Data Mining Algorithm Decision Tree Itterative Dechotomiser 3 (ID3) for Classification of Stroke

Zunaida Sitorus, Adi Widarma
{"title":"Data Mining Algorithm Decision Tree Itterative Dechotomiser 3 (ID3) for Classification of Stroke","authors":"Zunaida Sitorus, Adi Widarma","doi":"10.24114/cess.v8i2.47970","DOIUrl":null,"url":null,"abstract":"Penyakit stroke atau cerebrovascular merupakan penyakit yang terjadi karena terputusnya suplai  pasokan darah ke suatu bagian otak sehingga mengganggu sistem syaraf pusat. Penyakit ini sangat serius dan harus segera cepat ditangani karena dapat menyebabkan salah satu kematian sesuai data WHO (World  Health  Organization)  akibat stroke terjadi 70%  kematian  dunia. Penanganan yang cepat dan tepat serta pengetahuan masyarakat akan penyakit stroke sangat dibutuhkan agar dapat segera diatasi. Perkembangan teknologi seperti Machine Learning sangat dibutuhkan karena pendekatan yang populer untuk mampu melakukan prediksi stroke dengan akurat. Algoritma Machine Learning yaitu Data Mining dengan metode Decision Tree akan diterapkan. Dalam penelitian ini, kerangka kerja dilakukan  yang bertujuan untuk menganalisis kinerja model klasifikasi metode Decision Tree menggunakan ID3 dalam bidang prediksi penyakit stroke. Dataset public yang bersumber dari kaggle dengan jumlah record sebanyak 5110 dipilih dan diterapkan untuk membangun model klasifikasi dan menguji kinerjanya serta pengujian model akan dilakukan menggunakan aplikasi RapidMiner. Uji performance untuk evaluasi model data mining dengan Confusion Matrix digunakan sebagai indikator akurasi dalam kerangka untuk mengevaluasi kinerja klasifikasi. Perbandingan nilai evaluasi model data mining dengan membagi data menjadi data training dan data testing dan menghasilkan nilai accuracy dengan proporsi 90:10 sebesar 94,72%, 80:20 sebesar 95,21%, 70:30 sebesar 95,04% dan 60:40 sebesar 94,81%. Hasilnya menunjukkan bahwa proporsi data 80:20 memiliki nilai akurasi paling besar dibandingkan dengan proporsi data yang lainnya.Stroke or cerebrovascular disease is a disease that occurs due to the interruption of the blood supply to a part of the brain that disrupts the central nervous system. This disease is very serious and must be treated immediately because it can cause one of the deaths according to WHO (World Health Organization) data due to stroke occurring 70% of world deaths. Quick and precise treatment as well as public knowledge of stroke is urgently needed so that it can be resolved immediately. Technological developments such as Machine Learning are urgently needed because of the popular approach to being able to predict strokes accurately. Machine Learning Algorithm, namely Data Mining with the Decision Tree method will be applied. In this study, a framework was carried out which aimed to analyze the performance of the Decision Tree method classification model using ID3 in the field of stroke prediction. A public dataset sourced from kaggle with a total of 5110 records is selected and applied to build a classification model and test its performance and model testing will be carried out using the RapidMiner application. Evaluation of the Confusion Matrix data mining model is used as an indicator of accuracy in a framework for evaluating classifier performance. Comparison of the evaluation value of the data mining model by dividing the data into training data and testing data. The results show that the accuracy value with the proportion of 90:10 is 94.72%, 80:20 is 95.21%, 70:30 is 95.04% and 60:40 is 94.81%.","PeriodicalId":53361,"journal":{"name":"CESS Journal of Computer Engineering System and Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CESS Journal of Computer Engineering System and Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.24114/cess.v8i2.47970","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Penyakit stroke atau cerebrovascular merupakan penyakit yang terjadi karena terputusnya suplai  pasokan darah ke suatu bagian otak sehingga mengganggu sistem syaraf pusat. Penyakit ini sangat serius dan harus segera cepat ditangani karena dapat menyebabkan salah satu kematian sesuai data WHO (World  Health  Organization)  akibat stroke terjadi 70%  kematian  dunia. Penanganan yang cepat dan tepat serta pengetahuan masyarakat akan penyakit stroke sangat dibutuhkan agar dapat segera