检索结果-内蒙古大学图书馆

6th International Conference on Pattern Recognition and Image Analysis (IPRIA)

作者： Zarei, M. Alizadeh Nickfarjam, A. M. Islamic Azad Univ Kashan Dept Comp Engn Fac Elect & Comp Engn Kashan Iran Kashan Univ Med Sci Dept Hlth Informat Management & Technol Kashan Iran Kashan Univ Med Sci Res Ctr Hlth Informat Management Kashan Iran

ISBN: (纸本)9798350314557

In this paper, we propose a combination of k-means algorithm and Particle Swarm Optimization (PSO) method. The k-means algorithm is utilized for data clustering. On one hand, the number of clusters (k) should be determined by expert or found by try-and-error procedure in the k-means algorithm. On the other hand, initial centroids and number of clusters (k) are influenced on the quality of resulted grouping. Therefore, the aim of the proposed procedure is using PSO and the Structural Similarity Index (SSIM) criterion as a fitness function in order to find the best value for k parameter and better initial clusters' center. Due to different value of k parameter, the number of initial centroids which should be produced is variant. Thus, length of particles in PSO method may be different in each iteration. Experimental results show the superiority of this approach in comparison with standard k-means algorithm and both of them are evaluated on image segmentation problem.

关键词： Data Clustering Particle Swarm Optimization k-means algorithm Image Segmentation Structural Similarity Index

来源：评论

学校读者我要写书评

暂无评论

Research on image text recognition based on canny edge detection algorithm and k-means algorithm

引用

INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT 2022年第SUPPL 1期13卷 72-80页

作者： Wu, Fangsheng Zhu, Changan Xu, Jinxiu Bhatt, Mohammed Wasim Sharma, Ashutosh Anhui Business Vocat Coll Inst Informat Engn Hefei 231131 Anhui Peoples R China Univ Sci & Technol China Hefei 230026 Anhui Peoples R China Cent Univ Punjab Bathinda India Southern Fed Univ Inst Comp Technol & Informat Secur Southern Fed Dist Russia

The latest research in the field of recognition of image characters has led to various developments in the modern technological works for the improvement of recognition rate and precision. This technology is significant in the field of character recognition, business card recognition, document recognition, vehicle license plate recognition etc. for smart city planning, thus its effectiveness should be improved. In order to improve the accuracy of image text recognition effectively, this article uses canny algorithm to process edge detection of text, and k-means algorithm for cluster pixel recognition. This unique combination combined with maximally stable extremal region and optimization of stroke width for image text yields better results in terms of recognition rate, recall, precision, F-score and accuracy. The results show that the correct recognition rate is 88.3% and 72.4% respectively with an accuracy value of 90.5% for the proposed method. This algorithm has high image text recognition rate, can recognize images taken in complex environment, and has good noise removal function. It is significantly an optimal algorithm for image text recognition.

关键词： Canny edge detection algorithm k-means algorithm Image text recognition Noise removal

来源：评论

学校读者我要写书评

暂无评论

Text Clustering Based on Binary Particle Swarm and Spherical k-means algorithm 3

Text Clustering Based on Binary Particle Swarm and Spherical...

引用

2023 IEEE 3rd International Conference on Data Science and Computer Application, ICDSCA 2023

作者： Luo, Luoyang Qiu, Linrun Guangdong University of Science and Technology College of Computer Science Dongguan523083 China

ISBN: (纸本)9798350341546

Internet technology advancement has led to an exponential surge in text data. Among the pressing data types today, natural language data stands out. Leveraging natural language processing (NLP) technology, computers can comprehend human language and extract valuable information from extensive textual data. This paper introduces a novel approach for text clustering, combining binary particle swarm optimization with the spherical k-means algorithm. Empirical findings on a Chinese text dataset demonstrate the effectiveness of the feature selection method introduced in this paper, effectively diminishing feature overlap and enhancing clustering precision. © 2023 IEEE.

关键词： Binary particle swarm algorithm k-means algorithm Text clustering

来源：评论

学校读者我要写书评

暂无评论

Research on glass composition analysis based on k-means algorithm and Lasso regression algorithm 3

Research on glass composition analysis based on K-means algo...

