检索结果-内蒙古大学图书馆

BEARING LIFE PREDICTION MODEL FOR ELECTROMECHANICAL EQUIPMENT BY INTEGRATING DEEP NEURAL NETWORk AND k-nearest neighbor algorithm AND ITS APPLICATION

引用

JOURNAL OF THEORETICAL AND APPLIED MECHANICS 2024年第4期62卷 721-735页

作者： Ma, Yiming Jilin Jianzhu Univ Changchun Peoples R China

Current life prediction methods of Electromechanical equipment bearings have issues of low accuracy and lack of stability. To address these problems, firstly, indicators based on life degradation characteristics of bearings are selected. Then, a deep neural network-based life prediction model is constructed. Finally, the k-nearest neighbor algorithm is introduced to correct the deviation of the deep neural network prediction model, and a hybrid life prediction model is designed. Results show that effectiveness of the designed model was better, which was of great practical significance for detecting bearing failures in advance, reducing equipment losses and improving equipment reliability.

关键词： bearings deep neural network k-nearest neighbor algorithm deviation life pre- diction model

来源：评论

学校读者我要写书评

暂无评论

Packer Identification Method for Multi-Layer Executables Using Entropy Analysis with k-nearest neighbor algorithm

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 2023年第3期E106A卷 355-357页

作者： Omachi, Ryoto Murakami, Yasuyuki Osaka Electrocommun Univ Neyagawa 5728530 Japan

The damage cost caused by malware has been increasing in the world. Usually, malwares are packed so that it is not detected. It is a hard task even for professional malware analysts to identify the packers especially when the malwares are multi-layer packed. In this letter, we propose a method to identify the packers for multi-layer packed malwares by using k-nearest neighbor algorithm with entropy-analysis for the malwares.

关键词： key malware packer identification multi-layer packing k-nearest neighbor algorithm entropy analysis

来源：评论

学校读者我要写书评

暂无评论

k-nearest neighbor algorithm for selection of new gelatin-carboxymethylcellulose films with TiO2 nanoparticles and propolis extract with antioxidant and light barrier activity

引用

FOOD PACkAGING AND SHELF LIFE 2023年 38卷

作者： de Brito, Raira Sa Costa, Marcos Jhony Almeida Barbosa, Jhonatas Rodrigues Filho, Adilson Ferreira Santos Farias, Fabricio de Souza Lourenco, Lucia de Fatima Henriques Fed Univ Para UFPA Inst Technol ITEC Food Sci & Technol Dept Rua Augusto Correa S-N BR-66075900 Belem PA Brazil Fed Univ Para UFPA Fac Informat Syst BR-68400000 Cameta PA Brazil

Nanoparticles associated with antioxidant ingredients emerge as a new strategy to improve food packaging properties. In this study, we developed gelatin-carboxymethylcellulose films containing propolis extract and TiO2 nanoparticles (1 % and 5 %), and the k-nearest neighbor algorithm was used to select the best packaging composition. Films showed excellent antioxidant activity and those mixed with nanoparticles performed better with light and water barrier properties. The film with propolis and 5 % TiO2 nanoparticles showed higher antioxidant activity and opacity, lower water vapor permeability, solubility, water activity, moisture content, and thickness. These results indicate that the kNN algorithm, an artificial intelligence tool, is promising for classifying and selecting films with properties of interest. The films containing propolis extract and TiO2 nanoparticles have excellent properties that validate their application as food packaging.

关键词： k-nearest neighbor algorithm Nanoparticles Propolis extract Food packaging

来源：评论

学校读者我要写书评

暂无评论

Asphalt Pavement Performance Prediction Based on k-nearest neighbor algorithm 3

Asphalt Pavement Performance Prediction Based on K-Nearest N...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Chen, Weidong Chang'an-Dublin International College of Transportation Chang'an University Shaanxi Xi'an China

ISBN: (纸本)9798350319125

Today's social development is inseparable from road engineering, paving roads and building roads makes economic development an important link, which can make economic exchanges more convenient and convenient transportation. Among them, asphalt pavement is often used, and the performance of asphalt pavement structure greatly affects whether the road project can be successfully completed. Therefore, the role of asphalt pavement performance prediction in road engineering is very important. Ordinary performance prediction methods can no longer solve the problem of asphalt pavement performance in road engineering. Therefore, a k-nearest neighbor algorithm is proposed to analyze the performance of asphalt pavement. Firstly, data mining is used to predict and in the performance of asphalt pavement. Then, the data mining predicts the asphalt pavement performance of road engineering, forms the asphalt pavement performance scheme, and comprehensively analyzes the asphalt pavement performance results. the reliability of asphalt pavement performance prediction of k-nearest algorithm for road engineering are better than that of ordinary prediction performance methods. © 2023 IEEE.

