检索结果-内蒙古大学图书馆

3rd International Symposium on Image Computing and Digital Medicine (ISICDM)

作者： Zheng, Yongguo Liu, Kaijia Chen, Ming Li, Jianwei Zha, Guozhen Shandong Univ Sci & Technol Sch Comp Sci & Engn 579 Qianwangang Rd Huangdao Dist Peoples R China Shandong Univ Sci & Technol Coll Math & Syst Sci 579 Qianwangang Rd Huangdao Dist Peoples R China Jiangsu Ocean Univ 59 Cangwu Rd Lianyungang Jiangsu Peoples R China

ISBN: (纸本)9781450372626

In CT image-guided interventional surgery, the rapid and accurate location of an ablation needle plays a key role in clinical diagnosis and treatment, especially for the design of surgical navigation system. However, there is no universal and effective method for detection of line segment, especially for precise extraction of the features. Aiming at the ablation needle and its tip in CT images, we propose the detection and location method based on an improved Hough transform, where features are extracted using some prior information and the clustering algorithm. The proposed method effectively removes noise and improves the real-time and accuracy of calculation. The numerical simulation results show that some morphological information can be accurately extracted and located, such as the coordinates of the endpoints and the length of the needle.

关键词： CT image ablation needle line segment detection hough transform clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

clustering algorithms application to forming a representative sample in the training of a multilayer perceptron

引用

St. Petersburg Polytechnical University Journal: Physics and Mathematics 2017年第2期3卷 127-134页

作者： Aleksey A. Pastukhov Aleksander A. Prokofiev National Research University of Electronic Technology 5 Pass. 4806 Zelenograd Moscow 124498 Russian Federation

In this paper, we have considered the problem of effectively forming the representative sample for training a neural network of the multilayer perceptron (MLP) type. An approach based on the use of clustering that allowed to increase the entropy of the training set was put forward. Various clustering algorithms were examined in order to form the representative sample. The algorithm-based clustering of factor spaces of various dimensions was carried out, and a representative sample was formed. To verify our approach we synthesized the MLP neural network and trained it. The training technique was performed with the sets formed both with and without clustering. A comparative analysis of the effectiveness of clustering algorithms was carried out in relation to the problem of representative sample formation.

关键词： Neural network clustering algorithm Representative sample Multilayer perceptron

来源：评论

学校读者我要写书评

暂无评论

Comparative study of clustering algorithms for MANETs

引用

JOURNAL OF STATISTICS & MANAGEMENT SYSTEMS 2019年第4期22卷 653-664页

作者： Pathak, Sunil Jain, Sonal JK Lakshmipat Univ Dept Comp Sci & Engn Jaipur 302026 Rajasthan India

clustering algorithm in Mobile Ad Hoc Networks is considered as the suitable technique of routing. Endurance of clusterhead in a cluster for data sending improves the working in terms of established cluster composition, concentrated routing overhead and some degree of power utilization. On the other hand, due to the movement of clusterhead, common changes in clusterhead increases clustering overhead in terms of re-election of clusterhead within the current cluster. The constancy of the cluster extremely dependents on constancy of the clusterhead and hence extraordinary care should be taken during clusterhead selection and maintenance phase so that an efficient stable clusterhead is elected for longer time. In this manuscript we have carried out performance analysis of Novel Weight Based clustering algorithm (WBC), An Optimized Stable clustering algorithm (OSCA) and PBWCA (Priority Based Weighted clustering algorithm) clustering algorithms first and foremost paying attention on reducing frequent clusterhead changing procedure. These algorithms help in reducing the frequent clusterhead changes, communication overhead and increase of broadcast in the network. The algorithm works on node degree and battery power of mobile nodes to calculate node priority. PB-WCA also focuses on reducing the cluster reformation, clusterhead re-selection and clusterhead changes.

关键词： clustering algorithm Clusterhead Cluster Member clustering Overhead WBC OSCA PB-WCA LIC LCC CBRP

来源：评论

学校读者我要写书评

暂无评论

Evaluation of clustering algorithms for DAP Placement in Wireless Smart Meter Network 9th

Evaluation of Clustering Algorithms for DAP Placement in Wir...

引用

9th International Conference on Modelling, Identification and Control (ICMIC)

作者： Hassan, Asif Zhao, Yanxiao Pu, Lina Wang, Guodong Sun, Hui Winter, Robb M. South Dakota Sch Mines & Technol Rapid City SD 57701 USA Civil Aviat Univ China Informat Engn & Automat Tianjin Peoples R China

ISBN: (纸本)9781509065738

Wireless smart meter network has attracted extensive research interests for its capability on intelligent control and monitor the power consumption in residential as well as commercial area. Wireless smart meter network constitutes with a number of smart meters to sense the electricity or gas consumption, data aggregation point (DAP) to collect data from smart meters, and utility center to gather all data from DAPs. In this work, we investigate the clustering and optimal DAP placement problem in the multi-hop smart meter network. Three representative clustering algorithms, namely k-means, self-organizing map, and fuzzy c-means, are evaluated and compared in terms of multi-hop shortest path distance (MSPD), size of clusters and computation complexity. Simulation results indicate that the hard assignment based methods, k-means and self-organizing, achieve similar performance whereas the soft assignment based fuzzy c-means falls behind with longer maximum MSPD and higher complexity.

