检索结果-内蒙古大学图书馆

Improve customer churn prediction through the proposed PCA-PSO-k means algorithm in the communication industry (vol 79, pg 6871, 2023)

引用

JOURNAL OF SUPERCOMPUTING 2023年第13期79卷 15212-15212页

作者： Sadeghi, Maryam Dehkordi, Mohammad Naderi Barekatain, Behrang khani, Naser Islamic Azad Univ Dept Management Najafabad Branch Najafabad Iran Islamic Azad Univ Fac Comp Engn Najafabad Branch Najafabad Iran Islamic Azad Univ Big Data Res Ctr Najafabad Branch Najafabad Iran

Customer churn prediction is one of the areas in Customer Relationship Management that differentiates loyal customers from factors that have a negative impact on business growth. Hence, various machine learning-based methods have been developed by researchers to accurately predict customer churn. However, high dimensionality and low prediction accuracy are problems in identifying averse customers. This paper presents a new system called PCA-PSO-k means algorithm, which combines three algorithms: principal component analysis (PCA) for data set feature reduction, k means algorithm for classification, and particle swarm optimization (PSO) algorithm to optimize k means in providing initial centroids. The experimental results in the data set of one of the fixed internet providers in Isfahan Province show the improvement of the accuracy of customer churn prediction. The proposed system has an accuracy of 99.77%, a sensitivity of 75%, a specificity of 99.81% and a correlation coefficient of 0.443 ± 0.271. Found.

关键词： CRM Customer churn prediction Data mining Principal component analysis k means algorithm PSO algorithm

来源：评论

学校读者我要写书评

暂无评论

Centroid 360: An Enhanced Centroid Initialization Method for k means algorithm

Centroid 360: An Enhanced Centroid Initialization Method for...

引用

作者： Jovy Jay D.Cabrera Ariel M.Sison Ruji P.Medina Graduate Programs Technological Institute of the Philippines2. School of Computer Studies Emilio Aguinaldo College3. Dean Graduate Programs Technological Institute of the Philippines

A weakness of the classic k means algorithm uses a random method for initializing centroids since it will produce random results that is unpredictable making it unreliable. The enhanced k means algorithm uses an innovative solution through a new method called Centroid 360 that is consistent and uses radius and 360 degrees to distribute centroid positions while at the same time separating the initial centroids from each other resulting into less pull from clustering similar datapoints against each other which results better number of iterations making the enhanced k means algorithm for initializing centroids more accurate, more efficient and faster. The new algorithm is tested using popular synthetic and real datasets available that can be found on the internet. The research is a success as the enhancement to the algorithm is consistent, uses less iterations and provides 61.21% more efficiency, 45.57% faster when it comes to speed and 14.66%more accurate than the traditional k means using random initialization method.

关键词： Machine Learning Clustering k means algorithm Centroid Initialization

来源：评论

学校读者我要写书评

暂无评论

Enhancing k means by Unsupervised Learning using PSO algorithm

Enhancing K means by Unsupervised Learning using PSO Algorit...

引用

IEEE International Conference on Computing, Communication and Automation (ICCCA)

作者： Gupta, Aishwarya Pattanaik, Vishwajeet Singh, Mayank Krishna Engn Coll Dept Comp Sci & Engn Ghaziabad India Tallinn Univ Technol Dept Software Sci Tallinn Estonia

