检索结果-内蒙古大学图书馆

POLSAR Image Classification via clustering-WAE Classification Model

IEEE ACCESS 2018年 6卷 40041-40049页

作者： Xie, Wen Xie, Ziwei Zhao, Feng Ren, Bo Xian Univ Posts & Telecommun Minist Publ Secur Key Lab Elect Informat Proc Applicat Scene Invest Xian 710121 Shaanxi Peoples R China Xian Univ Technol Sch Automat & Informat Engn Xian 710048 Shaanxi Peoples R China Xidian Univ Sch Artificial Intelligence Xian 710126 Shaanxi Peoples R China

Considering the clustering algorithms could explore the label information automatically, this paper proposes a new method in terms of polarimetric synthetic aperture radar (POLSAR) image classification, which named a clustering-wishart-auto-encoder (WAE) classification model. With considering the statistical distribution characteristic of the POLSAR image, the WAE classification model, which proposed by ourselves, could improve the classification performance of the POLSAR image to some extent. The clustering-WAE classification model, that embedded the k-means clustering algorithm into the objective function of the WAE model, has the ability to improve the network performance. Our proposed method could minimize the difference of intra-class data and maximize the difference of inter-class data, from which the obtained POLSAR image features will be more compact to their corresponding cluster centers. Via simultaneously considering the compactness and statistical distribution of data, our method is capable of improving the POLSAR image classification results. The effectiveness of our proposed classification model has been demonstrated on four real POLSAR data sets.

关键词： POLSAR image classification k-means clustering algorithm AE network WAE classification model clustering-WAE classification mode

来源：评论

学校读者我要写书评

暂无评论

Development of Digital Evidence Collector and File Classification System with k-means algorithm 5

Development of Digital Evidence Collector and File Classific...

引用

IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)

作者： Ruriawan, Muhammad Faris Anggono, Bintaran Siahaan, Isaac Anugerah Purwanto, Yudha Telkom Univ Sch Elect Engn Bandung Indonesia

ISBN: (纸本)9781728148656

Digital forensic is a branch of forensic science that focuses on research on the usual storage media that electronic users use such as hard disks, flash drives or other devices used on computers. The output is called digital evidence. The purpose of doing digital forensics is to find an evidence that can be used in the investigation of a case, until the evidence becomes valid and could be used as evidence in court. In this research, we implement a system of digital evidence collection, recovery, and file classification application. The classification was done by k-means clustering algorithm. The system could detect the storage media, duplicate the content, and classify the output using k-means algorithm. It can help a forensic examiner in the collection, examination, analysis, and reporting phase in accordance with NIST SP 800-86. The application also can assist investigators in managing files in the storage media as digital evidence so that outputs are obtained in accordance with applicable law.

关键词： digital forensic digital evidence k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Short-Term Load Forecasting for Campus Building with Small-Scale Loads by Types Using Artificial Neural Network

Short-Term Load Forecasting for Campus Building with Small-S...

引用

IEEE-Power-and-Energy-Society Innovative Smart Grid Technologies Conference (ISGT)

作者： Baek, Sung-Jun Yoon, Sung-Guk Soongsil Univ Dept Elect Engn Seoul South Korea

ISBN: (纸本)9781538682326

Nowadays, the large portion of total energy is consumed by buildings, so it is essential to use the energy efficiency in buildings. With the deployment of a smart meter in the building, a small-scale load data are now available such as lighting, general and the other loads. We first analyze the small-scale loads through the fixed k-means clustering algorithm. Based on the analysis of load characteristics, we propose five artificial neural network-based forecasting models for campus buildings. The five models use total load, temperature and small-scale loads as input data with different input combinations. The case studies show that using small-scale loads improves the forecasting performance.

关键词： artificial neural network campus building small-scale load smart meter k-means clustering algorithm short-term load forecasting

来源：评论

学校读者我要写书评

暂无评论

MULTIMODAL OPTIMIZATION OF JOB-SHOP SCHEDULING PROBLEMS USING A clustering-GENETIC algorithm BASED APPROACH

引用

INTERNATIONAL JOURNAL OF INDUSTRIAL ENGINEERING-THEORY APPLICATIONS AND PRACTICE 2019年第5期26卷 651-662页

作者： Zou, Pan Rajora, Manik Liang, Steven Y. Georgia Inst Technol George W Woodruff Sch Mech Engn Atlanta GA 30332 USA Donghua Univ Coll Mech Engn Shanghai Peoples R China

