Clustering algorithms are one of the modern techniques that stem from unsupervised machine learning. They work to divide data into subgroups based on the degree of similarity of these data to each other. Clustering algorithms are classified into two main categories based on how data is assigned to groups, which are hard clustering and soft clustering. These algorithms are used in many applications such as security, health, finance, and many others. They are frequently used in communication networks. Clustering algorithms face many challenges, the most prominent of which are determining the number of clusters, high-dimensional data, calculating membership degrees, noise, and others. The paper emphasized the importance of customizing the choice of algorithm for a specific application environment to improve the efficiency and accuracy of clustering.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Clustering in Data Analysis: Comprehensive Insights into Techniques and Challenges

  • Ali Noori Gatea,
  • Haider Sh. Hashim,
  • Hamid Ali Abed AL-Asadi,
  • Didem Kıvanç Türeli,
  • Zaid Ameen Abduljabbar,
  • Vincent Omollo Nyangaresi

摘要

Clustering algorithms are one of the modern techniques that stem from unsupervised machine learning. They work to divide data into subgroups based on the degree of similarity of these data to each other. Clustering algorithms are classified into two main categories based on how data is assigned to groups, which are hard clustering and soft clustering. These algorithms are used in many applications such as security, health, finance, and many others. They are frequently used in communication networks. Clustering algorithms face many challenges, the most prominent of which are determining the number of clusters, high-dimensional data, calculating membership degrees, noise, and others. The paper emphasized the importance of customizing the choice of algorithm for a specific application environment to improve the efficiency and accuracy of clustering.