Scholarlink

The presence of redundant data can lead to superfluous storage space utilization and delayed response times, ultimately impacting the accuracy of classification. Increasing the amount of redundant data complicates the visualization and simulation of the training set. Therefore, it is imperative to decrease the data dimension by retaining solely pertinent information. For this reason, a novel dimensionality technique which is namely levels analysis of partially ordered sets (LAPOS) is introduced in this paper. LAPOS is founded on the properties of partially ordered sets. Utilizing different artificial intelligent models on various datasets, the computational study illustrated the superior performance of LAPOS in handling medical data in comparison to other well-known approaches.

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

A Novel Dimensionality Reduction Technique Based on Levels Analysis of Partially Ordered Sets

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Elsayed Badr,
  • Ahmed Zaglol,
  • Ahmed Hagag

摘要

The presence of redundant data can lead to superfluous storage space utilization and delayed response times, ultimately impacting the accuracy of classification. Increasing the amount of redundant data complicates the visualization and simulation of the training set. Therefore, it is imperative to decrease the data dimension by retaining solely pertinent information. For this reason, a novel dimensionality technique which is namely levels analysis of partially ordered sets (LAPOS) is introduced in this paper. LAPOS is founded on the properties of partially ordered sets. Utilizing different artificial intelligent models on various datasets, the computational study illustrated the superior performance of LAPOS in handling medical data in comparison to other well-known approaches.