vehicle manufacturers and energy efficiency improvement.(C) 2018 Elsevier Ltd. All rights reserved.

关键词： Daily driving pattern Electric vehicles two-level clustering Multifaceted driving patterns

来源：评论

学校读者我要写书评

暂无评论

Gabor Feature Based Unsupervised Change Detection of Multitemporal SAR Images Based on two-level clustering

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2015年第12期12卷 2458-2462页

作者： Li, Heng-Chao Celik, Turgay Longbotham, Nathan Emery, William J. Southwest Jiaotong Univ Sichuan Prov Key Lab Informat Coding & Transmiss Chengdu 610031 Peoples R China Univ Colorado Dept Aerosp Engn Sci Boulder CO 80309 USA Univ Witwatersrand Sch Comp Sci ZA-2000 Johannesburg South Africa DigitalGlobe Inc Longmont CO 80503 USA

In this letter, we propose a simple yet effective unsupervised change detection approach for multitemporal synthetic aperture radar images from the perspective of clustering. This approach jointly exploits the robust Gabor wavelet representation and the advanced cascade clustering. First, a log-ratio image is generated from the multitemporal images. Then, to integrate contextual information in the feature extraction process, Gabor wavelets are employed to yield the representation of the log-ratio image at multiple scales and orientations, whose maximum magnitude over all orientations in each scale is concatenated to form the Gabor feature vector. Next, a cascade clustering algorithm is designed in this discriminative feature space by successively combining the first-level fuzzy c-means clustering with the second-level nearest neighbor rule. Finally, the two-level combination of the changed and unchanged results generates the final change map. Experimental results are presented to demonstrate the effectiveness of the proposed approach.

关键词： Fuzzy c-means (FCM) Gabor wavelets multitemporal synthetic aperture radar (SAR) images two-level clustering unsupervised change detection

来源：评论

学校读者我要写书评

暂无评论

Multiple features fusion change detection method based on two-level clustering 19

Multiple features fusion change detection method based on Tw...

引用

International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)

作者： Chen, ZhangHua Leng, XiangGuang Lei, Lin Natl Univ Def Technol State Key Lab Complex Electromagnet Environm Effe Changsha Peoples R China

ISBN: (纸本)9781450372985

In order to more fully make use of the feature information of remote sensing image and improve the detection accuracy of remote sensing image, after preprocessing, we propose a multi-featured remote sensing image change detection method. Firstly, two different methods based on spectral features and gradient features are used to calculate the change intensity image for different time-phase images. Then, the fusion algorithm is used to fuse the spectral feature method and the gradient feature respectively, and then the fusion results are merged. The difference fusion intensity map based on the two features is obtained. Finally, the image threshold is segmented by two levels using the two-level clustering algorithm to obtain image change information. Compared with the traditional method, the method improves the comprehensiveness of the change information expression by fusing the multiple features of the optical image, and adopts the two-level clustering to introduce the middle term, and the final threshold segmentation of the change intensity map can further become more realistic. It is verified by two sets of experimental data that the method can better integrate multi-feature information and express change information more comprehensively.

关键词： Change Detection Multiple Features Fusion two-level clustering

来源：评论

学校读者我要写书评

暂无评论

Synthetic Aperture Radar Image Change Detection Based on Principal Component Analysis and two-level clustering

引用

REMOTE SENSING 2024年第11期16卷 1861-1861页

作者： Li, Liangliang Ma, Hongbing Zhang, Xueyu Zhao, Xiaobin Lv, Ming Jia, Zhenhong Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Xinjiang Univ Sch Comp Sci & Technol Urumqi 830046 Peoples R China

Synthetic aperture radar (SAR) change detection provides a powerful tool for continuous, reliable, and objective observation of the Earth, supporting a wide range of applications that require regular monitoring and assessment of changes in the natural and built environment. In this paper, we introduce a novel SAR image change detection method based on principal component analysis and two-level clustering. First, two difference images of the log-ratio and mean-ratio operators are computed, then the principal component analysis fusion model is used to fuse the two difference images, and a new difference image is generated. To incorporate contextual information during the feature extraction phase, Gabor wavelets are used to obtain the representation of the difference image across multiple scales and orientations. The maximum magnitude across all orientations at each scale is then concatenated to form the Gabor feature vector. Following this, a cascading clustering algorithm is developed within this discriminative feature space by merging the first-level fuzzy c-means clustering with the second-level neighbor rule. Ultimately, the two-level combination of the changed and unchanged results produces the final change map. Five SAR datasets are used for the experiment, and the results show that our algorithm has significant advantages in SAR change detection.

关键词： SAR change detection principal component analysis Gabor wavelets two-level clustering

来源：评论

学校读者我要写书评

暂无评论

two-level distributed clustering routing algorithm based on unequal clusters for large-scale Internet of Things networks

引用

JOURNAL OF SUPERCOMPUTING 2020年第3期76卷 2158-2190页

作者： Amini, S. M. Karimi, A. Univ Waterloo Dept Elect & Comp Engn Waterloo ON Canada Islamic Azad Univ Qazvin Branch Fac Comp & Informat Technol Engn Qazvin Iran

