检索结果-内蒙古大学图书馆

39th CCF National Conference on Computer Applications

作者： Wang, Yutang Gao, Erni Anhui Inst Informat Technol Wuhu Anhui Peoples R China

ISBN: (纸本)9789819796700;9789819796717

In the process of big data analysis, data integrity and consistency are often very important factors that affect the accuracy of analysis results. Therefore, before starting the analysis process, data cleaning work should be done on the collected data sources to ensure that subsequent analysis will not cause errors due to data anomalies. Therefore, maintaining data integrity is a very important task in data cleaning. One of the reasons for incomplete data is that the collected data contains missing values, which are caused by human negligence, instrument failure and other factors during the data collection process. The common methods for dealing with missing values are as follows: ignore the value group with missing values directly, or use the central tendency measurement (such as mean, median, etc.) of the missing value attribute to fill in the missing values. These methods may cause the loss of the original characteristics of the value group, which may affect the output of subsequent data analysis and application, and lead to incorrect results. To address this problem, this study uses machine learning methods to fill in missing values for a single field. We use data without missing values as training data, divide the data into multiple clusters using k-means clustering method to capture the hidden associations between data, and build prediction models for each cluster using multiple regression and artificial neural network. For missing values that need to be predicted, we first use kNN algorithm to find the cluster to which the data belongs, and then apply the model of that cluster to calculate the predicted value. The experiment proves that the multi-model filling method proposed in this study is better than the existing filling algorithms in terms of root mean square error.

关键词： Missing Value Multiple Regression Analysis Artificial Neural Network k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Predictive Maintenance in Twin Screw Air Compressors through Unsupervised Learning 25

Predictive Maintenance in Twin Screw Air Compressors through...

引用

25th International Carpathian Control Conference (ICCC)

作者： Zanoli, Silvia Maria Hancha, Mahmoud Sfar Farooq, Ali Mir Pepe, Crescenzo Univ Politecn Marche DII Ancona AN Italy MGA Automat Falconara Mma AN Italy

ISBN: (纸本)9798350350708;9798350350715

A predictive maintenance module for oil-injected twin screw compressors is proposed in the present paper. Oil-injected twin screw compressors are widely used in the pneumatic drive industry and their maintenance represents an important issue. In fact, periodic maintenance policies are exploited in this field;this practice can conduct to a decrease of the efficiency of the plant units where these devices are installed. In order to solve this problem, an unsupervised learning approach is proposed in order to design a predictive maintenance module. Reliable and significant data are acquired through an ad hoc data acquisition and storage system, based on Industry 4.0 principles. Data analysis represented a first crucial step for the exploitation of unsupervised learning methods. Three different operating conditions were taken into account, associated to the compressor's oil degradation. Satisfactory results in terms of accuracy were obtained in the tests of the developed module on real data.

关键词： twin screw air compressors predictive maintenance Maintenance 4.0 Industry 4.0 unsupervised learning k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Has the public habituated to the haze in China?

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2022年第15期29卷 21396-21411页

作者： Wang, Xinxin Chen, Nan Shi, Xingmin Shaanxi Normal Univ Sch Geog & Tourism Xian 710119 Peoples R China

The concept of haze habituation was proposed based on haze perception and behavior in this paper. This study employed factor analysis and Potential Conflict Index (PCI) to analyze the dimensions, degrees, and internal differences of the public's haze habituation. Then, k-means clustering algorithm was applied to classify the public into four categories. The entropy method was used to quantitatively evaluate the public's haze habituation, and the natural breakpoint method was used to grade it into five levels. Finally, an ordered logistic regression model was chosen to analyze the influencing factors of the public's haze habituation. The results indicate that: (1) The public's haze habituation can be measured from five dimensions: protective behavior, haze reduction behavior, haze attention, life impact perception, and health impact perception. The public had the same views on protective behavior, haze reduction behavior, life impact perception, and health impact perception. However, there is a wide divergence among the public on the haze attention;(2) Based on the above five dimensions, the public can be divided into the protective sensitive group, attention sensitive group, health sensitive group, and environmental protection sensitive group;(3) Generally, the public has a low haze habituation where the protective behavior, haze reduction behavior, and health impact perception are the crucial elements;(4) Gender, self-health assessment, and travel mode have a significant positive impact on the public's haze habituation, respectively. Age, the family with elders or children, and annual family income have a significant negative impact on the public's haze habituation, respectively.

关键词： Haze Perception Potential Conflict Index (PCI) k-means clustering algorithm Natural breakpoint method China

来源：评论

学校读者我要写书评

暂无评论

New clustering Techniques of Node Embeddings Based on Metaheuristic Optimization algorithms 13th

New Clustering Techniques of Node Embeddings Based on Metahe...

