Scholarlink

The Indian education system at the secondary level requires the student to choose the subject/stream of their interest to pursue at the higher secondary level. Students must carefully choose their subject/stream because it will influence how far their careers progress. Most subjects/streams are unable to alter later in one’s career. Selecting subjects inappropriately due to parental influence, insufficient knowledge, and other issues may limit performance in the selected field. Recommendations for subject/stream selection based on data gathered from top researchers in their area, as well as information on students’ interests, family background, prior education, and other criteria, might increase career success. This study employed data from many institutions and students from two different streams for teaching and evaluation purposes. Five ML methods were utilized in the study. When compared against other cutting-edge machine learning algorithms, the newly designed MHC-CNN method outperformed them all (94.86%). The created approach may be expanded and used for various subject/stream selections throughout the world.

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

MHC-CNN: A CNN Framework for Stream Selection in Secondary Education Using Modified Huffman Coding

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Kapil Sethi,
  • Rohit,
  • Abhineet Anand

摘要

The Indian education system at the secondary level requires the student to choose the subject/stream of their interest to pursue at the higher secondary level. Students must carefully choose their subject/stream because it will influence how far their careers progress. Most subjects/streams are unable to alter later in one’s career. Selecting subjects inappropriately due to parental influence, insufficient knowledge, and other issues may limit performance in the selected field. Recommendations for subject/stream selection based on data gathered from top researchers in their area, as well as information on students’ interests, family background, prior education, and other criteria, might increase career success. This study employed data from many institutions and students from two different streams for teaching and evaluation purposes. Five ML methods were utilized in the study. When compared against other cutting-edge machine learning algorithms, the newly designed MHC-CNN method outperformed them all (94.86%). The created approach may be expanded and used for various subject/stream selections throughout the world.