检索结果-内蒙古大学图书馆

14th International Conference on Graphics and Image Processing (ICGIP)

作者： Li, Zhuo Zhang, Jun Li, Biyuan Mei, Jianqiang Zhao, Xinchun Li, Binghui Tianjin Univ Technol & Educ Sch Elect Engn Tianjin 300222 Peoples R China

ISBN: (纸本)9781510666313;9781510666320

Optical Coherence Tomography (OCT) has become an important auxiliary diagnostic technology in the field of fundus disease detection due to its advantages of high resolution and high penetration depth. However, speckle noise exists in retinal images acquired by OCT. It is a difficult problem for OCT image processing technology to keep the middle layer structure information in the process of OCT image denoising. A novel OCT retinal image denoising method based on Gaussian mixture model and variational image decomposition is proposed. Firstly, the proposed BL-G-BM3D variational image decomposition model is used to initially denoise OCT images, and then the Gaussian mixture model is used to cluster the initial denoising results to obtain binary masks that can distinguish background and structure. Finally, the final denoising results are obtained by multiplying the mask image with the initial denoising results. An OCT retinal image with high noise and low contrast was tested and compared with five commonly used denoising methods. The results show that the proposed method can achieve both de-noising effect and laminar structure preservation for high-noise OCT retinal images.

关键词： Optical Coherence Tomography image denoising Gaussian Mixture Model Varitional Image Decomposition clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Remote monitoring system of new energy vehicles based on cluster analysis

引用

Procedia Computer Science 2025年 262卷 1410-1416页

作者： Li Wang College of Energy and Automotive Engineering Heilongjiang Polytechnic Harbin 150080 China

This paper takes the driving style of new energy vehicle drivers as the research object, and uses k-means algorithm to perform cluster analysis on the data set. Through the algorithm test results of 10 neural network programs, it can be seen that the correct rate of 10 runs is more than 90.5%, and the highest correct rate is 97.6%. The experimental results show that the correctness of the BP neural network model can be well verified by the clustering analysis algorithm. The algorithm can be applied to the driver’s driving style recognition of the new energy vehicle remote monitoring system and can be used as the main algorithm for the identification of the new energy vehicle remote monitoring system in the future.

关键词： clustering algorithm Remote monitoring Driving style

来源：评论

学校读者我要写书评

暂无评论

Residential Load Pattern clustering Based on Smart Meter Data Using Weighted Self-Organizing Map 33

Residential Load Pattern Clustering Based on Smart Meter Dat...

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Peng, Qing Chi, Ming Zhu, Mingxi Yu, Yunfan Wan, Diandian Liu, Zhi-Wei Huazhong Univ Sci & Technol Sch Articial Intelligence & Automat Wuhan 430074 Peoples R China State Grid Int Dev Co Ltd 15 West Changan St Beijing 100031 Peoples R China

ISBN: (纸本)9781665440899

With arrival of big data of smart meters, a large number of residential power consumption data are collected according to different sampling frequency, namely Residential Load Profiles (RLPs). In this paper, RLPs of smart meter customers are analyzed by clustering, which is of great significance to load management of smart grid. A two-stage Weighted Self-Organizing Map (WSOM) clustering algorithm and a clustering performance evaluation method, SSE-DBI, combining Sum of Squares Error (SSE) and Davies-Bouldin (DBI) are proposed. In first stage, Principal Component Analysis (PCA) is used to reduce the dimension of the RLPs. When dimension reduced data is fed into SOM network for clustering, update of weights of SOM is weighted according to PCA, and these clustering centers, namely Typical Residential Load Profiles (TRLPs) of each customer are obtained after some iterations of training. In second stage, above processing is repeated for TRLPs of each customer, TRLPs of all customer are obtained. According to SSE-DBI, final optimal cluster number and clustering performance score of the model are determined. Compared with several benchmark methods, the proposed method obtains optimal performance.

