检索结果-内蒙古大学图书馆

An improved method for coherent structure identification based on mutual K-nearest neighbors

JOURNAL OF TURBULENCE 2022年第11-12期23卷 655-673页

作者： Wei, Zeming Zhang, Jiazhong Jia, Ruidong Gao, Jingsheng China Aerodynam Res & Dev Ctr State Key Lab Aerodynam Mianyang Peoples R China Xi An Jiao Tong Univ Sch Energy & Power Engn Xian Peoples R China Tokushima Univ Adv Technol & Sci Tokushima Japan Xi An Jiao Tong Univ Sch Energy & Power Engn Xian 710049 Peoples R China

The clustering algorithm based on mutual K-nearest neighbors (MKNN) is presented to identify coherent structures in complicated fluid flows, in order to analyze the mass mixing and transport. First, both trajectory similarity and spatial proximity are used to describe and measure the coherence between particles. These two identification criteria are frame-invariant since they are derived from the relative distances of particles. Then, the concept of mutual K-nearest neighbors is introduced further, and particles with the same cluster label are identified as coherent structures after the initialization and merging process of clusters, while incoherent regions consist of incoherent particles, which cannot form a mutual K-nearest neighbors relationship with other particles. Finally, the MKNN-based clustering algorithm is applied to three examples, realizing the identification and tracking of coherent structures. The identification results show that the MKNN-based clustering algorithm is robust to parameter K, and a higher threshold lambda of cluster quantity will be helpful to identify the finer structures in flows. Moreover, spatial proximity performs better in vortex identification, and trajectory similarity is more suitable for elongated structures (jets) identification. Importantly, the method presented analyzes the evolutions of vortices in detail, including the generation, stretching, and merging processes. In summary, the MKNN-based clustering algorithm takes particle trajectories as input data, analyzes the evolution of relative distances between particles quantitatively, and carries out clustering analysis on particles according to trajectory similarity and spatial proximity. The combination of the MKNN-based clustering algorithm and frame-invariant identification criteria shows great potential in coherent structure identification of complicated fluid flows.

关键词： Mutual K-nearest neighbors clustering algorithm coherent structure vortex identification

来源：评论

学校读者我要写书评

暂无评论

Automatic Sorting System for Citrus with Fast Visual Recognition and Improved Multi-Criteria clustering

Automatic Sorting System for Citrus with Fast Visual Recogni...

引用

2025 International Conference on Electrical Automation and Artificial Intelligence, ICEAAI 2025

作者： Jiang, Jianuo Liu, Fei Peng, Jiyu Zhu, Fengle School of Science and Engineering The Chinese University of HongKong Shenzhen Shenzhen China School of Biosystems Engineering and Food Science Zhejiang University Hangzhou China College of Mechanical Engineering Zhejiang University of Technology Hangzhou China

ISBN: (纸本)9798331506797

This paper presents a fully automated fruit grading system designed for Chinese fruit farmers, utilizing industrial vision and clustering algorithm for rapid and precise sorting. This system consists of an image processing subsystem for dual vision detection of fruit appearance, a clustering subsystem optimized with an improved K-Means clustering algorithm, and a mechanical subsystem scheme of a two-degree-of-freedom linear module and a three-coordinate manipulator. This mechanical system efficiently handles loading, packing, and unloading small patches of fruits in multi-stations. The sorting process was based on visual detection and qualification of fruit shape, peel appearance, and weight, during which a fruit-shape-rating algorithm using Sobel edge detection was developed to precisely identify fruit contours and diameters. In the clustering grading process, a multi-level evaluation model, adhering to the NY/T-1190 standard, was established to assess fruit weight, shape, peel color, and defects. To optimize one-time boxing efficiency and overall profit of small-batch fruits, the enhanced K-Means algorithm employed dimensionless fruit parameters for clustering. Experiments showed that the system achieved a 97.4% accuracy in detecting fruit defects, a 5.2% improvement in edge detection, and an 89.9% grading accuracy, with a 10.3% increase in same-batch sorting efficiency for small batches of 72 fruits. © 2025 IEEE.

