{"title":"用于脑卒中分类的数据挖掘算法——决策树迭代Dechotomecur 3(ID3)","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":"{\"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}","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}
Data Mining Algorithm Decision Tree Itterative Dechotomiser 3 (ID3) for Classification of Stroke
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%.