关键词： smart meters RLPs WSOM clustering algorithm SSE-DBI PCA TRLPs

来源：评论

学校读者我要写书评

暂无评论

A Decomposition Method of Electricity Quantity Based on Typical Load Curve Simulation

A Decomposition Method of Electricity Quantity Based on Typi...

引用

58th IEEE/IAS Industrial and Commercial Power Systems Technical Conference Asia (IEEE I and CPS Asia)

作者： Hong, HuaWei Zhu, LingLing Hong, Liang Wang, Zimou Fujian Power Supply Co State Grid Elect Power Co Ltd Fuan Fujian Peoples R China

ISBN: (数字)9781665450669

ISBN: (纸本)9781665450669

In the settlement process of electricity spot market, it is crucial to obtain the real-time power of users. This paper designs a method to obtain the typical load curve of the users without smart meters in the spot market and then proposes a power decomposition strategy to determine the Time-of-Use consuming quantity of these users. Firstly, users are classified according to their industry characteristics, this paper assumes that the same type users will have similar daily load curve. Then, the history load data of the users with smart meters is collected, and the typical load curve is determined by an improved clustering algorithm based on these history data. Lastly, the Time-of-Use consuming quantity of the users without smart meters can be determined according to the typical load curve. In addition, an improved load curve clustering algorithm based on FCM is proposed, the improved XB clustering validity index is introduced to judge the effect of the clustering results. The actual power load data of Fujian province are used for case study, results verify the correctness and feasibility of the proposed method.

关键词： electricity spot market typical load curve clustering algorithm clustering validity index

来源：评论

学校读者我要写书评

暂无评论

RT-GSOM: Rough tolerance growing self-organizing map

引用

INFORMATION SCIENCES 2021年 566卷 19-37页

作者： Pramanik, Anima Sarkar, Sobhan Maiti, J. Mitra, Pabitra Indian Inst Technol Kharagpur Dept Ind & Syst Engn Kharagpur 721302 W Bengal India Univ Edinburgh Business Sch 29 Buccleuch Pl Edinburgh EH8 9JS Midlothian Scotland Indian Inst Technol Kharagpur Ctr Excellence Safety Engn & Analyt CoE Sea Kharagpur 721302 W Bengal India Indian Inst Technol Kharagpur Dept Comp Sci & Engn Kharagpur 721302 W Bengal India

The concept of rough tolerance set is introduced within growing self-organizing map (GSOM) to reduce the uncertainty in decision-making by developing a new algorithm, namely rough tolerance GSOM (RT-GSOM). This algorithm aims to address the issues of (i) identifying the suitable size of clusters in SOM, (ii) information loss in rough SOM (RSOM), and (iii) uncertainty arising from the overlapping patterns of decision classes in GSOM. In RT-GSOM, the network is allowed to grow based on indiscernible reducts and tol-erance thresholds extracted from data in an unsupervised way. The network is initialized with the samples extracted from these reducts, and the weights are initialized with ran-dom category index. For each decision class, one set of indiscernible reducts is obtained. The tolerance threshold for each decision class is defined using the average distance among all the samples present in the reduct set corresponding to the same class. The superiority of RT-GSOM is demonstrated over twelve benchmark datasets (both categorical and continu-ous) obtained from UCI machine learning repository. Results reveal that RT-GSOM is effi-cient than some state-of-the-art algorithms in terms of learning rate, and quality of clusters for both categorical, and continuous data. (c) 2021 Elsevier Inc. All rights reserved.