diatasi. Perkembangan teknologi seperti Machine Learning sangat dibutuhkan karena pendekatan yang populer untuk mampu melakukan prediksi stroke dengan akurat. Algoritma Machine Learning yaitu Data Mining dengan metode Decision Tree akan diterapkan. Dalam penelitian ini, kerangka kerja dilakukan  yang bertujuan untuk menganalisis kinerja model klasifikasi metode Decision Tree menggunakan ID3 dalam bidang prediksi penyakit stroke. Dataset public yang bersumber dari kaggle dengan jumlah record sebanyak 5110 dipilih dan diterapkan untuk membangun model klasifikasi dan menguji kinerjanya serta pengujian model akan dilakukan menggunakan aplikasi RapidMiner. Uji performance untuk evaluasi model data mining dengan Confusion Matrix digunakan sebagai indikator akurasi dalam kerangka untuk mengevaluasi kinerja klasifikasi. Perbandingan nilai evaluasi model data mining dengan membagi data menjadi data training dan data testing dan menghasilkan nilai accuracy dengan proporsi 90:10 sebesar 94,72%, 80:20 sebesar 95,21%, 70:30 sebesar 95,04% dan 60:40 sebesar 94,81%. Hasilnya menunjukkan bahwa proporsi data 80:20 memiliki nilai akurasi paling besar dibandingkan dengan proporsi data yang lainnya.Stroke or cerebrovascular disease is a disease that occurs due to the interruption of the blood supply to a part of the brain that disrupts the central nervous system. This disease is very serious and must be treated immediately because it can cause one of the deaths according to WHO (World Health Organization) data due to stroke occurring 70% of world deaths. Quick and precise treatment as well as public knowledge of stroke is urgently needed so that it can be resolved immediately. Technological developments such as Machine Learning are urgently needed because of the popular approach to being able to predict strokes accurately. Machine Learning Algorithm, namely Data Mining with the Decision Tree method will be applied. In this study, a framework was carried out which aimed to analyze the performance of the Decision Tree method classification model using ID3 in the field of stroke prediction. A public dataset sourced from kaggle with a total of 5110 records is selected and applied to build a classification model and test its performance and model testing will be carried out using the RapidMiner application. Evaluation of the Confusion Matrix data mining model is used as an indicator of accuracy in a framework for evaluating classifier performance. Comparison of the evaluation value of the data mining model by dividing the data into training data and testing data. The results show that the accuracy value with the proportion of 90:10 is 94.72%, 80:20 is 95.21%, 70:30 is 95.04% and 60:40 is 94.81%.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于脑卒中分类的数据挖掘算法——决策树迭代Dechotomecur 3(ID3)
中风或脑血管疾病是一种发生的疾病,因为它停止向大脑的一部分供血,从而扰乱中枢神经系统。这种疾病非常严重,必须迅速处理,因为根据世界卫生组织(世界贸易组织)的数据,它可能导致一人死亡,因为中风占世界死亡人数的70%。需要立即克服中风疾病的快速、准确的管理和公众知识。像机器学习这样的技术发展是非常必要的,因为这是一种准确预测中风的流行方法。机器学习算法是数据挖掘与决策树相结合的方法。在本研究中,开展了一个工作框架,旨在分析使用ID3的决策树方法分类模型在中风预测领域的性能。一个由kaggle组成的公共文件(记录编号为5110)将使用RapidMiner应用程序进行选择和应用,以建立分类模型并测试其性能和模型测试。用于挖掘数据模型评估的性能测试,使用Confusion矩阵作为框架中的准确指标来评估分类性能。通过将数据划分为训练数据和数据测试来比较挖掘数据模型评估的价值,并产生90:10比率94.72%、80:20比率95.21%、70:30比率95.04%和60:40比率94.81%的准确度值。结果表明,与其他数据比率相比,80:20的数据比率具有最大的精度值。中风或脑血管疾病是一种由于大脑中扰乱中枢神经系统的部分血液供应中断而发生的疾病。根据世界卫生组织的数据,这种疾病非常严重,必须立即治疗,因为它可能导致一人死亡,中风占世界死亡人数的70%。迫切需要快速、精确的治疗以及公众对中风的了解,以便立即解决。由于能够准确预测中风的流行方法,迫切需要机器学习等技术发展。将应用机器学习算法,即数据挖掘的决策树方法。在本研究中,提出了一个框架,旨在分析使用ID3的决策树方法分类模型在中风预测领域的性能。选择一个来自kaggle的共5110条记录的公共数据集,并将其应用于建立分类模型和测试其性能,并将使用RapidMiner应用程序进行模型测试。混淆矩阵数据挖掘模型的评估被用作评估分类器性能的框架中的准确性指标。通过将数据划分为训练数据和测试数据来比较数据挖掘模型的评估值。结果表明,90:10比例的准确率为94.72%,80:20比例为95.21%,70:30比例为95.04%,60:40比例为94.81%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
40
审稿时长
4 weeks
期刊最新文献
Implementation of the Multimedia Development Life Cycle in Making Educational Games About Indonesia Data Mining Algorithm Decision Tree Itterative Dechotomiser 3 (ID3) for Classification of Stroke Implementation of Weight Aggregated Sum Product Assessment (WASPAS) on the Selection of Online English Course Platforms Usability of Brain Tumor Detection Using the DNN (Deep Neural Network) Method Based on Medical Image on DICOM Performance Comparison Analysis of Multi Prime RSA and Multi Power RSA
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1