ISBN: (纸本)9781509064717

Data Clustering in Data Mining is a domain which never gets out of focus. Clustering a data was always an easy task but achieving the required accuracy, precision and performance was never so easy. k means being an archaic clustering algorithm got tested and experimented thousands of times with variety of datasets and other combination of algorithm due to its robustness and simplicity but what this algorithm proposed was not suggested before. It used k means algorithm for the evaluation and validation purposes whereas optimization of the data is done with the help of Particle Swarm Optimization algorithm. The drawbacks of k means mainly its local convergence property and initializing number of clusters at an early stage has aroused the process of working on this algorithm. So, for attaining the global convergence the Swarm Intelligence is preferred over Genetic algorithm and many other techniques and for the latter one we combined two functions one of them helps in knowing the number of clusters which are optimal for the particular dataset and the other one validates the results using another function and compares the various metrics which will define the goodness and fitness of an algorithm. In one line the complete overview of the proposed algorithm can be described as 'Evaluating the data using an Evalcluster Function, performing Validation with the help of an Evaluate Function of the k means and giving the final touch of Optimizing the data by k means PSO algorithm'. The algorithm is tested for over 4 datasets available in UCI Repository and the results were unexpectedly great.

关键词： Data Mining Clustering k means algorithm Calinski-Harabasz Index Genetic algorithm Particle Swarm Optimization(PSO) k means PSO

来源：评论

学校读者我要写书评

暂无评论

Integrating Curriculum Learning With k-means: A Data-Centric Approach to Faster Clustering

引用

IT PROFESSIONAL 2024年第5期26卷 36-46页

作者： Majeed, Abdul Hwang, Seong Oun Gachon Univ Dept Comp Engn Seongnam 13120 South Korea

k-means clustering is a very popular method that groups n observations into k clusters based on the nearest mean, whereas each observation serves as the prototype of a cluster. Although k-means yields desirable results in most cases, the computing overhead is very high even for modest-size datasets, which makes it unsuitable for larger datasets. To lower computing overhead without degrading performance, in this article, we propose and implement a curriculum learning (CL)-integrated k-means clustering method for efficiently clustering observations. In our method, the data to be clustered via k-means are evaluated beforehand and sorted based on complexity using the CL approach. By applying CL, the data portion that is naturally clustered is identified and bypassed by k-means so that only some complex portions of the data undergo processing, leading to a significant reduction in computing overhead.

关键词： Databases Clustering Methods Prototypes Clustering algorithms Benchmark Testing Complexity Theory Artificial Intelligence Curriculum Learning Computation Time Big Data Data Mining Machine Learning Techniques Unsupervised Learning Uneven Distribution Data Clustering Partial Data Benchmark Datasets Cluster Centers k means algorithm Portion Of Data Clustering Process High Coherence knowledge Discovery Choice Scenarios Clusters Of Data Points Unnecessary Computation Results In Most Cases Dominant Values Davies Bouldin Index Real Life Datasets Clusters Of Points Feature Classification Dataset Characteristics Size Classes Numerous Features Distance Calculation Clustering Effect

来源：评论

学校读者我要写书评

暂无评论

Enhancing Aluminum Extrusion Quality via AI-Driven Temperature Prediction in Cyberphysical Systems for Industry 4.0

引用

IT PROFESSIONAL 2024年第5期26卷 47-54页

作者： Chou, Yao-Hsin Chen, Chien-Ming Lai, Yun-Ting kuo, Shu-Yu Jiang, Yu-Chi Tseng, Fan-Hsun Natl Chi Nan Univ Dept Comp Sci & Informat Engn Puli 54561 Taiwan Natl Taiwan Univ Dept Elect Engn Taipei 10617 Taiwan Princeton Univ Dept Elect Engn Princeton NJ 08544 USA Natl Cheng Kung Univ Dept Comp Sci & Informat Engn Tainan 70101 Taiwan

Aluminum extrusion is pivotal in industrial manufacturing for ubiquitous daily products, and the extrusion process determines the profile quality. This study is the first to build a cyberphysical system (CPS) for aluminum extrusion that autonomously predicts profile temperatures by collecting sensor data, aiming to optimize the industrial process and boost productivity. The proposed artificial intelligence-driven CPS system excels at data collection from sensors, real-time preprocessing of extensive datasets, and leverages the eXtreme gradient boosting (XGBoost) method for accurate temperature prediction in real-world scenarios. This implementation demonstrates its practical adaptability across diverse extrusion methods. Experimental outcomes validate the model's precise temperature identification. As a result, this system can significantly bolster profile temperature and quality maintenance in aluminum extrusion, notably enhancing efficiency and reducing cost.