关键词： clustering algorithm unsupervised learning indiscernible reducts rough tolerance information GSOM

来源：评论

学校读者我要写书评

暂无评论

An Improved Light-Weight Traffic Sign Recognition algorithm Based on YOLOv4-Tiny

引用

IEEE ACCESS 2021年 9卷 124963-124971页

作者： Wang, Lanmei Zhou, Kun Chu, Anliang Wang, Guibao Wang, Lizhe Xidian Univ Sch Phys & Optoelect Engn Xian 710071 Peoples R China Shaanxi Univ Technol Sch Phys & Telecommun Engn Hanzhong 723001 Peoples R China

Aiming at the problems of low detection accuracy and inaccurate positioning accuracy of light-weight network in traffic sign recognition task, an improved light-weight traffic sign recognition algorithm based on YOLOv4-Tiny was proposed. By improving the K-means clustering algorithm, the anchor with appropriate size is generated for the traffic sign data set to improve the detection recall rate and target positioning accuracy. The strategy of large-scale feature map optimization is proposed, which enriches the feature level of the network by using the low-level information, strengthens the representation of the feature information of the small target, and improves the detection accuracy of the long-range small target. In view of the problem of missed detection of high overlapping targets in the post-processing stage of the model, the paper proposes an improved NMS algorithm to screen the prediction box, avoid deleting the prediction results of different targets, and further improve the detection accuracy and recall rate of the target. Experimental results show that, compared with the original YOLOv4-Tiny algorithm, the improved algorithm in traffic sign recognition task based on TT100K dataset, mAP and recall are improved by 5.73% and 7.29% respectively, and FPS value is maintained at about 87 f/s, which meets the accuracy and real-time requirements of traffic sign recognition task.

关键词： Feature extraction clustering algorithms Prediction algorithms Object detection Task analysis Target recognition Spatial resolution Traffic sign recognition YOLOv4-Tiny clustering algorithm large scale improved NMS algorithm

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach to Estimating Queuing Delay on a Router over a Single-Hop Path

A Machine Learning Approach to Estimating Queuing Delay on a...

引用

IEEE International Conference on Communications (ICC)

作者： Ricker, Travis Salehin, Khondaker Wang, Yi Chen, Alex Oki, Eiji Rojas-Cessa, Roberto Calif State Univ Dominguez Hills Carson CA 90747 USA Kyoto Univ Kyoto Japan NJIT Newark NJ USA

ISBN: (数字)9781538683477

ISBN: (纸本)9781538683477

Queuing delay is a dynamic network parameter that plays an important role in defining the performance of Internet applications over an end-to-end path. However, measurement of queuing delay is challenging because it requires a large infrastructural support from the path under test. In this paper, we propose an active scheme to measure queuing delay on a router using a probe-gap model. The scheme uses a popular data-clustering algorithm to process its data samples;therefore, its measurement efficacy is not dependent on the issues related to infrastructural access, certain variations (e.g., compression) in the probe gaps, and the number of clusters in the data processing. Here, we present a detailed evaluation of the scheme against the current state-of-the-art on a single-hop path through ns-3 simulation. Our results show that the proposed scheme is robust, consistent, quick, and highly accurate under different traffic conditions.

关键词： Network measurement queuing delay clustering algorithm wired networks ns-3 simulator

来源：评论

学校读者我要写书评

暂无评论

Identifying Urban Functional Regions by LDA Topic Model with POI Data 1

引用

10th CCF Big Data Conference (BigData)

作者： Huang, Yuhao Zhang, Lijun Wang, Haijun Wang, Siqi Northwestern Polytech Univ Sch Comp Sci Xian Peoples R China Northwestern Polytech Univ Minist Ind & Informat Technol Key Lab Big Data Storage & Management Xian Peoples R China

