Scholarlink

Technology has been developing faster than expected since all the applications are dependent on education systems only. There are several updated software and developments in programming and machines that are most applicable to education to improve the industry, offices, and much more. Enhancing the studies in schools and colleges using course improvement and learning platforms in universities is an important role for everyone. Involving students in offline methods of observation sometimes fails such that platforms like virtual learning are also involved in education. Existing applications such as Coursera, Geeks, and Tutorial Point are some of the examples. Leveraging web development is facing information security issues such as cyberattacks, phishing, and misuse of wrong recommendation systems. To overcome this limitation as Student Feedback and Academic Performance Data leakage as Information Security issues Novel Name Entity Recognition (NNER), a Natural Language Processing model is proposed here to initially handle the identification of individual categories based on the person, link, event or keywords, and so on. Secondly, the framework as a traditional machine learning model lacks feature extraction such that the classification of necessary classes is identified using NER_Convolutional Neural Network (CNN) which produces 92.4% accuracy and also includes performance metrics of precision and recall which implies informational security with the proposed model has efficient security access in the educational recommendation system.

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

Accurate Prediction of Ontology-Based Security in Education Using Novel Name Entity Relation in Combination with CNN Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • T. Devi,
  • N. Deepa

摘要

Technology has been developing faster than expected since all the applications are dependent on education systems only. There are several updated software and developments in programming and machines that are most applicable to education to improve the industry, offices, and much more. Enhancing the studies in schools and colleges using course improvement and learning platforms in universities is an important role for everyone. Involving students in offline methods of observation sometimes fails such that platforms like virtual learning are also involved in education. Existing applications such as Coursera, Geeks, and Tutorial Point are some of the examples. Leveraging web development is facing information security issues such as cyberattacks, phishing, and misuse of wrong recommendation systems. To overcome this limitation as Student Feedback and Academic Performance Data leakage as Information Security issues Novel Name Entity Recognition (NNER), a Natural Language Processing model is proposed here to initially handle the identification of individual categories based on the person, link, event or keywords, and so on. Secondly, the framework as a traditional machine learning model lacks feature extraction such that the classification of necessary classes is identified using NER_Convolutional Neural Network (CNN) which produces 92.4% accuracy and also includes performance metrics of precision and recall which implies informational security with the proposed model has efficient security access in the educational recommendation system.