关键词： Temperature Measurement Temperature Sensors Productivity Adaptation Models Temperature Distribution Aluminum Predictive Models Real Time Systems Maintenance Fourth Industrial Revolution Cyber Physical Systems Temperature Prediction Aluminum Extrusion Prediction Accuracy Friction Hardness Manufacturing Process Internet Of Things Real Time Data Critical Temperature Gradient Boosting XG Boost Extrusion Process Industrial Internet Of Things Extrusion Temperature Pyrometer Physical Equipment Abnormal Situations Training Set Tensile Strength Mean Absolute Percentage Error Highest Pressure Physical Sensations Automatic Processing Shape Of Profile k means algorithm Decision Tree Real World Processes Temperature Monitoring

来源：评论

学校读者我要写书评

暂无评论

A computer-based statistical pattern recognition for Doppler spectral waveforms of intracranial blood flow

引用

COMPUTERS IN BIOLOGY AND MEDICINE 1996年第1期26卷 53-63页

作者： Miao, JW Benkeser, PJ Nichols, FT MED COLL GEORGIA DEPT NEUROLAUGUSTAGA 30912

A computer-based statistical pattern recognition system has been developed for the analysis of transcranial Doppler (TCD) spectral waveforms of the intracranial middle cerebral artery with varying degrees of increased intracranial pressure. This system extracts multidimensional features from TCD waveforms and performs a cluster analysis of those features. The system can automatically recognize the pattern of spectral waveform and classify it as a normal, abnormal, or borderline subclass of TCD spectral waveform. An optimum decision function was generated based on the Bayes Gaussian classifier. The accuracy of the Bayes Gaussian model the spectral waveforms reaches 100% by estimating posterior probability and using the resubstituting method of estimating misclassification in the training TCD data.

关键词： Pattern recognition cluster analysis canonical discriminant technique k means algorithm Bayes classifier Doppler wave

来源：评论

学校读者我要写书评

暂无评论

An Enhancement in Automatic Seed Selection in Breast Cancer Ultrasound Images using Texture Features 5

An Enhancement in Automatic Seed Selection in Breast Cancer ...

引用

International Conference on Advances in Computing, Communications and Informatics (ICACCI)

作者： Panigrahi, Lipismita Verma, keshri Singh, Bikesh kumar NIT Raipur Dept Comp Applicat Raipur Madhya Pradesh India NIT Raipur Dept Biomed Engn Raipur Madhya Pradesh India

ISBN: (纸本)9781509020287

Automatic seed selection is an important and crucial step toward the boundary detection in ultrasound B-scan images. This paper focuses on a methodological framework that can automatically detect a seed point of an ultrasound image by using texture features. Based on the selected seeds of cluster the ultrasound images are segmented using active contour, k-means and Otsu methods. The comparative analysis of these segmentation techniques is also reported. The proposed method is applied on 116 ultrasound images in which 45 are benign cases and 71 malignant cases. The quantitative experimental results show that the proposed method can successfully find an accurate seed point based on texture features and it has the ability to segment the image with high accuracy of 89.65 %. The proposed method is faster and performs more accurate segmentation than existing algorithms.

关键词： Active contour k means algorithm Otsu Method Segmentation and Automatic seed selection

来源：评论

学校读者我要写书评

暂无评论

GAIT RECOGNITION-A NOVEL APPROACH TO QUALITY IMPROVEMENT IN HUMAN SILHOUETTES

GAIT RECOGNITION-A NOVEL APPROACH TO QUALITY IMPROVEMENT IN ...

