使用神经分析网络进行有条件的物理研究课程分析和映射

Gravity Jurnal Ilmiah Penelitian dan Pembelajaran Fisika Pub Date : 2022-09-30 DOI:10.26877/jp2f.v13i2.12979

Eva Gusmira, Muhammad Kukuh, Arif Ma’rufi

{"title":"使用神经分析网络进行有条件的物理研究课程分析和映射","authors":"Eva Gusmira, Muhammad Kukuh, Arif Ma’rufi","doi":"10.26877/jp2f.v13i2.12979","DOIUrl":null,"url":null,"abstract":"This study aims to analyze and map the conditional courses at the Tadris Physics Study Program, Faculty of Tarbiyah and Teacher Training, Sulthan Thaha Saifuddin State Islamic University Jambi. This research is an applied science research, data analysis using quantitative descriptive technique. The data is in the form of documenting the value of the 2019/2020 Tadris Physics Study Program students. The research sample consisted of 11 sample subjects from 19 population subjects. The data is processed using Backpropagation Neural Network with Python programming language. Validation and accuracy of prediction results using Mean Absolute Percentage Error and determinant coefficient R Square. The prediction results of conditional courses obtained are accurate and valid with MAPE values <10% (very good) and R Square values close to 1. This study shows that the mapping of prerequisite courses set by the study program is appropriate, except for Basic Physics Courses. 2 (R 0.216) and Mathematics Physics Course I (R 0.50) require additional other prerequisite courses.Keywords: mapping; conditional courses, backpropagation neural network","PeriodicalId":33966,"journal":{"name":"Gravity Jurnal Ilmiah Penelitian dan Pembelajaran Fisika","volume":"99 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Analisis dan Pemetaan Mata Kuliah Bersyarat Program Studi Fisika Menggunakan BackPropagation Neural Network\",\"authors\":\"Eva Gusmira, Muhammad Kukuh, Arif Ma’rufi\",\"doi\":\"10.26877/jp2f.v13i2.12979\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study aims to analyze and map the conditional courses at the Tadris Physics Study Program, Faculty of Tarbiyah and Teacher Training, Sulthan Thaha Saifuddin State Islamic University Jambi. This research is an applied science research, data analysis using quantitative descriptive technique. The data is in the form of documenting the value of the 2019/2020 Tadris Physics Study Program students. The research sample consisted of 11 sample subjects from 19 population subjects. The data is processed using Backpropagation Neural Network with Python programming language. Validation and accuracy of prediction results using Mean Absolute Percentage Error and determinant coefficient R Square. The prediction results of conditional courses obtained are accurate and valid with MAPE values <10% (very good) and R Square values close to 1. This study shows that the mapping of prerequisite courses set by the study program is appropriate, except for Basic Physics Courses. 2 (R 0.216) and Mathematics Physics Course I (R 0.50) require additional other prerequisite courses.Keywords: mapping; conditional courses, backpropagation neural network\",\"PeriodicalId\":33966,\"journal\":{\"name\":\"Gravity Jurnal Ilmiah Penelitian dan Pembelajaran Fisika\",\"volume\":\"99 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Gravity Jurnal Ilmiah Penelitian dan Pembelajaran Fisika\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.26877/jp2f.v13i2.12979\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Gravity Jurnal Ilmiah Penelitian dan Pembelajaran Fisika","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.26877/jp2f.v13i2.12979","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

本研究旨在分析和绘制苏尔坦塔哈赛夫丁国立伊斯兰大学占比分校塔比耶教师培训学院塔比里斯物理研究项目的条件课程。本研究是一项应用科学研究，数据分析采用定量描述技术。数据是以记录2019/2020年塔德里斯物理研究项目学生价值的形式。研究样本由19个人口样本中的11个样本组成。数据处理采用Python编程语言的反向传播神经网络。使用平均绝对百分比误差和决定系数R平方的预测结果的验证和准确性。得到的条件课程预测结果准确有效，MAPE值<10%(非常好)，R平方值接近1。本研究表明，除了基础物理课程2 (R 0.216)和数学物理课程1 (R 0.50)需要额外的其他先决条件课程外，学习计划设置的先决条件课程映射是适当的。关键词:映射;条件课程，反向传播神经网络

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Analisis dan Pemetaan Mata Kuliah Bersyarat Program Studi Fisika Menggunakan BackPropagation Neural Network

This study aims to analyze and map the conditional courses at the Tadris Physics Study Program, Faculty of Tarbiyah and Teacher Training, Sulthan Thaha Saifuddin State Islamic University Jambi. This research is an applied science research, data analysis using quantitative descriptive technique. The data is in the form of documenting the value of the 2019/2020 Tadris Physics Study Program students. The research sample consisted of 11 sample subjects from 19 population subjects. The data is processed using Backpropagation Neural Network with Python programming language. Validation and accuracy of prediction results using Mean Absolute Percentage Error and determinant coefficient R Square. The prediction results of conditional courses obtained are accurate and valid with MAPE values <10% (very good) and R Square values close to 1. This study shows that the mapping of prerequisite courses set by the study program is appropriate, except for Basic Physics Courses. 2 (R 0.216) and Mathematics Physics Course I (R 0.50) require additional other prerequisite courses.Keywords: mapping; conditional courses, backpropagation neural network

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Gravity Jurnal Ilmiah Penelitian dan Pembelajaran Fisika

自引率

0.00%

发文量

审稿时长

8 weeks