引用

13th International Conference on Large-Scale ScientificComputations (LSSC)

作者： Alihodzic, Adis Chahin, Malek Cunjalo, Fikret Univ Sarajevo Dept Math Zmaja Bosne 33-35 Sarajevo 71000 Bosnia & Herceg

ISBN: (纸本)9783030975494;9783030975487

Node embeddings present a powerful method of embedding graph-structured data into a low dimensional space while preserving local node information. clustering is a common preprocessing task on unsupervised data utilized to get the best insight into the input dataset. The most prominent clustering algorithm is the k-means algorithm. In this paper, we formulate clustering as an optimization problem using different objective functions following the idea of searching for the best fit centroid-based cluster exemplars. We also apply several nature-inspired optimization algorithms since the k-means algorithm is trapped in local optima during its execution. We demonstrate our cluster frameworks' capability on several graph clustering datasets used in node embeddings and node clustering tasks. Performance evaluation and comparison of our frameworks with the k-means algorithm are demonstrated and discussed in detail. We end this paper with a discussion on the impact of the objective function's choice on the clustering results.

关键词： Graph embedding Node embeddings clustering Community detection Metaheuristics k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine learning approach in mortality rate prediction for hemodialysis patients

引用

COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING 2022年第1期25卷 111-122页

作者： Radovic, Nevena Prelevic, Vladimir Erceg, Milena Antunovic, Tanja Univ Montenegro Elect Engn Dept Podgorica Montenegro Clin Ctr Montenegro Clin Nephrol Podgorica Montenegro Clin Ctr Montenegro Ctr Lab Diagnost Podgorica Montenegro

kernel support vector machine algorithm and k-means clustering algorithm are used to determine the expected mortality rate for hemodialysis patients. The national nephrology database of Montenegro has been used to conduct this research. Mortality rate prediction is realized with accuracy up to 94.12% and up to 96.77%, when a complete database is observed and when a reduced database (that contains data for the three most common basic diseases) is observed, respectively. Additionally, it is shown that just a few parameters, most of which are collected during the sole patient examination, are enough for satisfying results.

关键词： Mortality rate prediction support vector machine algorithm k-means clustering algorithm chronic kidney disease

来源：评论

学校读者我要写书评

暂无评论

A parallel strategy for predicting the quality of welded joints in automotive bodies based on machine learning

引用

JOURNAL OF MANUFACTURING SYSTEMS 2022年 62卷 636-649页

作者： Chen, Geng Sheng, Buyun Luo, Ruipin Jia, Pengzhen Wuhan Univ Technol Sch Mech & Elect Engn Wuhan 430070 Peoples R China

Due to the complexity of the resistance spot welding process, it is still a challenge to accurately know the operating status of the welding robot under the current parameter settings and to assess the welding quality of electrode caps under different types of plates in real time with large data sizes. To solve this problem, this paper classifies the overall data set and proposes a parallel strategy method for predicting the quality of weld joints using machine learning for subsets of the data with different distribution patterns. Firstly, the PCA dimensionality reduction model was used to set the number of principal components to reduce the dimensionality of the welding process feature value dataset and reduce the difficulty of classifying the data subgroups, and the elbow method was used to set the number of clustering centers to complete the classification of the sub-datasets by applying the k-means model on the basis of the dimensionality reduction data. Finally, the feature parameters of each sub-dataset are used as input for machine learning, and a parallel prediction strategy for weld joint quality is developed based on the data distribution characteristics of each sub-dataset. The test results show that the model in this paper outperforms the static BP neural network in predicting the quality of all types of welded joints, the machine learning parallel strategy tailored to the characteristics of the data population works well with more complexly distributed welded big data. This paper provides accurate and effective estimation of body resistance welding condition, which can provide some guidance for online inspection of body resistance spot welding quality in automotive production lines.

关键词： Resistance spot welding Quality prediction Principal component analysis (PCA) k-means clustering algorithm Back propagation neural network (BPN) Parallel strategies

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal evolution law and output prediction of construction waste in the People's Republic of China

引用

WASTE MANAGEMENT & RESEARCH 2022年第2期40卷 174-184页

作者： Zhao, Likun Liu, Yanqi Tian, Junsen North China Univ Technol Sch Civil Engn 5 Jinyuanzhuang Rd Beijing 100144 Peoples R China

Based on the relevant data of construction waste (CW) in the People's Republic of China (PRC) from 2010 to 2018, this study applied k-means clustering algorithm and grey prediction methods to systematically investigate the spatiotemporal characteristic distribution and provincial clustering of CW in the PRC, and predicted the annual output of CW in the next five years from the scientific perspective. Results showed that the annual output of CW in the PRC displayed an overall trend of "rising first and then falling" and "being high in the middle east and low in the northwest," and the areas with obvious agglomeration gradually spread from the west to the middle and eastern regions. The law of development was consistent with the goals of the Chinese government to promulgate urban agglomeration development policies, prefabricated building encouragement policies, and CW management regulations. In the next five years, the annual output of CW in the PRC will increase by a small margin. Thus, all aspects of CW resource management should be conducted in a planned and step-by-step manner.

关键词： Chinese construction waste spatiotemporal characteristics k-means clustering algorithm output prediction

来源：评论

学校读者我要写书评

暂无评论

Research on the Relationship between Fuel Economy and Driving Behavior of Heavy-Duty Vehicles 23

Research on the Relationship between Fuel Economy and Drivin...