引用

1st International Conference on Advancements in Automation and Control (ICAAC)

作者： Fathima, S. M. H. Sithi Shameem Banu, R. S. D. Wahida Syed Ammal Engn Coll Dept ECE Rameshwaram Tamil Nadu India Govt Coll Engn Salem India

ISBN: (纸本)9783038351245

This paper proposes a robust algorithm for the quality improvement in human silhouettes, to improve the gait recognition percentage of a person. In silhouette based gait recognition approach, the presence of incomplete and noisy silhouettes has a direct impact on recognition performance. Using blob detection, initially the incomplete silhouettes are identified. Fusion of frame difference energy image with dominant energy image of a silhouette along with a morphological filter output, preserve the kinetic and kinematic information to make incomplete silhouette into a high quality and a complete silhouette. The results prove that the resultant silhouettes are well suited for human gait recognition algorithm with improved variance. The silhouette database is taken from CASIA database. (Institute of Automation, Chinese Academy of Sciences).

关键词： FDEI k means algorithm DEI Morphological filter Silhouettes

来源：评论

学校读者我要写书评

暂无评论

Towards Predictive Maintenance and Management in Rail Sector: A Clustering Approach

Towards Predictive Maintenance and Management in Rail Sector...

引用

International Conference on Recent Trends in Information Technology (ICRTIT)

作者： Antony, J. John Victor Nasira, G. M. South Western Railway Training Ctr Bangalore Karnataka India Chikkanna Govt Arts Coll Tirupur Tamil Nadu India

ISBN: (纸本)9781479910243

It is accepted beyond doubt that the back bone of mass transportation in India is Railways and it is regarded as the lifeline of the nation. Indian Railways is using various information technology based systems to maintain and manage its infrastructural resources, leading to generation and accumulation of voluminous data. The data captured is expected to possess hidden meaning and trend which, if properly explored and modelled, can aid in implementing the new paradigm called Predictive Maintenance and Management. The thrust to usher in the new paradigm amply manifests in its Vision 2020 statement, too. The paper aims to showcase a methodology using Clustering, a Data Mining Technique that can bring in a maintenance plan built upon the predictive behaviour exhibited by failure data. The model outlined here has been tested on actual failure data pertaining to passenger carrying vehicles of trains.

关键词： Data Mining Pattern Analysis Railways Data Analysis Data Description Transportation Clustering k means algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on prepaid account financing model based on embedded system and Internet of Things

引用

MICROPROCESSORS AND MICROSYSTEMS 2021年 82卷 103935-103935页

作者： Zhang, Xiaoyi Wang, Yongsheng TongLing Univ Sch Accounting Tongling 244061 Anhui Peoples R China TongLing Univ Sch Math & Comp Sci Tongling 244061 Anhui Peoples R China

Internet of Things (IoT) network interconnection to create objects and things will play the Internet to play an active role in the global network in the future. For the Internet of Things, which is widely adopted through funding models, it must be trusted in the IoT security infrastructure. Efficiently and Securely IoT is very important to define how each other can communicate with remote servers and get Exchange account information. Prepayments for effective financial management and an important choice for financial IoT for service providers and customers. However, it must be supported by real-time credit checking and costing. Internet resources are consumed by these real-time action stuff providers and impose high costs on the old system. To solve this problem, to propose the k means algorithm scalable accounting solutions, where the user is hosted each occupies a prepaid account, constitute the components of embedded systems. Based on each of our prepaid billing components' supervision, it is at the same time consumed by the embedded system of all services, based on the calculation of the service packages consumed by the customer. Prepaid accounts are reassigned when the customer had sufficient credit to supplement their use and are allocated based on IoT services' consumption. This work aims to reduce the cost of pre-paid services and ensure that service delivery is not to interfere with the charging unit. Also, embedded systems' theoretical and experimental analysis shows that this work can store long-lived services on the Internet of Things to provide inexpensive accounting solutions.

关键词： k means algorithm Embedded systems Internet of Things Financial management Prepaid accounting system

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：