关键词： Asphalt pavement performance data mining k-nearest neighbor algorithm road works

来源：评论

学校读者我要写书评

暂无评论

HS-CGk: A HYBRID SAMPLING METHOD FOR IMBALANCE DATA BASED ON CONDITIONAL TABULAR GENERATIVE ADVERSARIAL NETWORk AND k-nearest neighbor algorithm

引用

COMPUTING AND INFORMATICS 2024年第2期43卷 213-239页

作者： Zhao, Xiaoyan Guan, Shaopeng Xue, Yuewei Pan, Hao Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai 264005 Peoples R China

Class imbalance problem in datasets can lead to biased classification decisions in favor of majority class samples. Additionally, class overlap can cause fuzzy classification boundaries, affecting the performance of classification algorithms. To address these issues, we propose a hybrid sampling method based on conditional tabular generative adversarial network (CTGAN) and k-nearest neighbor (kNN) algorithm. Firstly, we introduce an oversampling algorithm, named DB-CTGAN, based on CTGAN. This algorithm filters noisy and boundary samples using the density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm and generates synthetic samples that conform to the real data distribution using CTGAN. Finally, we combine the expanded fraudulent samples generated by DB-CTGAN with the normal samples and use the kNN overlap undersampling algorithm to remove the samples in the overlap region, solving the class overlap problem. Experimental results show that compared with eight sampling methods Vector Classification, and XGBoost), the proposed method significantly improves the F1, AUC, and G-mean metrics on five real datasets.

关键词： Imbalanced data class overlap conditional tabular generative adversarial network k-nearest neighbor algorithm hybrid sampling

来源：评论

学校读者我要写书评

暂无评论

A comprehensive evaluation method for moisture and aging state of oil-immersed paper bushings based on dielectric modulus and k-nearest neighbor algorithm

引用

FRONTIERS IN ENERGY RESEARCH 2024年 11卷

作者： Liang, Zhengping Sun, Yongbin Cheng, Hao Zhang, Na Li, Bo Liu, Yang Fang, Yan Zhang, Yiyi China Power Engn Consulting Grp North China Power Engn Co LTD Beijing Peoples R China Guangxi Univ Guangxi Power Transmiss & Distribut Network Lightn Nanning Peoples R China

The insulation performance of oil-immersed paper bushings is prone to deteriorate, primarily due to moisture intrusion and thermal aging. The frequency domain spectroscopy (FDS) method is commonly employed to assess the insulation condition of the bushing. However, identifying and extracting relaxation polarization information from the low-frequency region of the FDS curve can be challenging, and there is little research about the condition evaluation under the combined effects of aging states and moisture content. To address this issue, this article uses the Taylor formula mathematical model to extract characteristic parameters from the dielectric modulus curve of OIP bushings and uses the kNN algorithm to achieve the evaluation of aging and moisture status. Then, the effectiveness and accuracy of the proposed method are validated on three field OIP bushings. The results demonstrate that the evaluation accuracy of the proposed method exceeds 83%, which has significant advantages compared to other classification algorithms. The innovation of this article lies in extracting new feature parameters and combining them with intelligent classification algorithms to evaluate the moisture and aging state of the bushing.

关键词： aging state dielectric modulus frequency domain spectroscopy (FDS) k-nearest neighbor algorithm moisture content

来源：评论

学校读者我要写书评

暂无评论

Uncertainty prediction method for traffic flow based on k-nearest neighbor algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2020年第2期39卷 1489-1499页

作者： Yang, Lingmin Hubei Univ Educ Coll Management Wuhan 430205 Peoples R China

In order to overcome the problem of low fitting between traffic uncertainty prediction results and actual values in existing research methods, a traffic flow uncertainty prediction method based on k-nearest neighbor algorithm is proposed. The original database, classification center database, k-nearest neighbor database and intermediate search database are used to construct the database needed in the prediction process. Based on the database, multivariate linear regression is used to assign weights to state variables, and k-nearest neighbor algorithm and kalman filter are used to update the weights to adapt to the uncertainties of traffic flow until the predicted values are obtained, and the uncertainties of traffic flow are predicted. The experimental results show that the maximum average absolute error and average relative error of the proposed method are 0.018 and 0.02, respectively. Compared with the traditional method, the proposed method has higher overall prediction accuracy, higher fitting degree, and is feasible.

关键词： k-nearest neighbor algorithm traffic flow uncertainty prediction kalman filtering concept

来源：评论

学校读者我要写书评

暂无评论

Trust access control method of power metering automation system based on k nearest neighbor algorithm 11

Trust access control method of power metering automation sys...