ISBN: (数字)9789811983313

ISBN: (纸本)9789811983306;9789811983313

Identifying Urban Functional Regions (UFR) can achieve the rational aggregation of social resource space, realize urban economic and social functions, promote the deployment of urban infrastructure, radiate and drive the development of surrounding regions, so the identification of urban functional regions can promote the efficient development of cities. However, the traditional functional region identification method is mainly based on remote sensing mapping, which relies more on the natural geographical characteristics of the region to describe and identify the region, while the urban functional region is closely related to human activities, and the traditional functional region identification results are not ideal. Social data includes a series of data that reflect people's activities and behaviors, such as trajectory data, social media data, and travel data, thus the analysis of social data can more effectively solve the difficulties of traditional mapping and identification. POI (Point of Interest) data, as a typical type of social data, can be used to identify urban functional regions. We apply the LDA topic model to the POI data, and propose a new urban functional region identification method, which makes full use of the POI data to reflect the activity categories of urban populations to characterize the features of regional functions and achieve a high degree of identification of urban functional regions. Through experimental verification on real data, the experimental results show that the proposed method can more accurately identify urban functions, which proves the method reliable.

关键词： Urban functional regions identification POI LDA topic model clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Methods for Cognitive Diagnosis of Students' Abilities Based on Keystroke Features

引用

APPLIED SCIENCES-BASEL 2025年第9期15卷 4783-4783页

作者： Chi, Xu Guo, Xinyu Sheng, Yu Cent South Univ Sch Comp Sci & Engeering Changsha 410000 Peoples R China Univ Chinese Acad Sci Xinjiang Tech Inst Phys & Chem Urumqi 830011 Peoples R China

Keystroke data contain the behavioral information of students during the programming process. The clustering analysis of keystroke data can classify students based on specific characteristics in the programming process, thereby providing a basis for personalized teaching. Research combined with keystroke features is still in its initial stage. Due to the independence and discreteness of keystroke data, and the lack of a clear requirement for the selection of the number of clusters in traditional clustering algorithms, this selection is rather arbitrary, and outliers will affect the clustering effect. Aiming at the above problems, we improve the original method. Keystroke data were used to obtain students' programming behavior information and optimize the traditional clustering algorithm according to the characteristics of keystroke data. The K-means++ algorithm was adopted to determine the initial clustering centers, the elbow method was used to determine the number of clusters, and an outlier processing algorithm was introduced. We have independently constructed a keystroke dataset for computer-based programming examinations and used it to verify our method. Moreover, the improved algorithm has shown improvements in multiple evaluation indicators. Experiments have proven that the method proposed in this paper can more accurately classify students' proficiency levels in the evaluation of students' programming abilities in the educational field. This provides strong support for the formulation of teaching strategies and the allocation of resources, and the method possesses important application value and practical significance.

关键词： keystroke characteristics clustering algorithm cognitive diagnosis programming education

来源：评论

学校读者我要写书评

暂无评论

Ship Target Imaging in Airborne SAR System Based on Automatic Image Segmentation and ISAR Technique

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2021年 14卷 1985-2000页

作者： Cao, Rui Wang, Yong Zhao, Bin Lu, Xiaofei Harbin Inst Technol Res Inst Elect Engn Technol Harbin 150001 Peoples R China Jiuquan Satellite Launch Ctr Jiuquan 732750 Peoples R China

The airborne synthetic aperture radar (SAR) image of ship target will be blurred for the complex motion of the target, which will influence the performance of feature extraction and target classification. In this article, a refocusing method of ship target in airborne SAR image though the inverse synthetic aperture radar (ISAR) technique is presented. The novel contributions of this article can be summarized as follows: 1) the residual phase of processed signal is analyzed in detail to illustrate the necessity of adopting ISAR technique;2) a valid, labor-saving, and automatic image segmentation approach via clustering algorithm is put forward for automatic data extraction and inverse mapping. The clustering algorithm we choose is the agglomerative hierarchical cluster algorithm, which does not require the number of categories in advance;3) the refocused individual ISAR image of individual ship target is yielded though the range-instantaneous Doppler algorithm. Finally, the simulated and real measured data are processed, and imaging results verify the effectiveness of the novel algorithm presented in this article.

关键词： Automatic image segmentation clustering algorithm hierarchical cluster algorithm (HCA) inverse synthetic aperture radar (ISAR) refocusing ship target synthetic aperture radar (SAR)

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：