关键词： citrus sorting clustering algorithm comprehensive evaluation model edge detection

来源：评论

学校读者我要写书评

暂无评论

Research on Patent Text Classification Task Based on clustering 24

Research on Patent Text Classification Task Based on Cluster...

引用

Proceedings of the 2024 International Conference on Image Processing, Multimedia Technology and Maching Learning

作者： Xiaoxin Gao Yukai Liu Yuangeng Zhu Beijing CHINA-POWER INFORMATION Technology Co. Ltd. Beijing China

ISBN: (纸本)9798400713880

The traditional classification method based on manual labelling has problems such as low efficiency and high cost. To address this problem, this project proposes to combine the three feature extraction techniques of TF-IDF, Word2Vec and GloVe, and use K-means clustering algorithm to cluster and analyse the patent text. The experiment proves that compared with the conventional TF-IDF algorithm, the algorithm has a greater improvement in clustering effect, classification accuracy and retrieval effect, and can better reflect the semantics in patent text. On this basis, this project will propose a new type of patent text classification method based on image segmentation, and compare it with the conventional image segmentation technology, so that it has better classification effect and higher computational efficiency.

关键词： clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on sustainable design of sports centre based on algorithm verification

引用

APPLIED MATHEMATICS AND NONLINEAR SCIENCES 2022年第2期7卷 1023-1032页

作者： Hou, Ye Wang, Shaobin Shang, Jin Daria, Lisaia Elzefzafy, Hend Guangdong Univ Finance & Econ Sch Art & Design Guangzhou 510320 Guangdong Peoples R China South China Univ Technol Sch Architecture Guangzhou Peoples R China Appl Sci Univ Coll Engn Eker Bahrain

In the process of urbanisation in China, many cities expect to promote the development of new towns through the construction of sports centres. However, due to the unreasonable design of the scale, accessibility and vitality of the sports centre, the catalyst effect of the sports centre is difficult to play an effective role. Using cluster analysis algorithm and spatial syntax, this study analyses the algorithm of sports centres with sustainable development characteristics, and puts forward the conclusions of sustainable development planning strategies such as venue merger design under the principle of intensive, maintaining high accessibility of sports centres, ensuring the compound function of surrounding plots and grid space to improve regional vitality, in order to provide some inspiration for the planning and construction of Sports Centre in the future.

关键词： Sports centre clustering algorithm Spatial syntax sustainable development

来源：评论

学校读者我要写书评

暂无评论

Distribution characteristics of pycnocline in the northern South China Sea based on an improved vertical gradient method

引用

JOURNAL OF OCEANOGRAPHY 2022年第6期78卷 449-466页

作者： Zou, Li Wang, Xueyu Wen, Zehua Yu, Zongbing Ma, Xinyu Dalian Univ Technol Sch Naval Architecture State Key Lab Struct Anal Ind Equipment Dalian 116024 Peoples R China Collaborat Innovat Ctr Adv Ship & Deep Sea Explor Shanghai 200240 Peoples R China Tsinghua Univ Dept Hydraul Engn Beijing 100084 Peoples R China

Pycnocline is a widespread marine phenomenon across the world, which plays an important role in ocean engineering, oceanic meteorology, and biological applications. In this study, based on actual density data, statistical characteristics of complex density profiles are analyzed. It is found that the pycnocline interval d in multilayer structures conforms to the three-parameter Weibull distribution. To describe the multilayer structure more accurately, a dimensionless parameter alpha is proposed, which takes into account scale effects and the relative position of layers. Then, the probability density distribution of alpha is analyzed, from which the clustering phenomena are found. Therefore, clustering analysis is carried out to obtain a method for determining the location of pycnocline in complex density profiles. Based on this method, the statistical research of pycnocline distribution in the northern South China Sea is carried out including the key properties of pycnocline depth, pycnocline thickness, and pycnocline intensity. The result shows that the pycnocline distribution changes periodically with seasons, in which heat flux and monsoon are the main influencing factors. As the temperature increases, the formation of the pycnocline is encouraged, with the consequent decrease in pycnocline depth and increase in pycnocline thickness and intensity, vice versa. The monsoon influences the distribution of the pycnocline by affecting vertical mixing and Ekman wind-driven mechanism.