Though ample work has been performed on the optimization of job-shop scheduling problems (JSSPs), very few techniques can satisfy the requirement of modern-day workshops, i.e., providing multiple schedules that achieve the desired goal. These techniques also do not provide a good balance between converging to the optimal solution while finding multiple optimal solutions. To overcome this obstacle, a new algorithm is proposed by combining the k-means clustering algorithm and genetic algorithm (GA) for multimodal optimization of JSSPs. In the proposed algorithm, the k-means clustering algorithm is first utilized to cluster the individuals of every generation into different clusters based on some machine sequence-related features under the assumption that different global optima will have different features. Next, the adapted genetic operators are applied to the individuals belonging within the same cluster with the aim of independently searching for global optima within each cluster. The performance of the proposed algorithm is measured by its application to the multimodal optimization of benchmark JSSPs and comparing its performance against other multimodal optimization algorithms. The results of the case studies show that the algorithm has a better average optimal value and is also capable of finding multiple optimal solutions.

关键词： multimodal optimization job-shop scheduling problem (JSSP) k-means clustering algorithm genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A DD-means clustering algorithm for Intrusion Behavior Analysis

引用

电脑学刊 2019年第3期30卷 224-230页

作者： Yongxin Feng Yingyun kang Yuntao Zhao Wenbo Zhang

With the rapid development of Internet technology, network security is becoming more and more severe. Data transferred on the Internet can be divided into two categories, normal data and intrusion data. clustering is a popular data analysis technology to classify data according to the characteristics of the data and clustering can also be used for intrusion behavior analysis on the Internet. k-means is a simple and an efficient data clustering algorithm, but it has a tendency to converge to local optima and the optimization results depend on the initial values of cluster centers. Therefore, DD-means clustering algorithm, which selects the initial center points based on the density and the maximum distance of different data points, has been proposed to improve the performance of classical k-means. The performance of DD-means clustering algorithm is significantly better than that of classical k-means clustering algorithm in silhouette coefficient. The experimental results show that the proposed algorithm is effective and efficient for analyzing the intrusion behavior on the Internet.

关键词： classification DD-means k-means clustering algorithm network security

来源：评论

学校读者我要写书评

暂无评论

Improved Tabu Search algorithm for Solving the Vehicle Routing Problem with Soft Time Windows in B2C Environment

Improved Tabu Search Algorithm for Solving the Vehicle Routi...

引用

第32届中国控制与决策会议

作者： Lin Li Ying Chen Jiao Meng College of Science Shenyang Aerospace University

With the development of E-commerce,the B2 C E-commerce develop *** put forward higher requirements for delivery speed and *** paper studied the vehicle routing problem with soft time windows in B2 C *** improved the tabu search(TS) algorithm,and used k-means clustering algorithm to determine the initial solution to improve the algorithm's convergence *** algorithm was tested by using the data in literature[7].The computing results were compared with those results in the literature [7] to verify the effectiveness of the algorithm.

关键词： B2C E-commerce Soft time window k-means clustering algorithm Tabu search

来源：评论

学校读者我要写书评

暂无评论

A k-means clustering Based Message Forwarding Model for Internet of Things (IoT) 8

A K-Means Clustering Based Message Forwarding Model for Inte...

引用

8th IEEE International Conference on Cloud Computing, Data Science and Engineering (Confluence) / Global Technology, Innovation and Enterpreneurship Summit

作者： kumar, Sumit Raza, Zahid Jawaharlal Nehru Univ Sch Comp & Syst Sci Newdelhi India

ISBN: (纸本)9781538617199

Internet of Things (IoT) is establishing to be the next stage of Internet resulting in a relation between internet connection data generating smart objects. IoT is understood as a seamless interconnection of sensor objects with the computational world. clustering these objects is very helpful for data analytics generating a combination of structure of similar types of object characteristics. clustering, therefore, is very useful in IoT for improving the Quality of Service (QoS) and organizing the resources. In this work, a k-means clustering based resource allocation model for IoT has been discussed. The performance has been evaluated primarily for the response time realized for transmission of a message from the source to the destination. Simulation study reveals the effectiveness of the model.

关键词： Internet of Things (IoT) clustering k-means clustering algorithm Response time

来源：评论

学校读者我要写书评

暂无评论

Detection of Traffic Abnormity Based on clustering Analysis of Taxi GPS Data

Detection of Traffic Abnormity Based on Clustering Analysis ...