引用

23rd COTA International Conference of Transportation Professionals (CICTP) - Innovation-Empowered Technology for Sustainable, Intelligent, Decarbonized, and Connected Transportation

作者： Zhang, Shuai-Qi Xu, Ting Peng, Chong Wang, Jing-Tao Wang, Shu-Zhen Changan Univ Xian Coll Transportat Engn Xian Peoples R China Changan Univ Xian Coll Transportat Engn Dept Transportat Xian Peoples R China

ISBN: (数字)9780784484869

ISBN: (纸本)9780784484869

In order to study the influence of heavy-duty vehicle driving behavior on fuel economy, this paper collected the on-board diagnostics (OBD) data of vehicle driving on a circular urban arterial road. After data preprocessing, the kinematic segments were divided, and the characteristic parameter values were defined. Principal component analysis was used to reduce the dimension of the values. Then k-means clustering algorithm was carried out to classify driving behavior based on traffic and operating conditions. The cumulative fuel consumption and running time under the two conditions were analyzed. Finally, the abnormal driving behavior is defined, and the regression analysis of its impact on fuel consumption was carried out. The research shows that different traffic and operating conditions have a direct impact on vehicle fuel consumption per hundred kilometers, which can comprehensively evaluate the relationship between vehicle driving behavior and fuel economy.

关键词： Driving behavior Fuel economy kinematic segment characteristic value Principal component analysis k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Ocean Adaptation Zone Classification Prediction Model Based on Gravity Anomaly data 2

Research on Ocean Adaptation Zone Classification Prediction ...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： He, Chenkai He, Hongyi Chen, Yiru Dalian Polytechnic University School of Food Science and Technology Liaoning Dalian China Dalian Polytechnic University School of Biological Engineering Liaoning Dalian China

ISBN: (纸本)9798350317558

This paper aims to propel the development of the marine economy by proposing a crucial underwater navigation adaptation zone classification prediction technique. Firstly, through meticulous processing of gravity anomaly benchmark data, the maritime area is delineated, and adaptability is calibrated to ensure the navigation precision of underwater vehicles. Using the k-means classification model, the data is refined and categorized into zones of medium-high accuracy, low accuracy, medium accuracy, and high accuracy. Subsequently, specific feature attribute indicators are selected, and an effective regional adaptation zone classification prediction model system, denoted as F, is established to ensure navigation accuracy within regions with different gravity anomaly feature distributions. Finally, transferability predictions are performed on new gravity anomaly data to explore the model's applicability to novel data, validating the robustness and generalization capability of the model and fostering further advancements in underwater navigation technology. This research holds significant importance for driving the marine economy forward. © 2024 IEEE.

关键词： Data-driven interpolation processing k-means clustering algorithm Python SVM algorithm

来源：评论

学校读者我要写书评

暂无评论

Novel fusion of color balancing and superpixel based approach for detection of tomato plant diseases in natural complex environment

引用

JOURNAL OF kING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第6期34卷 3506-3516页

作者： khan, Saiqa Narvekar, Meera DJ Sanghvi Coll Engn Mumbai India

A large number of countries depend on agriculture. However, the biggest challenge for farmers is the plant-related diseases. The most observed part of the plant is leaf but the segmentation of a diseased lesion leaf image suffers from uneven illumination and cluttered complex natural environment problems. To overcome these problems, the proposed methodology is based on the fusion of color balancing and superpixel. First, the input image transforms into a color-balanced image to eliminate the effects of uneven illumination. Second, compact regions are created from the transformed image using superpixel operation and the empirically derived threshold is applied on Histogram of Gradients (HOG) and color channels of superpixel to separate the unwanted background from leaf image. k-means clustering is applied to find a diseased infected image. An extended form of HOG, Pyramid of HOG(PHOG) with Gray Level Co-occurrence Matrix (GLCM) features are used to represent a diseased infected part. Finally, different classifiers are compared and Random Forest (RF) is selected to classify diseases. To assess the robustness of the proposed method, an experiment is conducted to test its accuracy effectively on natural images acquired from various farms, downloaded images from the Internet and Plant-Village color dataset. Results indicate that the proposed method achieved an accuracy of 93.12% on a combined dataset using cross-validation to show that method is effective to classify diseases in the presence of a cluttered background. The proposed system is compared with ALDD method (Dhaygude and kumbhar, 2013), MVBPDR (Habib et al., 2018), AIMSD (Araujo and Peixoto, 2019) and CCF (Ma et al., 2017). The novelty of the proposed system lies in the fact that the proposed segmentation is effective for all the varied datasets and it is evaluated by True Positive Rate (TPR), False Positive Rate (FPR), False Negative Rate (FNR), Positive Prediction Value (PPV), False Discovery Rate (FDR), Accur

关键词： Tomato disease detection Color balancing Superpixel clustering k-means clustering algorithm Gray Level Co-occurrence Matrix (GLCM) Pyramid of histograms of orientation gradients (PHOG)

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：