关键词： Wireless smart meter network data aggregation point placement clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Feature Enhanced Speckle Reduction In Ultrasound Images: algorithms For Scan Modelling, Speckle Filtering, Texture Analysis And Feature Improvement

Feature Enhanced Speckle Reduction In Ultrasound Images: Alg...

引用

作者： Prerna Singh University of Canterbury

学位级别：博士

This thesis aims to contribute to the advancement of research in the field of ultrasound image analysis by developing several novel algorithms in three key areas: (i) modelling, analysis and validation of synthetic ultrasound images, (ii) characterization and reduction of speckle artifacts, and (iii) enhancement of image features. These three areas have been identified based on existing gaps in research and their importance in advanced ultrasound image analysis frameworks for segmentation and classification. Synthetic models of ultrasound image formation that can generate noise-free ground truth data with intensity and texture characteristics of real ultrasound images, are valuable for machine learning applications and performance evaluation of speckle reduction techniques. This thesis develops a complete framework for synthetic ultrasound image generation incorporating algorithms for image acquisition, sampling and speckle simulation. The framework allows us to simulate image acquisition in both sector and linear scans with varying axial and lateral resolutions. Speckle artifacts appear in the form of granular noise in ultrasound images, degrading their diagnostic quality. This thesis presents novel algorithms for speckle reduction while preserving edges, fine details, and contrast of the image. The first despeckling framework presented in the thesis uses a novel application of clustering algorithms based on a transformation to wavelet sub-bands, and is inspired by the success of such methods for synthetic aperture radar imagery. The second despeckling framework uses a modified adaptive Wiener filter along with the Canny edge detection and an enhanced steerable pyramid transformation algorithm. Additionally, a coherence component extraction method is used to enhance the overall texture and edge features even in the darker portions of the image. The filtering operations used in a majority of speckle reduction methods induce blurring that affects edges and other fine

关键词： Medical ultrasound scans Synthetic ultrasound image modelling Speckle simulation Interpolation Feature extraction and selection Gray level co-occurrence matrix Local binary patterns Image quality measures Speckle filtering clustering algorithm Steerable pyramid transform Contrast limited adaptive histogram equalization

来源：评论

学校读者我要写书评

暂无评论

Animation Recommendation System Based on Hybrid Mode

Animation Recommendation System Based on Hybrid Mode

引用

作者：沈正浩华中师范大学

学位级别：硕士

近年来,随着互联网的发展以及各种联网电子设备的普及,使得交流越来越方便与快捷,使得人们每天都在各种行业和领域产生着大量的数据,而这些数据也被保存了下来。而如何从这些大量的数据中挖掘出有用的内容,也正是一个需要关注的问题。... 详细信息