According to the recent advancements in communication technologies and the widespread use of smart devices, our environment can be transforming into the Internet of Things (IoT) because it can connect the physical, cyber, and biological world via smart sensors for different purposes. Wireless sensor networks are considered as one of the main infrastructures in the IoT systems. Therefore, decreasing the total energy consumption of sensor nodes and prolonging the network longevity are two important challenges that should be considered. To increase energy efficiency and to improve the network longevity, a two-level distributed clustering routing algorithm based on unequal clusters has been proposed for large-scale IoT systems. The main idea is to decrease the data transmission distances between member nodes and cluster heads to mitigate the hot spot problem by distributing two cluster heads in each cluster, which in turn leads to energy conservation and load balancing. The clustering method is two level due to the benefits it offers for the sensor nodes. First, each node can transfer its data to the nearest cluster head because a primary cluster head and a secondary cluster head have been considered for each cluster. Therefore, the nodes far from the primary cluster head can be organized based on their distances to the closest cluster head to reduce their data transmission distances to the cluster heads. Second, two cluster heads can be replaced with each other in different circumstances. This reduces the overhead of the cluster head selection algorithm in the proposed scheme. Third, the sensor nodes can benefit from the primary and secondary cluster heads to transfer the data to the sink through different paths with the minimum energy consumption. Simulation results indicate that the proposed algorithm has better performance in terms of total energy consumption, total network energy, and network longevity compared to previous similar schemes.

关键词： Wireless sensor network Distributed routing algorithm two-level clustering Unequal clusters Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A two-level Semi-supervised clustering Technique for News Articles

引用

INTERNATIONAL JOURNAL OF ENGINEERING 2021年第12期34卷

作者： Sadjadi, S. M. Mashayekhi, H. Hassanpour, H. Shahrood Univ Technol Fac Comp Engn Shahrood Iran

The web and social media are overcrowded with news pieces in terms of amount and diversity. Document clustering is a useful technique that is widely used in organizing and managing data into smaller groups. One of the factors influencing the quality of clustering is the way documents are represented. Some traditional methods of document representation depend on word frequencies and create sparse and large-sized document vectors. These methods cannot preserve proximity information between documents. In addition, neural network-based methods that preserve proximity information suffer from poor interpretability. Conceptual text representation methods have overcome the shortcomings of previous methods, but semi-supervised text clustering does not currently use concept-based document representation. This paper presents a two-level semi-supervised text clustering method that uses labeled and unlabeled data simultaneously to achieve higher clustering quality. In the first level, documents are represented based on the concepts extracted from the raw corpus. Second, the semi-supervised clustering process applies unlabeled data to capture the overall structure of the clusters and a small amount of labeled data to adjust the center of the clusters. Experiments on the Reuters-21578 and BBC News data collections show that the proposed model is superior to other semi-supervised approaches in both text classification and text clustering.

关键词： News clustering two-level clustering Semi-supervised Word Embedding Document clustering

来源：评论

学校读者我要写书评

暂无评论

An Energy-efficient Routing Protocol Based on two-Layer clustering in WSNs 6th

An Energy-efficient Routing Protocol Based on Two-Layer Clus...

引用

6th Asia Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data (APWeb-WAIM)

作者： Xu, Feng Ni, Qian Liu, PanFei Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Coll Artificial Intelligence Nanjing Peoples R China Collaborat Innovat Ctr Novel Software Technol & I Nanjing Peoples R China

ISBN: (纸本)9783031251573;9783031251580

The design of energy-efficient routing protocol for large-scale wireless sensor network (WSN) has become a challenge nowadays. In order to balance the energy consumption of nodes and prolong network lifetime, this paper proposes an energy-efficient routing protocol DKBDCERP based on two-layer clustering. It uses an improved DPC-MND clustering algorithm to cluster nodes at first layer. Then, in each cluster, first-level cluster heads (CHs) are elected according to residual energy of the node and distance to base station (BS). After that, using all the first-level CHs as second layer, K-Means algorithm is used to cluster, and the second-level CHs are elected according to remaining energy of the node and distance between the node and center of mass and BS. Finally, path weight of the second-level CHs is designed according to energy, distance, deflection angle and other factors. On the basis of Dijkstra algorithm, the theory of immune algorithm is introduced to obtain the optimal inter-cluster multi-hop routing. The simulation result shows that DKBDCERP has excellent performance in balancing node energy consumption and prolonging network lifetime.

关键词： Wsn routing algorithm two-level clustering Immune algorithm Dpc-mnd

来源：评论

学校读者我要写书评

暂无评论

A positional keyword-based approach to inferring fine-grained message formats

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2020年 102卷 369-381页

作者： Jiang, Jiaojiao Versteeg, Steve Han, Jun Hossain, M. D. Arafat Schneider, Jean-Guy Swinburne Univ Technol Sch Software & Elect Engn Melbourne Vic 3122 Australia RMIT Univ Sch Sci Comp Sci & Software Engn Melbourne Vic 3000 Australia Deakin Univ Sch Informat Technol Burwood Vic 3125 Australia

Message format extraction, the process of revealing the message syntax without access to the protocol specification, is important for a variety of applications such as service virtualization and network security. In this paper, we propose P-token, which mines fine-grained message formats from network traces. The novelty of our approach is twofold: a 'positional keyword' identification technique and a two-level hierarchical clustering strategy. Positional keywords are based on the insight that keywords or reserved words usually occur at relatively fixed positions in the messages. By associating positions as meta-information with keywords, we can more accurately distinguish keywords from message payload data. After identification, the positional keywords are used as features to cluster the messages using density peaks clustering. We then perform another level of clustering to refine the clusters with low homogeneity. Finally, the message format of each cluster is extracted based on the observed ordering of keywords. P-token improves on the current state-of-the-art techniques by successfully addressing two challenges that commonly afflict existing keyword based format extraction methods: message keyword mis-identification and message format over-generalization. We have conducted experiments on services and applications using various protocols, including SOAP, LDAP, IMS and a RESTful service. Our experimental results show that P-token outperforms existing methods in extracting message formats. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Protocol message formats Positional keyword two-level clustering

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：