Stroke or cerebro-vascular accident (CVA) is a condition in which part of the brain abruptly loses its source of nutrients, oxygen and glucose, that are normally delivered to it by way of the vascular system [11]. Lubis et al. [20] explained that there are two types of stroke, ischemic and hemorrhagic. An ischemic stroke (ISC) is one in which a solid blood clot blocks the flow of blood in an artery to the brain. On the other hand, a hemorrhagic stroke (HEM) is one in which a blood vessel bursts and the blood creates pressure in the brain [20]. Furthermore, a brief stroke attack that come about less than 24 h is called Transient Ischemic Attack (TIA). For over a 1000 years, stroke has become
No abstract
The data on heart disease patients obtained from the Ministry of Health of the Republic of Indonesia in 2020 explains that heart disease has increased every year and ranks as the highest cause of death in Indonesia, especially at productive ages. If people with heart disease are not treated properly, then in their effective period a patient can experience death more quickly. Thus, a predictive model that is able to help medical personnel solve health problems is built. This study employed the Random Forest and Decision Tree algorithm classification process by processing cardiac patient data to create a predictive model and based on the data obtained, showing that the data on heart disease was not balanced. Thus, to overcome the imbalance, an oversampling technique was carried out using ADASYN and SMOTE. This study proved that the performance of the ADASYN and SMOTE oversampling techniques on the C45 algorithm and the Random Forest Classifier had a significant effect on the prediction results. The usage of oversampling techniques to analyze data aims to handle unbalanced datasets, and the confusion matrix is used for testing Precision, Recall, and F1-SCORE, as well as Accuracy. Based on the results of research that has been carried out with the K-Fold 10 testing technique and oversampling technique, SMOTE + RF is one of the best oversampling techniques which has a greater Accuracy of 93.58% compared to Random Forest without SMOTE of 90.51% and SMOTE + ADASYN of 93.55%. The application of the SMOTE technique was proven to be able to overcome the problem of data imbalance and get better classification results than the application of the ADASYN technique.
Perkembangan Twitter di Indonesia sebagai platform media sosial yang digemari masyarakat, yang menunjukkan Indonesia negara pengguna Twitter terbanyak kelima di dunia pada Januari 2022. Seiring berkembangnya tren saat ini, memaksa pemerintah Indonesia untuk melakukan berbagai cara lebih banyak berinteraksi dengan masyarakat, salah satunya dengan penggunaan Twitter. Memanfaatkan media social Twitter, pemerintah akan mendapatkan berbagai informasi yang sedang kontroversial di kalangan masyarakat. Seperti dilaksanakannya kegiatan vaksinasi oleh pemerintah Indonesia, banyak masyarakat menilai kontroversial dalam kegiatan vaksinasi ini dan banyak kalangan di masyarakat yang memberikan berbagai pendapatnya di media sosial. Melalui Twitter salah satunya, masyarakat berbagi postingan opini masing-masing tentang vaksinasi ini. Tahapan analisis pada pengujian ini akan membandingkan dua algoritma klasifikasi yakni Naive Bayes Classifier (NBC) dengan Decision Tree dengan menggunakan perhitungan Confusion Matrix untuk mengukur kinerja pada kedua algoritma tersebut. Hasil tes pengujian akhir disajikan dalam bentuk nilai akurasi, presisi dan recall. Perbandingan kedua algoritma klasifikasi Naïve Bayes dengan Decision Tree hasil yang diperoleh memiliki perbedaan tingkat akurasi yang berbeda. Algoritma Naïve Bayes Classifier mendapat hasil akurasi 93.96 % dan nilai presisi 91% dengan nilai recall 98%, sedangkan pada algoritma Decision Tree menghasilkan nilai akurasi sebesar 88.64 %, dengan nilai presisi 91% dan nilai recall 94%. Hasil ini didasarkan pada perhitungan Confusion Matrix. Kemudian bisa disimpulkan jika algoritma NBC penelitian ini lebih akurat dibanding algoritma Decision Tree.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.