近年来,随着互联网的发展以及各种联网电子设备的普及,使得交流越来越方便与快捷,使得人们每天都在各种行业和领域产生着大量的数据,而这些数据也被保存了下来。而如何从这些大量的数据中挖掘出有用的内容,也正是一个需要关注的问题。然而这种快速增加的数据量带来了信息过载的问题,因此在很大程度上影响了人们对目的信息的获取,因此对这些信息进行过滤以及分类则有助于更加快速,有效的挑选出合适的信息。当用户输入句子以及关键词后,搜索引擎将会进行分词和过滤,提取出其中的有用信息,在后台进行信息的相关匹配,最后快速的将比较相关的结果返回给用户,使得用户能获取到限定范围内的信息。但这也是有一定缺陷的,因为这时候搜索是一种被动的行为,只有当用户提供十分具体的需求,如提供具体的品牌甚至于型号时,搜索系统才能给出令人满意的结果。而当用户对于关键词的描述是一个较大的范围甚至是十分模糊不清时。此时搜索引擎将无法给出一个十分令人满意的答案。例如,当用户想去商场购买某种类型的商品时,通过搜索引擎只能获得十分宽泛的答案,很难进一步了解到什么相关商品的品牌以及品质。而推荐系统则适用于这种场景,推荐系统是另外一种获取信息的方式。当用户所输入的需求是莫名不清时,抑或是用户本身不清楚哪些内容是最合适时,它能根据用户的以往数据进行分析以及自发推荐给用户相关的内容。这项技术已经广泛运用于生活的方方面面例如。例如现在的网购网站(如:淘宝,亚马逊等)虽然存在着许多同名的商品,但是依然能给用户提供正确的指引与介绍,以为推荐会自动根据销量,评分等银色给用户更优先的提供了某些广受好评的物品,从而让用户减少了搜索时间,提高了购买的效率,同时也进一步的提高了网站的收益。因此推荐系统的出现以及发展是十分必要以及富有前景的。本文针对的是动漫行业的推荐。据资料显示,中国的动漫用户规模以及动漫产业产值正在逐年增高,因此在动漫产业研究推荐系统是十分具有研究前景和研究价值的。但由于动漫普遍性不及电影,因此现有的有关动漫的推荐研究远远比电影推荐的要少。一般看来,电影和动漫推荐是类似的,因此可以采用相同的系统推荐,但他们本身是有区别的,完全采用电影的推荐系统可能存在一定问题。具体区别有以下几个方面:1.从他们的定义来说电影侧重于写实和记录,动漫侧重于假定虚幻的客观世界,不可否认现在的3G技术使得电影逐渐出现,使得电影的虚幻效果逐渐提高,逐渐也出现了虚幻的元素。即便存在着相互交融的过程,他们的根源却不是完全相同的。2.受众群体不同,电影的受众面比较广,适合于各个年龄阶段啊的人群,但是动漫一般侧重于儿童少年的群体,因此数据的来源可能较电影来说相对窄的多,而相对较少或者片面的的数据可能无法获得比较好的效果)3.由于国内的版权问题,因此国内的动漫网站无法对用户推荐最全最完整的动漫列表,而且不同的网站同时也会给出不同的动漫推荐排行榜,因此推荐的结果不具有统一性。并且由于国内的动漫行业较国外起步较晚,因此国内用户无法及时获取和跟进最新的动漫发展趋势。因此针对动漫行业的推荐系统的研究是有必要的。推荐算法作为推荐系统的一个重要组成部分,一般来说,有基于内存的协同过滤,又叫做基于领域的协同过滤,它是通过相似统计的方法来的到基友相似兴趣爱好的邻居用户。而现如今更多常见的是基于模型的协同过滤,它是先用历史数据训练得到一个模型,再通过该模型来对用户的输入进行结果的预测,其中有基于关联算法,聚类算法,回归算法等做协同过滤的研究。而单一的聚类或者是单一的关联规则进行数据的挖掘存在或多或少的问题:1.从聚类的角度来说:(1)聚类结果容易受到噪声的影响,当存在于大部分数据对象距离较远,单独的数据时,会影响簇中心的位置,从而造成中心偏移,导致聚类结果不好(2)聚类的簇选择存在问题,选择太少会导致特性的重叠,簇太多可能会导致具有相同特性的簇分散因此单独采用聚类结果解释所有挖掘数据的结果,有些困难2.从关联规则的角度来说:(1)花费时间较多,在每一阶段,都要重新读取数据库,因此数据量大时花费太多时间(2)阈值的设定问题,设定太高会导致产生的规则较少,使得无法完整表示全部数据,设定太低时导致门槛太低,使得产生的规则太多,使得可信度降低)在现行的Web站点上的推荐往往都不是单纯只采用了某一种推荐的机制和策略,他们往往是将多个方法混合在一起,综合运用各种方法的优势,组合起来成为一个效果强大的系统。关于如何组合各个推荐机制,其中现阶段比较流行的组合方法:1.加权的混合:用线性公式(linear formula)将几种不同的推荐通过分配不同的权重进行合成,但是具体的权重设置需要在实验中完善,从而达到最好的推荐效果。2.切换的混合(Switching Hybridization):对不同的情况(数据量以及运行方式等不同),会选择不同的推荐策略,也就是允许在不同

关键词： Recommendation system Hybrid Prediction Model Collaborative Filtering Algo-rithm clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved Particle Swarm Optimization algorithm of clustering in Underwater Acoustic Sensor Networks

Improved Particle Swarm Optimization Algorithm of Clustering...

引用

Oceans Aberdeen Conference

作者： Li, Pengwei Wang, Shilian Zhang, Hao Zhang, Eryang Natl Univ Def Technol Sch Elect Sci & Engn Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781509052783

Aiming at improving the poor stability and unsatisfactory clustering results of the existing underwater acoustic sensor networks (UASNs) clustering algorithms, this paper proposes a new clustering model. In the model the required transmission power of sensor nodes, as well as the cluster head residual energy and the cluster head loads are among consideration. With the clustering model, we design a novel clustering algorithm based on the discrete particle swarm optimization algorithm (PSO). We use the proposed clustering algorithm to cluster UASNs periodically with the cluster head being rotated dynamically. Simulation results demonstrate the reduction in network energy consumption and the prolonged network lifetime. Moreover it achieves higher stability.