引用

11th International Conference on Information Technology - IoT and Smart City (ITIoTSC)

作者： Liang, Yanhe Gong, You Li, Xinggang Cao, Hongyu Wang, Xiaoyu State Grid Heilongjiang Power Supply Serv Ctr Power Metering Ctr Harbin 150000 Heilongjiang Peoples R China

ISBN: (纸本)9798350328356;9798350328349

In the process of trust access control of electric energy metering automation system, malicious attacks will lead to data leakage, tampering and loss. k-nearest neighbor algorithm can predict or classify the data samples according to the similarity of electric energy measurement, and restrict only authorized users to access and modify the data through access control means, thus effectively avoiding data leakage, tampering and loss. Therefore, a trust access control method for electric energy metering automation system based on k nearest neighbor algorithm is proposed. The trust degree is calculated according to the access request and attribute value of the subject, the reasonable degree of network security and information security is evaluated, and the access permission is granted according to the evaluation result of the trust degree. The implicit information is used to calculate the user's trust degree and dynamically adjust the user's authority;The information to be collected at a fixed point is matched with the information in the power metering automation system by similarity, the nearest neighbor points are obtained, and the fuzzy entropy of each sample point is calculated according to the distance size. The weighted average method is used to predict the trust degree of the test samples. Based on k-nearest neighbor algorithm, accurate control of trust access to power metering automation system is realized. The simulation results show that this method has higher security and better dynamic planning ability of access path, and can complete the trust access control of power metering automation system in the shortest 2ms. It is proved that k-nearest neighbor algorithm can effectively complete the trust access control of electric power metering automation system.

关键词： k-nearest neighbor algorithm Electric power measurement Degree of trust Access control Automated system

来源：评论

学校读者我要写书评

暂无评论

PUNNHMD A: Microbe-Disease Association prediction based on PU learning and optimized k -nearest neighbor algorithm 11

PUNNHMD A: Microbe-Disease Association prediction based on P...

引用

11th Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2023

作者： Wang, Jianru Lu, Daying Wang, Lihui Lin, Yuanyuan Xu, Qingtao College of Cyber Science and Engineering Qufu Normal University Jining China

ISBN: (纸本)9798350333664

By deepening our understanding of the relationship between microorganisms and disease, we can study the formation and pathogenesis of various complex diseases. This, in turn, enables the development of more effective treatment methods and prevention measures to improve human health. However, traditional prediction methods are often faced with challenges in accurately predicting associations and can be time-consuming. As a result, computational approaches have emerged as a powerful tool for identifying and predicting potential associations between microorganisms and diseases. Here we develop a prediction algorithm called PUNNHMDA to predict associations. First, the PU learning (Positive-Unlabeled learning) method was used to select reliable negative microbe-disease association samples. Second, the Mahalanobis distance function was combined with the kNN (k-nearest neighbor) algorithm and utilized innovatively for microbe-disease association prediction. To validate the effectiveness of PUNNHMDA, we benchmarked it against five existing approaches on the task of predicting microbe-disease associations. Through evaluating PUNNHMDA on the HMDAD dataset using LOOCV and 10-fold cross-validation, the results demonstrated that PUNNHMDA achieved superior predictive performance over other advanced prediction models, attaining the highest accuracy scores. Specifically, it obtained accuracies of 0.9308 and 0.9351 in LOOCV and 10-fold CV respectively, which were markedly higher than those of other benchmarked methods. © 2023 IEEE.

关键词： k-nearest neighbor algorithm Mahalanobis distance Matrix Factorization Microbe-Disease Association prediction positive-unlabeled learning

来源：评论

学校读者我要写书评

暂无评论

Application of improved k-means k-nearest neighbor algorithm in the movie recommendation system 13

Application of improved k-means k-nearest neighbor algorithm...

引用

13th International Symposium on Computational Intelligence and Design (ISCID)

作者： Cai, Chang Wang, Li Univ Sci & Technol Liaoning Coll Comp & Software Engn Anshan Peoples R China

ISBN: (纸本)9781728184463

In this paper, we propose a clustering and reclassification method for movie recommendation. We use the improved k-means algorithm to cluster according to the scores of similar users, Firstly, the elbow function is used to estimate the number of clusters, and the elbow method is used to determine the k value. Then, the k-means algorithm of the maximum and minimum distance method is used to select the initial cluster center, and finally the cluster and cluster center are obtained. According to the similarity between the test data of the user's rating and user's personal information and the clustering center, they are divided into the cluster to which they belong, and the sample set in the cluster is used as the training set for k-nearest neighbor classification.

关键词： k-nearest neighbor algorithm k-means algorithm elbow method maximum-minimum distance

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：