引用

作者： Haoze Wang Yutong Si Beijing Jiaotong University Beijing University of Posts and Telecommunications

The paper proposes a method to detect the traffic abnormity based on clustering analysis of taxi GPS data. The traffic data used in this paper is obtained from traffic management bureau of *** data is cleaned based on several cleaning standards to eliminate error and noise data. Map-matching algorithm is used to match the trace points to the specific roads according to OSM map data. Non-Negative Matrix Factorization(NMF) is applied to extract the traffic patterns. In order to build abnormity detection model. k-means Cluster algorithm is applied to find the neighbor roads based on both physical distance and traffic pattern similarity.A scoring function is designed to provide the probability for the specific road to be abnormal. The result of this method is quite accurate as it provides the detection results by means of horizontal and vertical comparisons. Some comparisons with other existing methods will also be discussed at the end of paper.

关键词： GPS data map matching k-means clustering algorithm NMF non-negative matrix factorization scoring function traffic abnormity traffic analysis

来源：评论

学校读者我要写书评

暂无评论

Automated skin lesion segmentation of dermoscopic images using GrabCut and k-means algorithms

引用

IET COMPUTER VISION 2018年第8期12卷 1088-1095页

作者： Jaisakthi, Seetharani Murugaiyan Mirunalini, Palaniappan Aravindan, Chandrabose Vellore Inst Technol Sch Comp Sci & Engn Vellore Tamil Nadu India SSN Coll Engn Dept Comp Sci & Engn Chennai Tamil Nadu India

Skin cancer is the most common type of cancer in the world and the incidents of skin cancer have been rising over the past decade. Even with a dermoscopic imaging system, which magnifies the lesion region, detecting and classifying skin lesions by visual examination is laborious due to the complex structures of the lesions. This necessitates the need for an automated skin lesion diagnosis system to enhance the diagnostic capability of dermatologists. In this study, the authors propose an automatic skin lesion segmentation method which can be used as a preliminary step for lesion classification. The proposed method comprises two major steps, namely preprocessing and segmentation. In the preprocessing step, noise such as illumination, hair and rulers are removed using filtering techniques and in the segmentation phase, skin lesions are segmented using the GrabCut segmentation algorithm. The k-means clustering algorithm is then used along with the colour features learnt from the training images to improve the boundaries of the segments. To evaluate the authors' proposed method, they have used ISIC 2017 challenge dataset and dataset, respectively.

关键词： biomedical optical imaging image segmentation image classification image filtering object detection skin cancer medical image processing pattern clustering graph theory image colour analysis automatic skin lesion segmentation method dermoscopic images GrabCut segmentation algorithm k-means clustering algorithm skin cancer dermoscopic imaging system lesion region skin lesion detection skin lesion classification visual examination automated skin lesion diagnosis system diagnostic capability enhancement preprocessing step segmentation step filtering techniques colour features ISIC 2017 challenge dataset PH2 dataset

来源：评论

学校读者我要写书评

暂无评论

Improved clustering algorithm of Neighboring Reference Points Based on kNN for Indoor Localization 5

Improved Clustering Algorithm of Neighboring Reference Point...

引用

5th IEEE Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS)

作者： Xue, Weixing Hua, Xianghong Li, Qingquan Qiu, Weining Peng, Xuesheng Wuhan Univ Sch Geodesy & Geomat Wuhan 430079 Hubei Peoples R China Shenzhen Univ Dept Shenzhen Key Lab Spatial Smart Sensing & Ser Shenzhen 518060 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Hubei Peoples R China

ISBN: (纸本)9781538637555

Reference points (RP) clustering methods such as k-means are frequently used to reduce the region of search in most of fingerprint clustering algorithms. However, traditional clustering algorithms analysis the geometric proximity of RP only in the offline phase, which has nothing to do with the test point. Meanwhile, both the clustering pattern and the number of clusters need to be predefined directly or indirectly, which means an unsuitable clustering pattern or an unsuitable number of clusters would lead to poor estimation accuracy. In this letter, in order to improve the performance of kNN algorithm with the neighboring RP selection, we utilize the k-means clustering algorithm to analysis the geometric proximity between RP and test point in the online phase. In the proposed algorithm, k-means clustering algorithm groups M (M<k) nearest neighboring RPs according to their real physical distances to the test point instead of their signal distances. Then these M nearest neighboring RPs are used to estimate the location of the test point. Experiments were conducted in the fourteenth floor within an office building and the results demonstrate that the proposed method considerably outperforms the kNN algorithms in terms of positioning accuracy.

关键词： reference points clustering method geometric proximity physical real distance k-means clustering algorithm indoor location

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：