关键词： Pycnocline clustering algorithm Pycnocline merging method Northern South China Sea Pycnocline distribution

来源：评论

学校读者我要写书评

暂无评论

Using Pattern Analysis and Machine Learning to Categorise users of Online Directories based on their Surfing Habits

Using Pattern Analysis and Machine Learning to Categorise us...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Athinarayanan, S. Joel, M. Robinson Jumlesha, Shaik Susmitha, K. Charitha, Limgamgunta School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Cse Chennai Tamil Nadu Avadi600062 India Aits Department of Computer Science and Engineering Andra Pradesh Tirupati India Kings Engineering College Department of Information Technology Chennai India

ISBN: (纸本)9798350313987

The major goal is to group users together, including in student organizations. Assume that the notion is required to cluster consumers in educational institutions. A cluster of websites or web pages organized by user interest makes up an online use directory. Web mining is the process of using strategies to extract websites from the web proxy log file. We are employing the Apriori algorithm and the Fuzzy clustering technique for it. Typically, data cleaning, a preprocessing step, is followed by aggregation of the data after cleanliness in web use mining. We do a pattern analysis following the data's classification. The outcomes of the studies are contrasted with another intriguing technique that is made public. In comparison to other efforts, the outcomes produced by the suggested system exhibit better performance. The technique we utilised, called WDUM or web directories user mining, produces better results than earlier techniques. We compare user growth and penetration performance to the threshold values. Thus, after preprocessing, the log files are retrieved, and the Apriori algorithm and fuzzy logic classification are applied. These outcomes demonstrate the greatest methods for capturing user interest. Finally, the projected user clicked the prediction findings using machine learning techniques. © 2023 IEEE.

关键词： clustering algorithm Machine learning and Web proxy log Pattern analysis Web Usage Mining

来源：评论

学校读者我要写书评

暂无评论

A study on the big data scientific research model and the key mechanism based on blockchain

引用

OPEN COMPUTER SCIENCE 2022年第1期12卷 357-363页

作者： Wen, Shengwei Ganzhou Teachers Coll Dept Sci & Comp Ganzhou 341000 Jiangxi Peoples R China

In an era of open data sharing, the scientific research field puts forward an urgent need for the value of big data. However, big data still form "data islands," which seriously affects the level of scientific research and the progress of scientific research. In this regard, this article proposes the research and realization of the big data scientific research model and key mechanism based on blockchain. This article uses the K-means algorithm to cluster scientific research data and reasonably utilizes the decentralization, smart contracts, and non-tampering characteristics of the blockchain to design a distributed data model based on the blockchain. This article proposes that a BIZi network is formed based on a blockchain Interplanetary File System (IPFS) and Zigzag code (blockchain, IPF Sand Zigzag code, BIZi for short) to achieve reliable data connection and through a set of data access control mechanisms and data service customization mechanism to effectively provide data requirements for scientific research. Finally, IPFS network transmission speed performance can better meet the needs of scientific research. The larger the number of file blocks, the higher the fault tolerance rate of the scheme and the better the storage efficiency. In a completely open data-sharing scenario, the fault tolerance rate of Byzantine nodes is extremely high to ensure the stability of the blockchain. The current optimal consensus algorithm fault tolerance rate reaches 49%.