引用

2023 IEEE 3rd International Conference on Data Science and Computer Application, ICDSCA 2023

作者： Chen, Yutong Zhao, Chenrui Chen, Qiyan Li, Yuwan Fu, Tiantian Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9798350341546

This paper aims to study the relationship among weathering, color, species and ornamentation of glass relics by means of data preprocessing and statistical analysis. At the same time, the logistic regression model was used to classify the high potassium and lead barium glass. The k-means clustering algorithm is used to cluster the glass, and the chemical composition content rules of each class are found, and each class is regarded as a sub-class. Through the established k-means clustering algorithm to determine the central components of high-potassium and lead-barium glass, it is found that the central components of high-potassium glass are k2O and CaO, while the central components of lead-barium glass are SiO2, PbO and BaO. Through LASSO regression model based on Lars algorithm, 14 chemical elements were screened, and the main related elements of the two types of glass were obtained. It is found that SiO2 is strongly correlated in these two types of glass, while PbO and BaO are strongly correlated in lead-barium glass, but the correlation with high-potassium glass is very weak. This study is of great significance to elucidate the characteristics and classification of glass relics. © 2023 IEEE.

关键词： correlation coefficient k-means algorithm Lasso regression model logistic regression model

来源：评论

学校读者我要写书评

暂无评论

Fast Inspection Image Identification Method for Digital Electromechanical Equipment Based on k-means algorithm

Fast Inspection Image Identification Method for Digital Elec...

引用

2023 International Conference on Evolutionary algorithms and Soft Computing Techniques, EASCT 2023

作者： Fu, Jiang Guizhou City Vocational College Guiyang Guizhou China

ISBN: (纸本)9798350313413

The research of image recognition method based on k-means algorithm for digital motor equipment rapid inspection has important background and research significance. It represents a major advance in the field of device inspection. The core idea of this method is to detect and recognize equipment state automatically through image clustering and model training, so as to reduce the dependence on manual inspection and reduce the error rate. Firstly, k-means algorithm is used to cluster the images to be detected and divide them into different categories. Then, model training for each category is carried out to realize the classification and recognition of each category. In this way, it can automatically analyze and identify the inspection images of the equipment, quickly and accurately judge the status of the equipment, and reduce the interference of human factors. Experimental results show that this method is efficient and accurate. The recognition time of each image is no more than 21 seconds, the accuracy is higher than 95%, the response time is less than 13 seconds, and the output time is less than 17 seconds. This is a significant improvement over traditional inspection methods. In summary, the image recognition method of digital motor equipment rapid inspection based on k-means algorithm has important application prospect and research significance in the field of equipment inspection. It improves inspection efficiency, accuracy and cost effectiveness, and is expected to promote further improvement and optimization of equipment inspection work.. © 2023 IEEE.

关键词： automatic detection digital design electromechanical equipment image identification k-means algorithm

来源：评论

学校读者我要写书评

暂无评论

Methods for Generating Scene Animation Based on k-means algorithm 1

Methods for Generating Scene Animation Based on K-Means Algo...

引用

1st IEEE International Conference on Ambient Intelligence, knowledge Informatics and Industrial Electronics, AIkIIE 2023

作者： Zhang, Chulei Changchun Humanities and Sciences College Jilin Changchun130117 China

ISBN: (纸本)9798350316469

Animation scene design and production is an important part of the animation production process, which involves the layout and environmental design of the animation scene, and has a significant impact on the atmosphere, quality, and emotional expression of the animation. Based on the comparison of experimental results, it was found that compared with the evaluation of traditional and optimized scene animation generation methods by relevant staff, the average improvement in process optimization, output speed, work quality, and generation efficiency was 9%. Compared with traditional scene animation generation methods, the optimized scene animation generation method in this paper has higher scene image generation efficiency, can output more details of scene images, and greatly shorten the time required for animation production. This not only improves the quality of animation, but also promotes the integration of advanced information processing technology with the field of animation production. © 2023 IEEE.

关键词： Animation Production Generating Methods k-means algorithm Scene Image

来源：评论

学校读者我要写书评

暂无评论

Research on the Classification of E-Commerce Users Based on RFM Model and k-means algorithm

Research on the Classification of E-Commerce Users Based on ...

引用

2023 IEEE International Conference on Electrical, Automation and Computer Engineering, ICEACE 2023

作者： Yao, Yingzhu Tianjin University of Technology Tianjin China

ISBN: (纸本)9798350309614

The report provides an overview of the dataset and the models and algorithms applied in the project. Initially, we present a comprehensive review of the RFM model and clustering algorithms. Utilizing the online transaction data from a British e-retail company, we compile the data, apply the RFM model to extract user segmentation information, devise k-means algorithms, and ultimately leverage user behavior to efficiently meet user demands. This approach facilitates precise user targeting, minimizes marketing expenses, and maximizes overall returns. © 2023 IEEE.

关键词： clustering algorithm k-means algorithm RFM Model user classification

来源：评论

学校读者我要写书评

暂无评论

Construction and Application of Urban and Rural Planning Analysis Model Based on k-means algorithm 1

Construction and Application of Urban and Rural Planning Ana...