关键词： UASNs clustering model clustering algorithm PSO network lifetime network energy consumption

来源：评论

学校读者我要写书评

暂无评论

NETWORK INTRUSION DETECTION USING clustering AND GRADIENT BOOSTING 9

NETWORK INTRUSION DETECTION USING CLUSTERING AND GRADIENT BO...

引用

9th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

作者： Verma, Parag Anwar, Shayan Khan, Shadab Mane, Sunil B. Coll Engn Dept Comp Engn & IT Pune Maharashtra India

ISBN: (纸本)9781538644300

An unauthorized activity on the network is called network intrusion and device or software application which monitors the network parameters in order to detect such an intrusion is called network intrusion detection system (NIDS). With high rise in malicious activities on the internet, it is extremely important for NIDS to quickly and correctly identify any kind of malicious activity on the network. Moreover, the system must refrain from raising false alarms in case of normal usage detected as malicious. This paper proposes use of machine learning classification algorithms - XGBoost and AdaBoost with and without clustering to train a model for NIDS. The models are trained and tested using NSL KDD dataset and the results are an improvement over the previous works related to intrusion detection on the same dataset.

关键词： Intrusion detection XGBoost AdaBoost Machine learning decision trees classification algorithm clustering algorithm gradient boosting

来源：评论

学校读者我要写书评

暂无评论

Research on Auto-Generating Test-Paper Model Based on Spatial-Temporal clustering Analysis 14th

Research on Auto-Generating Test-Paper Model Based on Spatia...

引用

14th International Conference on Intelligent Computing (ICIC)

作者： Fan, Yuling Dong, Likai Sun, Xuesong Wang, Dong Qin, Wang Cao Aizeng Univ Jinan Sch Informat Sci & Engn Jinan 250022 Shandong Peoples R China Univ Jinan Shandong Prov Key Lab Network Based Intelligent C Jinan 250022 Shandong Peoples R China

ISBN: (纸本)9783319959320;9783319959337

In the process of auto-generating test-paper, the category and the difficulty of the title plays a key role in the quality of generating test-paper. It will produce low quality questions and hard to popularize when used the methods of artificial generating test-paper and random generating test-paper, because considering less on the knowledge point classification and difficulty in the subject. To improve the quality of auto-generating test-paper, this paper takes the evaluation data of ACM Online Judge system as the research object. After normalization, (1) we can get three different results by the K-means clustering analysis based on the temporal and spatial characteristics of time variance and average time;(2) On the basis of clustering, the difficulty index of each topic of all the categories is calculated by using the number of submissions and the number of submissions to solve the problem. The ratio of the two is proportional to the difficulty of the problem. In this paper, the ratio of the two to determine the degree of difficulty index;(3) The Gaussian stochastic process is used to extract numbers of questions of each knowledge point, and calculated the difficulty index which were extracted to make sure they are within range to complete the auto-generating test-paper. In the experiment, we try to train and test the automatic test paper model by the number of professional problems (about 50000 data) in the C language test question of the university OJ system. The average difficulty index of the test paper was 0.4663, which meet the requirements, and the difficulty index of the title fit in with the normal distribution. Compared with the traditional generating test-paper method, the automatic test paper model is based on the difficulty and discrimination of the subject, and it can evaluate the level of tester scientifically. The experimental results show that the proposed automatic test model is simple and effective.

关键词： Spatial-temporal feature clustering algorithm Difficult coefficient Auto-generating test paper

来源：评论

学校读者我要写书评

暂无评论

A Parallel Approach on clustering Traffic Data Stream based on the Density 6

A Parallel Approach on Clustering Traffic Data Stream based ...

引用

6th International Conference on Advanced Cloud and BigData (CBD)

作者： Lu, Jiamin Feng, Jun Zhang, Jin Xia, Peipei Xiao, Xianjian Hohai Univ Coll Comp & Informat Nanjing Peoples R China Changzhou Inst Technol Changzhou Jiangsu Peoples R China

ISBN: (纸本)9781538680346

Various portable and smart IoT devices are making our life much easier than before. A lot of them provides the positioning function, hence the streams of location information can be uploaded with permissions and be aggregated on the fly, in order to find or predict the areas where high-denstiy actions might happen in the real time. Along with the rapid development of the communication capabilities, such position data comes in a more intensive way, causing a big burden on the processing servers. In order to improve the clustering efficiency, with the help of the modern parallel computation framework, this paper intends to propose a novel parallel approach for the traffic data stream based on moving objects' density, called P-DenStream. The performance study with synthetic and real-world data sets demonstrate that our approach is well suited to high-volume and high-speed traffic stream, producing precise clusters with a minimal delay.

关键词： traffic data stream clustering algorithm parallel processing

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：