关键词： blockchain research big data scientific research model key mechanism clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Personalized Recommendation algorithm for Electronic Commerce Based on Artificial Intelligence Technology

Personalized Recommendation Algorithm for Electronic Commerc...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Zhang, Yiling Li, Caicai Shaanxi Fashion Engineering University Economics and Management College Shaanxi Xianyang China

ISBN: (纸本)9798350315455

In the era of e-commerce, a large amount of data and complex business models make traditional manual recommendations difficult to adapt to constantly changing personalized needs. Finding a more efficient product recommendation algorithm has become an important topic in the field of e-commerce. The scale of online shopping is constantly expanding, and it is necessary to match higher technological investments to explore the value of data. By comparing the advantages, disadvantages, and application scenarios of collaborative filtering algorithms and artificial intelligence technology, this article constructs a personalized recommendation system for e-commerce according to data mining. The results show that the recall rate of AI based recommendation algorithms is about 0.1 higher than that of collaborative filtering-based recommendation algorithms, and after using artificial intelligence algorithms for personalized recommendations, eBay's recommendation accuracy has improved by about 8.26%. The recommendation system designed in this article can provide recommendations for products or services that meet users' needs according to their interests as well as preferences, thereby improving their shopping experience. © 2023 IEEE.

关键词： Artificial Intelligence clustering algorithm Electronic Commerce Personalized Recommendation

来源：评论

学校读者我要写书评

暂无评论

Data mining in college student education management information system

引用

INTERNATIONAL JOURNAL OF EMBEDDED SYSTEMS 2022年第3期15卷 279-287页

作者： Yang, Huirong Zhang, Wenjie Fuzhou Univ Int Studies & Trade Sch Econ & Management Fuzhou 350000 Fujian Peoples R China Nanchang Inst Sci & Technol Sch Artificial Intelligence Nanchang 330000 Jiangxi Peoples R China

In recent years, with the maturity of database technology, the rapid popularisation of network technology, and the continuous updating of computer hardware, data mining technology has developed rapidly. This article mainly introduces the application of data mining technology in college student education management information systems, to provide some methods and ideas for better management of student information, and proposes the application research method of data mining in college student education management information systems, including education data. An overview of mining K-means algorithm and fuzzy C-means clustering algorithm is used to build a data mining system. The calculation results show that the average processing time of the algorithm in the system is 1.92 seconds, which guarantees the experience of education administrators with the system.

关键词： data mining clustering algorithm data pre-processing education management information system

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Multi-layered Employee Profile System for Power Enterprises Based on LSTM and Mini-batch K-means 5

Design and Implementation of a Multi-layered Employee Profil...

引用

5th International Conference on Frontiers Technology of Information and Computer, ICFTIC 2023

作者： Wang, Ziheng Li, Xiaozhen Meng, Yu Zhang, Qian State Grid Information and Communication Industry Group Co. LTD. Beijing China

ISBN: (纸本)9798350309034

Abstract-To facilitate more efficient and convenient online office work, major enterprises have launched mobile portal applications, integrating various office micro-applications to provide employees with a unified entry point. However, employees in different positions have varying application demands and there is a lack of a personalized recommendation mechanism. Accurately profiling employees has thus become a research focus for many scholars. In response to this issue, this paper proposes a multi-layered employee profile system for power enterprises. We designed a data collection model suitable for processing massive logs, and used LSTM and mini-batch K-means algorithms to cluster employees at two levels: application usage and provincial distribution. Employee labels were established through statistical characteristics and professional analysis, and a classification model was trained for employee profiling. To verify the effectiveness of the system proposed in this paper, real data was collected to conduct experiments. The results were compared with traditional clustering algorithms and other outstanding profile algorithms from previous studies. The findings demonstrate that the profile system proposed in this paper achieves superior performance in profiling employees of power enterprises compared to other algorithms. © 2023 IEEE.

关键词： Classification algorithm clustering algorithm LSTM Mini-batch K-means User Profiling

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：