引用

1st IEEE International Conference on Ambient Intelligence, knowledge Informatics and Industrial Electronics, AIkIIE 2023

作者： Wang, Huijuan Chen, Yanzhao Zhu, Guixiang School of Architecture and Civil Engineering Chongqing Metropolitan College of Science and Technology Chongqing China China West China Engineering Design and Construction Co. Ltd. Chongqing Branch Chongqing China

ISBN: (纸本)9798350316469

In recent years, traditional urban and rural planning analysis models have been continuously improved to deal with complex problems. Since the traditional model still has defects, the design and application of urban and rural planning analysis model based on k-means algorithm are proposed. The k-means algorithm is used to analyze urban and rural planning, and the basic workflow of the model is obtained, and the model is established and verified by application. The application in keshan Town, keshan County, Heilongjiang Province shows that the analysis results of the k-means model are consistent with the actual situation and are better than other models. © 2023 IEEE.

关键词： Cluster Data k-means algorithm Large-Scale Data Collection Urban and Rural Planning

来源：评论

学校读者我要写书评

暂无评论

Optimization of Machining Path for Complex Surface Milling in TC11 Based on the k-means algorithm

引用

INTEGRATED FERROELECTRICS 2024年第4-5期240卷 637-649页

作者： Qian, Qingwen Wang, Zhe Ji, Shuang Huangshan Univ Coll Mech & Elect Engn Huangshan Anhui Peoples R China Heilongjiang Acad Agr Sci Soybean Res Inst Harbin Heilongjiang Peoples R China

TC11 impeller blades are typical complex curved surface components. Due to the complex machining load variations, these types of components have always been difficult to effectively solve issues such as significant machining deformation and large machining errors. This article characterizes complex surface features based on Gaussian curvature and mean curvature. Different machining methods are employed for different regions of the TC11 material after partitioning, and a comparative experiment is conducted between traditional methods and surface slicing methods for machining. Different machining methods are applied to process the different regions of TC11 material after surface partitioning, and a comparative experiment is conducted between traditional methods and surface slicing methods for machining.

关键词： Machining path optimization complex surfaces k-means algorithm TC11

来源：评论

学校读者我要写书评

暂无评论

A Vis/NIRS device for evaluating leaf nitrogen content using k-means algorithm and feature extraction methods

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2024年 225卷

作者： Lu, Miao Wang, Haoyu Xu, Jinghua Wei, Ziyuan Li, Yihang Hu, Jin Tian, Shijie Northwest A&F Univ Coll Mech & Elect Engn Yangling 712100 Shaanxi Peoples R China Northwest A&F Univ Coll Informat Engn Yangling 712100 Shaanxi Peoples R China Minist Agr & Rural Affairs Key Lab Agr Internet Things Yangling 712100 Shaanxi Peoples R China Shaanxi Engn Res Ctr Agr Informat Intelligent Perc Yangling Shaanxi Peoples R China

Accurate assessing leaf nitrogen content (LNC) is crucial for actual production and fertilizer management. In this research, a portable device was designed to rapidly and non-destructively evaluate LNC with precision. Using hydroponically grown eggplants exposed to different nitrogen content nutrient solutions as experimental samples, we conducted various measurements, including chlorophyll fluorescence (ChlF) induction curves, hyper- spectral images, and LNC values. Correlations between LNC and ChlF parameters were calculated, and the parameter qN obtained the highest correlation with LNC. False color images of qN were segmented using the kmeans algorithm to obtain three regions. The spectral data and the measured LNC of the corresponding region in the leaf were matched, and a LNC prediction model was developed using the partial least square regression (PLSR) algorithm with the processed spectral data as input and the measured LNC as output. The results showed that the model using standard normal variate-iteratively retains informative variables- successive projections algorithm (SNV-IRIV-SPA-PLSR) yielded the best performance, with a correlation coefficient of prediction (R2) 2 ) of 0.9332, a root mean square error (RMSE) of 2.6890 mg/g, a residual prediction deviation (RPD) of 3.97 and a ratio of performance to interquartile distance (RPIQ) of 7.28. Based on the selected wavelengths from the SNVIRIV-SPA-PLSR-VIP model, six narrow-band light emitting diodes (LEDs) were chosen as the light source for the designed device. Inexpensive modules were employed to assemble the device, and accuracy tests were conducted. The PLSR algorithm was employed to develop the device's LNC evaluation model with the reflectance of the leaf under 6 LEDs as input (resulting in R2, 2 , RMSE, RPD, and RPIQ values of 0.8075 6.6242 mg/g, 2.30 and 4.26, respectively). The model was then embedded in the core processor. To validate the device's performance, an independent set was used, resulti

关键词： Spatial distribution SNV-IRIV-SPA-PLSR-VIP Visible/near-infrared reflectance spectroscopy Eggplant Chlorophyll fluorescence technology k-means algorithm

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：